Artificial intelligence models utilize lifestyle factors to predict dry eye related outcomes

Abstract The purpose of this study is to examine and interpret machine learning models that predict dry eye (DE)-related clinical signs, subjective symptoms, and clinician diagnoses by heavily weighting lifestyle factors in the predictions. Machine learning models were trained to take clinical asses...

Full description

Saved in:
Bibliographic Details
Main Authors: Andrew D. Graham, Jiayun Wang, Tejasvi Kothapalli, Jennifer E. Ding, Helen Tasho, Alisa Molina, Vivien Tse, Sarah M. Chang, Stella X. Yu, Meng C. Lin
Format: Article
Language:English
Published: Nature Portfolio 2025-04-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-96778-x
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850146293068857344
author Andrew D. Graham
Jiayun Wang
Tejasvi Kothapalli
Jennifer E. Ding
Helen Tasho
Alisa Molina
Vivien Tse
Sarah M. Chang
Stella X. Yu
Meng C. Lin
author_facet Andrew D. Graham
Jiayun Wang
Tejasvi Kothapalli
Jennifer E. Ding
Helen Tasho
Alisa Molina
Vivien Tse
Sarah M. Chang
Stella X. Yu
Meng C. Lin
author_sort Andrew D. Graham
collection DOAJ
description Abstract The purpose of this study is to examine and interpret machine learning models that predict dry eye (DE)-related clinical signs, subjective symptoms, and clinician diagnoses by heavily weighting lifestyle factors in the predictions. Machine learning models were trained to take clinical assessments of the ocular surface, eyelids, and tear film, combined with symptom scores from validated questionnaire instruments for DE and clinician diagnoses of ocular surface diseases, and perform a classification into DE-related outcome categories. Outcomes are presented for which the data-driven algorithm identified subject characteristics, lifestyle, behaviors, or environmental exposures as heavily weighted predictors. Models were assessed by 5-fold cross-validation accuracy and class-wise statistics of the predictors. Age was a heavily weighted factor in predictions of eyelid notching, Line of Marx anterior displacement, and fluorescein tear breakup time (FTBUT), as well as visual analog scale symptom ratings and a clinician diagnosis of blepharitis. Comfortable contact lens wearing time was heavily weighted in predictions of DE symptom ratings. Time spent in near work, alcohol consumption, exercise, and time spent outdoors were heavily weighted predictors for several ocular signs and symptoms. Exposure to airplane cabin environments and driving a car were predictors of DE-related symptoms but not clinical signs. Prediction accuracies for DE-related symptoms ranged from 60.7 to 86.5%, for diagnoses from 73.7 to 80.1%, and for clinical signs from 66.9 to 98.7%. The results emphasize the importance of lifestyle, subject, and environmental characteristics in the etiology of ocular surface disease. Lifestyle factors should be taken into account in clinical research and care to a far greater extent than has been the case to date.
format Article
id doaj-art-720e72b5beb847aabd5b9392ddd3eb76
institution OA Journals
issn 2045-2322
language English
publishDate 2025-04-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-720e72b5beb847aabd5b9392ddd3eb762025-08-20T02:27:53ZengNature PortfolioScientific Reports2045-23222025-04-0115111010.1038/s41598-025-96778-xArtificial intelligence models utilize lifestyle factors to predict dry eye related outcomesAndrew D. Graham0Jiayun Wang1Tejasvi Kothapalli2Jennifer E. Ding3Helen Tasho4Alisa Molina5Vivien Tse6Sarah M. Chang7Stella X. Yu8Meng C. Lin9Vision Science Group, University of CaliforniaDepartment of Electrical Engineering and Computer Science, University of CaliforniaVision Science Group, University of CaliforniaClinical Research Center, School of Optometry, University of CaliforniaClinical Research Center, School of Optometry, University of CaliforniaClinical Research Center, School of Optometry, University of CaliforniaClinical Research Center, School of Optometry, University of CaliforniaClinical Research Center, School of Optometry, University of CaliforniaElectrical Engineering and Computer Science Department, University of MichiganVision Science Group, University of CaliforniaAbstract The purpose of this study is to examine and interpret machine learning models that predict dry eye (DE)-related clinical signs, subjective symptoms, and clinician diagnoses by heavily weighting lifestyle factors in the predictions. Machine learning models were trained to take clinical assessments of the ocular surface, eyelids, and tear film, combined with symptom scores from validated questionnaire instruments for DE and clinician diagnoses of ocular surface diseases, and perform a classification into DE-related outcome categories. Outcomes are presented for which the data-driven algorithm identified subject characteristics, lifestyle, behaviors, or environmental exposures as heavily weighted predictors. Models were assessed by 5-fold cross-validation accuracy and class-wise statistics of the predictors. Age was a heavily weighted factor in predictions of eyelid notching, Line of Marx anterior displacement, and fluorescein tear breakup time (FTBUT), as well as visual analog scale symptom ratings and a clinician diagnosis of blepharitis. Comfortable contact lens wearing time was heavily weighted in predictions of DE symptom ratings. Time spent in near work, alcohol consumption, exercise, and time spent outdoors were heavily weighted predictors for several ocular signs and symptoms. Exposure to airplane cabin environments and driving a car were predictors of DE-related symptoms but not clinical signs. Prediction accuracies for DE-related symptoms ranged from 60.7 to 86.5%, for diagnoses from 73.7 to 80.1%, and for clinical signs from 66.9 to 98.7%. The results emphasize the importance of lifestyle, subject, and environmental characteristics in the etiology of ocular surface disease. Lifestyle factors should be taken into account in clinical research and care to a far greater extent than has been the case to date.https://doi.org/10.1038/s41598-025-96778-xDry eyeMeibomian gland dysfunctionLifestyleArtificial intelligenceMachine learningAge
spellingShingle Andrew D. Graham
Jiayun Wang
Tejasvi Kothapalli
Jennifer E. Ding
Helen Tasho
Alisa Molina
Vivien Tse
Sarah M. Chang
Stella X. Yu
Meng C. Lin
Artificial intelligence models utilize lifestyle factors to predict dry eye related outcomes
Scientific Reports
Dry eye
Meibomian gland dysfunction
Lifestyle
Artificial intelligence
Machine learning
Age
title Artificial intelligence models utilize lifestyle factors to predict dry eye related outcomes
title_full Artificial intelligence models utilize lifestyle factors to predict dry eye related outcomes
title_fullStr Artificial intelligence models utilize lifestyle factors to predict dry eye related outcomes
title_full_unstemmed Artificial intelligence models utilize lifestyle factors to predict dry eye related outcomes
title_short Artificial intelligence models utilize lifestyle factors to predict dry eye related outcomes
title_sort artificial intelligence models utilize lifestyle factors to predict dry eye related outcomes
topic Dry eye
Meibomian gland dysfunction
Lifestyle
Artificial intelligence
Machine learning
Age
url https://doi.org/10.1038/s41598-025-96778-x
work_keys_str_mv AT andrewdgraham artificialintelligencemodelsutilizelifestylefactorstopredictdryeyerelatedoutcomes
AT jiayunwang artificialintelligencemodelsutilizelifestylefactorstopredictdryeyerelatedoutcomes
AT tejasvikothapalli artificialintelligencemodelsutilizelifestylefactorstopredictdryeyerelatedoutcomes
AT jennifereding artificialintelligencemodelsutilizelifestylefactorstopredictdryeyerelatedoutcomes
AT helentasho artificialintelligencemodelsutilizelifestylefactorstopredictdryeyerelatedoutcomes
AT alisamolina artificialintelligencemodelsutilizelifestylefactorstopredictdryeyerelatedoutcomes
AT vivientse artificialintelligencemodelsutilizelifestylefactorstopredictdryeyerelatedoutcomes
AT sarahmchang artificialintelligencemodelsutilizelifestylefactorstopredictdryeyerelatedoutcomes
AT stellaxyu artificialintelligencemodelsutilizelifestylefactorstopredictdryeyerelatedoutcomes
AT mengclin artificialintelligencemodelsutilizelifestylefactorstopredictdryeyerelatedoutcomes