Explainable AI modelling of Comorbidity in Pregnant Women and Children with Tropical Febrile Conditions
Bibliographic record
Abstract
Febrile diseases often exhibit overlapping symptoms, posing a challenge for their differential diagnosis. This challenge is particularly critical in pregnant women and children, where early and accurate diagnosis is vital to mitigate the elevated risk of maternal mortality prevalent in tropical and subtropical regions. Despite the commonality of fever as a symptom, the diverse range of potential co-morbidities necessitates an exploration of associated illnesses. This study employs the eXtreme Gradient Boosting (XGBoost) machine learning algorithm to classify febrile diseases' co-morbidities in pregnant women and children under 5 years. The dataset, comprising 1,350 records from selected health facilities across Niger-delta states in Nigeria, contributes to informed decision-making by physicians, ultimately enhancing healthcare provision. Evaluation results demonstrate the classifier's high precision (0.995) and recall (1.00) for the children dataset, while precision and recall of 1.00 are achieved for the pregnant women dataset. To facilitate model explanation and result interpretation, an eXplainable Artificial Intelligence (XAI) approach, specifically the SHapley Additive exPlanations (SHAP) method, is applied. The summary plot highlights upper and lower respiratory tract infections and malaria as the predominant diseases co-morbidities in children. In contrast, pregnant women exhibit upper and lower urinary tract infections, and malaria as the highest-ranking diseases co-morbidity. These results underscore the potential of ML techniques in accurately classifying febrile conditions' co-morbidities, contributing to the reduction of adverse health outcomes. The study's findings offer valuable insights for healthcare providers, enabling them to deliver more targeted and effective care to these vulnerable populations, thereby enhancing overall well-being.
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 | 0.001 | 0.004 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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".