Multicenter evaluation of the Toxoplasma gondii Real-TM (Sacace) kit performance for the molecular diagnosis of toxoplasmosis.

The molecular detection of Toxoplasma gondii DNA is a key tool for the diagnosis of disseminated and congenital toxoplasmosis. This multicentric study from the Molecular Biology Pole of the French National Reference Center for toxoplasmosis aimed to evaluate Toxoplasma gondii Real-TM PCR kit (Sacace). The study compared the analytical and clinical performances of this PCR assay with the reference PCRs used in proficient laboratories. PCR efficiencies varied from 90% to 112%; linearity zone extended over four log units (R2 > 0.99) and limit of detection varied from 0.01 to ≤1 Tg/mL depending on the center. Determined on 173 cryopreserved DNAs from a large range of clinical specimens, clinical sensitivity was 100% [106/106; 95 confidence interval (CI): 96.5%-100%] and specificity was 100% (67/67; 95 CI: 94.6%-100%). The study revealed two potential limitations of the Sacace PCR assay: the first was the inconsistency of the internal control (IC) when added to the PCR mixture. This point was not found under routine conditions when the IC was added during the extraction step. The second is a lack of practicality, as the mixture is distributed over several vials, requiring numerous pipetting operations. Overall, this study provides useful information for the molecular diagnosis of toxoplasmosis; the analytical and clinical performances of the Sacace PCR kit were satisfactory, the kit having sensitivity and specificity similar to those of expert center methods and being able to detect low parasite loads, at levels where multiplicative analysis gives inconsistently positive results. Finally, the study recommends multiplicative analysis in particular for amniotic fluids, aqueous humor, and other single specimens.

Automatic patient-level recognition of four Plasmodium species on thin blood smear by a real-time detection transformer (RT-DETR) object detection algorithm: a proof-of-concept and evaluation.

Malaria remains a global health problem, with 247 million cases and 619,000 deaths in 2021. Diagnosis of Plasmodium species is important for administering the appropriate treatment. The gold-standard diagnosis for accurate species identification remains the thin blood smear. Nevertheless, this method is time-consuming and requires highly skilled and trained microscopists. To overcome these issues, new diagnostic tools based on deep learning are emerging. This study aimed to evaluate the performances of a real-time detection transformer (RT-DETR) object detection algorithm to discriminate Plasmodium species on thin blood smear images. The algorithm was trained and validated on a data set consisting in 24,720 images from 475 thin blood smears corresponding to 2,002,597 labels. Performances were calculated with a test data set of 4,508 images from 170 smears corresponding to 358,825 labels coming from six French university hospitals. At the patient level, the RT-DETR algorithm exhibited an overall accuracy of 79.4% (135/170) with a recall of 74% (40/54) and 81.9% (95/116) for negative and positive smears, respectively. Among Plasmodium-positive smears, the global accuracy was 82.7% (91/110) with a recall of 90% (38/42), 81.8% (18/22), and 76.1% (35/46) for P. falciparum, P. malariae, and P. ovale/vivax, respectively. The RT-DETR model achieved a World Health Organization (WHO) competence level 2 for species identification. Besides, the RT-DETR algorithm may be run in real-time on low-cost devices such as a smartphone and could be suitable for deployment in low-resource setting areas lacking microscopy experts.IMPORTANCEMalaria remains a global health problem, with 247 million cases and 619,000 deaths in 2021. Diagnosis of Plasmodium species is important for administering the appropriate treatment. The gold-standard diagnosis for accurate species identification remains the thin blood smear. Nevertheless, this method is time-consuming and requires highly skilled and trained microscopists. To overcome these issues, new diagnostic tools based on deep learning are emerging. This study aimed to evaluate the performances of a real-time detection transformer (RT-DETR) object detection algorithm to discriminate Plasmodium species on thin blood smear images. Performances were calculated with a test data set of 4,508 images from 170 smears coming from six French university hospitals. The RT-DETR model achieved a World Health Organization (WHO) competence level 2 for species identification. Besides, the RT-DETR algorithm may be run in real-time on low-cost devices and could be suitable for deployment in low-resource setting areas.