aceDiagnostic performance of the miLab MAL AI-driven automated digital microscopy system versus standard microscopy for <i>Plasmodium</i> spp. detection
Microscopic detection of Plasmodium spp. using thin and thick blood smears remains the gold standard for diagnosing malaria, but its performance is highly dependent on stain quality and microscopist expertise. Recently, artificial intelligence (AI)-based technologies have enhanced laboratory performance in malaria diagnosis. This study aimed to evaluate the performance of miLab MAL (Noul, Inc., Republic of Korea), an AI-assisted microscopy system designed to detect Plasmodium species using thin blood smears. Ove…
The AI-assisted microscope detected malaria parasites with 98.7% specificity and 90.4% sensitivity against LAMP and/or thick smear, rising to 97.4% sensitivity against thin smear alone.
The system misidentified some parasite species, failing to correctly name 11 P. falciparum and mistaking two P. ovale and one P. malariae for P. vivax, and it tended to underestimate parasitemia.
The system needs improvement for species differentiation and parasitemia quantification, and it tended to underestimate parasitemia, so its usefulness as a standalone tool is not established.
Evidence
- Peer-reviewedJournal of Clinical Microbiology2026-10-30
How should this claim be treated?
Truvace Impact Record TRV-2026-2320, v1: “Diagnostic performance of the miLab MAL AI-driven automated digital microscopy system versus standard microscopy for <i>Plasmodium</i> spp. detection.” Truvace, 2026-10-31. /record/TRV-2026-2320 (accessed at citation time). sha256 c7d6c97e70646dc4…
Calibration history
Every change to this record since certification, in the open. None yet — the reading has held since it entered the record.
Certified into the record
How to verify without trusting this page
Fetch the canonical text of any version from /api/record/TRV-2026-2320 and hash it yourself — for example shasum -a 256 on the saved canonical field. The result must equal content_hash, and each version’s text ends with prev:followed by the prior version’s hash (version 1 chains to 64 zeros). If a single character of any version had been altered since certification, the chain would not reproduce.