iMAGING: a novel automated system for malaria diagnosis by using artificial intelligence tools and a universal low-cost robotized microscope.

Introduction: 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. Methods: 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. Results: 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. Conclusion: 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.

Impact of time of culture specimen collection on the recovery of Neisseria gonorrhoeae after a positive nucleic acid amplification test.

OBJECTIVES: Culture of Neisseria gonorrhoeae remains essential for antimicrobial resistance (AMR) surveillance. We evaluated the effect of time of specimen collection on culture yield following a positive nucleic acid amplification test (NAAT). METHODS: We retrospectively assessed N. gonorrhoeae culture yield among asymptomatic individuals (largely men who have sex with men) who attended for sexual health screening and had a positive NAAT. Participants underwent either same-day testing and notification (Drassanes Exprés) or standard screening with deferred testing. RESULTS: Among 10 423 screened individuals, 809 (7.7%) tested positive for N. gonorrhoeae. A total of 995 different anatomical sites of infection culture was performed in 583 of 995 (58.6%) of anatomical sites (Drassanes Exprés 278 of 347, 80.1%; standard screening 305 of 648, 47.1%; p<0.001). Recovery was highest when culture specimens were collected within 3-7 days of screening with only a slight drop in recovery when the interval extended to 7 days . Recovery from pharynx was 38 of 149 (25.5%) within 3 days, 19 of 81 (23.4%) after 4-7 days (p=0.7245), 11 of 102 (10.7%) after 8-14 days (p<0.0036) and 1 of 22 (4.5%) with longer delays (p=0.00287). Recovery from rectum was 49 of 75 (65.3%) within 3 days, 28 of 45 (62.2%) after 4-7 days (p=0.7318), 41 of 69 (59.4%) after 8-14 days (p=0.4651) and 6 of 18 (33.3%) with longer delays (p=0.0131). Median culture specimen collection time was 1 day within Drassanes Exprés vs 8 days within standard screening. Consequently, the overall culture yield was slightly higher within Drassanes Exprés (102/278, 36.6% vs 99/305, 32.5%; p=0.2934). CONCLUSION: Reducing the interval between screening and collection of culture specimens increased N. gonorrhoeae recovery in extragenital samples. Implementing a same-day testing and notification programme increased collection of culture samples and culture yield in our setting, which may help AMR surveillance.

Unexpected Loa loa Finding in an Asymptomatic Patient From The Gambia: A Case Report.

A 17-year-old asymptomatic male from The Gambia presented for a routine health examination after migration to Spain. Laboratory diagnosis confirmed the presence of Loa loa microfilariae. This unusual finding emphasizes the importance of screening in newly arrived migrants and the need of an extended anamnesis including migratory route and previous travels.

Discordances Between Serology and Culture for Strongyloides in an Ethiopian Adopted Child With Multiple Parasitic Infections: A Case Report.

RATIONALE: infectious diseases screening of international adoptees is complex because of the concurrence of different pathogens in a child at same time. We describe an international adopted child born at Ethiopia infected by 5 different pathogens (Hymenolepis nana, Giardia intestinalis, Entamoeba histolytica, Strongyloides stercoralis, and Trichuris trichiura), 2 of them S. stercoralis and E. histolytica with a capacity to develop severe clinical complications if not detected promptly with appropriate diagnosis tests.Concerns of the patient: according to the screening protocol a stool sample is always processed for culture addressed to find out protozoan and helminthic pathogens but not specifically for S. stercoralis. Only, when eosinophilia is detected 3 serial stool samples are collected to rule out intestinal parasitic infection including S. stercoralis. INTERVENTIONS: in our case, S. stercoralis would not have been detected if we had followed the protocol because eosinophilia was absent and its specific serology was negative. Fortunately, the initial inclusion of the feces charcoal culture for S. stercoralis allowed us to detect this infection. OUTCOMES: discordances between direct methods such as culture and indirect as serology or antigen test forces us to be very cautious before ruling out S. stercoralis or E. histolytica infection, respectively. Also, if a child from tropical areas has persistent symptoms (such as diarrhea or fever) that have not been treated we have to rule out other infections that have not been detected yet.Main lessons: The introduction of different sequencing tests and the insistence to find out pathogens such as S. stercoralis or E. histolytica was determinant to be able to cure this symptomatic child and to prevent potential severe clinical forms in case of immunosuppression.

Prognostic factors and survival in a prospective cohort of patients with high-grade glioma treated with carmustine wafers or temozolomide on an intention-to-treat basis.

BACKGROUND: Patients with high-grade glioma can be treated with carmustine wafers or following the Stupp protocol. As far as we are aware, no scientific evidence has been published comparing the two treatments. The primary objective of this study was to analyse the survival of groups of patients with each of these treatment modalities. The secondary objective was to assess the influence of the usual prognostic factors on the patients in our hospital. METHODS: A prospective cohort of 110 patients with single, supratentorial high-grade glioma treated by craniotomy and tumour resection was retrospectively studied. Half of the patients had carmustine wafers placed during this operation while the others (55) did not, the latter group receiving first-line systemic chemotherapy on an intention-to-treat basis. FINDINGS: Patients treated with carmustine wafers had a median survival of 13.414 months compared with 11.047 in the group without implants (p = 0.856). For the overall cohort of patients, the following factors were found to influence survival: age (p < 0.0001), postoperative KPS score (p = 0.001), histological grade (p = 0.004), RPA class (p = 0.001), extent of resection (p = 0.002) and salvage surgery (p = 0.028). CONCLUSIONS: In this prospective cohort of patients, analysed on the basis of intention-to-treat at the time of the first surgery, no statistically significant differences in survival were found between the two treatment modalities (carmustine wafers vs. first-line systemic chemotherapy). On the other hand, age, preoperative KPS, histological grade, and RPA class were confirmed to be prognostic factors in this cohort. Finally, the extent of resection was also found to influence survival.