The Potential of SHAP and Machine Learning for Personalized Explanations of Influencing Factors in Myopic Treatment for Children
<i>Background and Objectives:</i> The rising prevalence of myopia is a significant global health concern. Atropine eye drops are commonly used to slow myopia progression in children, but their long-term use raises concern about intraocular pressure (IOP). This study uses SHapley Additive...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-12-01
|
| Series: | Medicina |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1648-9144/61/1/16 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832588009683288064 |
|---|---|
| author | Jun-Wei Chen Hsin-An Chen Tzu-Chi Liu Tzu-En Wu Chi-Jie Lu |
| author_facet | Jun-Wei Chen Hsin-An Chen Tzu-Chi Liu Tzu-En Wu Chi-Jie Lu |
| author_sort | Jun-Wei Chen |
| collection | DOAJ |
| description | <i>Background and Objectives:</i> The rising prevalence of myopia is a significant global health concern. Atropine eye drops are commonly used to slow myopia progression in children, but their long-term use raises concern about intraocular pressure (IOP). This study uses SHapley Additive exPlanations (SHAP) to improve the interpretability of machine learning (ML) model predicting end IOP, offering clinicians explainable insights for personalized patient management. <i>Materials and Methods:</i> This retrospective study analyzed data from 1191 individual eyes of 639 boys and 552 girls with myopia treated with atropine. The average age of the whole group was 10.6 ± 2.5 years old. The refractive error of spherical equivalent (SE) in myopia degree was base SE at 2.63D and end SE at 3.12D. Data were collected from clinical records, including demographic information, IOP measurements, and atropine treatment details. The patients were divided into two subgroups based on a baseline IOP of 14 mmHg. ML models, including Lasso, CART, XGB, and RF, were developed to predict the end IOP value. Then, the best-performing model was further interpreted using SHAP values. The SHAP module created a personalized and dynamic graphic to illustrate how various factors (e.g., age, sex, cumulative duration, and dosage of atropine treatment) affect the end IOP. <i>Results</i>: RF showed the best performance, with superior error metrics in both subgroups. The interpretation of RF with SHAP revealed that age and the recruitment duration of atropine consistently influenced IOP across subgroups, while other variables had varying effects. SHAP values also offer insights, helping clinicians understand how different factors contribute to predicted IOP value in individual children. <i>Conclusions:</i> SHAP provides an alternative approach to understand the factors affecting IOP in children with myopia treated with atropine. Its enhanced interpretability helps clinicians make informed decisions, improving the safety and efficacy of myopia management. This study demonstrates the potential of combining SHAP with ML models for personalized care in ophthalmology. |
| format | Article |
| id | doaj-art-a6f68c3431244406975afbdae94bb0bd |
| institution | Kabale University |
| issn | 1010-660X 1648-9144 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Medicina |
| spelling | doaj-art-a6f68c3431244406975afbdae94bb0bd2025-01-24T13:40:15ZengMDPI AGMedicina1010-660X1648-91442024-12-016111610.3390/medicina61010016The Potential of SHAP and Machine Learning for Personalized Explanations of Influencing Factors in Myopic Treatment for ChildrenJun-Wei Chen0Hsin-An Chen1Tzu-Chi Liu2Tzu-En Wu3Chi-Jie Lu4School of Medicine, Chang Gung University, Taoyuan 333, TaiwanSchool of Medicine, Chang Gung University, Taoyuan 333, TaiwanGraduate Institute of Business Administration, Fu Jen Catholic University, New Taipei City 242, TaiwanSchool of Medicine, Fu Jen Catholic University, New Taipei City 242, TaiwanGraduate Institute of Business Administration, Fu Jen Catholic University, New Taipei City 242, Taiwan<i>Background and Objectives:</i> The rising prevalence of myopia is a significant global health concern. Atropine eye drops are commonly used to slow myopia progression in children, but their long-term use raises concern about intraocular pressure (IOP). This study uses SHapley Additive exPlanations (SHAP) to improve the interpretability of machine learning (ML) model predicting end IOP, offering clinicians explainable insights for personalized patient management. <i>Materials and Methods:</i> This retrospective study analyzed data from 1191 individual eyes of 639 boys and 552 girls with myopia treated with atropine. The average age of the whole group was 10.6 ± 2.5 years old. The refractive error of spherical equivalent (SE) in myopia degree was base SE at 2.63D and end SE at 3.12D. Data were collected from clinical records, including demographic information, IOP measurements, and atropine treatment details. The patients were divided into two subgroups based on a baseline IOP of 14 mmHg. ML models, including Lasso, CART, XGB, and RF, were developed to predict the end IOP value. Then, the best-performing model was further interpreted using SHAP values. The SHAP module created a personalized and dynamic graphic to illustrate how various factors (e.g., age, sex, cumulative duration, and dosage of atropine treatment) affect the end IOP. <i>Results</i>: RF showed the best performance, with superior error metrics in both subgroups. The interpretation of RF with SHAP revealed that age and the recruitment duration of atropine consistently influenced IOP across subgroups, while other variables had varying effects. SHAP values also offer insights, helping clinicians understand how different factors contribute to predicted IOP value in individual children. <i>Conclusions:</i> SHAP provides an alternative approach to understand the factors affecting IOP in children with myopia treated with atropine. Its enhanced interpretability helps clinicians make informed decisions, improving the safety and efficacy of myopia management. This study demonstrates the potential of combining SHAP with ML models for personalized care in ophthalmology.https://www.mdpi.com/1648-9144/61/1/16myopiaatropineintraocular pressuremachine learningSHAP value |
| spellingShingle | Jun-Wei Chen Hsin-An Chen Tzu-Chi Liu Tzu-En Wu Chi-Jie Lu The Potential of SHAP and Machine Learning for Personalized Explanations of Influencing Factors in Myopic Treatment for Children Medicina myopia atropine intraocular pressure machine learning SHAP value |
| title | The Potential of SHAP and Machine Learning for Personalized Explanations of Influencing Factors in Myopic Treatment for Children |
| title_full | The Potential of SHAP and Machine Learning for Personalized Explanations of Influencing Factors in Myopic Treatment for Children |
| title_fullStr | The Potential of SHAP and Machine Learning for Personalized Explanations of Influencing Factors in Myopic Treatment for Children |
| title_full_unstemmed | The Potential of SHAP and Machine Learning for Personalized Explanations of Influencing Factors in Myopic Treatment for Children |
| title_short | The Potential of SHAP and Machine Learning for Personalized Explanations of Influencing Factors in Myopic Treatment for Children |
| title_sort | potential of shap and machine learning for personalized explanations of influencing factors in myopic treatment for children |
| topic | myopia atropine intraocular pressure machine learning SHAP value |
| url | https://www.mdpi.com/1648-9144/61/1/16 |
| work_keys_str_mv | AT junweichen thepotentialofshapandmachinelearningforpersonalizedexplanationsofinfluencingfactorsinmyopictreatmentforchildren AT hsinanchen thepotentialofshapandmachinelearningforpersonalizedexplanationsofinfluencingfactorsinmyopictreatmentforchildren AT tzuchiliu thepotentialofshapandmachinelearningforpersonalizedexplanationsofinfluencingfactorsinmyopictreatmentforchildren AT tzuenwu thepotentialofshapandmachinelearningforpersonalizedexplanationsofinfluencingfactorsinmyopictreatmentforchildren AT chijielu thepotentialofshapandmachinelearningforpersonalizedexplanationsofinfluencingfactorsinmyopictreatmentforchildren AT junweichen potentialofshapandmachinelearningforpersonalizedexplanationsofinfluencingfactorsinmyopictreatmentforchildren AT hsinanchen potentialofshapandmachinelearningforpersonalizedexplanationsofinfluencingfactorsinmyopictreatmentforchildren AT tzuchiliu potentialofshapandmachinelearningforpersonalizedexplanationsofinfluencingfactorsinmyopictreatmentforchildren AT tzuenwu potentialofshapandmachinelearningforpersonalizedexplanationsofinfluencingfactorsinmyopictreatmentforchildren AT chijielu potentialofshapandmachinelearningforpersonalizedexplanationsofinfluencingfactorsinmyopictreatmentforchildren |