Related Experiment Video
Updated: Jul 14, 2026
Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
Published on: April 14, 2023
Comparison of machine learning models for mucopolysaccharidosis early diagnosis using UAE medical records
Aamna AlShehhi1,2, Hiba Alblooshi3,4, Ruba Fadul5
1Department of Biomedical Engineering and Biotechnology, Khalifa University, Abu Dhabi, United Arab Emirates. aamna.alshehhi@ku.ac.ae.
Abstract:
Rare diseases, such as Mucopolysaccharidosis (MPS), present significant challenges to the healthcare system. Some of the most critical challenges are the delay and the lack of accurate disease diagnosis. Early diagnosis of MPS is crucial, as it has the potential to significantly improve patients' response to treatment, thereby reducing the risk of complications or death. This study evaluates the performance of different machine learning (ML) models for MPS diagnosis using electronic health records (EHR) from the Abu Dhabi Health Services Company (SEHA). The retrospective cohort comprises 115 registered patients aged ≤ 19 Years old from 2004 to 2022. Using nested cross-validation, we trained different feature selection algorithms in combination with various ML algorithms and evaluated their performance with multiple evaluation metrics. Finally, the best-performing model was further interpreted using feature contributions analysis methods such as Shapley additive explanations (SHAP) and Local Interpretable Model-Agnostic Explanations (LIME). We found that Naive Bayes trained on the domain expert selected features reported a superior performance with an accuracy of 0.93 (0.08), AUC of 0.96 (0.04), F1-score of 0.91 (0.1), and MCC of 0.86 (0.16). SHAP and LIME analysis that were conducted on the best-performing model highlighted key features related to dental manifestations and respiratory infections which are commonly presented in MPS patients, such as acute gingivitis, accretions on teeth, dental caries, acute pharyngitis, acute tonsillitis, and acute bronchitis. This study introduces a cost-effective screening approach for MPS disease using non-invasive EHR, which contributes to the advances in digital screening tools for the early diagnosis of rare diseases.
Insights
Machine learning models can accurately diagnose rare Mucopolysaccharidosis (MPS) using electronic health records. Early MPS diagnosis via these digital tools improves treatment response and patient outcomes.
Area of Science:
- Digital Health
- Medical Informatics
- Rare Disease Diagnosis
Background:
- Rare diseases like Mucopolysaccharidosis (MPS) pose diagnostic challenges, leading to delays and impacting patient outcomes.
- Early diagnosis of MPS is critical for effective treatment and reducing severe complications or mortality.
- Electronic Health Records (EHR) offer a valuable, non-invasive data source for disease screening.
Purpose of the Study:
- To evaluate the diagnostic performance of various machine learning (ML) models for Mucopolysaccharidosis (MPS) using EHR data.
- To identify key clinical features indicative of MPS through ML model interpretation.
- To introduce a cost-effective digital screening tool for early rare disease detection.
Main Methods:
- A retrospective cohort of 115 pediatric MPS patients (≤19 years) from 2004-2022 was analyzed.
- Nested cross-validation was employed to train and evaluate ML models combined with feature selection algorithms.
- Model performance was assessed using metrics like accuracy, AUC, F1-score, and MCC, with interpretation via SHAP and LIME.
Main Results:
- The Naive Bayes model, using domain expert-selected features, achieved superior performance: accuracy 0.93, AUC 0.96, F1-score 0.91, and MCC 0.86.
- SHAP and LIME analyses identified dental issues (gingivitis, caries) and respiratory infections (pharyngitis, tonsillitis, bronchitis) as key diagnostic indicators.
- The study demonstrates the feasibility of using non-invasive EHR data for MPS screening.
Conclusions:
- Machine learning models, particularly Naive Bayes, show high efficacy in diagnosing MPS from EHR data.
- Interpretable AI methods highlight specific clinical manifestations crucial for early MPS detection.
- This research advances digital screening tools for timely diagnosis of rare diseases, improving patient care.
