Comparing Clinical Risk Profiles of Adolescent and Adult Epilepsy
Undergraduate Research Team
2026-07-21
epilepsy <- read_csv("/Users/drlakeshialegettejones/Downloads/dataset.csv") %>%
clean_names()
glimpse(epilepsy)## Rows: 1,000
## Columns: 30
## $ age <dbl> 15, 4, 36, 32, 29, 18, 14, 70, 12, 76…
## $ gender <chr> "Male", "Female", "Female", "Female",…
## $ weight <dbl> 48.3, 56.0, 44.8, 70.4, 54.5, 62.1, 5…
## $ height <dbl> 168.2, 174.5, 156.2, 180.4, 161.7, 16…
## $ medication_status <chr> "On Medication", "On Medication", "On…
## $ alcohol_or_drug_use <chr> "Yes", "No", "No", "No", "No", "No", …
## $ eeg_abnormality_detected <chr> "Yes", "Yes", "Yes", "Yes", "Yes", "Y…
## $ mri_ct_scan_result <chr> "Normal", "Abnormal", "Abnormal", "No…
## $ seizure_frequency <dbl> 1, 1, 3, 0, 1, 1, 2, 1, 1, 5, 3, 1, 0…
## $ seizure_duration <dbl> 60, 30, 30, 60, 60, 30, 30, 30, 90, 3…
## $ seizure_type <chr> "Tonic-Clonic", "Generalized", "Tonic…
## $ aura_before_seizure <chr> "No", "Yes", "Yes", "Yes", "No", "Yes…
## $ loss_of_consciousness <chr> "Yes", "Yes", "No", "Yes", "Yes", "Ye…
## $ muscle_stiffness <chr> "No", "Yes", "Yes", "No", "Yes", "No"…
## $ jerky_movements <chr> "Yes", "Yes", "Yes", "Yes", "Yes", "Y…
## $ postictal_confusion <chr> "Yes", "Yes", "No", "Yes", "Yes", "Ye…
## $ blank_stare_episodes <chr> "No", "No", "Yes", "Yes", "No", "Yes"…
## $ eye_rolling <chr> "Yes", "No", "Yes", "No", "No", "No",…
## $ stress_or_anxiety_before_episode <chr> "Yes", "No", "Yes", "Yes", "Yes", "Ye…
## $ lack_of_sleep_before_episode <chr> "Yes", "No", "No", "Yes", "No", "Yes"…
## $ flashing_lights_sensitivity <chr> "Yes", "No", "No", "Yes", "No", "Yes"…
## $ loud_sound_sensitivity <chr> "Yes", "No", "Yes", "Yes", "Yes", "No…
## $ missed_medication <chr> "No", "No", "Yes", "No", "No", "No", …
## $ family_history_of_epilepsy <chr> "No", "Yes", "Yes", "No", "Yes", "Yes…
## $ head_injury_history <chr> "No", "Yes", "No", "No", "No", "No", …
## $ brain_tumor <chr> "No", "Yes", "No", "No", "Yes", "No",…
## $ history_of_stroke <chr> "No", "No", "No", "No", "No", "No", "…
## $ genetic_disorder <chr> "No", "No", "No", "No", "No", "No", "…
## $ developmental_delay_in_children <chr> "Yes", "No", "No", "No", "No", "No", …
## $ target_epilepsy_type <chr> "Generalized", "Generalized", "Genera…epilepsy <- epilepsy %>%
mutate(
age_group = case_when(
age >= 12 & age <= 19 ~ "Adolescent",
age >= 20 ~ "Adult",
age < 12 ~ "Child"
),
age_group = factor(age_group, levels = c("Adolescent", "Adult", "Child"))
)
analysis_data <- epilepsy %>%
filter(age_group %in% c("Adolescent", "Adult")) %>%
mutate(age_group = droplevels(age_group))
analysis_data %>%
count(age_group) %>%
mutate(percent = round(100 * n / sum(n), 1))## # A tibble: 2 × 3
## age_group n percent
## <fct> <int> <dbl>
## 1 Adolescent 92 10.6
## 2 Adult 773 89.44. Exploratory Data Analysis
analysis_data %>%
group_by(age_group) %>%
summarise(
n = n(),
mean_age = mean(age, na.rm = TRUE),
sd_age = sd(age, na.rm = TRUE),
mean_weight = mean(weight, na.rm = TRUE),
sd_weight = sd(weight, na.rm = TRUE),
mean_height = mean(height, na.rm = TRUE),
sd_height = sd(height, na.rm = TRUE)
)## # A tibble: 2 × 8
## age_group n mean_age sd_age mean_weight sd_weight mean_height sd_height
## <fct> <int> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 Adolescent 92 15.2 2.11 64.1 15.3 165. 9.27
## 2 Adult 773 49.7 17.6 66.1 15.3 165. 10.3analysis_data %>%
count(age_group, gender) %>%
group_by(age_group) %>%
mutate(percent = round(100 * n / sum(n), 1))## # A tibble: 6 × 4
## # Groups: age_group [2]
## age_group gender n percent
## <fct> <chr> <int> <dbl>
## 1 Adolescent Female 30 32.6
## 2 Adolescent Male 60 65.2
## 3 Adolescent Other 2 2.2
## 4 Adult Female 332 42.9
## 5 Adult Male 424 54.9
## 6 Adult Other 17 2.2ggplot(analysis_data, aes(x = age, fill = age_group)) +
geom_histogram(bins = 30, alpha = 0.7, position = "identity") +
labs(
title = "Age Distribution by Group",
x = "Age",
y = "Count"
)
ggplot(analysis_data, aes(x = gender, fill = age_group)) +
geom_bar(position = "dodge") +
labs(
title = "Gender Distribution by Age Group",
x = "Gender",
y = "Count"
)
symptom_vars <- c(
"aura_before_seizure",
"loss_of_consciousness",
"muscle_stiffness",
"jerky_movements",
"postictal_confusion",
"blank_stare_episodes",
"eye_rolling"
)
risk_vars <- c(
"alcohol_or_drug_use",
"stress_or_anxiety_before_episode",
"lack_of_sleep_before_episode",
"flashing_lights_sensitivity",
"loud_sound_sensitivity",
"missed_medication",
"family_history_of_epilepsy",
"head_injury_history",
"brain_tumor",
"history_of_stroke",
"genetic_disorder"
)
clinical_vars <- c(
"medication_status",
"eeg_abnormality_detected",
"mri_ct_scan_result",
"seizure_frequency",
"seizure_duration",
"seizure_type",
"target_epilepsy_type"
)analysis_data %>%
select(age_group, all_of(symptom_vars)) %>%
pivot_longer(
cols = all_of(symptom_vars),
names_to = "symptom",
values_to = "response"
) %>%
count(age_group, symptom, response) %>%
group_by(age_group, symptom) %>%
mutate(percent = 100 * n / sum(n)) %>%
filter(response == "Yes") %>%
ggplot(aes(x = symptom, y = percent, fill = age_group)) +
geom_col(position = "dodge") +
coord_flip() +
labs(
title = "Symptom Profiles by Age Group",
x = "Symptom",
y = "Percent Reporting Symptom"
)
analysis_data %>%
select(age_group, all_of(risk_vars)) %>%
pivot_longer(
cols = all_of(risk_vars),
names_to = "risk_factor",
values_to = "response"
) %>%
count(age_group, risk_factor, response) %>%
group_by(age_group, risk_factor) %>%
mutate(percent = 100 * n / sum(n)) %>%
filter(response == "Yes") %>%
ggplot(aes(x = risk_factor, y = percent, fill = age_group)) +
geom_col(position = "dodge") +
coord_flip() +
labs(
title = "Risk Factors by Age Group",
x = "Risk Factor",
y = "Percent Reporting Risk Factor"
)
5. Statistical Analysis
vars_to_test <- c(clinical_vars, symptom_vars, risk_vars)
chi_square_results <- map_df(vars_to_test, function(var) {
test_data <- analysis_data %>%
select(age_group, all_of(var)) %>%
drop_na()
tbl <- table(test_data$age_group, test_data[[var]])
if (nrow(tbl) < 2 || ncol(tbl) < 2) {
return(tibble(
variable = var,
chi_square = NA,
df = NA,
p_value = NA
))
}
test <- suppressWarnings(chisq.test(tbl))
tibble(
variable = var,
chi_square = round(as.numeric(test$statistic), 3),
df = as.numeric(test$parameter),
p_value = round(test$p.value, 4)
)
})
chi_square_results %>%
arrange(p_value)## # A tibble: 25 × 4
## variable chi_square df p_value
## <chr> <dbl> <dbl> <dbl>
## 1 seizure_type 41.1 3 0
## 2 target_epilepsy_type 24.0 5 0.0002
## 3 aura_before_seizure 2.03 1 0.154
## 4 seizure_duration 4.45 3 0.217
## 5 jerky_movements 1.48 1 0.224
## 6 loss_of_consciousness 1.39 1 0.239
## 7 postictal_confusion 1.30 1 0.255
## 8 history_of_stroke 0.863 1 0.353
## 9 mri_ct_scan_result 1.54 2 0.463
## 10 family_history_of_epilepsy 0.438 1 0.508
## # ℹ 15 more rowsmodel_data <- analysis_data %>%
mutate(
adolescent = ifelse(age_group == "Adolescent", 1, 0)
) %>%
select(
adolescent,
gender,
weight,
height,
medication_status,
alcohol_or_drug_use,
eeg_abnormality_detected,
mri_ct_scan_result,
seizure_frequency,
seizure_duration,
seizure_type,
aura_before_seizure,
loss_of_consciousness,
muscle_stiffness,
jerky_movements,
postictal_confusion,
blank_stare_episodes,
eye_rolling,
stress_or_anxiety_before_episode,
lack_of_sleep_before_episode,
missed_medication,
family_history_of_epilepsy,
head_injury_history,
genetic_disorder,
target_epilepsy_type
) %>%
mutate(across(where(is.character), as.factor)) %>%
drop_na()logit_model <- glm(
adolescent ~ .,
data = model_data,
family = binomial
)
logit_results <- tidy(
logit_model,
exponentiate = TRUE,
conf.int = TRUE
) %>%
arrange(p.value)
logit_results## # A tibble: 33 × 7
## term estimate std.error statistic p.value conf.low conf.high
## <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 seizure_typeFocal 0.121 0.524 -4.03 5.64e-5 0.0425 0.334
## 2 seizure_typeGenerali… 0.230 0.500 -2.94 3.30e-3 0.0854 0.610
## 3 seizure_typeTonic-Cl… 0.359 0.511 -2.00 4.52e-2 0.130 0.973
## 4 genderMale 1.61 0.250 1.91 5.67e-2 0.994 2.65
## 5 seizure_duration 0.992 0.00432 -1.77 7.64e-2 0.984 1.00
## 6 jerky_movementsYes 0.611 0.298 -1.66 9.77e-2 0.340 1.10
## 7 postictal_confusionY… 0.655 0.261 -1.62 1.05e-1 0.394 1.10
## 8 weight 0.989 0.00781 -1.40 1.63e-1 0.974 1.00
## 9 loss_of_consciousnes… 1.41 0.294 1.16 2.44e-1 0.797 2.53
## 10 mri_ct_scan_resultNo… 0.745 0.257 -1.14 2.52e-1 0.449 1.24
## # ℹ 23 more rowsrf_data <- model_data %>%
mutate(
adolescent = factor(
adolescent,
levels = c(0, 1),
labels = c("Adult", "Adolescent")
)
)
set.seed(123)
rf_model <- randomForest(
adolescent ~ .,
data = rf_data,
importance = TRUE,
ntree = 500
)
importance_df <- importance(rf_model) %>%
as.data.frame() %>%
rownames_to_column("variable") %>%
arrange(desc(MeanDecreaseGini))
importance_df## variable Adult Adolescent
## 1 weight 1.21225533 0.41573211
## 2 height -0.29711248 1.09277451
## 3 seizure_type 3.39799091 8.69402249
## 4 seizure_frequency -0.76198080 -2.32756338
## 5 target_epilepsy_type 1.24128761 1.44187408
## 6 seizure_duration -1.20245006 -0.80013987
## 7 mri_ct_scan_result -0.68716582 -0.34488143
## 8 eye_rolling 1.18580219 4.09113751
## 9 gender -1.41888108 -0.25370992
## 10 muscle_stiffness 2.50258063 -1.03090560
## 11 jerky_movements 1.82391510 3.01553318
## 12 lack_of_sleep_before_episode -0.38653867 -0.77670047
## 13 aura_before_seizure 0.08913831 -0.62671879
## 14 postictal_confusion 1.92697174 -0.05460891
## 15 family_history_of_epilepsy -1.99128271 1.50908312
## 16 stress_or_anxiety_before_episode -2.98509348 1.45899237
## 17 medication_status -1.69400793 -0.13358916
## 18 head_injury_history 0.06250515 0.82008398
## 19 blank_stare_episodes -3.25933420 0.22925981
## 20 loss_of_consciousness 0.51963175 0.20733471
## 21 missed_medication 0.78761861 -1.31314838
## 22 eeg_abnormality_detected -0.90039778 -1.10666739
## 23 genetic_disorder -2.89393562 2.55601013
## 24 alcohol_or_drug_use -1.37169823 -2.12010005
## MeanDecreaseAccuracy MeanDecreaseGini
## 1 1.22935484 24.996569
## 2 0.04969975 23.477850
## 3 6.30307802 11.374333
## 4 -1.50160457 10.863905
## 5 1.69840313 9.637369
## 6 -1.41328297 8.079422
## 7 -0.76666042 7.247477
## 8 2.55016127 4.766428
## 9 -1.50951374 4.584075
## 10 1.88172618 4.310033
## 11 2.67638799 4.174650
## 12 -0.59280314 4.133665
## 13 -0.08336847 4.095214
## 14 1.77196560 4.013726
## 15 -1.29984603 3.994467
## 16 -2.19681833 3.921945
## 17 -1.63109118 3.540770
## 18 0.36480064 3.534973
## 19 -3.03923438 3.493657
## 20 0.59903114 3.453896
## 21 0.34830511 3.416778
## 22 -1.24630948 2.762019
## 23 -1.88584648 2.569827
## 24 -2.11521592 2.108855varImpPlot(rf_model)
6. Topological Characterization of Clinical Risk Profiles
tda_data <- analysis_data %>%
select(
age_group,
gender,
medication_status,
alcohol_or_drug_use,
eeg_abnormality_detected,
mri_ct_scan_result,
seizure_frequency,
seizure_duration,
seizure_type,
aura_before_seizure,
loss_of_consciousness,
muscle_stiffness,
jerky_movements,
postictal_confusion,
blank_stare_episodes,
eye_rolling,
stress_or_anxiety_before_episode,
lack_of_sleep_before_episode,
missed_medication,
family_history_of_epilepsy,
head_injury_history,
genetic_disorder,
target_epilepsy_type
) %>%
drop_na()
age_labels <- tda_data$age_group
risk_profiles <- tda_data %>%
select(-age_group) %>%
mutate(across(where(is.character), as.factor))
str(risk_profiles)## tibble [865 × 22] (S3: tbl_df/tbl/data.frame)
## $ gender : Factor w/ 3 levels "Female","Male",..: 2 1 1 2 2 2 1 2 1 2 ...
## $ medication_status : Factor w/ 2 levels "Not on Medication",..: 2 2 1 2 2 1 2 1 2 2 ...
## $ alcohol_or_drug_use : Factor w/ 2 levels "No","Yes": 2 1 1 1 1 1 1 1 1 1 ...
## $ eeg_abnormality_detected : Factor w/ 2 levels "No","Yes": 2 2 2 2 2 1 2 1 2 2 ...
## $ mri_ct_scan_result : Factor w/ 3 levels "Abnormal","Normal",..: 2 1 3 3 1 3 2 2 1 2 ...
## $ seizure_frequency : num [1:865] 1 3 0 1 1 2 1 1 5 3 ...
## $ seizure_duration : num [1:865] 60 30 60 60 30 30 30 90 30 30 ...
## $ seizure_type : Factor w/ 4 levels "Absence","Focal",..: 4 4 2 4 4 1 1 4 4 3 ...
## $ aura_before_seizure : Factor w/ 2 levels "No","Yes": 1 2 2 1 2 1 2 2 1 2 ...
## $ loss_of_consciousness : Factor w/ 2 levels "No","Yes": 2 1 2 2 2 1 2 2 1 2 ...
## $ muscle_stiffness : Factor w/ 2 levels "No","Yes": 1 2 1 2 1 2 1 1 1 1 ...
## $ jerky_movements : Factor w/ 2 levels "No","Yes": 2 2 2 2 2 1 1 1 2 2 ...
## $ postictal_confusion : Factor w/ 2 levels "No","Yes": 2 1 2 2 2 2 1 1 2 1 ...
## $ blank_stare_episodes : Factor w/ 2 levels "No","Yes": 1 2 2 1 2 2 2 1 1 1 ...
## $ eye_rolling : Factor w/ 2 levels "No","Yes": 2 2 1 1 1 2 2 2 2 2 ...
## $ stress_or_anxiety_before_episode: Factor w/ 2 levels "No","Yes": 2 2 2 2 2 1 1 2 2 2 ...
## $ lack_of_sleep_before_episode : Factor w/ 2 levels "No","Yes": 2 1 2 1 2 1 2 2 2 2 ...
## $ missed_medication : Factor w/ 2 levels "No","Yes": 1 2 1 1 1 1 1 1 1 1 ...
## $ family_history_of_epilepsy : Factor w/ 2 levels "No","Yes": 1 2 1 2 2 2 1 2 2 1 ...
## $ head_injury_history : Factor w/ 2 levels "No","Yes": 1 1 1 1 1 2 1 1 1 2 ...
## $ genetic_disorder : Factor w/ 2 levels "No","Yes": 1 1 1 1 1 2 1 1 1 1 ...
## $ target_epilepsy_type : Factor w/ 6 levels "Absence","Complicated",..: 4 4 3 4 4 1 1 2 2 4 ...gower_dist <- daisy(risk_profiles, metric = "gower")
gower_matrix <- as.matrix(gower_dist)mds <- cmdscale(gower_dist, k = 2)
mds_df <- data.frame(
Dim1 = mds[, 1],
Dim2 = mds[, 2],
age_group = age_labels
)
ggplot(mds_df, aes(x = Dim1, y = Dim2, color = age_group)) +
geom_point(alpha = 0.7) +
labs(
title = "Risk Profile Space Using Gower Distance",
x = "Dimension 1",
y = "Dimension 2"
)
filter_values <- mds[, 1]
mapper_result <- mapper1D(
distance_matrix = gower_matrix,
filter_values = filter_values,
num_intervals = 10,
percent_overlap = 50,
num_bins_when_clustering = 10
)
mapper_vertices <- mapper_result$points_in_vertex
mapper_edges <- mapper_result$adjacency
g <- graph_from_adjacency_matrix(
mapper_edges,
mode = "undirected"
)
node_adolescent_prop <- sapply(mapper_vertices, function(indices) {
mean(age_labels[indices] == "Adolescent")
})
V(g)$adolescent_prop <- node_adolescent_propplot(
g,
vertex.size = 8 + 25 * V(g)$adolescent_prop,
vertex.label = NA,
main = "Mapper Graph of Epilepsy Risk Profiles"
)
mapper_summary <- tibble(
node = seq_along(mapper_vertices),
node_size = sapply(mapper_vertices, length),
adolescent_proportion = node_adolescent_prop
) %>%
arrange(desc(adolescent_proportion))
mapper_summary## # A tibble: 10 × 3
## node node_size adolescent_proportion
## <int> <int> <dbl>
## 1 4 176 0.148
## 2 9 250 0.132
## 3 10 166 0.127
## 4 8 201 0.119
## 5 5 203 0.0985
## 6 3 164 0.0976
## 7 7 160 0.0938
## 8 6 192 0.0677
## 9 1 45 0.0667
## 10 2 109 0.0642Interpretation Notes
The exploratory analysis describes differences between adolescents and adults in the dataset.
The statistical analysis identifies individual clinical, demographic, and behavioral variables that distinguish adolescent epilepsy patients from adult epilepsy patients.
The TDA analysis treats each patient as a multivariate clinical risk profile. Rather than studying variables one at a time, Mapper studies the shape of the risk-profile space and identifies clusters of patients with similar combinations of symptoms and risk factors.
library(tidyr)
seizure_summary <- analysis_data %>%
count(age_group, seizure_type) %>%
group_by(age_group) %>%
mutate(
Percent = round(100 * n / sum(n), 1),
Summary = paste0(n, " (", Percent, "%)")
) %>%
select(age_group, seizure_type, Summary) %>%
pivot_wider(
names_from = age_group,
values_from = Summary
)
seizure_summary## # A tibble: 4 × 3
## seizure_type Adolescent Adult
## <chr> <chr> <chr>
## 1 Absence 28 (30.4%) 82 (10.6%)
## 2 Focal 12 (13%) 280 (36.2%)
## 3 Generalized 29 (31.5%) 273 (35.3%)
## 4 Tonic-Clonic 23 (25%) 138 (17.9%)target_summary <- analysis_data %>%
count(age_group, target_epilepsy_type) %>%
group_by(age_group) %>%
mutate(
Percent = round(100 * n / sum(n), 1),
Summary = paste0(n, " (", Percent, "%)")
) %>%
select(
target_epilepsy_type,
age_group,
Summary
) %>%
pivot_wider(
names_from = age_group,
values_from = Summary
)
knitr::kable(
target_summary,
col.names = c(
"Target Epilepsy Type",
"Adolescent",
"Adult"
),
caption = "Distribution of Target Epilepsy Type by Age Group",
align = c("l", "c", "c")
)| Target Epilepsy Type | Adolescent | Adult |
|---|---|---|
| Absence | 19 (20.7%) | 69 (8.9%) |
| Complicated | 8 (8.7%) | 72 (9.3%) |
| Focal | 12 (13%) | 252 (32.6%) |
| Generalized | 46 (50%) | 327 (42.3%) |
| Normal | 6 (6.5%) | 34 (4.4%) |
| Not Confirmed | 1 (1.1%) | 19 (2.5%) |
library(tidyverse)
# Variables to summarize within each Mapper node
tda_symptom_vars <- c(
"aura_before_seizure",
"loss_of_consciousness",
"muscle_stiffness",
"jerky_movements",
"postictal_confusion",
"blank_stare_episodes",
"eye_rolling"
)
tda_risk_vars <- c(
"alcohol_or_drug_use",
"stress_or_anxiety_before_episode",
"lack_of_sleep_before_episode",
"missed_medication",
"family_history_of_epilepsy",
"head_injury_history",
"genetic_disorder"
)
# Function to identify the most common category
get_mode <- function(x) {
x <- x[!is.na(x)]
if (length(x) == 0) {
return(NA_character_)
}
counts <- sort(table(x), decreasing = TRUE)
names(counts)[1]
}
# Function to calculate the percentage in the most common category
get_mode_percent <- function(x) {
x <- x[!is.na(x)]
if (length(x) == 0) {
return(NA_real_)
}
counts <- sort(table(x), decreasing = TRUE)
round(100 * counts[1] / sum(counts), 1)
}
# Function to identify the most prevalent Yes/No variables
get_top_yes_variables <- function(data, variables, number_to_return = 3) {
available_variables <- variables[variables %in% names(data)]
if (length(available_variables) == 0) {
return(NA_character_)
}
prevalence <- map_dfr(available_variables, function(var) {
responses <- trimws(tolower(as.character(data[[var]])))
tibble(
variable = var,
percent_yes = round(
100 * mean(responses == "yes", na.rm = TRUE),
1
)
)
}) %>%
arrange(desc(percent_yes)) %>%
slice_head(n = number_to_return) %>%
mutate(
variable_label = str_replace_all(variable, "_", " "),
summary = paste0(variable_label, " (", percent_yes, "%)")
)
paste(prevalence$summary, collapse = "; ")
}
# Create a clinical summary for each Mapper node
mapper_node_profiles <- map_dfr(
seq_along(mapper_vertices),
function(node_number) {
# Row numbers of patients assigned to this node
node_indices <- mapper_vertices[[node_number]]
# Clinical records for patients in this node
node_data <- tda_data[node_indices, , drop = FALSE]
adolescent_n <- sum(
node_data$age_group == "Adolescent",
na.rm = TRUE
)
adult_n <- sum(
node_data$age_group == "Adult",
na.rm = TRUE
)
dominant_seizure <- get_mode(node_data$seizure_type)
dominant_seizure_percent <- get_mode_percent(node_data$seizure_type)
dominant_epilepsy <- get_mode(node_data$target_epilepsy_type)
dominant_epilepsy_percent <- get_mode_percent(
node_data$target_epilepsy_type
)
tibble(
node = node_number,
node_size = nrow(node_data),
adolescent_n = adolescent_n,
adult_n = adult_n,
adolescent_percent = round(
100 * adolescent_n / nrow(node_data),
1
),
most_common_seizure_type = paste0(
dominant_seizure,
" (",
dominant_seizure_percent,
"%)"
),
most_common_epilepsy_type = paste0(
dominant_epilepsy,
" (",
dominant_epilepsy_percent,
"%)"
),
top_symptoms = get_top_yes_variables(
node_data,
tda_symptom_vars,
number_to_return = 3
),
top_risk_factors = get_top_yes_variables(
node_data,
tda_risk_vars,
number_to_return = 3
)
)
}
) %>%
arrange(desc(adolescent_percent))
mapper_node_profiles## # A tibble: 10 × 9
## node node_size adolescent_n adult_n adolescent_percent
## <int> <int> <int> <int> <dbl>
## 1 4 176 26 150 14.8
## 2 9 250 33 217 13.2
## 3 10 166 21 145 12.7
## 4 8 201 24 177 11.9
## 5 5 203 20 183 9.9
## 6 3 164 16 148 9.8
## 7 7 160 15 145 9.4
## 8 6 192 13 179 6.8
## 9 1 45 3 42 6.7
## 10 2 109 7 102 6.4
## # ℹ 4 more variables: most_common_seizure_type <chr>,
## # most_common_epilepsy_type <chr>, top_symptoms <chr>, top_risk_factors <chr>print(
mapper_node_profiles,
n = Inf,
width = Inf
)## # A tibble: 10 × 9
## node node_size adolescent_n adult_n adolescent_percent
## <int> <int> <int> <int> <dbl>
## 1 4 176 26 150 14.8
## 2 9 250 33 217 13.2
## 3 10 166 21 145 12.7
## 4 8 201 24 177 11.9
## 5 5 203 20 183 9.9
## 6 3 164 16 148 9.8
## 7 7 160 15 145 9.4
## 8 6 192 13 179 6.8
## 9 1 45 3 42 6.7
## 10 2 109 7 102 6.4
## most_common_seizure_type most_common_epilepsy_type
## <chr> <chr>
## 1 Focal (60.2%) Focal (56.2%)
## 2 Generalized (64.4%) Generalized (99.2%)
## 3 Generalized (69.9%) Generalized (100%)
## 4 Generalized (61.7%) Generalized (85.1%)
## 5 Focal (54.7%) Focal (49.3%)
## 6 Focal (75.6%) Focal (67.1%)
## 7 Generalized (47.5%) Generalized (38.1%)
## 8 Focal (34.4%) Focal (29.2%)
## 9 Focal (86.7%) Focal (86.7%)
## 10 Focal (87.2%) Focal (81.7%)
## top_symptoms
## <chr>
## 1 aura before seizure (69.9%); muscle stiffness (61.9%); eye rolling (58.5%)
## 2 loss of consciousness (98%); jerky movements (97.6%); postictal confusion (9…
## 3 loss of consciousness (100%); jerky movements (98.8%); postictal confusion (…
## 4 loss of consciousness (88.6%); jerky movements (88.1%); postictal confusion …
## 5 postictal confusion (66%); eye rolling (60.1%); muscle stiffness (59.6%)
## 6 aura before seizure (78.7%); muscle stiffness (61%); eye rolling (54.9%)
## 7 postictal confusion (71.9%); jerky movements (70%); eye rolling (66.2%)
## 8 postictal confusion (81.8%); eye rolling (67.2%); jerky movements (65.1%)
## 9 aura before seizure (91.1%); muscle stiffness (62.2%); blank stare episodes …
## 10 aura before seizure (80.7%); muscle stiffness (62.4%); eye rolling (49.5%)
## top_risk_factors
## <chr>
## 1 lack of sleep before episode (69.9%); stress or anxiety before episode (68.2…
## 2 stress or anxiety before episode (67.2%); lack of sleep before episode (66.8…
## 3 lack of sleep before episode (63.3%); stress or anxiety before episode (60.8…
## 4 lack of sleep before episode (72.6%); stress or anxiety before episode (68.2…
## 5 stress or anxiety before episode (72.9%); lack of sleep before episode (71.4…
## 6 lack of sleep before episode (73.8%); stress or anxiety before episode (62.2…
## 7 lack of sleep before episode (70.6%); stress or anxiety before episode (66.9…
## 8 lack of sleep before episode (76%); stress or anxiety before episode (70.8%)…
## 9 lack of sleep before episode (75.6%); stress or anxiety before episode (53.3…
## 10 lack of sleep before episode (72.5%); stress or anxiety before episode (57.8…