Machine learning for biomarker-driven thalassemia diagnosis: a framework for causal effect estimation
8 affiliations
- 1Department of Computer Science, University College in Umluj, University of Tabuk, Umluj, Saudi Arabia
- 2Faculty of Artificial Intelligence, Department of Machine Learning and Information Retrieval, Kafrelsheikh University, Kafrelsheikh, Egypt
- 3Department of Anatomy, College of Medicine, King Saud University, Riyadh, Saudi Arabia
- 4Department of Pharmacology, Al-Ghad International College for Applied Medical Sciences, Al-Madinah Al-Munawara, Saudi Arabia
- 5Department of Basic Medical Sciences, Al-Rayan National College of Medicine, Al-Rayan National Colleges, Al Madinah Al Munawwarah, Saudi Arabia
- 6Department of Biotechnology, Faculty of Science, King Abdulaziz University, Jeddah, Saudi Arabia
- 7Basic Medical Sciences Department, College of Pharmacy & Applied Medical Sciences, Dar Al Uloom University, Riyadh, Saudi Arabia
- 8Department of Clinical Pharmacy, Al-Rayan National College of Health Sciences, Al-Rayan National Colleges, Al Madinah Al Munawwarah, Saudi Arabi
Abstract
Thalassemia is one of the most heterogeneous diseases, with more than a thousand mutation types recorded worldwide. Molecular diagnosis of thalassemia by conventional PCR-based DNA analysis is time- and resource-consuming owing to the phenotype variability, disease complexity, and molecular diagnostic test limitations. Thalassemia diagnosis relies heavily on complex interactions among hematological biomarkers, making it challenging to distinguish causal relationships from mere statistical correlations. To address this limitation, this study proposes a causal machine learning framework that integrates causal discovery and counterfactual inference to identify biomarker-driven treatment effects for thalassemia diagnosis. The proposed approach models clinical variables using a Directed Acyclic Graph (DAG) to capture underlying causal dependencies and enables robust estimation of treatment effects while accounting for confounding factors. To address the primary objective from complementary causal perspectives, the framework combines adjusted regression for confounding control, inverse probability weighting for propensity-based estimation, Random Forest-based analysis for nonlinear feature importance and heterogeneous treatment effects, and bootstrap resampling for uncertainty quantification. The adjusted linear regression model yielded a conservative causal effect estimate of 0.3008, while propensity-based methods demonstrated stronger effects, with IPW producing an estimate of 1.0604. The bootstrap approach confirmed the stability of these findings with a 95% confidence interval of [0.8806, 1.2161], indicating statistically significant treatment influence. Furthermore, heterogeneous effect analysis using CATE revealed substantial variability across individuals, with estimates ranging between 0.0848 and 2.5200, highlighting the importance of personalized assessment. Stratified analysis across age groups showed distinct differences, with the highest effect observed in adolescents (1.3484) and lower effects in children (0.8856), emphasizing demographic-specific variations. The results demonstrate that key biomarkers, particularly hemoglobin-related features, exert significant causal influence on thalassemia diagnosis.
Related
- PLA2G2A is a candidate biomarker for sepsis diagnosis in mice through machine learning algorithms
- Machine Learning-Based Diagnosis of Coronary Heart Disease with Clinical and Biomarker Data.
- Single-molecule real-time (SMRT) sequencing technology shows advantages in the clinical diagnosis of complex thalassemia
- Parameter Estimation for the Intravoxel Incoherent Motion-diffusional Kurtosis Imaging Model Using Synthetic Q-space Learning Toward Breast Tumor Diagnosis
- Explainable computational framework for subtype classification and biomarker identification in head and neck squamous cell carcinoma using machine learning
BibTeX
@article{elrashidy2026machine,
title = {{Machine learning for biomarker-driven thalassemia diagnosis: a framework for causal effect estimation}},
author = {Nora ElRashidy and M. A. Elsabagh and Esraa Hassan and Ahmed F. El Fouhil and Mohamed Y. Alhussainy and Saad Ali S. Aljohani and Ikhlas A. Sindi and Shaimaa M. Hassan and Nevein M. Abdelhady},
journal = {Frontiers in Medicine},
year = {2026},
month = oct,
doi = {10.3389/fmed.2026.1926776},
url = {https://doi.org/10.3389/fmed.2026.1926776},
note = {CC BY},
}
RIS
TY - JOUR
TI - Machine learning for biomarker-driven thalassemia diagnosis: a framework for causal effect estimation
AU - Nora ElRashidy
AU - M. A. Elsabagh
AU - Esraa Hassan
AU - Ahmed F. El Fouhil
AU - Mohamed Y. Alhussainy
AU - Saad Ali S. Aljohani
AU - Ikhlas A. Sindi
AU - Shaimaa M. Hassan
AU - Nevein M. Abdelhady
PY - 2026
DA - 2026/10/29
JO - Frontiers in Medicine
DO - 10.3389/fmed.2026.1926776
UR - https://doi.org/10.3389/fmed.2026.1926776
AB - Thalassemia is one of the most heterogeneous diseases, with more than a thousand mutation types recorded worldwide. Molecular diagnosis of thalassemia by conventional PCR-based DNA analysis is time- and resource-consuming owing to the phenotype variability, disease complexity, and molecular diagnostic test limitations. Thalassemia diagnosis relies heavily on complex interactions among hematological biomarkers, making it challenging to distinguish causal relationships from mere statistical correlations. To address this limitation, this study proposes a causal machine learning framework that integrates causal discovery and counterfactual inference to identify biomarker-driven treatment effects for thalassemia diagnosis. The proposed approach models clinical variables using a Directed Acyclic Graph (DAG) to capture underlying causal dependencies and enables robust estimation of treatment effects while accounting for confounding factors. To address the primary objective from complementary causal perspectives, the framework combines adjusted regression for confounding control, inverse probability weighting for propensity-based estimation, Random Forest-based analysis for nonlinear feature importance and heterogeneous treatment effects, and bootstrap resampling for uncertainty quantification. The adjusted linear regression model yielded a conservative causal effect estimate of 0.3008, while propensity-based methods demonstrated stronger effects, with IPW producing an estimate of 1.0604. The bootstrap approach confirmed the stability of these findings with a 95% confidence interval of [0.8806, 1.2161], indicating statistically significant treatment influence. Furthermore, heterogeneous effect analysis using CATE revealed substantial variability across individuals, with estimates ranging between 0.0848 and 2.5200, highlighting the importance of personalized assessment. Stratified analysis across age groups showed distinct differences, with the highest effect observed in adolescents (1.3484) and lower effects in children (0.8856), emphasizing demographic-specific variations. The results demonstrate that key biomarkers, particularly hemoglobin-related features, exert significant causal influence on thalassemia diagnosis.
SN - 2296-858X
ER -