A Data-Driven Intelligent Methodology for Developing Explainable Diagnostic Model for Febrile Diseases
Bibliographic record
Abstract
Febrile diseases such as typhoid fever, malaria, tuberculosis, and HIV/AIDS present diagnostic challenges in Low- and Middle-Income Countries (LMICs). Misdiagnosis leads to delayed treatment, higher healthcare costs, and increased mortality. This study proposes a data-driven diagnostic framework leveraging explainable artificial intelligence (XAI) and machine learning (ML) to enhance diagnostic accuracy and usability in resource-limited settings. To develop and evaluate a diagnostic system combining ML algorithms and XAI techniques for accurate and interpretable detection of febrile diseases, focusing on usability in clinical settings. A dataset of 3,914 patient records from secondary and tertiary hospitals was used to train and validate predictive models. Random Forest, Extreme Gradient Boost, and Multi-Layer Perceptron algorithms were employed, with hyperparameter tuning for optimization. XAI frameworks, including Large Language Models and Local Interpretable Model-agnostic Explanations, were integrated to enhance interpretability. A mobile-based platform was developed for real-time diagnostic use. The ML models demonstrated high diagnostic accuracy across multiple febrile diseases. Integrating XAI frameworks provided intuitive visualizations and textual explanations, enabling clinicians to understand the reasoning behind predictions better. The mobile-based implementation facilitated real-time decision-making, particularly in resource-constrained environments. The study highlights the potential of combining ML algorithms with explainable AI to improve diagnostic accuracy and usability in LMICs. While the system demonstrated effectiveness, limitations such as excluding pediatric data and certain febrile diseases were noted. Future research will expand the dataset, include additional diseases, and optimize system deployment to enhance adoption. This work establishes a foundation for transparent, AI-driven diagnostic tools in resource-poor settings.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.003 | 0.010 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.003 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".