Machine Learning Does Not Improve Humeral Torsion Prediction Compared to Regression in Baseball Pitchers
# Background Humeral torsion is an important osseous adaptation in throwing athletes that can contribute to arm injuries. Currently there are no cheap and easy to use clinical tools to measure humeral torsion, inhibiting clinical assessment. Models with low error and "good" calibration sl...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
North American Sports Medicine Institute
2022-04-01
|
| Series: | International Journal of Sports Physical Therapy |
| Online Access: | https://doi.org/10.26603/001c.32380 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1825196986971717632 |
|---|---|
| author | Garrett S Bullock Charles A Thigpen Gary S Collins Nigel K Arden Thomas K Noonan Michael J Kissenberth Ellen Shanley |
| author_facet | Garrett S Bullock Charles A Thigpen Gary S Collins Nigel K Arden Thomas K Noonan Michael J Kissenberth Ellen Shanley |
| author_sort | Garrett S Bullock |
| collection | DOAJ |
| description | # Background
Humeral torsion is an important osseous adaptation in throwing athletes that can contribute to arm injuries. Currently there are no cheap and easy to use clinical tools to measure humeral torsion, inhibiting clinical assessment. Models with low error and "good" calibration slope may be helpful for prediction.
# Hypothesis/Purpose
To develop prediction models using a range of machine learning methods to predict humeral torsion in professional baseball pitchers and compare these models to a previously developed regression-based prediction model.
# Study Design
Prospective cohort
# Methods
An eleven-year professional baseball cohort was recruited from 2009-2019. Age, arm dominance, injury history, and continent of origin were collected as well as preseason shoulder external and internal rotation, horizontal adduction passive range of motion, and humeral torsion were collected each season. Regression and machine learning models were developed to predict humeral torsion followed by internal validation with 10-fold cross validation. Root mean square error (RMSE), which is reported in degrees (°) and calibration slope (agreement of predicted and actual outcome; best = 1.00) were assessed.
# Results
Four hundred and seven pitchers (Age: 23.2 +/-2.4 years, body mass index: 25.1 +/-2.3 km/m^2^, Left-Handed: 17%) participated. Regression model RMSE was 12° and calibration was 1.00 (95% CI: 0.94, 1.06). Random Forest RMSE was 9° and calibration was 1.33 (95% CI: 1.29, 1.37). Gradient boosting machine RMSE was 9° and calibration was 1.09 (95% CI: 1.04, 1.14). Support vector machine RMSE was 10° and calibration was 1.13 (95% CI: 1.08, 1.18). Artificial neural network RMSE was 15° and calibration was 1.03 (95% CI: 0.97, 1.09).
# Conclusion
This is the first study to show that machine learning models do not improve baseball humeral torsion prediction compared to a traditional regression model. While machine learning models demonstrated improved RMSE compared to the regression, the machine learning models displayed poorer calibration compared to regression. Based on these results it is recommended to use a simple equation from a statistical model which can be quickly and efficiently integrated within a clinical setting.
# Levels of Evidence
2 |
| format | Article |
| id | doaj-art-0906e13f1c1d4d65ab8f5e79c9c38c4f |
| institution | Kabale University |
| issn | 2159-2896 |
| language | English |
| publishDate | 2022-04-01 |
| publisher | North American Sports Medicine Institute |
| record_format | Article |
| series | International Journal of Sports Physical Therapy |
| spelling | doaj-art-0906e13f1c1d4d65ab8f5e79c9c38c4f2025-02-11T20:27:32ZengNorth American Sports Medicine InstituteInternational Journal of Sports Physical Therapy2159-28962022-04-01173Machine Learning Does Not Improve Humeral Torsion Prediction Compared to Regression in Baseball PitchersGarrett S BullockCharles A ThigpenGary S CollinsNigel K ArdenThomas K NoonanMichael J KissenberthEllen Shanley# Background Humeral torsion is an important osseous adaptation in throwing athletes that can contribute to arm injuries. Currently there are no cheap and easy to use clinical tools to measure humeral torsion, inhibiting clinical assessment. Models with low error and "good" calibration slope may be helpful for prediction. # Hypothesis/Purpose To develop prediction models using a range of machine learning methods to predict humeral torsion in professional baseball pitchers and compare these models to a previously developed regression-based prediction model. # Study Design Prospective cohort # Methods An eleven-year professional baseball cohort was recruited from 2009-2019. Age, arm dominance, injury history, and continent of origin were collected as well as preseason shoulder external and internal rotation, horizontal adduction passive range of motion, and humeral torsion were collected each season. Regression and machine learning models were developed to predict humeral torsion followed by internal validation with 10-fold cross validation. Root mean square error (RMSE), which is reported in degrees (°) and calibration slope (agreement of predicted and actual outcome; best = 1.00) were assessed. # Results Four hundred and seven pitchers (Age: 23.2 +/-2.4 years, body mass index: 25.1 +/-2.3 km/m^2^, Left-Handed: 17%) participated. Regression model RMSE was 12° and calibration was 1.00 (95% CI: 0.94, 1.06). Random Forest RMSE was 9° and calibration was 1.33 (95% CI: 1.29, 1.37). Gradient boosting machine RMSE was 9° and calibration was 1.09 (95% CI: 1.04, 1.14). Support vector machine RMSE was 10° and calibration was 1.13 (95% CI: 1.08, 1.18). Artificial neural network RMSE was 15° and calibration was 1.03 (95% CI: 0.97, 1.09). # Conclusion This is the first study to show that machine learning models do not improve baseball humeral torsion prediction compared to a traditional regression model. While machine learning models demonstrated improved RMSE compared to the regression, the machine learning models displayed poorer calibration compared to regression. Based on these results it is recommended to use a simple equation from a statistical model which can be quickly and efficiently integrated within a clinical setting. # Levels of Evidence 2https://doi.org/10.26603/001c.32380 |
| spellingShingle | Garrett S Bullock Charles A Thigpen Gary S Collins Nigel K Arden Thomas K Noonan Michael J Kissenberth Ellen Shanley Machine Learning Does Not Improve Humeral Torsion Prediction Compared to Regression in Baseball Pitchers International Journal of Sports Physical Therapy |
| title | Machine Learning Does Not Improve Humeral Torsion Prediction Compared to Regression in Baseball Pitchers |
| title_full | Machine Learning Does Not Improve Humeral Torsion Prediction Compared to Regression in Baseball Pitchers |
| title_fullStr | Machine Learning Does Not Improve Humeral Torsion Prediction Compared to Regression in Baseball Pitchers |
| title_full_unstemmed | Machine Learning Does Not Improve Humeral Torsion Prediction Compared to Regression in Baseball Pitchers |
| title_short | Machine Learning Does Not Improve Humeral Torsion Prediction Compared to Regression in Baseball Pitchers |
| title_sort | machine learning does not improve humeral torsion prediction compared to regression in baseball pitchers |
| url | https://doi.org/10.26603/001c.32380 |
| work_keys_str_mv | AT garrettsbullock machinelearningdoesnotimprovehumeraltorsionpredictioncomparedtoregressioninbaseballpitchers AT charlesathigpen machinelearningdoesnotimprovehumeraltorsionpredictioncomparedtoregressioninbaseballpitchers AT garyscollins machinelearningdoesnotimprovehumeraltorsionpredictioncomparedtoregressioninbaseballpitchers AT nigelkarden machinelearningdoesnotimprovehumeraltorsionpredictioncomparedtoregressioninbaseballpitchers AT thomasknoonan machinelearningdoesnotimprovehumeraltorsionpredictioncomparedtoregressioninbaseballpitchers AT michaeljkissenberth machinelearningdoesnotimprovehumeraltorsionpredictioncomparedtoregressioninbaseballpitchers AT ellenshanley machinelearningdoesnotimprovehumeraltorsionpredictioncomparedtoregressioninbaseballpitchers |