PERFILES CALIDAD VIDA

Analisis exploratorio base de datos

• Cargue de la base de datos ajustada con el diccionario de datos
• Analisis exploratorio de los datos

# Establecer el directorio de trabajo 

library(readxl)
library(summarytools)

DATA_SET <- read_excel("DATA_SET2.xlsx") #cargue base de datos
print(dfSummary(DATA_SET), method = 'render')

Data Frame Summary

DATA_SET

Dimensions: 200 x 180
Duplicates: 0

No	Variable	Stats / Values	Freqs (% of Valid)	Graph	Valid	Missing
1	ID [numeric]	Mean (sd) : 100.5 (57.9) min ≤ med ≤ max: 1 ≤ 100.5 ≤ 200 IQR (CV) : 99.5 (0.6)	200 distinct values		200 (100.0%)	0 (0.0%)
2	CE_MUJER [character]	1. Si	200 ( 100.0% )		200 (100.0%)	0 (0.0%)
3	CE_EDAD_18 [character]	1. Si	200 ( 100.0% )		200 (100.0%)	0 (0.0%)
4	CE_DX_mama [character]	1. Si	200 ( 100.0% )		200 (100.0%)	0 (0.0%)
5	CE_TRAT [character]	1. Si	200 ( 100.0% )		200 (100.0%)	0 (0.0%)
6	CE_TRAT_2 [character]	1. No 2. Si	140 ( 70.0% ) 60 ( 30.0% )		200 (100.0%)	0 (0.0%)
7	CE_libre_cancer [character]	1. Si	200 ( 100.0% )		200 (100.0%)	0 (0.0%)
8	CE_CJO [character]	1. Si	200 ( 100.0% )		200 (100.0%)	0 (0.0%)
9	CE_COM_mental [character]	1. No	200 ( 100.0% )		200 (100.0%)	0 (0.0%)
10	CE_CAMA [character]	1. No	200 ( 100.0% )		200 (100.0%)	0 (0.0%)
11	CE_PARTICIPACION [character]	1. Si	200 ( 100.0% )		200 (100.0%)	0 (0.0%)
12	CE_CONSENTIMIENTO [character]	1. Si	200 ( 100.0% )		200 (100.0%)	0 (0.0%)
13	CE_COMPLETO [character]	1. Complete	200 ( 100.0% )		200 (100.0%)	0 (0.0%)
14	qlq_c30_1 [character]	1. Bastante 2. Mucho 3. Para nada 4. Un poco	42 ( 21.0% ) 17 ( 8.5% ) 80 ( 40.0% ) 61 ( 30.5% )		200 (100.0%)	0 (0.0%)
15	qlq_c30_2 [character]	1. Bastante 2. Mucho 3. Para nada 4. Un poco	20 ( 10.0% ) 10 ( 5.0% ) 132 ( 66.0% ) 38 ( 19.0% )		200 (100.0%)	0 (0.0%)
16	qlq_c30_3 [character]	1. Bastante 2. Para nada 3. Un poco	6 ( 3.0% ) 172 ( 86.0% ) 22 ( 11.0% )		200 (100.0%)	0 (0.0%)
17	qlq_c30_4 [character]	1. Bastante 2. Mucho 3. Para nada 4. Un poco	8 ( 4.0% ) 1 ( 0.5% ) 171 ( 85.5% ) 20 ( 10.0% )		200 (100.0%)	0 (0.0%)
18	qlq_c30_5 [character]	1. Bastante 2. Para nada 3. Un poco	1 ( 0.5% ) 194 ( 97.0% ) 5 ( 2.5% )		200 (100.0%)	0 (0.0%)
19	qlq_c30_6 [character]	1. Bastante 2. Mucho 3. Para nada 4. Un poco	16 ( 8.0% ) 4 ( 2.0% ) 144 ( 72.0% ) 36 ( 18.0% )		200 (100.0%)	0 (0.0%)
20	qlq_c30_7 [character]	1. Bastante 2. Mucho 3. Para nada 4. Un poco	6 ( 3.0% ) 4 ( 2.0% ) 179 ( 89.5% ) 11 ( 5.5% )		200 (100.0%)	0 (0.0%)
21	qlq_c30_8 [character]	1. Bastante 2. Mucho 3. Para nada 4. Un poco	8 ( 4.0% ) 1 ( 0.5% ) 158 ( 79.0% ) 33 ( 16.5% )		200 (100.0%)	0 (0.0%)
22	qlq_c30_9 [character]	1. Bastante 2. Mucho 3. Para nada 4. Un poco	29 ( 14.5% ) 15 ( 7.5% ) 79 ( 39.5% ) 77 ( 38.5% )		200 (100.0%)	0 (0.0%)
23	qlq_c30_10 [character]	1. Bastante 2. Mucho 3. Para nada 4. Un poco	21 ( 10.5% ) 5 ( 2.5% ) 101 ( 50.5% ) 73 ( 36.5% )		200 (100.0%)	0 (0.0%)
24	qlq_c30_11 [character]	1. Bastante 2. Mucho 3. Para nada 4. Un poco	23 ( 11.5% ) 15 ( 7.5% ) 94 ( 47.0% ) 68 ( 34.0% )		200 (100.0%)	0 (0.0%)
25	qlq_c30_12 [character]	1. Bastante 2. Mucho 3. Para nada 4. Un poco	17 ( 8.5% ) 3 ( 1.5% ) 138 ( 69.0% ) 42 ( 21.0% )		200 (100.0%)	0 (0.0%)
26	qlq_c30_13 [character]	1. Bastante 2. Mucho 3. Para nada 4. Un poco	8 ( 4.0% ) 3 ( 1.5% ) 174 ( 87.0% ) 15 ( 7.5% )		200 (100.0%)	0 (0.0%)
27	qlq_c30_14 [character]	1. Bastante 2. Mucho 3. Para nada 4. Un poco	2 ( 1.0% ) 3 ( 1.5% ) 175 ( 87.5% ) 20 ( 10.0% )		200 (100.0%)	0 (0.0%)
28	qlq_c30_15 [character]	1. Para nada 2. Un poco	194 ( 97.0% ) 6 ( 3.0% )		200 (100.0%)	0 (0.0%)
29	qlq_c30_16 [character]	1. Bastante 2. Mucho 3. Para nada 4. Un poco	11 ( 5.5% ) 2 ( 1.0% ) 148 ( 74.0% ) 39 ( 19.5% )		200 (100.0%)	0 (0.0%)
30	qlq_c30_17 [character]	1. Bastante 2. Mucho 3. Para nada 4. Un poco	5 ( 2.5% ) 2 ( 1.0% ) 179 ( 89.5% ) 14 ( 7.0% )		200 (100.0%)	0 (0.0%)
31	qlq_c30_18 [character]	1. Bastante 2. Mucho 3. Para nada 4. Un poco	21 ( 10.5% ) 9 ( 4.5% ) 90 ( 45.0% ) 80 ( 40.0% )		200 (100.0%)	0 (0.0%)
32	qlq_c30_19 [character]	1. Bastante 2. Mucho 3. Para nada 4. Un poco	24 ( 12.0% ) 9 ( 4.5% ) 120 ( 60.0% ) 47 ( 23.5% )		200 (100.0%)	0 (0.0%)
33	qlq_c30_20 [character]	1. Bastante 2. Mucho 3. Para nada 4. Un poco	18 ( 9.0% ) 4 ( 2.0% ) 137 ( 68.5% ) 41 ( 20.5% )		200 (100.0%)	0 (0.0%)
34	qlq_c30_21 [character]	1. Bastante 2. Mucho 3. Para nada 4. Un poco	23 ( 11.5% ) 6 ( 3.0% ) 125 ( 62.5% ) 46 ( 23.0% )		200 (100.0%)	0 (0.0%)
35	qlq_c30_22 [character]	1. Bastante 2. Mucho 3. Para nada 4. Un poco	26 ( 13.0% ) 14 ( 7.0% ) 88 ( 44.0% ) 72 ( 36.0% )		200 (100.0%)	0 (0.0%)
36	qlq_c30_23 [character]	1. Bastante 2. Mucho 3. Para nada 4. Un poco	15 ( 7.5% ) 8 ( 4.0% ) 135 ( 67.5% ) 42 ( 21.0% )		200 (100.0%)	0 (0.0%)
37	qlq_c30_24 [character]	1. Bastante 2. Mucho 3. Para nada 4. Un poco	15 ( 7.5% ) 13 ( 6.5% ) 118 ( 59.0% ) 54 ( 27.0% )		200 (100.0%)	0 (0.0%)
38	qlq_c30_25 [character]	1. Bastante 2. Mucho 3. Para nada 4. Un poco	26 ( 13.0% ) 3 ( 1.5% ) 97 ( 48.5% ) 74 ( 37.0% )		200 (100.0%)	0 (0.0%)
39	qlq_c30_26 [character]	1. Bastante 2. Para nada 3. Un poco	8 ( 4.0% ) 170 ( 85.0% ) 22 ( 11.0% )		200 (100.0%)	0 (0.0%)
40	qlq_c30_27 [character]	1. Bastante 2. Para nada 3. Un poco	10 ( 5.0% ) 169 ( 84.5% ) 21 ( 10.5% )		200 (100.0%)	0 (0.0%)
41	qlq_c30_28 [character]	1. Bastante 2. Mucho 3. Para nada 4. Un poco	11 ( 5.5% ) 4 ( 2.0% ) 160 ( 80.0% ) 25 ( 12.5% )		200 (100.0%)	0 (0.0%)
42	qlq_c30_29 [numeric]	Mean (sd) : 5.6 (1.1) min ≤ med ≤ max: 1 ≤ 6 ≤ 7 IQR (CV) : 1 (0.2)	1 : 1 ( 0.5% ) 2 : 1 ( 0.5% ) 3 : 8 ( 4.0% ) 4 : 20 ( 10.0% ) 5 : 61 ( 30.5% ) 6 : 63 ( 31.5% ) 7 : 46 ( 23.0% )		200 (100.0%)	0 (0.0%)
43	qlq_c30_30 [numeric]	Mean (sd) : 5.8 (1.2) min ≤ med ≤ max: 2 ≤ 6 ≤ 7 IQR (CV) : 2 (0.2)	2 : 4 ( 2.0% ) 3 : 7 ( 3.5% ) 4 : 12 ( 6.0% ) 5 : 51 ( 25.5% ) 6 : 64 ( 32.0% ) 7 : 62 ( 31.0% )		200 (100.0%)	0 (0.0%)
44	qlq_c30_31 [character]	1. Bastante 2. Mucho 3. Para nada 4. Un poco	31 ( 15.5% ) 10 ( 5.0% ) 97 ( 48.5% ) 62 ( 31.0% )		200 (100.0%)	0 (0.0%)
45	qlq_c30_32 [character]	1. Bastante 2. Mucho 3. Para nada 4. Un poco	3 ( 1.5% ) 1 ( 0.5% ) 179 ( 89.5% ) 17 ( 8.5% )		200 (100.0%)	0 (0.0%)
46	qlq_c30_33 [character]	1. Bastante 2. Mucho 3. Para nada 4. Un poco	21 ( 10.5% ) 8 ( 4.0% ) 103 ( 51.5% ) 68 ( 34.0% )		200 (100.0%)	0 (0.0%)
47	qlq_c30_34 [character]	1. Bastante 2. Mucho 3. Para nada 4. Un poco	32 ( 16.0% ) 12 ( 6.0% ) 114 ( 57.0% ) 42 ( 21.0% )		200 (100.0%)	0 (0.0%)
48	qlq_c30_35 [character]	1. Bastante 2. Mucho 3. Para nada 4. Un poco	18 ( 9.6% ) 12 ( 6.4% ) 135 ( 72.2% ) 22 ( 11.8% )		187 (93.5%)	13 (6.5%)
49	qlq_c30_36 [character]	1. Bastante 2. Mucho 3. Para nada 4. Un poco	26 ( 13.0% ) 5 ( 2.5% ) 124 ( 62.0% ) 45 ( 22.5% )		200 (100.0%)	0 (0.0%)
50	qlq_c30_37 [character]	1. Bastante 2. Mucho 3. Para nada 4. Un poco	35 ( 17.5% ) 19 ( 9.5% ) 100 ( 50.0% ) 46 ( 23.0% )		200 (100.0%)	0 (0.0%)
51	qlq_c30_38 [character]	1. Bastante 2. Mucho 3. Para nada 4. Un poco	26 ( 13.0% ) 3 ( 1.5% ) 119 ( 59.5% ) 52 ( 26.0% )		200 (100.0%)	0 (0.0%)
52	qlq_c30_39 [character]	1. Bastante 2. Mucho 3. Para nada 4. Un poco	12 ( 6.0% ) 7 ( 3.5% ) 151 ( 75.5% ) 30 ( 15.0% )		200 (100.0%)	0 (0.0%)
53	qlq_c30_40 [character]	1. Bastante 2. Mucho 3. Para nada 4. Un poco	4 ( 2.0% ) 2 ( 1.0% ) 175 ( 87.5% ) 19 ( 9.5% )		200 (100.0%)	0 (0.0%)
54	qlq_c30_41 [character]	1. Bastante 2. Mucho 3. Para nada 4. Un poco	4 ( 2.0% ) 4 ( 2.0% ) 163 ( 81.5% ) 29 ( 14.5% )		200 (100.0%)	0 (0.0%)
55	qlq_c30_42 [character]	1. Bastante 2. Mucho 3. Para nada 4. Un poco	1 ( 0.5% ) 5 ( 2.5% ) 162 ( 81.0% ) 32 ( 16.0% )		200 (100.0%)	0 (0.0%)
56	qlq_c30_43 [character]	1. Bastante 2. Mucho 3. Para nada 4. Un poco	48 ( 24.0% ) 13 ( 6.5% ) 74 ( 37.0% ) 65 ( 32.5% )		200 (100.0%)	0 (0.0%)
57	qlq_c30_44 [character]	1. Bastante 2. Mucho 3. Para nada 4. Un poco	13 ( 6.5% ) 3 ( 1.5% ) 140 ( 70.0% ) 44 ( 22.0% )		200 (100.0%)	0 (0.0%)
58	qlq_c30_45 [character]	1. Bastante 2. Mucho 3. Para nada 4. Un poco	11 ( 5.5% ) 2 ( 1.0% ) 140 ( 70.0% ) 47 ( 23.5% )		200 (100.0%)	0 (0.0%)
59	qlq_c30_46 [character]	1. Bastante 2. Mucho 3. Para nada 4. Un poco	23 ( 12.9% ) 2 ( 1.1% ) 124 ( 69.7% ) 29 ( 16.3% )		178 (89.0%)	22 (11.0%)
60	qlq_c30_47 [character]	1. Bastante 2. Mucho 3. Para nada 4. Un poco	26 ( 13.0% ) 11 ( 5.5% ) 85 ( 42.5% ) 78 ( 39.0% )		200 (100.0%)	0 (0.0%)
61	qlq_c30_48 [character]	1. Bastante 2. Mucho 3. Para nada 4. Un poco	15 ( 7.5% ) 6 ( 3.0% ) 155 ( 77.5% ) 24 ( 12.0% )		200 (100.0%)	0 (0.0%)
62	qlq_c30_49 [character]	1. Bastante 2. Mucho 3. Para nada 4. Un poco	12 ( 6.0% ) 5 ( 2.5% ) 134 ( 67.0% ) 49 ( 24.5% )		200 (100.0%)	0 (0.0%)
63	qlq_c30_50 [character]	1. Bastante 2. Mucho 3. Para nada 4. Un poco	12 ( 6.0% ) 4 ( 2.0% ) 127 ( 63.5% ) 57 ( 28.5% )		200 (100.0%)	0 (0.0%)
64	qlq_c30_51 [character]	1. Bastante 2. Para nada 3. Un poco	4 ( 2.0% ) 181 ( 90.5% ) 15 ( 7.5% )		200 (100.0%)	0 (0.0%)
65	qlq_c30_52 [character]	1. Bastante 2. Mucho 3. Para nada 4. Un poco	15 ( 7.5% ) 6 ( 3.0% ) 128 ( 64.0% ) 51 ( 25.5% )		200 (100.0%)	0 (0.0%)
66	qlq_c30_53 [character]	1. Bastante 2. Mucho 3. Para nada 4. Un poco	9 ( 4.5% ) 4 ( 2.0% ) 151 ( 75.5% ) 36 ( 18.0% )		200 (100.0%)	0 (0.0%)
67	EDAD [numeric]	Mean (sd) : 65.1 (9.5) min ≤ med ≤ max: 37 ≤ 65 ≤ 93 IQR (CV) : 13 (0.1)	44 distinct values		200 (100.0%)	0 (0.0%)
68	ESTRATO [numeric]	Mean (sd) : 2.7 (0.9) min ≤ med ≤ max: 1 ≤ 3 ≤ 6 IQR (CV) : 1 (0.3)	1 : 12 ( 6.0% ) 2 : 70 ( 35.0% ) 3 : 84 ( 42.0% ) 4 : 27 ( 13.5% ) 5 : 5 ( 2.5% ) 6 : 2 ( 1.0% )		200 (100.0%)	0 (0.0%)
69	AFILIACION_SALUD [character]	1. Contributivo 2. Subsidiado	194 ( 97.0% ) 6 ( 3.0% )		200 (100.0%)	0 (0.0%)
70	EDUCACION [character]	1. Educación básica (primari 2. Educación media (bachille 3. Educación preescolar 4. Educación superior (unive 5. Educación técnica 6. Posgrado (especializacion 7. Sin educación formal	73 ( 36.5% ) 42 ( 21.0% ) 5 ( 2.5% ) 27 ( 13.5% ) 37 ( 18.5% ) 12 ( 6.0% ) 4 ( 2.0% )		200 (100.0%)	0 (0.0%)
71	SIT_MARITAL [character]	1. Casado(a) 2. Divorciado(a) 3. Separado(a) 4. Soltero(a) 5. Unión libre 6. Viudo(a)	76 ( 38.2% ) 1 ( 0.5% ) 20 ( 10.1% ) 45 ( 22.6% ) 23 ( 11.6% ) 34 ( 17.1% )		199 (99.5%)	1 (0.5%)
72	OCUPACION [character]	1. Ama de Casa 2. Pensionado 3. Hogar 4. Vendedor 5. Auxiliar Varios 6. Cesante 7. Personal de Servidumbre 8. Administrador de Empresas 9. Contadores 10. Empleados de Oficina [ 11 others ]	59 ( 29.5% ) 56 ( 28.0% ) 32 ( 16.0% ) 9 ( 4.5% ) 5 ( 2.5% ) 5 ( 2.5% ) 5 ( 2.5% ) 4 ( 2.0% ) 4 ( 2.0% ) 4 ( 2.0% ) 17 ( 8.5% )		200 (100.0%)	0 (0.0%)
73	FRACCION_OCUPACIONES [numeric]	Mean (sd) : 60.5 (30.6) min ≤ med ≤ max: 1 ≤ 56.5 ≤ 100 IQR (CV) : 55.2 (0.5)	31 distinct values		200 (100.0%)	0 (0.0%)
74	SATISFACCION_ATENCION_SALUD [character]	1. Extremadamente satisfecho 2. Moderadamente satisfecho 3. Muy satisfecho 4. Poco satisfecho	99 ( 49.5% ) 11 ( 5.5% ) 85 ( 42.5% ) 5 ( 2.5% )		200 (100.0%)	0 (0.0%)
75	PERCEPCION_RELIGION [numeric]	Mean (sd) : 8.1 (2.3) min ≤ med ≤ max: 0 ≤ 9 ≤ 10 IQR (CV) : 3 (0.3)	0 : 4 ( 2.0% ) 1 : 1 ( 0.5% ) 3 : 4 ( 2.0% ) 4 : 1 ( 0.5% ) 5 : 26 ( 13.0% ) 6 : 9 ( 4.5% ) 7 : 12 ( 6.0% ) 8 : 40 ( 20.0% ) 9 : 17 ( 8.5% ) 10 : 86 ( 43.0% )		200 (100.0%)	0 (0.0%)
76	PERCEPCION_ESPIRITUAL [numeric]	Mean (sd) : 8.5 (1.9) min ≤ med ≤ max: 0 ≤ 9 ≤ 10 IQR (CV) : 3 (0.2)	0 : 2 ( 1.0% ) 5 : 17 ( 8.5% ) 6 : 8 ( 4.0% ) 7 : 25 ( 12.5% ) 8 : 34 ( 17.0% ) 9 : 17 ( 8.5% ) 10 : 97 ( 48.5% )		200 (100.0%)	0 (0.0%)
77	PERCEPCION_SOPORTE_SOCIAL [numeric]	Mean (sd) : 8.6 (2) min ≤ med ≤ max: 1 ≤ 10 ≤ 10 IQR (CV) : 2 (0.2)	1 : 1 ( 0.5% ) 2 : 3 ( 1.5% ) 3 : 3 ( 1.5% ) 4 : 2 ( 1.0% ) 5 : 13 ( 6.5% ) 6 : 7 ( 3.5% ) 7 : 11 ( 5.5% ) 8 : 29 ( 14.5% ) 9 : 26 ( 13.0% ) 10 : 105 ( 52.5% )		200 (100.0%)	0 (0.0%)
78	COMPLETE_SOCIODEMOGRAFICO [character]	1. Complete	200 ( 100.0% )		200 (100.0%)	0 (0.0%)
79	TIEMPO_SUPERVIVENCIA [numeric]	Mean (sd) : 8.2 (4.8) min ≤ med ≤ max: 1 ≤ 7 ≤ 26 IQR (CV) : 6 (0.6)	23 distinct values		200 (100.0%)	0 (0.0%)
80	EDAD_DX [numeric]	Mean (sd) : 56.9 (10.1) min ≤ med ≤ max: 31 ≤ 57.5 ≤ 90 IQR (CV) : 14.2 (0.2)	43 distinct values		200 (100.0%)	0 (0.0%)
81	LATERIALDAD_MAMA_DERECHO [character]	1. Checked 2. Unchecked	108 ( 54.0% ) 92 ( 46.0% )		200 (100.0%)	0 (0.0%)
82	LATERIALDAD_MAMA_IZQUIERDO [character]	1. Checked 2. Unchecked	90 ( 45.0% ) 110 ( 55.0% )		200 (100.0%)	0 (0.0%)
83	LATERIALDAD_MAMA_BILATERAL [character]	1. Checked 2. Unchecked	3 ( 1.5% ) 197 ( 98.5% )		200 (100.0%)	0 (0.0%)
84	ESTADIFICACION_MAMA_NCCN [character]	1. 0 2. IA 3. IB 4. IIA 5. IIB 6. IIIA 7. IIIB 8. IIIC 9. IV 10. No reporta	2 ( 1.0% ) 50 ( 25.0% ) 3 ( 1.5% ) 52 ( 26.0% ) 37 ( 18.5% ) 26 ( 13.0% ) 9 ( 4.5% ) 5 ( 2.5% ) 2 ( 1.0% ) 14 ( 7.0% )		200 (100.0%)	0 (0.0%)
85	TIPO_HISTOLOGICO_CIE_10 [character]	1. Adenoideo quístico 2. Ductal 3. Lobulillar 4. Medular 5. Mucinoso 6. No reporta 7. Otro 8. Papilar 9. Tubular	1 ( 0.5% ) 155 ( 77.5% ) 11 ( 5.5% ) 2 ( 1.0% ) 3 ( 1.5% ) 12 ( 6.0% ) 7 ( 3.5% ) 8 ( 4.0% ) 1 ( 0.5% )		200 (100.0%)	0 (0.0%)
86	CLASIFICACION_INMUNOHISTOQUIMICA_RE_POSITIVO [character]	1. Checked 2. Unchecked	161 ( 80.5% ) 39 ( 19.5% )		200 (100.0%)	0 (0.0%)
87	CLASIFICACION_INMUNOHISTOQUIMICA_RP_POSITIVO [character]	1. Checked 2. Unchecked	136 ( 68.0% ) 64 ( 32.0% )		200 (100.0%)	0 (0.0%)
88	CLASIFICACION_INMUNOHISTOQUIMICA_TRIPLE_NEGATIVO [character]	1. Checked 2. Unchecked	17 ( 8.5% ) 183 ( 91.5% )		200 (100.0%)	0 (0.0%)
89	CLASIFICACION_INMUNOHISTOQUIMICA_HER2_POSITIVO [character]	1. Checked 2. Unchecked	31 ( 15.5% ) 169 ( 84.5% )		200 (100.0%)	0 (0.0%)
90	CLASIFICACION_INMUNOHISTOQUIMICA_KI_67_POSITIVO [character]	1. Checked 2. Unchecked	54 ( 27.0% ) 146 ( 73.0% )		200 (100.0%)	0 (0.0%)
91	CLASIFICACION_INMUNOHISTOQUIMICA_OTRO [character]	1. Unchecked	200 ( 100.0% )		200 (100.0%)	0 (0.0%)
92	CLASIFICACION_INMUNOHISTOQUIMICA_NO_REPORTA [character]	1. Checked 2. Unchecked	9 ( 4.5% ) 191 ( 95.5% )		200 (100.0%)	0 (0.0%)
93	TRAT_QUIMIOTERAPIA_NEOADYUVANTE [character]	1. Checked 2. Unchecked	69 ( 34.5% ) 131 ( 65.5% )		200 (100.0%)	0 (0.0%)
94	TRAT_ANTIHER2 [character]	1. Checked 2. Unchecked	29 ( 14.5% ) 171 ( 85.5% )		200 (100.0%)	0 (0.0%)
95	TRAT_RADIOTERAPIA_NEOADYUVANTE [character]	1. Unchecked	200 ( 100.0% )		200 (100.0%)	0 (0.0%)
96	TRAT_CIRUGIA_RADICAL [character]	1. Checked 2. Unchecked	16 ( 8.0% ) 184 ( 92.0% )		200 (100.0%)	0 (0.0%)
97	TRAT_CIRUGIA_RADICAL_MODIFICADA [character]	1. Checked 2. Unchecked	64 ( 32.0% ) 136 ( 68.0% )		200 (100.0%)	0 (0.0%)
98	TRAT_CIRUGIA_CONSERVADORA [character]	1. Checked 2. Unchecked	127 ( 63.5% ) 73 ( 36.5% )		200 (100.0%)	0 (0.0%)
99	TRAT_VACIAMIENTO_GANGLIONAR [character]	1. Checked 2. Unchecked	145 ( 72.5% ) 55 ( 27.5% )		200 (100.0%)	0 (0.0%)
100	TRAT_TRATAMIENTO_HORMONAL [character]	1. Checked 2. Unchecked	152 ( 76.0% ) 48 ( 24.0% )		200 (100.0%)	0 (0.0%)
101	TRAT_QUIMIOTERAPIA_ADYUVANTE [character]	1. Checked 2. Unchecked	98 ( 49.0% ) 102 ( 51.0% )		200 (100.0%)	0 (0.0%)
102	TRAT_RADIOTERAPIA_ADYUVANTE [character]	1. Checked 2. Unchecked	165 ( 82.5% ) 35 ( 17.5% )		200 (100.0%)	0 (0.0%)
103	TRAT_CIRUGIA_RECONSTRUCTIVA [character]	1. Checked 2. Unchecked	35 ( 17.5% ) 165 ( 82.5% )		200 (100.0%)	0 (0.0%)
104	TRAT_OTRO [character]	1. Checked 2. Unchecked	1 ( 0.5% ) 199 ( 99.5% )		200 (100.0%)	0 (0.0%)
105	TRAT_NO_REPORTA [character]	1. Unchecked	200 ( 100.0% )		200 (100.0%)	0 (0.0%)
106	TIPO_T_SISTEMICO_NEOADYUVANTE_QUIMIOTERAPIA [character]	1. Checked 2. Unchecked	64 ( 32.0% ) 136 ( 68.0% )		200 (100.0%)	0 (0.0%)
107	TIPO_T_SISTEMICO_NEOADYUVANTE_ANTIHER2 [character]	1. Checked 2. Unchecked	11 ( 5.5% ) 189 ( 94.5% )		200 (100.0%)	0 (0.0%)
108	TIPO_T_SISTEMICO_NEOADYUVANTE_T.BLANCO [character]	1. Checked 2. Unchecked	2 ( 1.0% ) 198 ( 99.0% )		200 (100.0%)	0 (0.0%)
109	TIPO_T_SISTEMICO_NEOADYUVANTE_INMUNOTERAPIA [character]	1. Unchecked	200 ( 100.0% )		200 (100.0%)	0 (0.0%)
110	TIPO_T_SISTEMICO_NEOADYUVANTE_HORMONOTERAPIA [character]	1. Checked 2. Unchecked	3 ( 1.5% ) 197 ( 98.5% )		200 (100.0%)	0 (0.0%)
111	TIPO_T_SISTEMICO_NEOADYUVANTE_NO_REPORTA [character]	1. Checked 2. Unchecked	1 ( 0.5% ) 199 ( 99.5% )		200 (100.0%)	0 (0.0%)
112	TIPO_T_SISTEMICO_ADYUVANTE_QUIMIOTERAPIA [character]	1. Checked 2. Unchecked	86 ( 43.0% ) 114 ( 57.0% )		200 (100.0%)	0 (0.0%)
113	TIPO_T_SISTEMICO_ADYUVANTE_ANTIHER2 [character]	1. Checked 2. Unchecked	18 ( 9.0% ) 182 ( 91.0% )		200 (100.0%)	0 (0.0%)
114	TIPO_T_SISTEMICO_ADYUVANTE_T.BLANCO [character]	1. Checked 2. Unchecked	1 ( 0.5% ) 199 ( 99.5% )		200 (100.0%)	0 (0.0%)
115	TIPO_T_SISTEMICO_ADYUVANTE_INMUNOTERAPIA [character]	1. Unchecked	200 ( 100.0% )		200 (100.0%)	0 (0.0%)
116	TIPO_T_SISTEMICO_ADYUVANTE_HORMONOTERAPIA [character]	1. Checked 2. Unchecked	40 ( 20.0% ) 160 ( 80.0% )		200 (100.0%)	0 (0.0%)
117	TIPO_T_SISTEMICO_ADYUVANTE_NO_REPORTA [character]	1. Checked 2. Unchecked	3 ( 1.5% ) 197 ( 98.5% )		200 (100.0%)	0 (0.0%)
118	TIPO_RADIOTERAPIA_NEOADYUVANTE_RADIACION_TODO_SENO_CONVENCIONAL [character]	1. Unchecked	200 ( 100.0% )		200 (100.0%)	0 (0.0%)
119	TIPO_RADIOTERAPIA_NEOADYUVANTE_RADIACION_TODO_SENO_HIPOFRACCIONADA [character]	1. Unchecked	200 ( 100.0% )		200 (100.0%)	0 (0.0%)
120	TIPO_RADIOTERAPIA_NEOADYUVANTE_RADIOT_IORT [character]	1. Unchecked	200 ( 100.0% )		200 (100.0%)	0 (0.0%)
121	TIPO_RADIOTERAPIA_NEOADYUVANTE_RADIOT_3D_CRT [character]	1. Unchecked	200 ( 100.0% )		200 (100.0%)	0 (0.0%)
122	TIPO_RADIOTERAPIA_NEOADYUVANTE_RADIOT_IMRT [character]	1. Unchecked	200 ( 100.0% )		200 (100.0%)	0 (0.0%)
123	TIPO_RADIOTERAPIA_NEOADYUVANTE_BRAQUITERAPIA [character]	1. Unchecked	200 ( 100.0% )		200 (100.0%)	0 (0.0%)
124	TIPO_RADIOTERAPIA_NEOADYUVANTE_RADIACION_GANGLIOS [character]	1. Unchecked	200 ( 100.0% )		200 (100.0%)	0 (0.0%)
125	TIPO_RADIOTERAPIA_NEOADYUVANTE_OTRO [character]	1. Unchecked	200 ( 100.0% )		200 (100.0%)	0 (0.0%)
126	TIPO_RADIOTERAPIA_NEOADYUVANTE_NO_REPORTA [character]	1. Unchecked	200 ( 100.0% )		200 (100.0%)	0 (0.0%)
127	TIPO_RADIOTERAPIA_ADYUVANTE_RADIACION_TODO_SENO_CONVENCIONAL [character]	1. Checked 2. Unchecked	4 ( 2.0% ) 196 ( 98.0% )		200 (100.0%)	0 (0.0%)
128	TIPO_RADIOTERAPIA_ADYUVANTE_RADIACION_TODO_SENO_HIPOFRACCIONADA [character]	1. Checked 2. Unchecked	2 ( 1.0% ) 198 ( 99.0% )		200 (100.0%)	0 (0.0%)
129	TIPO_RADIOTERAPIA_ADYUVANTE_RADIOT_IORT [character]	1. Unchecked	200 ( 100.0% )		200 (100.0%)	0 (0.0%)
130	TIPO_RADIOTERAPIA_ADYUVANTE_RADIOT_3D_CRT [character]	1. Checked 2. Unchecked	6 ( 3.0% ) 194 ( 97.0% )		200 (100.0%)	0 (0.0%)
131	TIPO_RADIOTERAPIA_ADYUVANTE_RADIOT_IMRT [character]	1. Checked 2. Unchecked	123 ( 61.5% ) 77 ( 38.5% )		200 (100.0%)	0 (0.0%)
132	TIPO_RADIOTERAPIA_ADYUVANTE_BRAQUITERAPIA [character]	1. Checked 2. Unchecked	1 ( 0.5% ) 199 ( 99.5% )		200 (100.0%)	0 (0.0%)
133	TIPO_RADIOTERAPIA_ADYUVANTE_RADIACION_GANGLIOS [character]	1. Checked 2. Unchecked	10 ( 5.0% ) 190 ( 95.0% )		200 (100.0%)	0 (0.0%)
134	TIPO_RADIOTERAPIA_ADYUVANTE_OTRO [character]	1. Checked 2. Unchecked	1 ( 0.5% ) 199 ( 99.5% )		200 (100.0%)	0 (0.0%)
135	TIPO_RADIOTERAPIA_ADYUVANTE_NO_REPORTA [character]	1. Checked 2. Unchecked	29 ( 14.5% ) 171 ( 85.5% )		200 (100.0%)	0 (0.0%)
136	TRAT_HORMONAL_COMPLETADO [character]	1. Inhibidor de aromatasa ex 2. Inhibidor de aromatasa po 3. Otro 4. Tamoxifeno 2 años y switc 5. Tamoxifeno 2 años y switc 6. Tamoxifeno extendido (7-1 7. Tamoxifeno por 5 años	23 ( 14.6% ) 33 ( 21.0% ) 11 ( 7.0% ) 20 ( 12.7% ) 15 ( 9.6% ) 20 ( 12.7% ) 35 ( 22.3% )		157 (78.5%)	43 (21.5%)
137	TRAT_HORMONAL_ACTUAL [character]	1. Anastrazol 2. Exemestane 3. Letrozol 4. No esta recibiendo actual 5. Otro 6. Tamoxifeno	15 ( 9.6% ) 1 ( 0.6% ) 22 ( 14.0% ) 104 ( 66.2% ) 1 ( 0.6% ) 14 ( 8.9% )		157 (78.5%)	43 (21.5%)
138	RECAIDA_CANCER_MAMA [character]	1. No 2. Si	196 ( 98.0% ) 4 ( 2.0% )		200 (100.0%)	0 (0.0%)
139	CATEGORIA_RIESGO_HC [character]	1. Alto riesgo 2. Bajo riesgo 3. Intermedio riesgo 4. No reporta	75 ( 37.5% ) 58 ( 29.0% ) 50 ( 25.0% ) 17 ( 8.5% )		200 (100.0%)	0 (0.0%)
140	TRAT_RECAIDA_QUIMIOTERAPIA [character]	1. Checked 2. Unchecked	1 ( 0.5% ) 199 ( 99.5% )		200 (100.0%)	0 (0.0%)
141	TRAT_RECAIDA_ANTI_HER2 [character]	1. Unchecked	200 ( 100.0% )		200 (100.0%)	0 (0.0%)
142	TRAT_RECAIDA_T._BLANCO [character]	1. Unchecked	200 ( 100.0% )		200 (100.0%)	0 (0.0%)
143	TRAT_RECAIDA_INMUNOTERAPIA [character]	1. Unchecked	200 ( 100.0% )		200 (100.0%)	0 (0.0%)
144	TRAT_RECAIDA_HORMONOTERAPIA [character]	1. Checked 2. Unchecked	3 ( 1.5% ) 197 ( 98.5% )		200 (100.0%)	0 (0.0%)
145	TRAT_RECAIDA_RADIOTERAPIA [character]	1. Checked 2. Unchecked	1 ( 0.5% ) 199 ( 99.5% )		200 (100.0%)	0 (0.0%)
146	TRAT_RECAIDA_NO_REPORTA [character]	1. Unchecked	200 ( 100.0% )		200 (100.0%)	0 (0.0%)
147	ATENCION_UA_CUIDADO_PALIATIVO [character]	1. Checked 2. Unchecked	25 ( 12.5% ) 175 ( 87.5% )		200 (100.0%)	0 (0.0%)
148	ATENCION_UA_PROGRAMA_LINFEDEMA [character]	1. Checked 2. Unchecked	2 ( 1.0% ) 198 ( 99.0% )		200 (100.0%)	0 (0.0%)
149	ATENCION_UA_PROGRAMA_FATIGA_REH_ONCOLOGICA [character]	1. Checked 2. Unchecked	3 ( 1.5% ) 197 ( 98.5% )		200 (100.0%)	0 (0.0%)
150	ATENCION_UA_PSICOONCOLOGIA [character]	1. Checked 2. Unchecked	7 ( 3.5% ) 193 ( 96.5% )		200 (100.0%)	0 (0.0%)
151	ATENCION_UA_SEXOLOGIA_GINECOLOGIA_FUNCIONAL [character]	1. Checked 2. Unchecked	2 ( 1.0% ) 198 ( 99.0% )		200 (100.0%)	0 (0.0%)
152	ATENCION_UA_NEUROLOGIA [character]	1. Checked 2. Unchecked	5 ( 2.5% ) 195 ( 97.5% )		200 (100.0%)	0 (0.0%)
153	ATENCION_UA_TRABAJO_SOCIAL [character]	1. Checked 2. Unchecked	2 ( 1.0% ) 198 ( 99.0% )		200 (100.0%)	0 (0.0%)
154	ATENCION_UA_NUTRICION [character]	1. Checked 2. Unchecked	5 ( 2.5% ) 195 ( 97.5% )		200 (100.0%)	0 (0.0%)
155	ATENCION_UA_MEDICINA_OCUPACIONAL [character]	1. Checked 2. Unchecked	1 ( 0.5% ) 199 ( 99.5% )		200 (100.0%)	0 (0.0%)
156	ATENCION_UA_MEDICINA_CIRUGIA_PLASTICA_RECONSTRUCTIVA [character]	1. Checked 2. Unchecked	11 ( 5.5% ) 189 ( 94.5% )		200 (100.0%)	0 (0.0%)
157	ATENCION_UA_MEDICINA_FISIATRIA_MEDICINA_FISICA [character]	1. Checked 2. Unchecked	12 ( 6.0% ) 188 ( 94.0% )		200 (100.0%)	0 (0.0%)
158	ATENCION_UA_OTRO [character]	1. Checked 2. Unchecked	4 ( 2.0% ) 196 ( 98.0% )		200 (100.0%)	0 (0.0%)
159	ATENCION_UA_NINGUNO [character]	1. Checked 2. Unchecked	154 ( 77.0% ) 46 ( 23.0% )		200 (100.0%)	0 (0.0%)
160	SEGUIMIENTO_SUPERVIVENCIA_UA_MEDICINA FAMILIAR [character]	1. Checked 2. Unchecked	170 ( 85.0% ) 30 ( 15.0% )		200 (100.0%)	0 (0.0%)
161	SEGUIMIENTO_SUPERVIVENCIA_UA_ONCOLOGIA_CLINICA [character]	1. Checked 2. Unchecked	64 ( 32.0% ) 136 ( 68.0% )		200 (100.0%)	0 (0.0%)
162	SEGUIMIENTO_SUPERVIVENCIA_UA_CIRUGIA_MAMA [character]	1. Checked 2. Unchecked	72 ( 36.0% ) 128 ( 64.0% )		200 (100.0%)	0 (0.0%)
163	SEGUIMIENTO_SUPERVIVENCIA_UA_OTRO [character]	1. Checked 2. Unchecked	1 ( 0.5% ) 199 ( 99.5% )		200 (100.0%)	0 (0.0%)
164	SEGUIMIENTO_SUPERVIVENCIA_UA_NINGUNO [character]	1. Unchecked	200 ( 100.0% )		200 (100.0%)	0 (0.0%)
165	ANT_INFARTO_MIOCARDIO [character]	1. No 2. Si	199 ( 99.5% ) 1 ( 0.5% )		200 (100.0%)	0 (0.0%)
166	ANT_FALLA_CARDIACA [character]	1. No 2. Si	191 ( 96.0% ) 8 ( 4.0% )		199 (99.5%)	1 (0.5%)
167	ANT_FALLA_ENF_VASCULAR_PERIFERICA [character]	1. No 2. Si	177 ( 88.9% ) 22 ( 11.1% )		199 (99.5%)	1 (0.5%)
168	ANT_FALLA_ENF_CEREBROVASCULAR [character]	1. No 2. Si	193 ( 97.0% ) 6 ( 3.0% )		199 (99.5%)	1 (0.5%)
169	ANT_FALLA_ENF_DEMENCIA [character]	1. No 2. Si	199 ( 99.5% ) 1 ( 0.5% )		200 (100.0%)	0 (0.0%)
170	ANT_FALLA_ENF_PULMONAR_OBSTRUCTIVA_CRONICA [character]	1. No 2. Si	194 ( 97.0% ) 6 ( 3.0% )		200 (100.0%)	0 (0.0%)
171	ANT_FALLA_ENF_TEJIDO_CONECTIVO [character]	1. No 2. Si	192 ( 96.0% ) 8 ( 4.0% )		200 (100.0%)	0 (0.0%)
172	ANT_FALLA_ULCERA_PEPTICA [character]	1. No 2. Si	188 ( 94.5% ) 11 ( 5.5% )		199 (99.5%)	1 (0.5%)
173	ANT_FALLA_ENF_HEPATICA [character]	1. Enfermedad hepática leve 2. Enfermedad hepática moder 3. Sin antecedente de enferm	7 ( 3.5% ) 1 ( 0.5% ) 190 ( 96.0% )		198 (99.0%)	2 (1.0%)
174	ANT_FALLA_DIABETES_MELLITUS [character]	1. Antecedente de Diabetes m 2. Diabetes mellitus sin co 3. Sin antecedente de diabet	2 ( 1.0% ) 12 ( 6.1% ) 183 ( 92.9% )		197 (98.5%)	3 (1.5%)
175	ANT_FALLA_HEMIPLEJIA [character]	1. No 2. Si	195 ( 98.0% ) 4 ( 2.0% )		199 (99.5%)	1 (0.5%)
176	ANT_ENF_RENAL_CRONICA [character]	1. Enfermedad renal crónica 2. Enfermedad renal crónica 3. Sin antecedente de enferm	5 ( 2.5% ) 3 ( 1.5% ) 190 ( 96.0% )		198 (99.0%)	2 (1.0%)
177	ANT_VIH [character]	1. No	198 ( 100.0% )		198 (99.0%)	2 (1.0%)
178	ANT_SIDA [character]	1. No	194 ( 100.0% )		194 (97.0%)	6 (3.0%)
179	INDICE_CHARLSON [numeric]	Mean (sd) : 4.6 (1.4) min ≤ med ≤ max: 2 ≤ 4 ≤ 9 IQR (CV) : 1 (0.3)	2 : 10 ( 5.0% ) 3 : 31 ( 15.5% ) 4 : 61 ( 30.5% ) 5 : 55 ( 27.5% ) 6 : 25 ( 12.5% ) 7 : 14 ( 7.0% ) 8 : 2 ( 1.0% ) 9 : 2 ( 1.0% )		200 (100.0%)	0 (0.0%)
180	ANTECEDENTES_COMPLETE [character]	1. Complete	200 ( 100.0% )		200 (100.0%)	0 (0.0%)

Generated by summarytools 1.1.4 (R version 4.4.2)
2025-09-03

Analisis descriptivo

• Recodificacion variables sociodemograficas y clinicas
• Cruce de variables

# Estrato 

library(dplyr)
DATA_SET <- DATA_SET %>% mutate(Estrato_cat = cut(ESTRATO, 
                                          breaks = c (0,2, 4, 6), 
                                          right = T, 
                                          labels = c("Bajo", "Medio", "Alto")))
# EDUCACION

DATA_SET$EDUCACION_CAT <- ifelse(DATA_SET$EDUCACION %in% c("Educación preescolar", "Educación básica (primaria)", "Sin educación formal"), "Primaria o menos", ifelse(DATA_SET$EDUCACION %in% c("Educación media (bachiller)"), "Basica/secundaria", ifelse(DATA_SET$EDUCACION %in% c("Educación superior (universitaria)", "Educación técnica", "Posgrado (especializacion, maestria, doctorado)"), "Mas que secundaria", DATA_SET$EDUCACION)))

DATA_SET$EDUCACION_CAT <- factor(DATA_SET$EDUCACION_CAT, levels = c("Primaria o menos", "Basica/secundaria", "Mas que secundaria") ) #REORDENANDO LAS CATEGORIAS


#Situacion marital 
DATA_SET$SIT_MARITAL_CAT <- ifelse(DATA_SET$SIT_MARITAL %in% c("Casado(a)", "Unión libre"), "Casada/Union Libre", 
                            ifelse(DATA_SET$SIT_MARITAL %in% c("Separado(a)", "Divorciado(a)", "Viudo(a)"), "Separada/Viuda", 
                            ifelse(DATA_SET$SIT_MARITAL %in% c("Soltero(a)"), "Soltera", DATA_SET$SIT_MARITAL)))

DATA_SET$SIT_MARITAL_CAT <- factor(DATA_SET$SIT_MARITAL_CAT, levels = c("Soltera", "Casada/Union Libre", "Separada/Viuda") ) #REORDENANDO LAS CATEGORIAS

#OCUPACION 

DATA_SET$OCUPACIONL_CAT <- ifelse(DATA_SET$OCUPACION %in% c("Ama de Casa", "Hogar"), "Ama de casa/hogar", 
                            ifelse(DATA_SET$OCUPACION %in% c("Abogado", "Administrador de Empresas", "Auxiliar Varios", "Auxiliares de Enfermeria", "Cocineros", "Contadores", "Empleados de Oficina", "Estilistas", "Ingenieros", "Oficiales de Cubierta", "Personal de Servidumbre", "Personal Directivo de la Administraci󮠐blica", "Profesores y Educadores", "Sastres y Modistos", "Secretaria", "Socioantrop󬯧o", "Vendedor"), "empleado/ocupado", 
                            DATA_SET$OCUPACION))

DATA_SET$OCUPACIONL_CAT<- factor(DATA_SET$OCUPACIONL_CAT, levels = c("Ama de casa/hogar", "empleado/ocupado", "Pensionado", "Cesante") ) #REORDENANDO LAS CATEGORIAS

#Satisfaccion salud

DATA_SET$SATISFACCION_CAT <- ifelse(DATA_SET$SATISFACCION_ATENCION_SALUD %in% c("Poco satisfecho", "Moderadamente satisfecho"), "Poco satisfechas", 
                             ifelse(DATA_SET$SATISFACCION_ATENCION_SALUD %in% c("Muy satisfecho", "Extremadamente satisfecho"), "Muy satisfechas", DATA_SET$SATISFACCION_ATENCION_SALUD))

#ESTADIO 

DATA_SET$ESTADIO <- ifelse(DATA_SET$ESTADIFICACION_MAMA_NCCN %in% c("0", "IA", "IB", "IIA"), "Temprano", 
                    ifelse(DATA_SET$ESTADIFICACION_MAMA_NCCN %in% c("IIB", "IIIA", "IIIB", "IIIC"), "Localmente avanzado", 
                    ifelse(DATA_SET$ESTADIFICACION_MAMA_NCCN %in% c("IV"), "Metastasico", DATA_SET$ESTADIFICACION_MAMA_NCCN)))


DATA_SET$ESTADIO<- factor(DATA_SET$ESTADIO, levels = c("Temprano", "Localmente avanzado", "Metastasico", "No reporta") ) #REORDENANDO LAS CATEGORIAS

#CLASIFICACION_INMUNOHISTOQUIMICA

DATA_SET <- DATA_SET %>% 
  mutate(LUMINAL_A = ifelse((CLASIFICACION_INMUNOHISTOQUIMICA_RE_POSITIVO == "Checked" | CLASIFICACION_INMUNOHISTOQUIMICA_RP_POSITIVO == "Checked" ) & (CLASIFICACION_INMUNOHISTOQUIMICA_KI_67_POSITIVO == "Unchecked" & CLASIFICACION_INMUNOHISTOQUIMICA_HER2_POSITIVO  == "Unchecked"), "Si", "No"))


DATA_SET <- DATA_SET %>% 
  mutate(LUMINAL_B = ifelse((CLASIFICACION_INMUNOHISTOQUIMICA_RE_POSITIVO == "Checked" | CLASIFICACION_INMUNOHISTOQUIMICA_RP_POSITIVO == "Checked" ) & (CLASIFICACION_INMUNOHISTOQUIMICA_KI_67_POSITIVO == "Checked" & CLASIFICACION_INMUNOHISTOQUIMICA_HER2_POSITIVO  == "Unchecked"), "Si", "No"))

DATA_SET <- DATA_SET %>% 
  mutate(HER2_POSITIVO = ifelse(CLASIFICACION_INMUNOHISTOQUIMICA_HER2_POSITIVO == "Checked", "Si", "No"))

DATA_SET <- DATA_SET %>% 
  mutate(TRIPLE_NEGATIVO = ifelse(CLASIFICACION_INMUNOHISTOQUIMICA_RE_POSITIVO == "Unchecked" & CLASIFICACION_INMUNOHISTOQUIMICA_RP_POSITIVO == "Unchecked" &  CLASIFICACION_INMUNOHISTOQUIMICA_HER2_POSITIVO  == "Unchecked", "Si", "No"))


#CLASIFICACION TRATAMIENTOS

DATA_SET <- DATA_SET %>% 
  mutate(TRAT_SISTEMICO = ifelse(TRAT_QUIMIOTERAPIA_NEOADYUVANTE == "Checked" |  TRAT_QUIMIOTERAPIA_ADYUVANTE == "Checked" | TIPO_T_SISTEMICO_NEOADYUVANTE_QUIMIOTERAPIA == "Checked" | TIPO_T_SISTEMICO_NEOADYUVANTE_T.BLANCO == "Checked" | TIPO_T_SISTEMICO_NEOADYUVANTE_INMUNOTERAPIA == "Checked" | TIPO_T_SISTEMICO_ADYUVANTE_QUIMIOTERAPIA == "Checked" | TIPO_T_SISTEMICO_ADYUVANTE_T.BLANCO == "Checked", "Si", "No"))


DATA_SET <- DATA_SET %>% 
  mutate(TRAT_RADIOTERAPIA = ifelse(TRAT_RADIOTERAPIA_NEOADYUVANTE == "Checked" |TRAT_RADIOTERAPIA_ADYUVANTE == "Checked" | TIPO_RADIOTERAPIA_ADYUVANTE_RADIACION_TODO_SENO_CONVENCIONAL == "Checked" | TIPO_RADIOTERAPIA_ADYUVANTE_RADIACION_TODO_SENO_HIPOFRACCIONADA == "Checked" | TIPO_RADIOTERAPIA_ADYUVANTE_RADIOT_3D_CRT == "Checked" | TIPO_RADIOTERAPIA_ADYUVANTE_RADIOT_IMRT == "Checked" | TIPO_RADIOTERAPIA_ADYUVANTE_BRAQUITERAPIA == "Checked" | TIPO_RADIOTERAPIA_ADYUVANTE_RADIACION_GANGLIOS == "Checked" | TIPO_RADIOTERAPIA_ADYUVANTE_OTRO == "Checked", "Si", "No"))

DATA_SET <- DATA_SET %>% 
  mutate(TRAT_CIRUGIA = ifelse(TRAT_CIRUGIA_RADICAL == "Checked" | TRAT_CIRUGIA_RADICAL_MODIFICADA == "Checked" | TRAT_CIRUGIA_CONSERVADORA == "Checked" | TRAT_VACIAMIENTO_GANGLIONAR == "Checked" | TRAT_CIRUGIA_RECONSTRUCTIVA == "Checked", "Si", "No"))

DATA_SET <- DATA_SET %>% 
  mutate(
    TRAT_HORMONOTERAPIA = ifelse(
      TRAT_TRATAMIENTO_HORMONAL == "Checked" |
      !is.na(TRAT_HORMONAL_COMPLETADO) |
      !is.na(TRAT_HORMONAL_ACTUAL),
      "Si",
      "No"
    )
  )

# Cuidado de soporte se prueban dos maneras: Recibio o no atencion y por recepcion de cuidado de soporte oncologico primario

DATA_SET <- DATA_SET %>% 
  mutate(Cuidado_soporte_UA = ifelse(ATENCION_UA_NINGUNO == "Unchecked", "Si", "No"))

DATA_SET <- DATA_SET %>% 
  mutate(Cuidado_soporte_primario = ifelse(ATENCION_UA_CUIDADO_PALIATIVO == "Checked" | ATENCION_UA_PSICOONCOLOGIA == "Checked" | ATENCION_UA_NUTRICION == "Checked" | ATENCION_UA_PROGRAMA_LINFEDEMA == "Checked" | ATENCION_UA_PROGRAMA_FATIGA_REH_ONCOLOGICA == "Checked", "Si", "No"))

#Indice charlson 

DATA_SET <- DATA_SET %>% 
  mutate(charlson_cat = cut(INDICE_CHARLSON,
                            breaks = c (-Inf, 2, 4, Inf),
                            right = T, 
                            labels = c ("1-2", "3-4", "=>5")
                            ))

Cruce de variables

Analisis descriptivo de las variables

#dput(names(DATA_SET))


myVars1 <- c("EDAD","Estrato_cat","EDUCACION_CAT", "SIT_MARITAL_CAT", "OCUPACIONL_CAT", "FRACCION_OCUPACIONES" , "SATISFACCION_CAT", "TIEMPO_SUPERVIVENCIA", "EDAD_DX",  "ESTADIO", "LUMINAL_A", "LUMINAL_B", "HER2_POSITIVO", "TRIPLE_NEGATIVO", "TRAT_SISTEMICO", "TRAT_ANTIHER2", "TRAT_RADIOTERAPIA", "TRAT_CIRUGIA", "TRAT_HORMONOTERAPIA", "RECAIDA_CANCER_MAMA", "charlson_cat", "Cuidado_soporte_UA", "Cuidado_soporte_primario") 
catVars1 <- c("Estrato_cat","EDUCACION_CAT", "SIT_MARITAL_CAT", "OCUPACIONL_CAT",  "SATISFACCION_CAT", "ESTADIO", "LUMINAL_A", "LUMINAL_B", "HER2_POSITIVO", "TRIPLE_NEGATIVO", "TRAT_SISTEMICO", "TRAT_ANTIHER2", "TRAT_RADIOTERAPIA", "TRAT_CIRUGIA", "TRAT_HORMONOTERAPIA", "RECAIDA_CANCER_MAMA", "charlson_cat", "Cuidado_soporte_UA", "Cuidado_soporte_primario")  

library(tableone)
tab1 <- CreateTableOne(vars = myVars1, factorVars= catVars1, data = DATA_SET, includeNA = T, test = T,addOverall = T)

table1 <- as.data.frame(print(tab1, showAllLevels= TRUE, printToggle = FALSE, noSpaces = TRUE))
rownames(table1) <- gsub("\\.{3,}", "", rownames(table1))  # Quita puntos suspensivos "..."
rownames(table1) <- gsub("\\.{1,}", "_", rownames(table1))  # Quita puntos suspensivos "..."
rownames(table1) <- gsub("\\_{1,}", " ", rownames(table1))  # Quita puntos suspensivos "..."


library(knitr)
library(kableExtra)

kable(table1, format = "html", caption = "Variable sociodemograficas") %>%
  kable_styling(bootstrap_options = c("striped", "hover", "condensed"), full_width = F,position = "center") %>%
  column_spec(1, bold = T, color = "white", background = "black") %>%
  column_spec(2, border_left = T, color = "white", background = "grey")

Variable sociodemograficas

	level	Overall
n		200
EDAD mean SD		65.12 (9.54)
Estrato cat	Bajo	82 (41.0)
X	Medio	111 (55.5)
X 1	Alto	7 (3.5)
EDUCACION CAT	Primaria o menos	82 (41.0)
X 2	Basica/secundaria	42 (21.0)
X 3	Mas que secundaria	76 (38.0)
SIT MARITAL CAT	Soltera	45 (22.5)
X 4	Casada/Union Libre	99 (49.5)
X 5	Separada/Viuda	55 (27.5)
X 6	NA	1 (0.5)
OCUPACIONL CAT	Ama de casa/hogar	91 (45.5)
X 7	empleado/ocupado	48 (24.0)
X 8	Pensionado	56 (28.0)
X 9	Cesante	5 (2.5)
FRACCION OCUPACIONES mean SD		60.47 (30.57)
SATISFACCION CAT	Muy satisfechas	184 (92.0)
X 10	Poco satisfechas	16 (8.0)
TIEMPO SUPERVIVENCIA mean SD		8.20 (4.84)
EDAD DX mean SD		56.92 (10.15)
ESTADIO	Temprano	107 (53.5)
X 11	Localmente avanzado	77 (38.5)
X 12	Metastasico	2 (1.0)
X 13	No reporta	14 (7.0)
LUMINAL A	No	89 (44.5)
X 14	Si	111 (55.5)
LUMINAL B	No	168 (84.0)
X 15	Si	32 (16.0)
HER2 POSITIVO	No	169 (84.5)
X 16	Si	31 (15.5)
TRIPLE NEGATIVO	No	174 (87.0)
X 17	Si	26 (13.0)
TRAT SISTEMICO	No	56 (28.0)
X 18	Si	144 (72.0)
TRAT ANTIHER2	Checked	29 (14.5)
X 19	Unchecked	171 (85.5)
TRAT RADIOTERAPIA	No	35 (17.5)
X 20	Si	165 (82.5)
TRAT CIRUGIA	No	2 (1.0)
X 21	Si	198 (99.0)
TRAT HORMONOTERAPIA	No	43 (21.5)
X 22	Si	157 (78.5)
RECAIDA CANCER MAMA	No	196 (98.0)
X 23	Si	4 (2.0)
charlson cat	1-2	10 (5.0)
X 24	3-4	92 (46.0)
X 25	=>5	98 (49.0)
Cuidado soporte UA	No	154 (77.0)
X 26	Si	46 (23.0)
Cuidado soporte primario	No	172 (86.0)
X 27	Si	28 (14.0)

Cruce variables

Cruzar ocupadas - ocupadas con fraccion de ocupaciones

DATA_CR <- DATA_SET %>% select(OCUPACIONL_CAT, FRACCION_OCUPACIONES)
print(stby(data = DATA_CR, INDICES = DATA_CR$OCUPACIONL_CAT, 
     FUN = descr, stats = "common", transpose = TRUE), method = 'render')

Descriptive Statistics

by OCUPACIONL_CAT

Data Frame: DATA_CR
N: 200

	Mean	Std.Dev	Min	Median	Max	N.Valid	N	Pct.Valid
Ama de casa/hogar	72.93	25.76	10.00	80.00	100.00	91	91	100.00
empleado/ocupado	39.83	26.09	5.00	30.00	100.00	48	48	100.00
Pensionado	59.20	31.87	1.00	56.50	100.00	56	56	100.00
Cesante	45.80	25.75	4.00	50.00	75.00	5	5	100.00

Generated by summarytools 1.1.4 (R version 4.4.2)
2025-09-03

# %>%
 # stview() ver en markdown 

Revisando diferencias

Se realiza una prueba de normalidad por cada categoría.

#install.packages("broom")
library(broom)
library(tidyr)
library(purrr)

tabla_shapiro <- DATA_CR %>%
  group_by(OCUPACIONL_CAT) %>%
  summarise(
    shapiro = list(shapiro.test(FRACCION_OCUPACIONES)),
    .groups = "drop"
  ) %>%
  mutate(shapiro = map(shapiro, tidy)) %>%
  unnest(shapiro)


library(gt)
tabla_shapiro %>%
  gt() %>%
  tab_header(
    title = md("**Prueba de normalidad Shapiro-Wilk por grupo**"),
    subtitle = "Resultados agrupados"
  ) %>%
  tab_style(
    style = cell_text(align = "center", weight = "bold", color = "darkblue"),
    locations = cells_column_labels(everything())
  ) %>%
  tab_style(
    style = cell_text(align = "center"),
    locations = cells_body(columns = everything())
  ) %>%
  fmt_number(
    columns = where(is.numeric),
    decimals = 4
  ) %>%
  opt_table_outline() %>%
  opt_row_striping()

Prueba de normalidad Shapiro-Wilk por grupo
Resultados agrupados
OCUPACIONL_CAT	statistic	p.value	method
Ama de casa/hogar	0.8764	0.0000	Shapiro-Wilk normality test
empleado/ocupado	0.8972	0.0005	Shapiro-Wilk normality test
Pensionado	0.9183	0.0010	Shapiro-Wilk normality test
Cesante	0.8394	0.1634	Shapiro-Wilk normality test

Se encontró una distribución no normal, se usa la prueba Kruskall wallis

kruskal_res <- kruskal.test(
  x = DATA_CR$FRACCION_OCUPACIONES,
  g = DATA_CR$OCUPACIONL_CAT
)

# convertir a tibble
kruskal_table <- tidy(kruskal_res)


kruskal_table %>%
  gt() %>%
  tab_header(
    title = md("**Prueba de Kruskal-Wallis**"),
    subtitle = md("Comparación de medianas entre grupos")
  ) %>%
  fmt_number(
    columns = everything(),
    decimals = 4
  ) %>%
  tab_style(
    style = list(
      cell_text(weight = "bold", color = "darkblue", align = "center")
    ),
    locations = cells_column_labels(everything())
  ) %>%
  opt_table_outline() %>% 
  tab_options(
    table.border.top.color    = "black",
    table.border.bottom.color = "black",
    table.font.size = 14
  )

Prueba de Kruskal-Wallis
Comparación de medianas entre grupos
statistic	p.value	parameter	method
37.9675	0.0000	3.0000	Kruskal-Wallis rank sum test

Hay diferencias en al menos en la distribución de una variable (hay al menos una mediana diferente). Se revisa la comparación entre pares (no parametrico)

library(FSA)

# Correr la prueba de Dunn
dunn_res <- dunnTest(FRACCION_OCUPACIONES ~ OCUPACIONL_CAT, 
                     data = DATA_CR, 
                     method = "bonferroni")

# Extraer la tabla de resultados
tabla_dunn <- dunn_res$res

# Pasar a gt para embellecer
tabla_dunn %>%
  gt() %>%
  tab_header(
    title = "Prueba de Dunn post-hoc",
    subtitle = "Ajuste por Bonferroni"
  ) %>%
  cols_label(
    Comparison = "Comparación",
    Z          = "Estadístico Z",
    P.unadj    = "p-valor sin ajuste",
    P.adj      = "p-valor ajustado"
  ) %>%
  fmt_number(
    columns = c(Z, P.unadj, P.adj),
    decimals = 4
  ) %>%
  tab_style(
    style = list(
      cell_text(weight = "bold", align = "center")
    ),
    locations = cells_column_labels(everything())
  )

Prueba de Dunn post-hoc
Ajuste por Bonferroni
Comparación	Estadístico Z	p-valor sin ajuste	p-valor ajustado
Ama de casa/hogar - Cesante	1.9816	0.0475	0.2851
Ama de casa/hogar - empleado/ocupado	6.0429	0.0000	0.0000
Cesante - empleado/ocupado	0.3570	0.7211	1.0000
Ama de casa/hogar - Pensionado	2.5181	0.0118	0.0708
Cesante - Pensionado	−1.0338	0.3012	1.0000
empleado/ocupado - Pensionado	−3.3060	0.0009	0.0057

Hay diferencias entre todas las modalidades de ocupación y la fracción de ocupaciones.

Revisando intersecciones cuidado de soporte

library(limma)
library(UpSetR)
BASE_UPSET <- DATA_SET %>% select(ATENCION_UA_CUIDADO_PALIATIVO, ATENCION_UA_PSICOONCOLOGIA, ATENCION_UA_NUTRICION, ATENCION_UA_PROGRAMA_LINFEDEMA, ATENCION_UA_PROGRAMA_FATIGA_REH_ONCOLOGICA, ATENCION_UA_SEXOLOGIA_GINECOLOGIA_FUNCIONAL, ATENCION_UA_NEUROLOGIA, ATENCION_UA_TRABAJO_SOCIAL, ATENCION_UA_MEDICINA_OCUPACIONAL, ATENCION_UA_MEDICINA_CIRUGIA_PLASTICA_RECONSTRUCTIVA, ATENCION_UA_MEDICINA_FISIATRIA_MEDICINA_FISICA)

colnames(BASE_UPSET)[colnames(BASE_UPSET) =="ATENCION_UA_CUIDADO_PALIATIVO"] <- "Cuidado paliativo"

colnames(BASE_UPSET)[colnames(BASE_UPSET) =="ATENCION_UA_PSICOONCOLOGIA"] <- "Psicooncologia"

colnames(BASE_UPSET)[colnames(BASE_UPSET) =="ATENCION_UA_NUTRICION"] <- "Nutricion"

colnames(BASE_UPSET)[colnames(BASE_UPSET) =="ATENCION_UA_PROGRAMA_LINFEDEMA"] <- "Linfedema"

colnames(BASE_UPSET)[colnames(BASE_UPSET) =="ATENCION_UA_PROGRAMA_FATIGA_REH_ONCOLOGICA"] <- "Programa Fatiga"

colnames(BASE_UPSET)[colnames(BASE_UPSET) =="ATENCION_UA_SEXOLOGIA_GINECOLOGIA_FUNCIONAL"] <- "Sexologia Gineco"

colnames(BASE_UPSET)[colnames(BASE_UPSET) =="ATENCION_UA_NEUROLOGIA"] <- "Neurologia"

colnames(BASE_UPSET)[colnames(BASE_UPSET) =="ATENCION_UA_TRABAJO_SOCIAL"] <- "Trabajo social"

colnames(BASE_UPSET)[colnames(BASE_UPSET) =="ATENCION_UA_MEDICINA_OCUPACIONAL"] <- "Medicina Ocupacional"

colnames(BASE_UPSET)[colnames(BASE_UPSET) =="ATENCION_UA_MEDICINA_CIRUGIA_PLASTICA_RECONSTRUCTIVA"] <- "Cirugia plastica"

colnames(BASE_UPSET)[colnames(BASE_UPSET) =="ATENCION_UA_MEDICINA_FISIATRIA_MEDICINA_FISICA"] <- "Medicina fisica"


BASE_UPSET <- BASE_UPSET %>%
  mutate(across(c(1:11), ~ recode(., "Checked" = 1, "Unchecked" = 0)))

BASE_UPSET<- as.data.frame(BASE_UPSET)

upset(BASE_UPSET, order.by = "freq", nsets = 11, nintersects = 20,
      matrix.color = "#2F4F4F",  main.bar.color = "darkblue", sets.bar.color = "#5F9EA0", mainbar.y.label = "Intersecciones Cuidado soporte",  sets.x.label = "Atencion especialidad", point.size = 2, line.size = 0.5, number.angles = 0, group.by = "degree", shade.alpha = 1, matrix.dot.alpha = 1, scale.intersections = "identity", scale.sets = "identity", text.scale = 1, set_size.show = T)

Perfiles latentes

• Se ajusta la base de datos (variables continuas)
• Se busca identificar potenciales pacientes “descuidados”
• Se imputan los datos (vecino más cercano)
• Se estiman los perfiles con todos los datos y sin todos los datos

#Ajuste base datos

library(dplyr)
DATA_PROFILES <- DATA_SET %>% mutate(across(c(14:41, 44:66), ~ recode(., "Un poco" = 1, "Para nada" = 2, "Mucho"  = 3, "Bastante" = 4))) # no se incluyeron las columnas 44 y 45 debido que son items que van de 1 a 7

# se invirtieron los items 44, 45 y 46. 
DATA_PROFILES<- DATA_PROFILES %>%
  mutate(across(57:59, ~ recode(., `1` = 4,`2` = 3, `3` = 2, `4` = 1)))

Revisando posibles pacientes “descuidados”

#install.packages("careless")
library(careless)
library(psych)


DATA_PROFILES_careless <- DATA_PROFILES %>%
  select(1, 14:43) %>%  # Solo columna 1 (ID) + columnas 14:66 (variables QLQ)
  mutate(string = longstring(select(., -1))) %>%      # Calcular longstring excluyendo ID
  mutate(md = outlier(select(., -1), plot = FALSE))   # Calcular MD excluyendo ID

library(knitr)
library(kableExtra)

# Crear tabla de frecuencias
tabla_freq <- freq(DATA_PROFILES_careless$string, report.nas = TRUE)
tabla_df <- as.data.frame(tabla_freq)


# Mostrar tabla con bordes
kable(tabla_df, caption = "Frecuencia de la variable", align = "c") %>%
  kable_styling(
    bootstrap_options = c("striped", "bordered", "hover", "condensed"),
    full_width = FALSE,
    position = "center"
  )

Frecuencia de la variable

	Freq	% Valid	% Valid Cum.	% Total	% Total Cum.
2	1	0.5	0.5	0.5	0.5
3	7	3.5	4.0	3.5	4.0
4	12	6.0	10.0	6.0	10.0
5	28	14.0	24.0	14.0	24.0
6	16	8.0	32.0	8.0	32.0
7	28	14.0	46.0	14.0	46.0
8	17	8.5	54.5	8.5	54.5
9	29	14.5	69.0	14.5	69.0
10	20	10.0	79.0	10.0	79.0
11	3	1.5	80.5	1.5	80.5
12	6	3.0	83.5	3.0	83.5
14	3	1.5	85.0	1.5	85.0
15	2	1.0	86.0	1.0	86.0
16	2	1.0	87.0	1.0	87.0
17	4	2.0	89.0	2.0	89.0
18	4	2.0	91.0	2.0	91.0
19	6	3.0	94.0	3.0	94.0
20	2	1.0	95.0	1.0	95.0
21	2	1.0	96.0	1.0	96.0
22	1	0.5	96.5	0.5	96.5
24	2	1.0	97.5	1.0	97.5
27	1	0.5	98.0	0.5	98.0
28	4	2.0	100.0	2.0	100.0
<NA>	0	NA	NA	0.0	100.0
Total	200	100.0	100.0	100.0	100.0

Se identifican los ID

indices_problematicos <- which(DATA_PROFILES_careless$string >= 20)
print(paste("Números de fila con longstring >= 20:", paste(indices_problematicos, collapse = ", ")))

## [1] "Números de fila con longstring >= 20: 16, 25, 65, 82, 95, 104, 105, 107, 120, 123, 160, 199"

tabla_df2<- DATA_PROFILES_careless[c(16, 25, 65, 82, 95, 104, 105, 107, 120, 123, 160, 199),]


kable(tabla_df2, caption = "Casos con patron ´descuidado´", align = "c") %>%
  kable_styling(
    bootstrap_options = c("striped", "bordered", "hover", "condensed"),
    full_width = FALSE,
    position = "center"
  )

Casos con patron ´descuidado´

ID	qlq_c30_1	qlq_c30_2	qlq_c30_3	qlq_c30_4	qlq_c30_5	qlq_c30_6	qlq_c30_7	qlq_c30_8	qlq_c30_9	qlq_c30_10	qlq_c30_11	qlq_c30_12	qlq_c30_13	qlq_c30_14	qlq_c30_15	qlq_c30_16	qlq_c30_17	qlq_c30_18	qlq_c30_19	qlq_c30_20	qlq_c30_21	qlq_c30_22	qlq_c30_23	qlq_c30_24	qlq_c30_25	qlq_c30_26	qlq_c30_27	qlq_c30_28	qlq_c30_29	qlq_c30_30	string	md
16	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	7	7	28	13.067318
25	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	7	7	28	13.067318
65	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	1	2	2	2	2	2	6	6	22	8.212105
82	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	1	1	2	1	2	2	2	2	7	7	20	8.298888
95	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	1	1	2	2	2	2	2	6	7	21	8.607638
104	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	7	7	28	13.067318
105	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	7	7	28	13.067318
107	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	1	2	2	2	7	7	24	9.251880
120	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	1	2	2	1	2	2	2	7	7	21	8.054821
123	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	1	2	2	2	6	6	24	9.773573
160	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	1	1	2	2	2	2	2	2	6	6	20	6.927155
199	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	2	4	6	7	27	27.569145

Se mantuvieron los ID, puesto que tienen sentido clínico

#se limpio la base de datos eliminando esos 5 datos. 
#DATA_PROFILES_clean <- DATA_PROFILES %>%
# filter(!ID %in% c(16, 25, 104, 105, 199))  

Imputando las observaciones faltantes

Se utilizo el metodo del vecino mas cercano: K-nearest neighbors (KNN). Utiliza observaciones similares (vecinos) en múltiples variables para predecir un valor razonable para el dato faltante. No asume una distribución especifica y puede asignar valores diferentes a distintos casos faltantes, lo cual refleja mejor la dispersión natural de los datos.

Solo se uso para el item 1

Teniendo en cuenta que se completaron los datos perdidos, no fue necesario la imputación.

#install.packages("VIM")
#library(VIM)

#DATA_PROFILES_imp <- kNN(DATA_PROFILES, 
#                           variable = c("qlq_c30_1"), 
#                           k = 5, 
#                           imp_var = FALSE)

Generacion de totales

########################## BASE #############################


DATA_PROFILES <- DATA_PROFILES %>% 
  mutate(PF = qlq_c30_1 + qlq_c30_2 + qlq_c30_3 + qlq_c30_4 + qlq_c30_5) #Physical functioning 1

DATA_PROFILES <- DATA_PROFILES%>% 
  mutate(RF = qlq_c30_6 + qlq_c30_7) # Role functioning 2 

DATA_PROFILES <- DATA_PROFILES %>% 
  mutate(CF = qlq_c30_20 + qlq_c30_25) #Cognitive functioning 3 

DATA_PROFILES <- DATA_PROFILES %>% 
  mutate(EF = qlq_c30_21 + qlq_c30_22 + qlq_c30_23 + qlq_c30_24) #Emotional functioning 4 

DATA_PROFILES <- DATA_PROFILES %>% 
  mutate(SF = qlq_c30_26 + qlq_c30_27)#Social functioning 5

DATA_PROFILES <- DATA_PROFILES %>% 
  mutate(GLH = qlq_c30_29 + qlq_c30_30) #Global health status / QoL 6 

DATA_PROFILES <- DATA_PROFILES %>% 
  mutate(FA = qlq_c30_10 + qlq_c30_12 + qlq_c30_18) #Fatigue 7 

DATA_PROFILES <- DATA_PROFILES %>% 
  mutate(NV = qlq_c30_14 + qlq_c30_15) #Nausea and vomiting 8 

DATA_PROFILES <- DATA_PROFILES %>% 
  mutate(PA = qlq_c30_9 + qlq_c30_19) #Pain 9 

DATA_PROFILES <- DATA_PROFILES %>% 
  mutate(DY = qlq_c30_8) #Dyspnoea 10 

DATA_PROFILES <- DATA_PROFILES %>% 
  mutate(SL = qlq_c30_11) #Insomnia 11 

DATA_PROFILES <- DATA_PROFILES %>% 
  mutate(AP = qlq_c30_13) #Appetite loss 12 

DATA_PROFILES <- DATA_PROFILES %>% 
  mutate(CO = qlq_c30_16) #Constipation 13 

DATA_PROFILES <- DATA_PROFILES %>% 
  mutate(DI = qlq_c30_17) #Diarrhoea 14

#################### Escalas suplementarias ############################

DATA_PROFILES <- DATA_PROFILES %>% 
  mutate(FI = qlq_c30_28) #Financial difficulties 15 

DATA_PROFILES <- DATA_PROFILES %>% 
  mutate(BRST = qlq_c30_31 + qlq_c30_32 + qlq_c30_33 + qlq_c30_34 + qlq_c30_36 + qlq_c30_37 + qlq_c30_38) #Systemic therapy side effects 16 

DATA_PROFILES <- DATA_PROFILES %>% 
  mutate(BRHL = qlq_c30_35) #Upset by hair loss 17

DATA_PROFILES <- DATA_PROFILES %>% 
  mutate(BRBI = qlq_c30_39 + qlq_c30_40 + qlq_c30_41 + qlq_c30_42) #Body image 18

DATA_PROFILES <- DATA_PROFILES %>% 
  mutate(BRFU = qlq_c30_43) #Future perspective 19

DATA_PROFILES <- DATA_PROFILES %>% 
  mutate(BRSEF = qlq_c30_44 + qlq_c30_45) #Sexual functionning 20

DATA_PROFILES <- DATA_PROFILES %>% 
  mutate(BRSEE = qlq_c30_46) #Sexual enjoyment 21

DATA_PROFILES <- DATA_PROFILES %>% 
  mutate(BRAS = qlq_c30_47 + qlq_c30_48 + qlq_c30_49) #Arm symptoms 22

DATA_PROFILES <- DATA_PROFILES %>% 
  mutate(BRBS = qlq_c30_50 + qlq_c30_51 + qlq_c30_52 + qlq_c30_53) #Breast symptoms 23

Perfiles

#latent profile analysis 


colnames(DATA_PROFILES)[colnames(DATA_PROFILES) =="qlq_c30_1"] <- "QL1"

colnames(DATA_PROFILES)[colnames(DATA_PROFILES) =="qlq_c30_2"] <- "QL2"

colnames(DATA_PROFILES)[colnames(DATA_PROFILES) =="qlq_c30_3"] <- "QL3"

colnames(DATA_PROFILES)[colnames(DATA_PROFILES) =="qlq_c30_4"] <- "QL4"

colnames(DATA_PROFILES)[colnames(DATA_PROFILES) =="qlq_c30_5"] <- "QL5"

colnames(DATA_PROFILES)[colnames(DATA_PROFILES) =="qlq_c30_6"] <- "QL6"

colnames(DATA_PROFILES)[colnames(DATA_PROFILES) =="qlq_c30_7"] <- "QL7"

colnames(DATA_PROFILES)[colnames(DATA_PROFILES) =="qlq_c30_8"] <- "QL8"

colnames(DATA_PROFILES)[colnames(DATA_PROFILES) =="qlq_c30_9"] <- "QL9"

colnames(DATA_PROFILES)[colnames(DATA_PROFILES) =="qlq_c30_10"] <- "QL10"

colnames(DATA_PROFILES)[colnames(DATA_PROFILES) =="qlq_c30_11"] <- "QL11"

colnames(DATA_PROFILES)[colnames(DATA_PROFILES) =="qlq_c30_12"] <- "QL12"

colnames(DATA_PROFILES)[colnames(DATA_PROFILES) =="qlq_c30_13"] <- "QL13"

colnames(DATA_PROFILES)[colnames(DATA_PROFILES) =="qlq_c30_14"] <- "QL14"

colnames(DATA_PROFILES)[colnames(DATA_PROFILES) =="qlq_c30_15"] <- "QL15"

colnames(DATA_PROFILES)[colnames(DATA_PROFILES) =="qlq_c30_16"] <- "QL16"

colnames(DATA_PROFILES)[colnames(DATA_PROFILES) =="qlq_c30_17"] <- "QL17"

colnames(DATA_PROFILES)[colnames(DATA_PROFILES) =="qlq_c30_18"] <- "QL18"

colnames(DATA_PROFILES)[colnames(DATA_PROFILES) =="qlq_c30_19"] <- "QL19"

colnames(DATA_PROFILES)[colnames(DATA_PROFILES) =="qlq_c30_20"] <- "QL20"

colnames(DATA_PROFILES)[colnames(DATA_PROFILES) =="qlq_c30_21"] <- "QL21"

colnames(DATA_PROFILES)[colnames(DATA_PROFILES) =="qlq_c30_22"] <- "QL22"

colnames(DATA_PROFILES)[colnames(DATA_PROFILES) =="qlq_c30_23"] <- "QL23"

colnames(DATA_PROFILES)[colnames(DATA_PROFILES) =="qlq_c30_24"] <- "QL24"

colnames(DATA_PROFILES)[colnames(DATA_PROFILES) =="qlq_c30_25"] <- "QL25"

colnames(DATA_PROFILES)[colnames(DATA_PROFILES) =="qlq_c30_26"] <- "QL26"

colnames(DATA_PROFILES)[colnames(DATA_PROFILES) =="qlq_c30_27"] <- "QL27"

colnames(DATA_PROFILES)[colnames(DATA_PROFILES) =="qlq_c30_28"] <- "QL28"

colnames(DATA_PROFILES)[colnames(DATA_PROFILES) =="qlq_c30_29"] <- "QL29"

colnames(DATA_PROFILES)[colnames(DATA_PROFILES) =="qlq_c30_30"] <- "QL30"

library(mclust)
DATA_PROFILES_ANALYSIS_TOTAL <- DATA_PROFILES %>% 
  select(ID, PF, RF, CF, EF, SF, GLH, FA, NV, PA, DY, SL, AP, CO, DI )

DATA_PROFILES_ITEM <- DATA_PROFILES %>% 
  select(ID, QL1, QL2, QL3, QL4, QL5, QL6, QL7, QL20, QL25, QL21, QL22, QL23, QL24, QL26, QL27, QL10, QL12, QL18, QL14, QL15, QL9, QL19, QL8, QL11, QL13, QL16, QL17, QL29, QL30)


mc1 <-mclustBIC(DATA_PROFILES_ITEM[,-1]) #create the model items
mc2 <-mclustBIC(DATA_PROFILES_ANALYSIS_TOTAL[,-1]) #create the model totals

set.seed(2025)
summary(mc1) # 2 - 4 GRUPOS CON item

## Best BIC values:
##              VEI,3      VEI,2     EEI,2
## BIC      -8932.165 -9907.6195 -11702.78
## BIC diff     0.000  -975.4549  -2770.62

summary(mc2) # 7 - 9 GRUPOS CON totales

## Best BIC values:
##             VEI,9      VEI,8      VEI,7
## BIC      -6226.15 -6454.1912 -6492.3054
## BIC diff     0.00  -228.0413  -266.1555

Cuando se analizan items se podrian encontrar entre 2 a 4 perfiles

Cuando se analizan totales se podrian encontrar entre 7 a 9 perfiles

Hay menos grupos cuando se analizan items que los totales

#install.packages("factoextra")
library(factoextra) #plotting the best model
mc1.1 <-Mclust(DATA_PROFILES_ITEM[,-1])
fviz_mclust_bic(mc1.1)

Se encontrarian una mejor solucion en 4 perfiles

Se utiliza el modelo de analisis por items

model1 <- Mclust(DATA_PROFILES_ITEM[,-1], modelNames = "VEI", G = 3)
summary(model1)

## ---------------------------------------------------- 
## Gaussian finite mixture model fitted by EM algorithm 
## ---------------------------------------------------- 
## 
## Mclust VEI (diagonal, equal shape) model with 3 components: 
## 
##  log-likelihood   n  df       BIC       ICL
##       -4148.183 200 120 -8932.165 -8933.862
## 
## Clustering table:
##   1   2   3 
##  67  30 103

Graficando los perfiles

Se obtienen primero las probabilidades de pertencia

library(tibble)
library(tidyr)

means <- data.frame(model1$parameters$mean) %>%
  rownames_to_column() %>%
  rename(DATA_PROFILES_imp = rowname) %>%
  pivot_longer(cols = c(X1, X2, X3), names_to = "Profile", values_to = "Mean") %>%
  mutate(
    Mean = round(Mean, 2),
    # Estandarización Z (normalización usando media y desviación estándar)
    Mean = (Mean - mean(Mean)) / sd(Mean)
  )


p <- means %>%
  mutate(Profile = recode(Profile, 
                          X1 = "P1",
                          X2 = "P2", 
                          X3 = "P3")) %>%
  ggplot(aes(DATA_PROFILES_imp, Mean, group = Profile, color = Profile)) +
  geom_point(size = 2.25) +
  geom_line(size = 1.25) +
  scale_x_discrete(limits = c("QL1", "QL2", "QL3", "QL4", "QL5", "QL6", "QL7", "QL20", "QL25", 
"QL21", "QL22", "QL23", "QL24", "QL26", "QL27", "QL10", "QL12", "QL18", "QL14", "QL15", "QL9", "QL19", "QL8", "QL11", "QL13", "QL16", "QL17", "QL29", "QL30" )) +
    scale_color_manual(values = c("P1" = "blue2", "P2" = "green4", "P3" = "darkorange2"))+
  labs(x = "Items calidad vida", y = "Media estandarizada", title = "Perfiles Calidad de vida") +
  theme_bw(base_size = 14) +
  theme(
    axis.text.x = element_text(angle = 90, hjust = 1, size = 10, face = "bold"),   # Letras eje X más grandes y en negrita
    axis.text.y = element_text(size = 14, face = "bold"),                         # Letras eje Y más grandes y en negrita
    axis.title.x = element_text(size = 16, face = "bold"),                       # Aumentar tamaño de la etiqueta del eje X
    axis.title.y = element_text(size = 16, face = "bold"),                       # Aumentar tamaño de la etiqueta del eje Y
    legend.position = "right", 
    legend.text = element_text(size = 10, face = "bold"),                        # Aumentar el tamaño de la leyenda y ponerla en negrita
    legend.title = element_text(size = 16, face = "bold")                       # Aumentar tamaño del título de la leyenda
  )
p

Se encontraron solamente 3 perfiles

Se procede a caracterizarlos

#Primero se conoce la clasificaicón por perfil 

# Extraer las clasificaciones del modelo
clases <- model1$classification

# Agregar las clases al data frame "attitudes_clean"
DATA_PROFILES <- DATA_PROFILES %>%
  mutate(Perfil = clases)


myVars2 <- c("EDAD","Estrato_cat","EDUCACION_CAT", "SIT_MARITAL_CAT", "OCUPACIONL_CAT", "FRACCION_OCUPACIONES" , "SATISFACCION_CAT", "TIEMPO_SUPERVIVENCIA", "EDAD_DX",  "ESTADIO", "LUMINAL_A", "LUMINAL_B", "HER2_POSITIVO", "TRIPLE_NEGATIVO", "TRAT_SISTEMICO", "TRAT_ANTIHER2", "TRAT_RADIOTERAPIA", "TRAT_CIRUGIA", "TRAT_HORMONOTERAPIA", "RECAIDA_CANCER_MAMA", "charlson_cat", "Cuidado_soporte_UA", "Cuidado_soporte_primario", "PF", "RF", "CF", "EF", "SF", "GLH", "FA", "NV", "PA", "DY", "SL", "AP", "CO", "DI", "FI", "BRST", "BRHL", "BRBI", "BRFU", "BRSEF", "BRSEE", "BRAS", "BRBS") 
catVars2 <- c("Estrato_cat","EDUCACION_CAT", "SIT_MARITAL_CAT", "OCUPACIONL_CAT",  "SATISFACCION_CAT", "ESTADIO", "LUMINAL_A", "LUMINAL_B", "HER2_POSITIVO", "TRIPLE_NEGATIVO", "TRAT_SISTEMICO", "TRAT_ANTIHER2", "TRAT_RADIOTERAPIA", "TRAT_CIRUGIA", "TRAT_HORMONOTERAPIA", "RECAIDA_CANCER_MAMA", "charlson_cat", "Cuidado_soporte_UA", "Cuidado_soporte_primario")  


tab2 <- CreateTableOne(vars = myVars2, factorVars= catVars2, data = DATA_PROFILES, strata ="Perfil", includeNA = T, test = T,addOverall = T)

table2 <- as.data.frame(print(tab2, showAllLevels= TRUE, printToggle = FALSE, noSpaces = TRUE))
rownames(table2) <- gsub("\\.{3,}", "", rownames(table2))  # Quita puntos suspensivos "..."
rownames(table2) <- gsub("\\.{1,}", "_", rownames(table2))  # Quita puntos suspensivos "..."
rownames(table2) <- gsub("\\_{1,}", " ", rownames(table2))  # Quita puntos suspensivos "..."

kable(table2, format = "html", caption = "Variable sociodemograficas") %>%
  kable_styling(bootstrap_options = c("striped", "hover", "condensed"), full_width = F,position = "center") %>%
  column_spec(1, bold = T, color = "white", background = "black") %>%
  column_spec(2, border_left = T, color = "white", background = "grey")

Variable sociodemograficas

	level	Overall	1	2	3	p	test
n		200	67	30	103
EDAD mean SD		65.12 (9.54)	65.75 (9.68)	66.53 (10.32)	64.31 (9.22)	0.432
Estrato cat	Bajo	82 (41.0)	27 (40.3)	16 (53.3)	39 (37.9)	0.524
X	Medio	111 (55.5)	37 (55.2)	14 (46.7)	60 (58.3)
X 1	Alto	7 (3.5)	3 (4.5)	0 (0.0)	4 (3.9)
EDUCACION CAT	Primaria o menos	82 (41.0)	26 (38.8)	17 (56.7)	39 (37.9)	0.171
X 2	Basica/secundaria	42 (21.0)	11 (16.4)	4 (13.3)	27 (26.2)
X 3	Mas que secundaria	76 (38.0)	30 (44.8)	9 (30.0)	37 (35.9)
SIT MARITAL CAT	Soltera	45 (22.5)	10 (14.9)	8 (26.7)	27 (26.2)	0.316
X 4	Casada/Union Libre	99 (49.5)	36 (53.7)	11 (36.7)	52 (50.5)
X 5	Separada/Viuda	55 (27.5)	21 (31.3)	11 (36.7)	23 (22.3)
X 6	NA	1 (0.5)	0 (0.0)	0 (0.0)	1 (1.0)
OCUPACIONL CAT	Ama de casa/hogar	91 (45.5)	26 (38.8)	16 (53.3)	49 (47.6)	0.430
X 7	empleado/ocupado	48 (24.0)	19 (28.4)	6 (20.0)	23 (22.3)
X 8	Pensionado	56 (28.0)	20 (29.9)	6 (20.0)	30 (29.1)
X 9	Cesante	5 (2.5)	2 (3.0)	2 (6.7)	1 (1.0)
FRACCION OCUPACIONES mean SD		60.47 (30.57)	59.34 (29.93)	54.27 (28.79)	63.00 (31.46)	0.364
SATISFACCION CAT	Muy satisfechas	184 (92.0)	62 (92.5)	27 (90.0)	95 (92.2)	0.906
X 10	Poco satisfechas	16 (8.0)	5 (7.5)	3 (10.0)	8 (7.8)
TIEMPO SUPERVIVENCIA mean SD		8.20 (4.84)	8.55 (5.60)	7.87 (3.77)	8.08 (4.61)	0.757
EDAD DX mean SD		56.92 (10.15)	57.19 (11.28)	58.67 (9.17)	56.23 (9.66)	0.496
ESTADIO	Temprano	107 (53.5)	33 (49.3)	25 (83.3)	49 (47.6)	0.007
X 11	Localmente avanzado	77 (38.5)	26 (38.8)	4 (13.3)	47 (45.6)
X 12	Metastasico	2 (1.0)	0 (0.0)	0 (0.0)	2 (1.9)
X 13	No reporta	14 (7.0)	8 (11.9)	1 (3.3)	5 (4.9)
LUMINAL A	No	89 (44.5)	25 (37.3)	14 (46.7)	50 (48.5)	0.343
X 14	Si	111 (55.5)	42 (62.7)	16 (53.3)	53 (51.5)
LUMINAL B	No	168 (84.0)	58 (86.6)	25 (83.3)	85 (82.5)	0.777
X 15	Si	32 (16.0)	9 (13.4)	5 (16.7)	18 (17.5)
HER2 POSITIVO	No	169 (84.5)	59 (88.1)	24 (80.0)	86 (83.5)	0.551
X 16	Si	31 (15.5)	8 (11.9)	6 (20.0)	17 (16.5)
TRIPLE NEGATIVO	No	174 (87.0)	59 (88.1)	27 (90.0)	88 (85.4)	0.768
X 17	Si	26 (13.0)	8 (11.9)	3 (10.0)	15 (14.6)
TRAT SISTEMICO	No	56 (28.0)	21 (31.3)	12 (40.0)	23 (22.3)	0.125
X 18	Si	144 (72.0)	46 (68.7)	18 (60.0)	80 (77.7)
TRAT ANTIHER2	Checked	29 (14.5)	9 (13.4)	6 (20.0)	14 (13.6)	0.650
X 19	Unchecked	171 (85.5)	58 (86.6)	24 (80.0)	89 (86.4)
TRAT RADIOTERAPIA	No	35 (17.5)	12 (17.9)	6 (20.0)	17 (16.5)	0.901
X 20	Si	165 (82.5)	55 (82.1)	24 (80.0)	86 (83.5)
TRAT CIRUGIA	No	2 (1.0)	1 (1.5)	0 (0.0)	1 (1.0)	0.791
X 21	Si	198 (99.0)	66 (98.5)	30 (100.0)	102 (99.0)
TRAT HORMONOTERAPIA	No	43 (21.5)	12 (17.9)	7 (23.3)	24 (23.3)	0.681
X 22	Si	157 (78.5)	55 (82.1)	23 (76.7)	79 (76.7)
RECAIDA CANCER MAMA	No	196 (98.0)	65 (97.0)	29 (96.7)	102 (99.0)	0.560
X 23	Si	4 (2.0)	2 (3.0)	1 (3.3)	1 (1.0)
charlson cat	1-2	10 (5.0)	4 (6.0)	1 (3.3)	5 (4.9)	0.314
X 24	3-4	92 (46.0)	31 (46.3)	9 (30.0)	52 (50.5)
X 25	=>5	98 (49.0)	32 (47.8)	20 (66.7)	46 (44.7)
Cuidado soporte UA	No	154 (77.0)	60 (89.6)	18 (60.0)	76 (73.8)	0.003
X 26	Si	46 (23.0)	7 (10.4)	12 (40.0)	27 (26.2)
Cuidado soporte primario	No	172 (86.0)	64 (95.5)	22 (73.3)	86 (83.5)	0.008
X 27	Si	28 (14.0)	3 (4.5)	8 (26.7)	17 (16.5)
PF mean SD		10.18 (1.71)	9.78 (0.83)	11.80 (2.54)	9.97 (1.59)	<0.001
RF mean SD		4.03 (0.87)	3.97 (0.17)	4.57 (1.65)	3.90 (0.76)	0.001
CF mean SD		3.90 (1.31)	3.66 (0.64)	4.53 (1.70)	3.87 (1.46)	0.009
EF mean SD		7.92 (2.16)	7.40 (1.18)	8.87 (2.66)	7.99 (2.39)	0.007
SF mean SD		3.96 (0.90)	4.00 (0.00)	4.57 (2.06)	3.77 (0.49)	<0.001
GLH mean SD		11.31 (2.05)	12.63 (1.27)	9.23 (2.31)	11.06 (1.78)	<0.001
FA mean SD		5.70 (1.64)	5.58 (0.74)	7.60 (2.49)	5.22 (1.35)	<0.001
NV mean SD		3.90 (0.45)	4.00 (0.00)	3.83 (0.99)	3.86 (0.34)	0.105
PA mean SD		4.03 (1.67)	3.57 (0.87)	4.83 (2.17)	4.10 (1.81)	0.002
DY mean SD		1.92 (0.57)	1.90 (0.31)	2.00 (0.91)	1.91 (0.58)	0.696
SL mean SD		1.97 (0.94)	1.82 (0.63)	2.47 (1.22)	1.91 (0.97)	0.005
AP mean SD		2.02 (0.50)	2.00 (0.00)	2.40 (0.93)	1.92 (0.44)	<0.001
CO mean SD		1.93 (0.65)	1.82 (0.39)	1.93 (0.83)	1.99 (0.72)	0.251
DI mean SD		1.99 (0.43)	2.00 (0.00)	2.20 (0.92)	1.92 (0.30)	0.006
FI mean SD		2.00 (0.61)	1.99 (0.33)	2.20 (1.06)	1.96 (0.56)	0.156
BRST mean SD		14.37 (2.50)	13.39 (1.49)	16.47 (2.64)	14.40 (2.62)	<0.001
BRHL mean SD		2.14 (0.74)	1.94 (0.25)	2.21 (0.83)	2.25 (0.89)	0.029
BRBI mean SD		7.75 (1.29)	7.76 (0.61)	7.57 (2.28)	7.80 (1.23)	0.692
BRFU mean SD		2.22 (1.14)	1.85 (0.82)	2.70 (1.24)	2.32 (1.23)	0.001
BRSEF mean SD		6.19 (1.13)	6.31 (1.12)	6.07 (0.94)	6.15 (1.18)	0.519
BRSEE mean SD		2.89 (0.83)	2.82 (0.95)	2.92 (0.65)	2.94 (0.79)	0.677
BRAS mean SD		5.88 (1.64)	5.34 (1.16)	6.90 (1.81)	5.94 (1.72)	<0.001
BRBS mean SD		7.68 (1.63)	7.52 (0.82)	7.97 (2.34)	7.69 (1.78)	0.464

Nota:

• PF = Physical functioning
  
• RF = Role functioning
• DY = Dyspnoea
• PA = Pain
• FA = Fatigue
• SL = Insomnia
• FA = Fatigue
• AP = Appetite loss
• NV = Nausea and vomiting
• CO = Constipation
• DI = Diarrhoea
• CF = Cognitive functioning
• EF = Emotional functioning
• SF = Social functioning
• FI = Financial difficulties
• GLH = Global health status

Escalas complementarias

• BRST = Systemic therapy side effects
• BRHL = Upset by hair loss
• BRBI = Body image
• BRFU = Future perspective
• BRSEF = Sexual functioning
• BRSEE = Sexual enjoyment
• BRAS = Arm symptoms
• BRBS = Breast symptoms

Se seleccionan las variables para el modelo multivariado si el p valor fue igual o menor a 0.2 EDUCACION CAT, ESTADIO, TRAT SISTEMICO, Cuidado soporte UA, “BRST”, “BRHL”, “BRFU”, “BRAS”. No se incluyen los ítems con los que se calcularon los perfiles

Modelo de regresión

Frecuencias por perfil

library(sjmisc)
library(sjPlot)
library(nnet)
library(wakefield)

frq(DATA_PROFILES, Perfil)

## Perfil <numeric> 
## # total N=200 valid N=200 mean=2.18 sd=0.91
## 
## Value |   N | Raw % | Valid % | Cum. %
## --------------------------------------
##     1 |  67 | 33.50 |   33.50 |  33.50
##     2 |  30 | 15.00 |   15.00 |  48.50
##     3 | 103 | 51.50 |   51.50 | 100.00
##  <NA> |   0 |  0.00 |    <NA> |   <NA>

modelo_REG1 <- multinom(Perfil ~ EDUCACION_CAT + ESTADIO + TRAT_SISTEMICO + Cuidado_soporte_UA + BRST+ BRHL+BRFU + BRAS, data = DATA_PROFILES)

## # weights:  39 (24 variable)
## initial  value 205.440498 
## iter  10 value 154.417199
## iter  20 value 137.792268
## iter  30 value 137.629178
## iter  40 value 137.626750
## final  value 137.626737 
## converged

modelo_REG2 <- multinom(Perfil ~ EDUCACION_CAT + Cuidado_soporte_UA + BRST + BRAS, data = DATA_PROFILES)

## # weights:  21 (12 variable)
## initial  value 219.722458 
## iter  10 value 171.354809
## final  value 167.568334 
## converged

#Se estiman los valores p 
z_values <- summary(modelo_REG2)$coefficients / summary(modelo_REG2)$standard.errors
p_values <- 2 * (1 - pnorm(abs(z_values)))  # Prueba z para cada coeficiente
p_values

##    (Intercept) EDUCACION_CATBasica/secundaria EDUCACION_CATMas que secundaria
## 2 1.076103e-08                      0.1204459                      0.01127531
## 3 1.816483e-03                      0.4490423                      0.22901571
##   Cuidado_soporte_UASi         BRST        BRAS
## 2          0.001937233 6.684219e-06 0.006579934
## 3          0.011219684 1.061375e-02 0.038877167

Se retienen las variales significativas en al menos en una modalidad

modelo_REG1$AIC;modelo_REG2$AIC

## [1] 323.2535

## [1] 359.1367

Se realiza prueba de verosimilitud, fue necesario realizarlo solamente con los datos completos

vars <- c("Perfil", "EDUCACION_CAT", "ESTADIO", "TRAT_SISTEMICO", 
          "Cuidado_soporte_UA", "BRST", "BRHL", "BRFU", "BRAS")

DATA_SUB <- DATA_PROFILES[complete.cases(DATA_PROFILES[, vars]), ]

modelo_REG1.1 <- multinom(Perfil ~ EDUCACION_CAT + ESTADIO + TRAT_SISTEMICO + 
                                   Cuidado_soporte_UA + BRST + BRHL + BRFU + BRAS, 
                        data = DATA_SUB)

## # weights:  39 (24 variable)
## initial  value 205.440498 
## iter  10 value 154.417199
## iter  20 value 137.792268
## iter  30 value 137.629178
## iter  40 value 137.626750
## final  value 137.626737 
## converged

modelo_REG2.2 <- multinom(Perfil ~ EDUCACION_CAT + Cuidado_soporte_UA + BRST + BRAS, 
                        data = DATA_SUB)

## # weights:  21 (12 variable)
## initial  value 205.440498 
## iter  10 value 154.758722
## final  value 150.072406 
## converged

library(lmtest)
lrtest(modelo_REG1.1, modelo_REG2.2)

## Likelihood ratio test
## 
## Model 1: Perfil ~ EDUCACION_CAT + ESTADIO + TRAT_SISTEMICO + Cuidado_soporte_UA + 
##     BRST + BRHL + BRFU + BRAS
## Model 2: Perfil ~ EDUCACION_CAT + Cuidado_soporte_UA + BRST + BRAS
##   #Df  LogLik  Df  Chisq Pr(>Chisq)  
## 1  24 -137.63                        
## 2  12 -150.07 -12 24.891    0.01535 *
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1

No hay una mejora significativa al eliminar las variables del primer modelo.

Se prueba con la opcion de stepwise

library(MASS)
modelo_stepwise <- stepAIC(modelo_REG1.1 , direction = "backward", trace = TRUE)

## Start:  AIC=323.25
## Perfil ~ EDUCACION_CAT + ESTADIO + TRAT_SISTEMICO + Cuidado_soporte_UA + 
##     BRST + BRHL + BRFU + BRAS
## 
## # weights:  33 (20 variable)
## initial  value 205.440498 
## iter  10 value 158.150794
## iter  20 value 144.532110
## iter  30 value 144.463220
## final  value 144.462862 
## converged
## # weights:  30 (18 variable)
## initial  value 205.440498 
## iter  10 value 158.504747
## iter  20 value 141.931391
## final  value 141.901372 
## converged
## # weights:  36 (22 variable)
## initial  value 205.440498 
## iter  10 value 154.074842
## iter  20 value 139.075499
## iter  30 value 139.007211
## iter  40 value 139.006380
## iter  40 value 139.006379
## iter  40 value 139.006379
## final  value 139.006379 
## converged
## # weights:  36 (22 variable)
## initial  value 205.440498 
## iter  10 value 155.537482
## iter  20 value 143.622231
## iter  30 value 143.388982
## iter  40 value 143.386853
## final  value 143.386846 
## converged
## # weights:  36 (22 variable)
## initial  value 205.440498 
## iter  10 value 153.355783
## iter  20 value 147.656687
## iter  30 value 147.561318
## final  value 147.560986 
## converged
## # weights:  36 (22 variable)
## initial  value 205.440498 
## iter  10 value 154.497007
## iter  20 value 140.370427
## iter  30 value 140.295440
## iter  40 value 140.294843
## iter  40 value 140.294841
## iter  40 value 140.294841
## final  value 140.294841 
## converged
## # weights:  36 (22 variable)
## initial  value 205.440498 
## iter  10 value 150.144664
## iter  20 value 139.731225
## iter  30 value 139.653996
## iter  40 value 139.653091
## final  value 139.653087 
## converged
## # weights:  36 (22 variable)
## initial  value 205.440498 
## iter  10 value 149.714827
## iter  20 value 141.167848
## iter  30 value 141.066302
## iter  40 value 141.065551
## iter  40 value 141.065551
## iter  40 value 141.065551
## final  value 141.065551 
## converged
##                      Df    AIC
## - ESTADIO             6 319.80
## - TRAT_SISTEMICO      2 322.01
## <none>                  323.25
## - BRFU                2 323.31
## - BRHL                2 324.59
## - BRAS                2 326.13
## - EDUCACION_CAT       4 328.93
## - Cuidado_soporte_UA  2 330.77
## - BRST                2 339.12
## # weights:  30 (18 variable)
## initial  value 205.440498 
## iter  10 value 158.504747
## iter  20 value 141.931391
## final  value 141.901372 
## converged
## 
## Step:  AIC=319.8
## Perfil ~ EDUCACION_CAT + TRAT_SISTEMICO + Cuidado_soporte_UA + 
##     BRST + BRHL + BRFU + BRAS
## 
## # weights:  24 (14 variable)
## initial  value 205.440498 
## iter  10 value 163.710795
## iter  20 value 149.120266
## iter  20 value 149.120265
## iter  20 value 149.120265
## final  value 149.120265 
## converged
## # weights:  27 (16 variable)
## initial  value 205.440498 
## iter  10 value 163.005849
## iter  20 value 144.644688
## final  value 144.644454 
## converged
## # weights:  27 (16 variable)
## initial  value 205.440498 
## iter  10 value 158.737695
## iter  20 value 147.645931
## final  value 147.645794 
## converged
## # weights:  27 (16 variable)
## initial  value 205.440498 
## iter  10 value 157.355306
## iter  20 value 153.693680
## final  value 153.693652 
## converged
## # weights:  27 (16 variable)
## initial  value 205.440498 
## iter  10 value 157.596001
## iter  20 value 144.205453
## final  value 144.205112 
## converged
## # weights:  27 (16 variable)
## initial  value 205.440498 
## iter  10 value 152.817569
## iter  20 value 144.165653
## final  value 144.165425 
## converged
## # weights:  27 (16 variable)
## initial  value 205.440498 
## iter  10 value 152.053168
## iter  20 value 145.220508
## final  value 145.220059 
## converged
##                      Df    AIC
## <none>                  319.80
## - BRFU                2 320.33
## - BRHL                2 320.41
## - TRAT_SISTEMICO      2 321.29
## - BRAS                2 322.44
## - EDUCACION_CAT       4 326.24
## - Cuidado_soporte_UA  2 327.29
## - BRST                2 339.39

summary(modelo_stepwise)

## Call:
## multinom(formula = Perfil ~ EDUCACION_CAT + TRAT_SISTEMICO + 
##     Cuidado_soporte_UA + BRST + BRHL + BRFU + BRAS, data = DATA_SUB)
## 
## Coefficients:
##   (Intercept) EDUCACION_CATBasica/secundaria EDUCACION_CATMas que secundaria
## 2  -13.860561                     -1.5120403                      -1.8723087
## 3   -5.369163                      0.5275818                      -0.4294469
##   TRAT_SISTEMICOSi Cuidado_soporte_UASi      BRST      BRHL      BRFU      BRAS
## 2       -1.0700249             2.092083 0.6082768 0.4568024 0.5360574 0.4812402
## 3        0.2659014             1.434807 0.1733728 0.6211012 0.2380442 0.2244102
## 
## Std. Errors:
##   (Intercept) EDUCACION_CATBasica/secundaria EDUCACION_CATMas que secundaria
## 2    2.403455                      0.8917908                       0.7053533
## 3    1.498918                      0.5044136                       0.4089697
##   TRAT_SISTEMICOSi Cuidado_soporte_UASi       BRST      BRHL      BRFU
## 2        0.6344658            0.7263246 0.14233664 0.4070211 0.2582899
## 3        0.3956298            0.5243993 0.09573652 0.3082520 0.1778203
##        BRAS
## 2 0.1933626
## 3 0.1374586
## 
## Residual Deviance: 283.8027 
## AIC: 319.8027

Mejora el aporte de información del modelo

lrtest(modelo_REG1.1, modelo_stepwise)

## Likelihood ratio test
## 
## Model 1: Perfil ~ EDUCACION_CAT + ESTADIO + TRAT_SISTEMICO + Cuidado_soporte_UA + 
##     BRST + BRHL + BRFU + BRAS
## Model 2: Perfil ~ EDUCACION_CAT + TRAT_SISTEMICO + Cuidado_soporte_UA + 
##     BRST + BRHL + BRFU + BRAS
##   #Df  LogLik Df  Chisq Pr(>Chisq)
## 1  24 -137.63                     
## 2  18 -141.90 -6 8.5493     0.2006

El modelo reducido aporta mayor información

Se estima el OR

Modelo reduido manualmente

library(gtsummary)
tbl_regression(modelo_REG2.2, exponentiate = TRUE, add_estimate_to_reference_rows=TRUE)  %>% add_global_p()

Characteristic	OR	95% CI	p-value
2
EDUCACION_CAT			0.004
Primaria o menos	1.00	—
Basica/secundaria	0.21	0.04, 1.14
Mas que secundaria	0.15	0.04, 0.55
Cuidado_soporte_UA			0.001
No	1.00	—
Si	8.95	2.29, 35.0
BRST	1.88	1.45, 2.42	<0.001
BRAS	1.62	1.13, 2.31	0.024
3
EDUCACION_CAT			0.004
Primaria o menos	1.00	—
Basica/secundaria	1.51	0.58, 3.95
Mas que secundaria	0.61	0.28, 1.34
Cuidado_soporte_UA			0.001
No	1.00	—
Si	4.36	1.58, 12.0
BRST	1.29	1.08, 1.54	<0.001
BRAS	1.28	0.98, 1.67	0.024
Abbreviations: CI = Confidence Interval, OR = Odds Ratio

Modelo reducido automáticamente

library(gtsummary)
tbl_regression(modelo_stepwise, exponentiate = TRUE, add_estimate_to_reference_rows=TRUE)  %>% add_global_p()

Characteristic	OR	95% CI	p-value
2
EDUCACION_CAT			0.006
Primaria o menos	1.00	—
Basica/secundaria	0.22	0.04, 1.27
Mas que secundaria	0.15	0.04, 0.61
TRAT_SISTEMICO			0.064
No	1.00	—
Si	0.34	0.10, 1.19
Cuidado_soporte_UA			0.003
No	1.00	—
Si	8.10	1.95, 33.6
BRST	1.84	1.39, 2.43	<0.001
BRHL	1.58	0.71, 3.51	0.10
BRFU	1.71	1.03, 2.84	0.10
BRAS	1.62	1.11, 2.36	0.036
3
EDUCACION_CAT			0.006
Primaria o menos	1.00	—
Basica/secundaria	1.69	0.63, 4.55
Mas que secundaria	0.65	0.29, 1.45
TRAT_SISTEMICO			0.064
No	1.00	—
Si	1.30	0.60, 2.83
Cuidado_soporte_UA			0.003
No	1.00	—
Si	4.20	1.50, 11.7
BRST	1.19	0.99, 1.43	<0.001
BRHL	1.86	1.02, 3.41	0.10
BRFU	1.27	0.90, 1.80	0.10
BRAS	1.25	0.96, 1.64	0.036
Abbreviations: CI = Confidence Interval, OR = Odds Ratio