Febrile disease modeling and diagnosis system for optimizing medical decisions in resource-scarce settings
Bibliographic record
Abstract
Febrile diseases are highly prevalent in tropical regions due to elevated humidity and high temperatures. These regions, mainly comprising low- and middle-income countries, often face challenges related to inadequate medical infrastructure and a lack of skilled personnel for accurately diagnosing febrile diseases. Distinguishing one febrile illness from another posed a significant challenge, adding to the complexity of accurate diagnoses. This study developed a multi-symptom multi-disease model to address this challenge, leveraging exploratory data analysis of patient datasets from field studies and the expertise of medical practitioners specializing in tropical diseases. The research investigated the most effective modeling approach for differentiating among 11 febrile illnesses that are prevalent in Nigeria using three intelligent techniques: Extreme Gradient Boost (XGBoost), Fuzzy Cognitive Map (FCM), and Analytic Hierarchy Process (AHP). Comparative analysis demonstrates that AHP surpassed the others, achieving a precision of 84%, recall of 83%, and an F1-score of 84%. Consequently, the AHP technique was integrated into the development of “Febra Diagnostica,” an app aimed at enhancing febrile disease diagnosis in resource-constrained settings. The app was then deployed and utilized in select Nigerian states, offering scalability and empowering frontline health workers in primary health facilities. Febra Diagnostica featured user-friendly interfaces, automated diagnosis and treatment suggestions, streamlined referrals, and provisions for further investigations. Encryption, access control, and multi-factor authentication were some of the security and privacy considerations in the app which gained acceptance from medical experts and adapted to regulatory and ethical policies for smart healthcare systems.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.010 | 0.033 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".