ENT Ergonomics Data
Daniel Cheong
2026-01-06
Click to see summary of the data.
Summary of Data
PChar2 is a data frame that describes all 80 procedures and the various parameters that were also collected of interest (Post op scores/NDI/OLBD, surgeon, surgeon age/sex/glove size/height/weight, overall/L/R rula, and procedure length/category/difficulty).
Surg is a data frame that describes the surgeons and their baseline characteristics.
##
## Attaching package: 'dplyr'## The following objects are masked from 'package:stats':
##
## filter, lag## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union## Warning: package 'patchwork' was built under R version 4.3.3Notice that many surgeons report an OLBD of 0 and/or low NDI scores (OLBD_Total and NDI_Score columns). Only a few outliers express pain.
## # A tibble: 17 × 7
## Training Sex Age Height Weight OLBD_Total NDI_Score
## <chr> <chr> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 Attending Female 41 153 105 0 3
## 2 Resident Female 26 138 115 0 1
## 3 Resident Female 32 162 160 0 3
## 4 Resident Female 28 160 150 10 5
## 5 Resident Female 27 165 95 0 0
## 6 Attending Male 55 177 180 0 1
## 7 Attending Male 58 178 180 0 0
## 8 Attending Male 37 172 155 0 0
## 9 Resident Male 31 190 175 0 0
## 10 Resident Male 30 175 170 0 0
## 11 Resident Male 35 171 166 0 1
## 12 Resident Male 28 185. 165 0 1
## 13 Resident Male 30 180 200 0 1
## 14 Resident Male 34 178. 240 12 10
## 15 Resident Male 29 178. 205 8 11
## 16 Resident Male 29 183 175 4 6
## 17 Attending Male 56 182 250 0 0Surgery characteristics (80 procedures)
Pchar2 is displayed along with a brief summary of the parameters.
## # A tibble: 6 × 28
## Record_ID Length_surgery_min2 Length_surgery_min3 Category_Procedure POScores
## <dbl> <chr> <dbl> <chr> <dbl>
## 1 15 0-60 mins 47 Other 1
## 2 16 0-60 mins 47 Other 1
## 3 19 61-180 mins 90 Resection 1
## 4 20 61-180 mins 120 Resection 0
## 5 21 61-180 mins 120 Resection 1
## 6 23 360+ mins 400 Resection 3
## # ℹ 23 more variables: Surgeon <dbl>, Difficulty <chr>, RULA <dbl>,
## # RULA_sd <dbl>, RULA_count <int>, Sex <chr>, Height <dbl>, Weight <dbl>,
## # Age <dbl>, Glove_size <dbl>, Training <chr>, NDI_Score <dbl>,
## # OLBD_Total <dbl>, avg_RULA_L <dbl>, SD_RULA_L <dbl>, count_L <int>,
## # avg_RULA_R <dbl>, SD_RULA_R <dbl>, count_R <int>, RULAWL <dbl>,
## # RULAWR <dbl>, POPRaw <dbl>, RULAWB <dbl>## Record_ID Length_surgery_min2 Length_surgery_min3 Category_Procedure
## Min. : 15.00 Length:80 Min. : 20.00 Length:80
## 1st Qu.: 39.75 Class :character 1st Qu.: 92.25 Class :character
## Median : 61.50 Mode :character Median :148.50 Mode :character
## Mean : 61.00 Mean :202.18
## 3rd Qu.: 83.25 3rd Qu.:284.25
## Max. :103.00 Max. :848.00
##
## POScores Surgeon Difficulty RULA
## Min. :-1.000 Min. : 1.000 Length:80 Min. :2.000
## 1st Qu.: 1.000 1st Qu.: 8.000 Class :character 1st Qu.:3.542
## Median : 1.000 Median : 9.000 Mode :character Median :4.118
## Mean : 1.775 Mean : 9.512 Mean :4.340
## 3rd Qu.: 3.000 3rd Qu.:11.000 3rd Qu.:5.025
## Max. : 7.000 Max. :17.000 Max. :7.000
##
## RULA_sd RULA_count Sex Height
## Min. :0.0000 Min. : 2.00 Length:80 Min. :138.0
## 1st Qu.:0.5164 1st Qu.: 6.00 Class :character 1st Qu.:171.0
## Median :0.8904 Median : 9.00 Mode :character Median :172.0
## Mean :0.8573 Mean :12.12 Mean :174.6
## 3rd Qu.:1.1493 3rd Qu.:16.00 3rd Qu.:182.0
## Max. :1.9400 Max. :58.00 Max. :190.0
##
## Weight Age Glove_size Training
## Min. :105.0 Min. :26.0 Min. :6.000 Length:80
## 1st Qu.:155.0 1st Qu.:31.0 1st Qu.:7.000 Class :character
## Median :166.0 Median :35.0 Median :7.000 Mode :character
## Mean :171.2 Mean :38.8 Mean :7.138
## 3rd Qu.:175.0 3rd Qu.:41.0 3rd Qu.:7.500
## Max. :250.0 Max. :58.0 Max. :8.000
##
## NDI_Score OLBD_Total avg_RULA_L SD_RULA_L
## Min. : 0.000 Min. : 0.000 Min. :2.000 Min. :0.0000
## 1st Qu.: 0.000 1st Qu.: 0.000 1st Qu.:3.500 1st Qu.:0.5774
## Median : 1.000 Median : 0.000 Median :4.000 Median :0.9512
## Mean : 1.188 Mean : 0.725 Mean :4.330 Mean :0.9417
## 3rd Qu.: 1.000 3rd Qu.: 0.000 3rd Qu.:5.033 3rd Qu.:1.2536
## Max. :10.000 Max. :12.000 Max. :7.000 Max. :2.0616
## NA's :7
## count_L avg_RULA_R SD_RULA_R count_R
## Min. : 1.000 Min. :2.000 Min. :0.0000 Min. : 1.000
## 1st Qu.: 3.000 1st Qu.:3.607 1st Qu.:0.7071 1st Qu.: 3.000
## Median : 4.500 Median :4.045 Median :1.0000 Median : 4.500
## Mean : 6.062 Mean :4.349 Mean :0.9824 Mean : 6.062
## 3rd Qu.: 8.000 3rd Qu.:5.000 3rd Qu.:1.2111 3rd Qu.: 8.000
## Max. :29.000 Max. :7.000 Max. :2.0817 Max. :29.000
## NA's :7
## RULAWL RULAWR POPRaw RULAWB
## Min. :2.00 Min. :2.00 Min. :1.000 Min. :2.00
## 1st Qu.:4.00 1st Qu.:5.00 1st Qu.:1.000 1st Qu.:5.00
## Median :6.00 Median :6.00 Median :2.000 Median :6.00
## Mean :5.40 Mean :5.55 Mean :2.538 Mean :5.65
## 3rd Qu.:6.25 3rd Qu.:7.00 3rd Qu.:4.000 3rd Qu.:7.00
## Max. :7.00 Max. :7.00 Max. :8.000 Max. :7.00
## All surgeon characteristics
## # A tibble: 17 × 33
## ID Name Training Record Age Sex Height Weight `Glove size` NDI
## <dbl> <chr> <chr> <dbl> <dbl> <chr> <dbl> <dbl> <dbl> <chr>
## 1 1 Patel Attendi… 3 41 Fema… 153 105 6.5 The …
## 2 2 Goff Resident 7 26 Fema… 138 115 6 I ha…
## 3 3 Sluder Resident 10 32 Fema… 162 160 6.5 The …
## 4 4 Jan Resident 12 28 Fema… 160 150 6.5 The …
## 5 5 Kapoor Resident 53 27 Fema… 165 95 5.5 I ha…
## 6 6 Vasan Attendi… 1 55 Male 177 180 7 I ha…
## 7 7 Krempl Attendi… 4 58 Male 178 180 7 I ha…
## 8 8 Mhawej Attendi… 5 37 Male 172 155 7 I ha…
## 9 9 Greene Resident 6 31 Male 190 175 7.5 I ha…
## 10 10 Abbott Resident 8 30 Male 175 170 7 I ha…
## 11 11 Hawsawi Resident 9 35 Male 171 166 7 I ha…
## 12 12 Erickson Resident 11 28 Male 185. 165 7.5 I ha…
## 13 13 Krutz Resident 13 30 Male 180 200 7.5 I ha…
## 14 14 Klug Resident 14 34 Male 178. 240 7 The …
## 15 15 Hasanjee Resident 22 29 Male 178. 205 7.5 The …
## 16 16 Gupta Resident 54 29 Male 183 175 7.5 The …
## 17 17 Sanclement Attendi… 25 56 Male 182 250 8 I ha…
## # ℹ 23 more variables: NDI_ADLS <chr>, NDI_LIFTING <chr>, NDI_READING <chr>,
## # NDI_HEADACHES <chr>, NDI_CONCENTRATION <chr>, NDI_WORK <chr>,
## # NDI_DRIVING <chr>, NDI_SLEEP <chr>, NDI_ACTIVITIES <chr>, NDI_Score <dbl>,
## # `Pain baseline` <dbl>, OLBD <chr>, LookAfterSelf <chr>, Lifting <chr>,
## # Walking <chr>, Sitting <chr>, Standing <chr>, Sleep <chr>, Social <chr>,
## # Travel <chr>, Homemaking <chr>, OLBD_Sum <dbl>, OLBD_Total <dbl>Click to see breakdown of pain scores by training and sex.
Breakdown of Pain Scores (NOTE: Goff’s data was excluded from plots due to missing survey) # Pain Scores A box-and-whisker plot of pain scores was constructed, including the overall trend and the breakdown by training level and sex.
## Warning: The `size` argument of `element_line()` is deprecated as of ggplot2 3.4.0.
## ℹ Please use the `linewidth` argument instead.
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.
Why do the overall, “resident”, and “male” plots look similar?
Summary statistics were calculated for the post op pain score overall and for the subgroups of gender and training.
## # A tibble: 5 × 8
## Group Subgroup n mean_Pain sd_Pain min_Pain max_Pain median_Pain
## <chr> <chr> <int> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 Overall All 80 1.78 1.52 -1 7 1
## 2 Sex Female 10 2.7 2.06 0 7 2
## 3 Sex Male 70 1.64 1.39 -1 5 1
## 4 Training Attending 37 1.70 1.71 0 7 1
## 5 Training Resident 43 1.84 1.34 -1 5 1## # A tibble: 2 × 7
## Subgroup n mean_Pain sd_Pain min_Pain max_Pain median_Pain
## <chr> <int> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 Attending 37 1.70 1.71 0 7 1
## 2 Resident 43 1.84 1.34 -1 5 1## # A tibble: 2 × 7
## Subgroup n mean_Pain sd_Pain min_Pain max_Pain median_Pain
## <chr> <int> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 Female 10 2.7 2.06 0 7 2
## 2 Male 70 1.64 1.39 -1 5 1Click to see breakdown of pain scores by surgery characteristics.
Other Pain Score Data (Surgery specific - length, category, and
difficulty)
Summary of these surgery pain score by length, category, and difficulty.
## # A tibble: 4 × 7
## Length_surgery_min2 n mean_pain median_pain sd_pain min_pain max_pain
## <chr> <int> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 0-60 mins 13 1.69 1 1.11 1 4
## 2 181-360 mins 24 1.96 1 1.94 0 7
## 3 360+ mins 9 1.56 1 0.726 1 3
## 4 61-180 mins 34 1.74 1.5 1.50 -1 5## # A tibble: 5 × 7
## Category_Procedure n mean_pain median_pain sd_pain min_pain max_pain
## <chr> <int> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 Endoscopic/Diagnostic 1 1 1 NA 1 1
## 2 LN/neck dissections 9 1.56 1 1.33 0 4
## 3 Other 4 1.25 1 0.5 1 2
## 4 Reconstructive 17 1.71 1 1.86 0 5
## 5 Resection 49 1.90 1 1.50 -1 7## # A tibble: 4 × 7
## Difficulty n mean_pain median_pain sd_pain min_pain max_pain
## <chr> <int> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 Average 43 1.74 1 1.27 0 4
## 2 Easier than average 7 1.14 1 0.900 0 3
## 3 More difficult than ave… 24 1.79 1.5 1.61 -1 5
## 4 Most difficult 6 2.67 2 2.88 0 7Click to see breakdown of RULA Scores (n = 970) by training and sex.
Breakdown of RULA Scores by Individual Recordings (Using the 970 RULA Recordings)
A summary of RULA scores by sex and training was also found.
## # A tibble: 1 × 6
## n mean median sd min max
## <int> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 970 4.35 4 1.39 0 7## # A tibble: 2 × 7
## Training n mean median sd min max
## <chr> <int> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 Attending 386 4.29 4 1.30 2 7
## 2 Resident 584 4.40 4 1.44 0 7## # A tibble: 2 × 7
## Sex n mean median sd min max
## <chr> <int> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 Female 102 4.10 4 1.29 2 7
## 2 Male 868 4.38 4 1.40 0 7## # A tibble: 4 × 8
## Training Sex n mean median sd min max
## <chr> <chr> <int> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 Attending Female 42 3.86 4 1.03 3 7
## 2 Attending Male 344 4.34 4 1.32 2 7
## 3 Resident Female 60 4.27 4 1.44 2 7
## 4 Resident Male 524 4.41 4 1.44 0 7Click to see breakdown of RULA scores (n = 970) by procedure characteristics.
A breakdown by length, difficulty, and category of the RULA scores was constructed.
## # A tibble: 4 × 7
## Length_surgery_min2 n mean median sd min max
## <chr> <int> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 0-60 mins 40 4.35 4 1.53 2 7
## 2 181-360 mins 388 4.39 4 1.38 2 7
## 3 360+ mins 284 4.34 4 1.35 0 7
## 4 61-180 mins 258 4.32 4 1.43 2 7## # A tibble: 4 × 7
## Difficulty n mean median sd min max
## <chr> <int> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 Average 394 4.25 4 1.32 1 7
## 2 Easier than average 38 4.26 4 1.75 2 7
## 3 More difficult than average 414 4.52 4 1.45 0 7
## 4 Most difficult 124 4.14 4 1.22 2 7## # A tibble: 5 × 7
## Category_Procedure n mean median sd min max
## <chr> <int> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 Endoscopic/Diagnostic 2 5 5 0 5 5
## 2 LN/neck dissections 94 3.97 4 1.16 1 7
## 3 Other 20 3.35 3 0.489 3 4
## 4 Reconstructive 228 4.04 4 1.42 0 7
## 5 Resection 626 4.56 4 1.38 2 7Click to see breakdown of average RULA Score per procedure (n = 80 surgeries) by training and sex.
Breakdown of RULA Scores by Average Score per Procedure (80 procedures from 970 recordings) by training and sex.
## # A tibble: 5 × 7
## Group n mean median sd min max
## <fct> <int> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 Overall 80 4.34 4.12 1.07 2 7
## 2 Attending 37 4.22 4.07 0.917 3 6.5
## 3 Resident 43 4.44 4.17 1.18 2 7
## 4 Male 70 4.38 4.14 1.09 2 7
## 5 Female 10 4.09 3.93 0.923 2.67 5.7Click to see breakdown of average RULA Score (n = 80 surgeries) by length, category, and difficulty.
Breakdown of RULA Scores by Average Score per Procedure (80 procedures from 970 recordings) by length, category, and difficulty.
## Warning: `aes_string()` was deprecated in ggplot2 3.0.0.
## ℹ Please use tidy evaluation idioms with `aes()`.
## ℹ See also `vignette("ggplot2-in-packages")` for more information.
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.
## # A tibble: 4 × 7
## Length_surgery_min2 n mean median sd min max
## <chr> <int> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 0-60 mins 13 4.25 4 1.45 2 7
## 2 181-360 mins 24 4.40 4.24 0.926 2.71 6.5
## 3 360+ mins 9 4.18 3.85 0.698 3.5 5.5
## 4 61-180 mins 34 4.37 4.08 1.10 2.67 6.5## # A tibble: 5 × 7
## Category_Procedure n mean median sd min max
## <chr> <int> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 Endoscopic/Diagnostic 1 5 5 NA 5 5
## 2 LN/neck dissections 9 4.03 3.75 0.706 3.4 5.7
## 3 Other 4 3.36 3.35 0.330 3 3.75
## 4 Reconstructive 17 4.19 4.07 0.984 2.67 6.17
## 5 Resection 49 4.51 4.56 1.14 2 7## # A tibble: 4 × 7
## Difficulty n mean median sd min max
## <chr> <int> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 Average 43 4.21 4 1.04 2 6.5
## 2 Easier than average 7 4.76 4 1.60 2.71 7
## 3 More difficult than average 24 4.52 4.66 1.01 2.67 6.5
## 4 Most difficult 6 4.01 3.86 0.618 3.42 5.17Click to see breakdown of worst RULA Score per procedure (n = 80 surgeries) by training and sex.
Breakdown of RULA Scores by Worst Score per Procedure (80 procedures from 970 recordings, worst score across both hands was used)
Inspired by a reviewer comment: From your RULA, you deviated from industrial use which typically uses the worst posture not a periodic sampling of posture (e.g. ever 30 minutes). This said, it is similar to those who have continuous monitoring of the neck, back and arms, but much less frequent.
## # A tibble: 5 × 6
## Group n mean sd median IQR
## <fct> <int> <dbl> <dbl> <dbl> <dbl>
## 1 Overall 80 5.65 1.30 6 2
## 2 Attending 37 5.38 1.30 6 2
## 3 Resident 43 5.88 1.28 6 2
## 4 Male 70 5.69 1.31 6 2
## 5 Female 10 5.4 1.26 5 2.5Click to see breakdown of worst RULA Score (n = 80 surgeries) by procedure length, category, and difficulty.
Breakdown of RULA Scores by worst Score per Procedure (80 procedures from 970 recordings) by procedure length, category, and difficulty.
## # A tibble: 1 × 6
## n mean median sd min max
## <int> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 80 5.65 6 1.30 2 7## # A tibble: 4 × 7
## Length_surgery_min2 n mean median sd min max
## <chr> <int> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 0-60 mins 13 4.54 4 1.71 2 7
## 2 181-360 mins 24 6.17 6 0.761 4 7
## 3 360+ mins 9 6.44 6 0.527 6 7
## 4 61-180 mins 34 5.5 5 1.29 3 7## # A tibble: 5 × 7
## Category_Procedure n mean median sd min max
## <chr> <int> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 Endoscopic/Diagnostic 1 5 5 NA 5 5
## 2 LN/neck dissections 9 5.22 5 1.09 4 7
## 3 Other 4 3.75 4 0.5 3 4
## 4 Reconstructive 17 5.88 6 1.27 3 7
## 5 Resection 49 5.82 6 1.29 2 7## # A tibble: 4 × 7
## Difficulty n mean median sd min max
## <chr> <int> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 Average 43 5.35 6 1.41 2 7
## 2 Easier than average 7 5.43 5 1.51 4 7
## 3 More difficult than average 24 6.12 6 0.992 4 7
## 4 Most difficult 6 6.17 6 0.753 5 7Bar graphs of mean rula and worst rula per procedure.
Bar charts for the curious.
.
Statistical Analysis
First are the results from the ANOVA test. Factorial ANOVA (FANOVA) was employed, as it allows individual dependent variables to be analyzed with respect to multiple groups of independent variables (procedure length, category, and duration in this case). Each outcome was examined individually.
FANOVAs for Average RULA Score, Worst RULA Score, and change in pain were all obtained.
Click to see a summary of the ANOVA results for average RULA score.
Displayed are the results from the ANOVA test for average RULA score. None of the p-values were significant across variables, their two-way interactions, or their 3-way interactions.
## Warning: package 'car' was built under R version 4.3.3## Loading required package: carData## Warning: package 'carData' was built under R version 4.3.3##
## Attaching package: 'car'## The following object is masked from 'package:dplyr':
##
## recode## Warning: package 'effectsize' was built under R version 4.3.3## Note: model has aliased coefficients
## sums of squares computed by model comparison## Anova Table (Type II tests)
##
## Response: RULA
## Sum Sq Df F value Pr(>F)
## Length_surgery_min2 1.041 3 0.2931 0.83017
## Difficulty 4.032 2 1.7024 0.19285
## Category_Procedure 8.154 4 1.7212 0.16038
## Length_surgery_min2:Difficulty 8.632 4 1.8222 0.13958
## Length_surgery_min2:Category_Procedure 1.101 5 0.1859 0.96660
## Difficulty:Category_Procedure 2.621 4 0.5532 0.69756
## Length_surgery_min2:Difficulty:Category_Procedure 3.827 1 3.2318 0.07839 .
## Residuals 58.030 49
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1## # Effect Size for ANOVA (Type I)
##
## Parameter | Eta2 (partial) | 95% CI
## ---------------------------------------------------------------------------------
## Length_surgery_min2 | 0.02 | [0.00, 1.00]
## Difficulty | 0.05 | [0.00, 1.00]
## Category_Procedure | 0.11 | [0.00, 1.00]
## Length_surgery_min2:Difficulty | 0.12 | [0.00, 1.00]
## Length_surgery_min2:Category_Procedure | 0.05 | [0.00, 1.00]
## Difficulty:Category_Procedure | 0.04 | [0.00, 1.00]
## Length_surgery_min2:Difficulty:Category_Procedure | 0.06 | [0.00, 1.00]
##
## - One-sided CIs: upper bound fixed at [1.00].## Warning: not plotting observations with leverage one:
## 2, 18, 23, 24, 27, 44, 59, 60, 67, 69
Click to see a summary of the ANOVA results for worst RULA score.
Displayed are the results from the ANOVA test for worst RULA score. Similar to the case for average RULA score, none of the p-values were significant across variables, their two-way interactions, or their 3-way interactions.
## Note: model has aliased coefficients
## sums of squares computed by model comparison## Anova Table (Type II tests)
##
## Response: RULAWB
## Sum Sq Df F value Pr(>F)
## Length_surgery_min2 13.006 3 2.7517 0.05251 .
## Difficulty 2.821 2 0.8952 0.41512
## Category_Procedure 8.332 4 1.3222 0.27493
## Length_surgery_min2:Difficulty 7.585 4 1.2036 0.32122
## Length_surgery_min2:Category_Procedure 0.438 5 0.0556 0.99791
## Difficulty:Category_Procedure 4.518 4 0.7170 0.58442
## Length_surgery_min2:Difficulty:Category_Procedure 1.296 1 0.8229 0.36878
## Residuals 77.200 49
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1## # Effect Size for ANOVA (Type I)
##
## Parameter | Eta2 (partial) | 95% CI
## ---------------------------------------------------------------------------------
## Length_surgery_min2 | 0.26 | [0.07, 1.00]
## Difficulty | 0.03 | [0.00, 1.00]
## Category_Procedure | 0.09 | [0.00, 1.00]
## Length_surgery_min2:Difficulty | 0.08 | [0.00, 1.00]
## Length_surgery_min2:Category_Procedure | 0.03 | [0.00, 1.00]
## Difficulty:Category_Procedure | 0.06 | [0.00, 1.00]
## Length_surgery_min2:Difficulty:Category_Procedure | 0.02 | [0.00, 1.00]
##
## - One-sided CIs: upper bound fixed at [1.00].## Warning: not plotting observations with leverage one:
## 2, 18, 23, 24, 27, 44, 59, 60, 67, 69
Click to a summary of the ANOVA results for change in pain.
Displayed are the results from the ANOVA test for change in pain. None of the p-values were significant across variables, their two-way interactions, or their 3-way interactions.
## Note: model has aliased coefficients
## sums of squares computed by model comparison## Anova Table (Type II tests)
##
## Response: POScores
## Sum Sq Df F value Pr(>F)
## Length_surgery_min2 1.647 3 0.2708 0.84618
## Difficulty 2.262 2 0.5579 0.57600
## Category_Procedure 3.494 4 0.4308 0.78569
## Length_surgery_min2:Difficulty 2.040 4 0.2515 0.90738
## Length_surgery_min2:Category_Procedure 12.627 5 1.2455 0.30253
## Difficulty:Category_Procedure 7.091 4 0.8743 0.48616
## Length_surgery_min2:Difficulty:Category_Procedure 6.756 1 3.3321 0.07404 .
## Residuals 99.350 49
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1## # Effect Size for ANOVA (Type I)
##
## Parameter | Eta2 (partial) | 95% CI
## ---------------------------------------------------------------------------------
## Length_surgery_min2 | 2.40e-03 | [0.00, 1.00]
## Difficulty | 0.03 | [0.00, 1.00]
## Category_Procedure | 0.03 | [0.00, 1.00]
## Length_surgery_min2:Difficulty | 0.02 | [0.00, 1.00]
## Length_surgery_min2:Category_Procedure | 0.12 | [0.00, 1.00]
## Difficulty:Category_Procedure | 0.07 | [0.00, 1.00]
## Length_surgery_min2:Difficulty:Category_Procedure | 0.06 | [0.00, 1.00]
##
## - One-sided CIs: upper bound fixed at [1.00].## Warning: not plotting observations with leverage one:
## 2, 18, 23, 24, 27, 44, 59, 60, 67, 69
Next are the results from the linear regression modeling. Separate simple regression was employed due to collinearity. The predictors employed for this model were Age, Height, Weight, and Glove Size.
Click to a summary of the linear regression results for average RULA score.
Displayed are the results from the linear regression test on average RULA score. None of the p-values were significant across variables.
## Warning: package 'broom' was built under R version 4.3.3## $Age
## # A tibble: 2 × 7
## term estimate std.error statistic p.value conf.low conf.high
## <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 (Intercept) 4.80 0.491 9.79 3.16e-15 3.83 5.78
## 2 Age -0.0120 0.0123 -0.976 3.32e- 1 -0.0364 0.0124
##
## $Height
## # A tibble: 2 × 7
## term estimate std.error statistic p.value conf.low conf.high
## <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 (Intercept) 1.37 2.02 0.679 0.499 -2.65 5.40
## 2 Height 0.0170 0.0116 1.47 0.146 -0.00603 0.0400
##
## $Weight
## # A tibble: 2 × 7
## term estimate std.error statistic p.value conf.low conf.high
## <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 (Intercept) 4.12 0.635 6.48 0.00000000763 2.85 5.38
## 2 Weight 0.00131 0.00364 0.360 0.720 -0.00594 0.00856
##
## $Glove_size
## # A tibble: 2 × 7
## term estimate std.error statistic p.value conf.low conf.high
## <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 (Intercept) 3.17 2.05 1.55 0.125 -0.902 7.24
## 2 Glove_size 0.164 0.286 0.573 0.568 -0.405 0.733Click to see a summary of the linear regression results for worst RULA score.
Displayed are the results from the linear regression test on worst RULA score. None of the p-values were significant across variables.
## $Age
## # A tibble: 2 × 7
## term estimate std.error statistic p.value conf.low conf.high
## <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 (Intercept) 6.01 0.602 9.97 1.43e-15 4.81 7.21
## 2 Age -0.00922 0.0151 -0.612 5.42e- 1 -0.0392 0.0208
##
## $Height
## # A tibble: 2 × 7
## term estimate std.error statistic p.value conf.low conf.high
## <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 (Intercept) 2.94 2.49 1.18 0.241 -2.02 7.89
## 2 Height 0.0155 0.0142 1.09 0.278 -0.0128 0.0439
##
## $Weight
## # A tibble: 2 × 7
## term estimate std.error statistic p.value conf.low conf.high
## <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 (Intercept) 5.22 0.776 6.72 0.00000000269 3.67 6.76
## 2 Weight 0.00253 0.00445 0.569 0.571 -0.00633 0.0114
##
## $Glove_size
## # A tibble: 2 × 7
## term estimate std.error statistic p.value conf.low conf.high
## <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 (Intercept) 4.71 2.51 1.88 0.0641 -0.282 9.69
## 2 Glove_size 0.132 0.350 0.377 0.707 -0.565 0.830Click to see a summary of the linear regression results for change in pain score.
Displayed are the results from the linear regression test on change in pain score. Statistical significance was found in age, weight, and glove size (height was not found to be significant), albeit with low effect size. All three were found to correlate negatively with change in pain score.
## $Age
## # A tibble: 2 × 7
## term estimate std.error statistic p.value conf.low conf.high
## <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 (Intercept) 4.06 0.651 6.23 0.0000000219 2.76 5.35
## 2 Age -0.0588 0.0163 -3.61 0.000535 -0.0912 -0.0264
##
## $Height
## # A tibble: 2 × 7
## term estimate std.error statistic p.value conf.low conf.high
## <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 (Intercept) 4.19 2.91 1.44 0.154 -1.60 9.98
## 2 Height -0.0138 0.0166 -0.832 0.408 -0.0469 0.0193
##
## $Weight
## # A tibble: 2 × 7
## term estimate std.error statistic p.value conf.low conf.high
## <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 (Intercept) 5.22 0.814 6.42 0.00000000990 3.60 6.84
## 2 Weight -0.0201 0.00467 -4.31 0.0000466 -0.0294 -0.0108
##
## $Glove_size
## # A tibble: 2 × 7
## term estimate std.error statistic p.value conf.low conf.high
## <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 (Intercept) 8.42 2.82 2.99 0.00378 2.81 14.0
## 2 Glove_size -0.931 0.395 -2.36 0.0208 -1.72 -0.146Finally are the results from the binary variables, sex and training level. A test for normality was conducted and either a t-test or a wilcoxen signed rank test was used pending the normality of the data.
Click to see a summary of sex and training influence for average RULA score.
Displayed are the results from shapiro-wilks test for normality. Only Average RULA - Female, Post op - Female, and average - resident were normal in distribution.
P-values were adjusted with bonferroni correction (factor of 15). RULA = Average RULA score, RULAWB = Worst RULA Score collected bilaterally (both hands), and POScore = difference in pain score from baseline.
To summarize, significance was identified in worst rula score for the overall, male, and both resident and attending subgroups. Significance was also found in post-op pain change from baseline in overall, male, female, and both resident and attending subgroups (same as for worst rula score).
Significance was identified in average RULA score for the female and resident subgroups.
##
## Attaching package: 'rstatix'## The following objects are masked from 'package:effectsize':
##
## cohens_d, eta_squared## The following object is masked from 'package:stats':
##
## filter##
## Shapiro-Wilk normality test
##
## data: PChar2$RULA
## W = 0.96587, p-value = 0.03107##
## Shapiro-Wilk normality test
##
## data: PChar2$RULAWB
## W = 0.86426, p-value = 5.037e-07##
## Shapiro-Wilk normality test
##
## data: PChar2$POScores
## W = 0.89725, p-value = 9.34e-06## PChar2$Sex: Female
##
## Shapiro-Wilk normality test
##
## data: dd[x, ]
## W = 0.96937, p-value = 0.8849
##
## ------------------------------------------------------------
## PChar2$Sex: Male
##
## Shapiro-Wilk normality test
##
## data: dd[x, ]
## W = 0.9626, p-value = 0.03492## PChar2$Sex: Female
##
## Shapiro-Wilk normality test
##
## data: dd[x, ]
## W = 0.83805, p-value = 0.04181
##
## ------------------------------------------------------------
## PChar2$Sex: Male
##
## Shapiro-Wilk normality test
##
## data: dd[x, ]
## W = 0.85069, p-value = 7.046e-07## PChar2$Sex: Female
##
## Shapiro-Wilk normality test
##
## data: dd[x, ]
## W = 0.91103, p-value = 0.2881
##
## ------------------------------------------------------------
## PChar2$Sex: Male
##
## Shapiro-Wilk normality test
##
## data: dd[x, ]
## W = 0.89069, p-value = 1.696e-05## PChar2$Training: Attending
##
## Shapiro-Wilk normality test
##
## data: dd[x, ]
## W = 0.92643, p-value = 0.0174
##
## ------------------------------------------------------------
## PChar2$Training: Resident
##
## Shapiro-Wilk normality test
##
## data: dd[x, ]
## W = 0.97172, p-value = 0.3618## PChar2$Training: Attending
##
## Shapiro-Wilk normality test
##
## data: dd[x, ]
## W = 0.88974, p-value = 0.001547
##
## ------------------------------------------------------------
## PChar2$Training: Resident
##
## Shapiro-Wilk normality test
##
## data: dd[x, ]
## W = 0.81832, p-value = 9.132e-06## PChar2$Training: Attending
##
## Shapiro-Wilk normality test
##
## data: dd[x, ]
## W = 0.85075, p-value = 0.0001638
##
## ------------------------------------------------------------
## PChar2$Training: Resident
##
## Shapiro-Wilk normality test
##
## data: dd[x, ]
## W = 0.83877, p-value = 2.758e-05## Warning: Returning more (or less) than 1 row per `summarise()` group was deprecated in
## dplyr 1.1.0.
## ℹ Please use `reframe()` instead.
## ℹ When switching from `summarise()` to `reframe()`, remember that `reframe()`
## always returns an ungrouped data frame and adjust accordingly.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.## Warning: Returning more (or less) than 1 row per `summarise()` group was deprecated in
## dplyr 1.1.0.
## ℹ Please use `reframe()` instead.
## ℹ When switching from `summarise()` to `reframe()`, remember that `reframe()`
## always returns an ungrouped data frame and adjust accordingly.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.## # A tibble: 15 × 4
## Outcome Group `Shapiro–Wilk W` `p value`
## <chr> <chr> <dbl> <dbl>
## 1 Average RULA score Overall 0.966 0.0311
## 2 Worst RULA score Overall 0.864 0.000000504
## 3 Post-operative pain change Overall 0.897 0.00000934
## 4 Average RULA score Female 0.969 0.885
## 5 Worst RULA score Female 0.838 0.0418
## 6 Post-operative pain change Female 0.911 0.288
## 7 Average RULA score Male 0.963 0.0349
## 8 Worst RULA score Male 0.851 0.000000705
## 9 Post-operative pain change Male 0.891 0.0000170
## 10 Average RULA score Attending 0.926 0.0174
## 11 Worst RULA score Attending 0.890 0.00155
## 12 Post-operative pain change Attending 0.851 0.000164
## 13 Average RULA score Resident 0.972 0.362
## 14 Worst RULA score Resident 0.818 0.00000913
## 15 Post-operative pain change Resident 0.839 0.0000276After checking normality, either a t-test or a wilcoxen signed rank test is used.
T-test results:
##
## One Sample t-test
##
## data: PChar2$RULA[PChar2$Sex == "Female"]
## t = 14.01, df = 9, p-value = 2.038e-07
## alternative hypothesis: true mean is not equal to 0
## 95 percent confidence interval:
## 3.428915 4.749418
## sample estimates:
## mean of x
## 4.089167##
## One Sample t-test
##
## data: PChar2$POScores[PChar2$Sex == "Female"]
## t = 4.1498, df = 9, p-value = 0.002485
## alternative hypothesis: true mean is not equal to 0
## 95 percent confidence interval:
## 1.228148 4.171852
## sample estimates:
## mean of x
## 2.7##
## One Sample t-test
##
## data: PChar2$RULA[PChar2$Training == "Resident"]
## t = 24.693, df = 42, p-value < 2.2e-16
## alternative hypothesis: true mean is not equal to 0
## 95 percent confidence interval:
## 4.078273 4.804206
## sample estimates:
## mean of x
## 4.44124Wilcoxen results:
## # A tibble: 15 × 6
## Outcome Group n W p_value p_adj
## <chr> <chr> <int> <dbl> <dbl> <dbl>
## 1 RULA Overall 80 0.966 0.0311 0.466
## 2 RULA Female 10 0.969 0.885 1
## 3 RULA Male 70 0.963 0.0349 0.524
## 4 RULA Attending 37 0.926 0.0174 0.261
## 5 RULA Resident 43 0.972 0.362 1
## 6 RULAWB Overall 80 0.864 0.000000504 0.00000756
## 7 RULAWB Female 10 0.838 0.0418 0.627
## 8 RULAWB Male 70 0.851 0.000000705 0.0000106
## 9 RULAWB Attending 37 0.890 0.00155 0.0232
## 10 RULAWB Resident 43 0.818 0.00000913 0.000137
## 11 POScores Overall 80 0.897 0.00000934 0.000140
## 12 POScores Female 10 0.911 0.288 1
## 13 POScores Male 70 0.891 0.0000170 0.000254
## 14 POScores Attending 37 0.851 0.000164 0.00246
## 15 POScores Resident 43 0.839 0.0000276 0.000414.
P-values were adjusted with bonferroni correction (factor of 15). RULA = Average RULA score, RULAWB = Worst RULA Score collected bilaterally (both hands), and POScore = difference in pain score from baseline.
To summarize, significance was identified in worst rula score for the overall, male, and both resident and attending subgroups. Significance was also found in post-op pain change from baseline in overall, male, female, and both resident and attending subgroups (same as for worst rula score).
Significance was identified in average RULA score for the female and resident subgroups.
Click to a table of breakdown of parameters by underlying demographics.
Displayed is a table summarizing the results, with descriptive statistics only. RULA = Average RULA score, RULAWB = Worst RULA Score collected bilaterally (both hands), and POScore = difference in pain score from baseline.
## # A tibble: 9 × 10
## Training Sex Avg_RULA_Mean Avg_RULA_SD Worst_RULA_Mean Worst_RULA_SD
## <chr> <chr> <dbl> <dbl> <dbl> <dbl>
## 1 All All 4.34 1.07 5.65 1.30
## 2 All Female 4.09 0.923 5.4 1.26
## 3 All Male 4.38 1.09 5.69 1.31
## 4 Attending All 4.22 0.917 5.38 1.30
## 5 Attending Female 3.95 0.647 5 1.22
## 6 Attending Male 4.26 0.953 5.44 1.32
## 7 Resident All 4.44 1.18 5.88 1.28
## 8 Resident Female 4.23 1.20 5.8 1.30
## 9 Resident Male 4.47 1.19 5.89 1.29
## # ℹ 4 more variables: PostOpPainChange_Mean <dbl>, PostOpPainChange_SD <dbl>,
## # PostOpPainRaw_Mean <dbl>, PostOpPainRaw_SD <dbl>