Canonical text (the exact bytes fingerprinted)

TRUVACE RECORD VERSION
record: TRV-2026-2320
version: 1
kind: certified
reason: Certified into the record
timestamp: 2026-10-31T06:45:30.625353Z
status: published
lens: trace
sector: health
headline: Diagnostic performance of the miLab MAL AI-driven automated digital microscopy system versus standard microscopy for <i>Plasmodium</i> spp. detection
dek: 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…
gain_title: 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.
problem_title: 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.
trace_subject: miLab MAL AI-assisted microscopy for malaria diagnosis
gain_reading: 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.
gain_evidence: miLab MAL showed a sensitivity of 90.4%, a specificity of 98.7%, and a Cohen's kappa of 0.89
problem_reading: 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.
problem_evidence: 11 P. falciparum were not correctly identified at the species level | the miLab MAL tended to underestimate parasitemia
quick_read: Researchers in France prospectively tested an AI-assisted digital microscopy system, miLab MAL, on thin blood smears from patients with suspected malaria or post-treatment follow-up. Over six months, 162 samples were compared against conventional diagnostic methods.

The results suggest such tools could support malaria diagnosis where microscopy expertise is scarce. However, the system's weaker species identification and parasite quantification mean it is not yet a full replacement, and the findings come from a single evaluation.
limitation: 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.
tag: Dual reading
key_points: Conventional methods found 83 positive and 79 negative samples; miLab MAL found 76 positive and 86 negative. | Against thin smear microscopy alone, sensitivity was 97.4%, specificity 97.7%, and kappa 0.95. | Eleven P. falciparum samples were not correctly identified at the species level. | Two P. ovale and one P. malariae were misidentified as P. vivax. | The authors say it could become valuable in resource-limited or high-burden settings after optimization.
rundown: Malaria diagnosis by thin and thick blood smear is the gold standard but depends on stain quality and the expertise of the microscopist. The study tested whether an AI-assisted system from Noul could help with this.

The 162 samples came from patients with suspected malaria or undergoing post-treatment follow-up and were analyzed prospectively over six months. The reference comparison used LAMP and/or thick blood smear, as well as thin smear microscopy alone.

Agreement was strong, with a kappa of 0.89 against the combined reference and 0.95 against thin smear. The authors describe this as the first evaluation of miLab MAL in France.
sources:
- peer_reviewed | Journal of Clinical Microbiology | https://doi.org/10.1128/jcm.00254-26 | 2026-10-30
prev: 0000000000000000000000000000000000000000000000000000000000000000

sha256

c7d6c97e70646dc4134713b69b4bb1fee60eea52d065ae7ca9c3330fa032cb68

previous

0000000000000000000000000000000000000000000000000000000000000000