[This corrects the article DOI: 10.1371/journal.pntd.0014007.].

Urogenital schistosomiasis caused by Schistosoma haematobium remains endemic in sub-Saharan Africa. Diagnosis traditionally relies on urine microscopy to detect parasite eggs; however, its sensitivity declines in low-intensity infections. Artificial intelligence (AI)-assisted image analysis offers a promising approach to automate egg detection and enhance diagnostic accuracy, but its performance compared with standard microscopy is not well established. We conducted a systematic review following the PRISMA guidelines and checklist. Studies evaluating AI-assisted detection of S. haematobium compared with microscopy and/or molecular reference standards, published up to August 2025, were identified through searches in PubMed/MEDLINE, HINARI, Epistemonikos, Science Direct, Google Scholar and grey literature sources. Eligible studies were selected based on pre-defined inclusion and exclusion criteria. The quality of included studies was assessed using the QUADAS-2 tool. Heterogeneity among studies was evaluated using the Cochrane Q test and I² statistic. Data was analyzed using STATA version 14.1 and Review Manager version 5.4.1. Ten studies (15 datasets, 5,564 urine samples) conducted in sub-Saharan Africa met the inclusion criteria. AI-assisted tools demonstrated high diagnostic accuracy. The pooled sensitivity was 88% (95%CI 83%-91%) and pooled specificity was 89% (95% CI 83%-93%). The pooled diagnostic odds ratio was 54.00 (95% CI 30.41-95.88), indicating strong discrimination between infected and uninfected cases. The SROC curve yielded an AUC of 0.94 (95% CI 0.92-0.96), reflecting excellent overall accuracy. Heterogeneity across studies was high (I² = 100%), suggesting results varied by the specific AI platform and study context. AI-assisted microscopic diagnosis of S. haematobium achieved very good in this meta-analysis. These automated tools, whether smartphone-based or bench-top systems, showed promise for detecting infections and could help screen populations in endemic areas. With further validation in field settings and comparison to highly sensitive reference tests, AI diagnostic technology may become a valuable tool to improve case detection and support schistosomiasis control and elimination efforts.

Acute pancreatitis (AP) is an under-recognized but clinically relevant complication of dengue fever (DF), associated with rapid clinical deterioration and increased risk of mortality. However, the true incidence of this condition remains uncertain. Following PRISMA 2020 guidelines, we systematically searched PubMed, Web of Science, Embase and China National Knowledge Infrastructure (CNKI) up to May 2025 for observational studies reporting AP among DF hospitalized patients. Eligible studies were identified according to predefined inclusion and exclusion criteria based on the Population, Intervention, Comparison, Outcome, and Study design (PICOS) framework. Two reviewers independently screened the literature and assessed study quality using the Newcastle-Ottawa Scale (NOS). Pooled incidence rates were estimated using random or common effect models depending on heterogeneity. Eight observational studies from five countries, comprising 1,078 hospitalized patients with DF, were included. Among them, 135 were diagnosed with AP. The pooled incidence of AP complicating DF was 12.4% (95% CI: 10.5-14.4%). Subgroup analysis suggested a higher incidence in studies with ≥100 participants compared to smaller cohorts (13.5% vs. 8.3%, P = 0.03). No evidence of significant publication bias was detected. DF-associated AP represents a clinically important complication, given the global burden of dengue and the potential severity of AP. Our findings underscore the importance of considering pancreatic enzyme testing, supplemented by imaging when clinically warranted, in dengue patients with persistent or severe abdominal symptoms and/or features of severe dengue. Large-scale, multicenter prospective studies are warranted to establish the true incidence and case-fatality risk, thereby informing evidence-based prevention and management strategies.

In Rwanda, about 1 in 3 people are affected by soil-transmitted helminthiases (38.7%) and 1 in 4 by schistosomiasis in high-risk areas (27.2% by point-of-care circulating cathodic antigen), both associated with poor water, sanitation, and hygiene (WASH). Mass drug administration (MDA) is the primary control strategy, but reported coverage may not reflect true reach. This study assessed MDA coverage of albendazole/mebendazole and praziquantel in selected districts, identified reasons for non-reach, examined factors associated with uptake, and described household WASH conditions. A cross-sectional, community-based survey was conducted in five purposively selected districts using a stratified cluster design. Survey-weighted estimates summarized treatment reach (offered the drug), uptake (swallowed the drug), and household WASH conditions. Survey-weighted logistic regression was used to identify individual and implementation factors associated with uptake. Albendazole/mebendazole uptake was 91.9% (95% CI: 84.3-96.0), closely matching reported coverage of 96%. The main reasons for non-reach were drug stockouts (23.7%), absence during MDA (15.8%), and unwillingness to take the drug (15.2%). Praziquantel uptake was 88.0% (95% CI: 78.7-93.6), consistent with reported coverage of 80%. For praziquantel, unwillingness to take tablets (29.6%) and absence during MDA (14.4%) were the most common reasons for non-reach. Receiving sufficient information about MDA to make an informed decision was associated with higher odds of uptake for both ALB/MBZ (adjusted odds ratios [aOR]: 5.17, 95% CI: 2.01-13.27) and PZQ (aOR: 3.58, 95% CI: 1.33-9.64). For ALB/MBZ, finding MDA participation easy (aOR: 11.41, 95% CI: 2.59-50.16), feeling comfortable with the MDA distributor (aOR: 10.05, 95% CI: 2.43-41.47), and feeling comfortable with the MDA location (aOR: 3.23, 95% CI: 1.25-8.39) were each independently associated with higher uptake. For PZQ, males had significantly higher odds of uptake compared to females (aOR: 2.64, 95% CI: 1.15-6.07). Among households, 65.6% used improved drinking water sources, 91.4% obtained water from public places, 50.7% treated their water, 84.4% had improved toilets, 51.6% had visibly clean toilets, and 62% lacked a handwashing station. MDA coverage in Rwanda exceeded WHO targets and closely matched reported estimates, reflecting strong implementation. Addressing remaining gaps in drug supply, MDA communication, and WASH infrastructure will be important to sustain and strengthen control of soil-transmitted helminthiases and schistosomiasis.

Chagas disease affects 6-7 million people worldwide and causes approximately 12,000 deaths annually. Diagnostic methods vary by disease stage, with serological tests commonly used in the chronic phase, while microscopy and molecular techniques like PCR and LAMP are employed in the acute phase. While microscopy remains the most accessible tool in resource constrained settings, its effectiveness depends on skilled personnel, creating diagnostic bottlenecks. To overcome these limitations, we developed a portable, smartphone-integrated AI system for real-time Trypanosoma cruzi detection in microscopy images. The platform combines a 3D-printed microscope adapter which aligns the smartphone camera with the microscope ocular to digitize images, with telemedicine-enabled annotation workflows, and lightweight AI models (SSD-MobileNetV2, YOLOv8) deployed on smartphone for real-time analysis. Trained on a diverse dataset of human samples (478 images from 20 samples), including thick/thin blood smears and cerebrospinal fluid) and murine thin smears (570 images from 33 samples), the SSD-MobileNetV2 model achieved 86% precision, 87% recall, and 86.5% F1-score on human samples, demonstrating robust performance across variable imaging conditions. We additionally piloted a real-world experiment with the proposed system. Three thin blood smears were scanned by a user operating the smartphone-based system, with predictions generated in real time. Model outputs were benchmarked against expert annotations as the ground truth. At the object level, the algorithm achieved a precision of 67.1%, a recall of 96.4%, and an F1-score of 79.1%, showing high sensitivity under operational conditions with a configuration possibly suitable for screening. This system could enable rapid, accurate parasite detection in field settings without advanced infrastructure, addressing critical gaps in early diagnosis and monitoring. Its modular design allows adaptation to other pathogens and cellular structures, offering a scalable solution for neglected tropical disease diagnostics. By bridging AI innovation with microscopy, this approach holds promise for advancing equitable healthcare delivery in endemic regions and aligning with global health priorities.

Recurring outbreaks of leptospirosis in flood-prone areas caused by heavy rainfall pose a major public health concern, particularly in megacities such as Jakarta, Indonesia. From December 2019 through February 2020, Jakarta experienced a large leptospirosis outbreak due to extensive flooding following extreme monsoonal rainfall. We conducted a comprehensive retrospective analysis of the outbreak based on complete surveillance data from all five districts and 42 of 44 subdistricts in Jakarta. A total of 282 cases (97 suspected, 153 probable, and 32 confirmed) were reported in West (n = 162), South (n = 64), East (n = 30), North (n = 14) and Central (n = 12) Jakarta. Cases were predominantly adult males exposed to floodwaters. Of 241 cases tested, 164 (68.0%) had a positive IgM-based rapid diagnostic test (RDT). Of 118 cases tested with TaqMan RT-PCR targeting lipL32, 32 (27.1%) were positive. Of 95 cases tested with both assays, the combined detection rate was 74.7% (71/95); of whom 27 were positive by both RDT and RT-PCR. RT-PCR identified 5 additional RDT-negative cases, all of whom had fever <7 days. We sequenced 42 archived blood samples using Multi Locus Sequence Typing (MLST) and identified Leptospira interrogans and L. borgpeterseni as the predominant species. The findings emphasise the importance of rapid and early laboratory-based diagnosis during leptospirosis outbreaks in flood-prone urban areas, to better target public health interventions. Climate-resilient urban planning is critical for vulnerable megacities in low-resource settings, where complex environmental and infrastructural challenges are compounded by the effects of a changing climate.

Modern knowledge regarding 'healthy bacterial carriers' traces back to the legacy of Typhoid Mary, who unknowingly infected >50 people with enteric fever. Yet, the intricacies of typhoidal Salmonella carriage, inclusive of Salmonella Typhi and Paratyphi A/B, remain largely unknown. Using data collected by the United Kingdom Health Security Agency's Salmonella reference laboratory and enhanced surveillance, we examined cases of enteric fever in England and Wales between 2004-2023, to track disease trends and identify carriers. In total, 8,297 cases of enteric fever were reported during the study period, including concerning rises post-pandemic that are not linked to emerging bacterial strains. 92% of cases reported travel, mainly to South Asia and disease was most prevalent in more deprived communities. Around 2.7% of cases failed to clear after three weeks, constituting carriage, but only 0.1% persisted over a year. Odds of carriage were significantly increased in patients aged 81-90 (447%, p < 0.001) and in non-travel associated cases(64%, p = 0.025) while odds were significantly decreased in patients aged 21-30 (35%, p = 0.046) and in S. Paratyphi A infections (35%, p = 0.01). Isolates linked to carriage failed to cluster under specific lineages or genotypic clades, aside from a small S. Paratyphi B population potentially circulating locally in England. This study highlights increased prevalence of acute enteric fever infection in more deprived communities, and elevated risk of TS carriage in elderly patients and those without recent foreign travel. Our findings suggest host immune function likely plays a greater role in carriage risk than bacterial genotype. Given the lack of genetic signature for carriage, future research must focus on host factors influencing persistence and repeat sampling post-antibiotic treatment should be implemented to identify 'modern day Typhoid Marys' and reduce disease transmission.

Melioidosis is a clinical disease in humans and animals following infection with the soil and water bacterium Burkholderia pseudomallei. The global footprint of melioidosis has been rapidly expanding, but it remains unclear how much this represents unmasking of longstanding but previously unrecognised presence of B. pseudomallei and how much is from recent dispersal of B. pseudomallei. What is now clear is that the predicted establishment of B. pseudomallei in the southern United States has eventuated, with melioidosis endemic in Mississippi and likely to be endemic in Georgia and Texas. It is now time to move beyond concern of B. pseudomallei as a biothreat agent and to pivot towards addressing the gaps in public health responses to the enigmatic disease that it causes.

Early prediction of dengue shock syndrome (DSS) is crucial for effective patient triage and management. However, the lack of consensus regarding the precise definition of the laboratory warning sign (WS) -"an increase in hematocrit concurrent with a rapid decrease in platelet count"- has made it difficult to utilize this WS for predicting DSS. A matched case - control study was conducted among adult dengue patients (aged ≥16 years) hospitalized within the first four days of illness between November 2022 and August 2023, with each DSS case was matched with three non-DSS ones. There were 448 patients (112 DSS and 336 non-DSS) included in this study. An increase in hematocrit concurrent with a rapid decrease in platelet count was observed 1-2 days prior to the development of DSS. The cut-off value of an increase in hematocrit by ≥5% concurrent with a decrease in platelet count by ≥50% as compared with those of the previous day was found to be a predictor of DSS, with a sensitivity of 60.71% and a specificity of 83.04%. A DSS scoring system developed using these two cut-off values, along with the number of clinical WSs, can be used to predict the risk of DSS in adult patients. It achieved an area under the receiver operating characteristic curve (AUC) of 0.93 (95% CI: 0.90-0.96), sensitivity of 86.6%, and specificity of 87.8%. The Score enables triage of patients into low-, intermediate-, and high-risk groups for appropriate monitoring and management. The WS "an increase in hematocrit concurrent with a rapid decrease in platelet count" can be defined as "an increase in hematocrit ≥5% concurrent with a decrease in platelet count ≥50% compared to the previous day". The DSS score, developed from traditional WSs, serves as a good predictor of DSS in adult patients.

Anthropogenic factors have contributed to the expansion of the dengue vector Aedes aegypti into previously non-endemic regions. In East Africa, rising dengue cases highlight gaps in understanding the role of Ae. aegypti . Here, we present a molecular characterization of Ae. aegypti in Somaliland following a dengue outbreak. Adult Aedes mosquitoes were collected from Hargeisa, Berbera and Burao. PCR and sequencing were applied to determine species, identify vgsc resistance mutations, and analyze bloodmeal sources. WHO bioassays were also conducted to determine the status of pyrethroid insecticide resistance. Multiple COI haplotypes were identified, with Hargeisa exhibiting the highest diversity. Pyrethroid resistance mutations S989P, V1016G, and F1534C were detected at all locations, with the highest frequency observed in Burao. While no association was observed between allele frequencies and insecticide resistance, resistance was associated with total heterozygous genotypes. The detection of S989P/V1016G mutation combinations, observed mostly in Asia underscores the need for investigations into the origin of uncommon Ae. aegypti lineages into East Africa. Overall, this study reveals the varying utility of molecular markers for species identification and tracking phylogeographic shifts in the distribution of Ae. aegypti lineages. This highlights the need for improved vector control strategies and strengthen surveillance in Somaliland.