Medical Knowledge Base
PearMedica's AI is powered by a curated, peer-reviewed knowledge base specialised for African diseases. This page explains what's in the knowledge base, how it's built, and how it stays current.
Coverage at a Glance
Condition Categories
| Category | Examples | Count |
|---|---|---|
| Vector-Borne | Malaria, Yellow Fever, Dengue, Chikungunya | 8+ |
| Gastrointestinal | Typhoid, Cholera, Amoebic Dysentery | 6+ |
| Respiratory | Tuberculosis, Pneumonia, COVID-19 | 5+ |
| Viral Haemorrhagic | Lassa Fever, Ebola, Marburg | 3+ |
| Bacterial | Meningitis, Tetanus, Brucellosis | 4+ |
| Parasitic | Schistosomiasis, Onchocerciasis, Trypanosomiasis | 4+ |
Regional Coverage
The knowledge base includes location-aware disease prevalence weighting for African regions. When a patient's location is provided, the API adjusts condition probabilities based on regional disease patterns.
West Africa
Nigeria, Ghana, Sierra Leone, Liberia
Focus: Malaria, Lassa Fever, Yellow Fever
East Africa
Kenya, Tanzania, Uganda, Ethiopia
Focus: Malaria, Cholera, TB
Central Africa
DRC, Cameroon, Congo
Focus: Ebola, Trypanosomiasis, Malaria
Southern Africa
South Africa, Mozambique, Zimbabwe
Focus: HIV/TB co-infection, Schistosomiasis
Content Development Process
Every piece of medical content goes through a rigorous 10-step process before reaching production. This process is modelled after peer-reviewed journal standards and clinical guideline development.
Scope Definition
Identify target conditions based on African disease burden data, WHO prevalence reports, and pilot feedback.
Expert Knowledge Elicitation
Medical experts document diagnostic criteria, symptom profiles, risk factors, and regional prevalence patterns.
Peer Review
Content reviewed by independent clinicians for accuracy, completeness, and alignment with current guidelines.
Clinical Case Assembly
Real-world case studies are built to test diagnostic reasoning and edge cases across demographics.
Expert Review
Chief Medical Officer validates all clinical content against WHO, FMOH, and regional guidelines.
Technical Review
Engineering validates data schema, symptom IDs, and integration with the assessment engine.
Regression Testing
Automated test suite runs against all conditions to ensure no accuracy regressions.
Manual Testing
Clinical team manually tests edge cases, atypical presentations, and demographic-specific patterns.
Translation Updates
Symptom aliases and region-specific terminology are updated (e.g., "body dey pain" → generalised aches).
Staged Deployment
A/B tested on 50% of traffic for 7 days, then deployed to production after accuracy metrics are confirmed.
Data Sources
The knowledge base is built from authoritative, publicly available medical sources:
- WHO African Region Guidelines — Malaria, TB, HIV, Cholera, Yellow Fever protocols
- Africa CDC Surveillance Data — Disease outbreak patterns and epidemiological profiles
- PubMed African Disease Studies — 500+ peer-reviewed papers on African diseases
- FMOH/SAHPRA Treatment Protocols — Regional regulatory guidance