Authors:
Piotr Artiemjew
1
;
Radosław Cybulski
1
;
Mohammad Hassan Emamian
2
;
Andrzej Grzybowski
3
;
Andrzej Jankowski
1
;
Carla Lanca
4
;
5
;
Shiva Mehravaran
6
;
Marcin Młyński
1
;
Cezary Morawski
1
;
Klaus Nordhausen
7
;
Olavi Pärssinen
8
and
Krzysztof Ropiak
1
Affiliations:
1
University of Warmia and Mazury in Olsztyn, Poland
;
2
Ophthalmic Epidemiology Research Center, Shahroud University of Medical Sciences, Shahroud, Iran
;
3
Foundation for Ophthalmology Development & University of Warmia and Mazury, Poland
;
4
Lisbon School of Health Technology, Lisbon, Portugal
;
5
Comprehensive Health Research Center (CHRC), Escola Nacional de Saúde Pública, Universidade Nova de Lisboa, Lisboa, Portugal
;
6
Department of Biology, School of Computer, Mathematical, and Natural Sciences, Morgan State University, U.S.A.
;
7
Department of Mathematics and Statistics, University of Jyväskylä, Finland
;
8
Gerontology Research Centre and Faculty of Sport and Health Sciences, University of Jyväskylä, Finland
Keyword(s):
Myopia Prediction, Machine Learning, Data Analysis, Monte Carlo Simulations, Lasso Regression.
Abstract:
This study presents the initial results of the Myopia Risk Calculator (MRC) Consortium, introducing an innovative approach to predict myopia risk by using trustworthy machine-learning models. The dataset included approximately 7,945 records (eyes) from 3,989 children. We developed a myopia risk calculator and an accompanying web interface. Central to our research is the challenge of model trustworthiness, specifically evaluating the effectiveness and robustness of AI (Artificial Intelligence)/ML (Machine Learning)/NLP (Natural Language Processing) models. We adopted a robust methodology combining Monte Carlo simulations with cross-validation techniques to assess model performance. Our experiments revealed that an ensemble of classifiers and regression models with Lasso regression techniques provided the best outcomes for predicting myopia risk. Future research aims to enhance model accuracy by integrating image and synthetic data, including advanced Monte Carlo simulations.