Semantic Explanation for Malaria Diagnosis: Comparing Human and Machine Generated Annotations for Plasmodium Species and Life-Stage Features
Kamal B. Jillahi, Zainab S. Usman, Charles Nche · 2026
Read Semantic Explanation for Malaria Diagnosis: Comparing Human and Machine Generated Annotations for Plasmodium Species and Life-Stage Features by Kamal B. Jillahi, Zainab S. Usman, Charles Nche (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13278739.txt.
Description
Kamal Jillahi and co-authors test a smart way to label malaria images for AI training. The study appeared in 2026. Sharp labels are slow to make by hand, yet AI tools for malaria checks need them to learn well. Poor labels are a real block in places with few experts.
The team trained the same image model three ways. One used expert hand labels, one used plain AI labels, and one used AI labels cleaned by rules from a health knowledge base. The cleaned labels matched expert labels in quality and beat plain AI labels. The rules tossed out a share of bad labels that broke known facts. Doctors rated the cleaned output as clear and safe.
Catalog record
| CREATOR | Kamal B. Jillahi, Zainab S. Usman, Charles Nche |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 36 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |