BACKGROUND: Accurate diagnosis and timely treatment are crucial in combating malaria.
METHODS: A total of 449 samples were screened for Plasmodium falciparum infection by expert microscopy, qPCR, and three RDTs, namely Rapigen Biocredit Malaria Ag Pf (detecting HRP2 and pLDH on separate bands), Abbott NxTek Eliminate Malaria Ag Pf (detecting HRP2), and SD Bioline Malaria Ag Pf (detecting HRP2). hrp2/3 deletion typing was done by digital PCR.
RESULTS: 45.7% (205/449) individuals tested positive by qPCR for P. falciparum with a mean parasite density of 12.5 parasites/μL. Using qPCR as reference, the sensitivity of microscopy was 28.3% (58/205), the Biocredit RDT was 52.2% (107/205), the NxTek RDT was 49.3% (101/205), and the Bioline RDT was 39.5% (81/205). When only samples with densities > 20 parasites/μL were included (n = 89), sensitivity of 62.9% (56/89) by microscopy, 88.8% (79/89) by Biocredit, 88.8% (79/89) by NxTek, and 78.7% (70/89) by Bioline were obtained. All three RDTs demonstrated specificities > 95%. The limits of detection (95% probability that a sample tested positive) was 4393 parasites/μL (microscopy), 56 parasites/μL (Biocredit, considering either HRP2 or pLDH), 84 parasites/μL (NxTek), and 331 parasites/μL (Bioline). None of the three qPCR-confirmed P. falciparum positive samples, identified solely through the pLDH target, or eight samples negative for all RDTs but qPCR-positive at densities > 20 parasites/µL carried hrp2/3 deletions.
CONCLUSIONS: The Biocredit and NxTek RDTs demonstrated comparable diagnostic efficacies. All three RDTs performed better than microscopy.

Malaria in pregnancy causes adverse consequences and prompt and accurate diagnosis is essential for case management. In malaria endemic countries, diagnosis is mainly based on rapid diagnostic tests (RDT) and microscopy. However, increasing reports of false negatives caused by low parasitemia and pfhrp2/3 deletions raise concerns about HRP2-based RDT usefulness. This study aimed to assess RDT and microscopy performance and to describe pfhrp2/3 deletions in a cohort of 418 pregnant women in Burkina Faso. Malaria was diagnosed using RDT and microscopy and blood samples were collected during antenatal care visits. Diagnostic results were compared to PCR as gold standard. Pfhrp2 and pfhrp3 deletions were characterized for patients with confirmed P. falciparum infection. RDT had better sensitivity (76%) but lower specificity (83%) than microscopy (sensitivity = 57%; specificity = 98%). Low parasitemia (<150 parasites/µL), especially in multigravidae, was the principal factor causing false negatives by both methods. Moreover, pfhrp2 deletion frequency among overall false negatives by RDT was 21.43%. Higher frequency of deletions was found among all samples, independently of RDT result, for example around 2% of samples had double deletions meaning that the majority of deletions had no effect on RDT testing. Finally, it was found higher pfhrp2 deletion in women with lower uterine height during the first trimester. Wider and National surveillance study of deletions is recommended among pregnant women and in Burkina Faso.

Improvements in digital microscopy are critical for the development of a malaria diagnosis method that is accurate at the cellular level and exhibits satisfactory clinical performance. Digital microscopy can be enhanced by improving deep learning algorithms and achieving consistent staining results. In this study, a novel miLab™ device incorporating the solid hydrogel staining method was proposed for consistent blood film preparation, eliminating the use of complex equipment and liquid reagent maintenance. The miLab™ ensures consistent, high-quality, and reproducible blood films across various hematocrits by leveraging deformable staining patches. Embedded-deep-learning-enabled miLab™ was utilized to detect and classify malarial parasites from autofocused images of stained blood cells using an internal optical system. The results of this method were consistent with manual microscopy images. This method not only minimizes human error but also facilitates remote assistance and review by experts through digital image transmission. This method can set a new paradigm for on-site malaria diagnosis. The miLab™ algorithm for malaria detection achieved a total accuracy of 98.86% for infected red blood cell (RBC) classification. Clinical validation performed in Malawi demonstrated an overall percent agreement of 92.21%. Based on these results, miLab™ can become a reliable and efficient tool for decentralized malaria diagnosis.

Prompt diagnosis of malaria infection is critical for effective management, yet it can be challenging due to varying incubation periods and the need for physician-initiated laboratory workups. We present a case of a 40-year-old male with fever and dark-colored urine, initially evaluated for sepsis. Plasmodium vivax was incidentally identified on a peripheral smear review after obtaining a remote travel history from a malaria-endemic area. Consultation with the Centers for Disease Control confirmed the diagnosis, emphasizing the importance of thorough travel history assessment and timely laboratory investigation in suspected cases of malaria. This case underscores the significance of early diagnosis in managing this potentially life-threatening infection.

Malaria is a significant health concern worldwide, particularly in Africa where its prevalence is still alarmingly high. Using artificial intelligence algorithms to diagnose cells with malaria provides great convenience for clinicians. In this paper, a densely connected convolutional dynamic learning network (DCDLN) is proposed for the diagnosis of malaria disease. Specifically, after data processing and partitioning of the dataset, the densely connected block is trained as a feature extractor. To classify the features extracted by the feature extractor, a classifier based on a dynamic learning network is proposed in this paper. Based on experimental results, the proposed DCDLN method demonstrates a diagnostic accuracy rate of 97.23%, surpassing the diagnostic performance than existing advanced methods on an open malaria cell dataset. This accurate diagnostic effect provides convincing evidence for clinicians to make a correct diagnosis. In addition, to validate the superiority and generalization capability of the DCDLN algorithm, we also applied the algorithm to the skin cancer and garbage classification datasets. DCDLN achieved good results on these datasets as well, demonstrating that the DCDLN algorithm possesses superiority and strong generalization performance.

Following a 2-week trip to Kazakhstan, a 42-year-old woman presented at the emergency department in Germany with fever, headache, nausea, and neurological symptoms. An infection with Plasmodium falciparum was rapidly diagnosed. The patient was immediately treated with intravenous artesunate and transferred to an intensive care unit. The initial parasite density was as high as 30% infected erythrocytes with 845,880 parasites/µL. Since Kazakhstan was declared malaria-free in 2012, molecular testing for Plasmodium has been initiated to identify a possible origin. Genotyping of the msp-1 gene and microsatellite markers showed that the parasites are of African origin, with two different alleles indicating a polyclonal infection. After a hospitalization of 10 days, the patient was discharged in good health. Overall, our results emphasize that malaria must be on the list of differential diagnoses for patients with fever of unknown origin, even if they come from countries where malaria does not commonly occur.

UNASSIGNED: Malaria is one of the most prevalent infectious diseases in sub-Saharan Africa, with 247 million cases reported worldwide in 2021 according to the World Health Organization. Optical microscopy remains the gold standard technique for malaria diagnosis, however, it requires expertise, is time-consuming and difficult to reproduce. Therefore, new diagnostic techniques based on digital image analysis using artificial intelligence tools can improve diagnosis and help automate it.
UNASSIGNED: In this study, a dataset of 2571 labeled thick blood smear images were created. YOLOv5x, Faster R-CNN, SSD, and RetinaNet object detection neural networks were trained on the same dataset to evaluate their performance in Plasmodium parasite detection. Attention modules were applied and compared with YOLOv5x results. To automate the entire diagnostic process, a prototype of 3D-printed pieces was designed for the robotization of conventional optical microscopy, capable of auto-focusing the sample and tracking the entire slide.
UNASSIGNED: Comparative analysis yielded a performance for YOLOv5x on a test set of 92.10% precision, 93.50% recall, 92.79% F-score, and 94.40% mAP0.5 for leukocyte, early and mature Plasmodium trophozoites overall detection. F-score values of each category were 99.0% for leukocytes, 88.6% for early trophozoites and 87.3% for mature trophozoites detection. Attention modules performance show non-significant statistical differences when compared to YOLOv5x original trained model. The predictive models were integrated into a smartphone-computer application for the purpose of image-based diagnostics in the laboratory. The system can perform a fully automated diagnosis by the auto-focus and X-Y movements of the robotized microscope, the CNN models trained for digital image analysis, and the smartphone device. The new prototype would determine whether a Giemsa-stained thick blood smear sample is positive/negative for Plasmodium infection and its parasite levels. The whole system was integrated into the iMAGING smartphone application.
UNASSIGNED: The coalescence of the fully-automated system via auto-focus and slide movements and the autonomous detection of Plasmodium parasites in digital images with a smartphone software and AI algorithms confers the prototype the optimal features to join the global effort against malaria, neglected tropical diseases and other infectious diseases.

Due to the difficulty of obtaining blood samples, which is the invasive method that is currently used for the detection of Plasmodium spp., alternative diagnostic sampling methods that are effective and non-invasive are needed, particularly for long-term studies. Saliva and stool samples from malaria-infected individuals contain trace amounts of Plasmodium DNA and therefore could be used as alternatives. Malaria was screened using rapid diagnosis tests and confirmed via microscopy. Nested PCR tests targeting the Plasmodium falciparum-specific STEVOR gene were performed for blood, saliva and stool samples that were positive for malaria. Three hundred sixty-seven (367) children were enrolled and eighty (22.22%) were confirmed to be positive for malaria. Matched blood, saliva and stool samples were available for 35 children. By using blood smears as the gold standard for the diagnosis of malaria, our study indicates that Plasmodium DNA was more detectable in blood (100%) than in saliva (22.86%) and stools (14.29%). Applying qPCR to the STEVOR gene to detect Plasmodium falciparum DNA in saliva and stool samples cannot be considered as an alternative to the current malaria detection processes using blood specimens.

UNASSIGNED: Accurate diagnosis and timely treatment are crucial in combating malaria.
UNASSIGNED: We evaluated the diagnostic performance of three Rapid Diagnostic Tests (RDTs) in diagnosing febrile patients, namely: Abbott NxTek Eliminate Malaria Ag Pf (detecting HRP2), Rapigen Biocredit Malaria Ag Pf (detecting HRP2 and LDH on separate bands), and SD Bioline Malaria Ag Pf (detecting HRP2). Results were compared to qPCR.
UNASSIGNED: Among 449 clinical patients, 45.7% (205/449) tested positive by qPCR for P. falciparum with a mean parasite density of 12.5parasites/μL. The sensitivity of the Biocredit RDT was 52.2% (107/205), NxTek RDT was 49.3% (101/205), and Bioline RDT was 40.5% (83/205). When samples with parasite densities lower than 20 parasites/uL were excluded (n=116), a sensitivity of 88.8% (79/89, NxTek), 89.9% (80/89, Biocredit), and 78.7% (70/89, Bioline) was obtained. All three RDTs demonstrated specificity above 95%. The limits of detection was 84 parasites/μL (NxTek), 56 parasites/μL (Biocredit, considering either HRP2 or LDH), and 331 parasites/μL (Bioline). None of the three qPCR-confirmed P. falciparum positive samples, identified solely through the LDH target, carried hrp2/3 deletions.
UNASSIGNED: The Biocredit and NxTek RDTs demonstrated comparable diagnostic efficacies and both RDTs performed better than Bioline RDT.

Malaria is a significant public health concern, with ∼95% of cases occurring in Africa, but accurate and timely diagnosis is problematic in remote and low-income areas. Here, we developed an artificial intelligence-based object detection system for malaria diagnosis (AIDMAN). In this system, the YOLOv5 model is used to detect cells in a thin blood smear. An attentional aligner model (AAM) is then applied for cellular classification that consists of multi-scale features, a local context aligner, and multi-scale attention. Finally, a convolutional neural network classifier is applied for diagnosis using blood-smear images, reducing interference caused by false positive cells. The results demonstrate that AIDMAN handles interference well, with a diagnostic accuracy of 98.62% for cells and 97% for blood-smear images. The prospective clinical validation accuracy of 98.44% is comparable to that of microscopists. AIDMAN shows clinically acceptable detection of malaria parasites and could aid malaria diagnosis, especially in areas lacking experienced parasitologists and equipment.