Machine learning approach to identify malaria risk in travelers using real-world evidence.

Background: Pre-travel consultation and chemoprophylaxis measures for malaria are a key component in the prevention of imported malaria in travelers. In this study we report a predictive tool for assessing personalized malaria risk in travelers based on the analysis of electronic medical records from travel consultations. The tool aims to guide physicians in the recommendation of appropriate prophylaxis prior to their trip. We also provide best-practice recommendations for pre-processing noisy and highly sparse real world evidence data. Methods: We leveraged a large EMR dataset, containing demographic information about travelers and their destination. The data has been previously preprocessed using various strategies to handle missing and unbalanced data. We compared multiple machine learning approaches to assess the risk of malaria acquisition in travelers during their travels. Additionally, a feature importance analysis was performed using SHAP (SHapley Additive Explanations) values to identify patterns associated with malaria risk. Results: Our study revealed that our XGB models achieved high predictive capacity (AUC >0.80). The most significant features predicting malaria infection during travel included travel destinations with low malaria risk, vaccination history, number of countries visited, age, and trip duration. Remarkably, we were able to obtain a reduced model with only five features. When comparing this model with a population of travelers recommended for malaria chemoprophylaxis, we observed that it was deemed necessary in only 40% of these travelers. This suggests that 60% received chemoprophylaxis despite having a low personalized risk of malaria. Conclusion: We have developed an algorithmic tool that utilizes a concise survey to generate a personalized travel risk assessment, effectively minimizing the prescription of unnecessary malaria chemoprophylaxis. Through the identification of patterns linked to predictions, our model significantly enhances the efficacy of pre-travel consultations.

Mapping the global distribution of Strongyloides stercoralis and hookworms by ecological niche modeling.

BACKGROUND: The WHO has established a control strategy for Strongyloides stercoralis in school-aged children as well as targets and to maintain control programs for Ascaris lumbricoides, Trichuris trichiura and hookworms. For an efficient development of control programs, it is necessary to know the target countries around the world, as well as the areas within each country where efforts should be focused. Therefore, maps that provide information on the areas at risk for soil-transmitted helminth (STH) infections on a national and sub-national scale would allow for a better allocation of resources. METHODS: We used the ecological niche models MaxEnt and Kuenm R library to estimate the global distribution of S. stercoralis and hookworms. We used occurrence points of both species extracted from surveys of two literature reviews and from the Global Atlas of Helminth Infection database, together with 14 raster maps of environmental variables. RESULTS: We obtained two raster maps with the presence probability of S. stercoralis and hookworm infections at a global level and then estimated the global population at risk to be 2.6 and 3.4 billion, respectively. The population at risk was also estimated at the country level using estimations for areas as small as 25 km2. A relationship was found between the probability of the presence of S. stercoralis and its prevalence, and a raster map was generated. Annual precipitation, annual temperature, soil carbon content and land cover were the main associated environmental variables. The ecological niches of Strongyloides stercoralis and hookworms had an overlap of 68%. CONCLUSIONS: Here we provide information that can be used for developing more efficient and integrated control strategies for S. stercoralis and hookworm infections. This information can be annexed to the study of other risk factors or even other diseases to assess the health status of a community. GRAPHICAL ABSTARCT.

Safety and Efficacy of a MEURI Program for the Use of High Dose Ivermectin in COVID-19 Patients.

Background: In the absence of antiviral alternatives, interventions under research for COVID-19 might be offered following guidelines from WHO for monitored emergency use of unregistered and experimental interventions (MEURI). Ivermectin is among several drugs explored for its role against SARS-CoV-2, with a well-known safety profile but conflicting data regarding clinical utility for COVID-19. The aim of this report is to inform on the results of a MEURI Program of high-dose ivermectin in COVID-19 carried out by the Ministry of Health of the Province of La Pampa, Argentina. Methods: COVID-19 subjects, within 5 days of symptoms onset were invited to participate in the program, which consisted in the administration of ivermectin 0.6 mg/kg/day for 5 days plus standard of care. Active pharmacosurveillance was performed for 21 days, and hepatic laboratory assessments were performed in a subset of patients. Frequency of Intensive Care Unit (ICU) admission and COVID-19-related mortality of subjects in the ivermectin intention to treat group were compared with that observed in inhabitants of the same province during the same period not participating in the program. Results: From 21,232 subjects with COVID-19, 3,266 were offered and agreed to participate in the ivermectin program and 17,966 did not and were considered as controls. A total of 567 participants reported 819 adverse events (AEs); 3.13% discontinued ivermectin due to adverse events. ICU admission was significantly lower in the ivermectin group compared to controls among participants ≥40 year-old (1.2 vs. 2.0%, odds ratio 0.608; p = 0.024). Similarly, mortality was lower in the ivermectin group in the full group analysis (1.5 vs. 2.1%, odds ratio 0.720; p = 0.029), as well as in subjects ≥ 40 year- old (2.7 vs. 4.1%, odds ratio 0.655; p = 0.005). Conclusions: This report highlights the safety and possible efficacy of high dose ivermectin as a potentially useful intervention deserving public health-based consideration for COVID-19 patients.

Performance evaluation of Baermann techniques: The quest for developing a microscopy reference standard for the diagnosis of Strongyloides stercoralis.

BACKGROUND: Soil-transmitted helminths (STH) are common in low and middle income countries where there is lack of access to clean water and sanitation. Effective diagnosis and treatment are essential for the control of STH infections. However, among STH parasites, Strongyloides stercoralis is the most neglected species, both in diagnostics and control strategies. Diagnostic methods cover different approaches, each with different sensitivities and specificities, such as serology, molecular techniques and microscopy based techniques. Of the later, the Baermann technique is the most commonly used procedure. In the literature, several ways have been described to perform the Baermann method, which illustrates the overall lack of a '(gold) reference standard' method for the diagnosis of S. stercoralis infection. In this study we have evaluated the performance of three Baermann techniques in order to improve the reference standard for the microscopic diagnosis of S. stercoralis infection thereby facilitating individual case detection, mapping of the disease and proper evaluation of treatment responses. METHODS/PRINCIPAL FINDINGS: A community based cross sectional study was conducted at Zenzelima, Bahir Dar Zuria Ethiopia. A total of 437 stool samples were collected and analyzed by the following procedures: conventional Baermann (CB), modified Baermann (MB), and modified Baermann with charcoal pre-incubation (MBCI). The diagnostic sensitivity and Negative Predictive Value (NPV) of each technique was calculated using the combination of all the three techniques as a composite reference standard. Our result indicated that larvae of S. stercoralis were detected in 151 (34.6%) stool samples. The prevalence of S. stercoralis infection based on the three diagnostic methods was 9.6%, 8.0%, and 31.3% by CB, MB, and MBCI respectively. The sensitivity and NPV for CB, MB, and MBCI were 26.7% and 70.8%, 22.1% and 69.6%, and 87.0% and 93.2%, respectively. The MBCI showed significant difference (P- value = <0.001) in the sensitivity and NPV values when compared with CB and MB values. The agreement between CB, MB, and MBCI with the composite reference standard was 31.8%, 26.7%, 89.6%, respectively. CONCLUSION/SIGNIFICANCE: Our results suggest the superior performance of MBCI. It is relatively easy to implement, simple to perform and comparatively cheaper. The CB is by far the commonly used method in routine diagnostic although this technique significantly underestimates the true burden of the disease and thereby contributing to the exclusion of S. stercoralis from the control strategies. Therefore, MBCI is recommended as a routine microscopy-based diagnostic test for S. stercoralis infection, particularly in settings where molecular procedures are not available.

Molecular Identification of Leishmania spp. DNA from Archived Giemsa-Stained Slides of Patients from Salta, Argentina.

Cutaneous leishmaniasis is endemic in Salta province, which belongs to the northwest of Argentina. Leishmania spp. DNA from Giemsa-stained slides of up to 12 years in storage of patients from Salta was characterized through polymerase chain reaction (PCR) restriction fragment length polymorphism (RFLP). One hundred smears positive for microscopy, classified in a semiquantitative scale for amastigote density, were analyzed. Also, Leishmanin skin test (LST) results were included. DNA extraction was carried out applying lysis buffer with proteinase K, and then DNA was amplified with ribosomal internal transcribed spacer 1 primers. PCR products were digested with HaeIII enzyme. All PCR-positive smears (74/100) belonged to Viannia subgenus. A statistically significant, directly proportional relationship between semiquantitative microscopy and PCR results was detected. All patients had LST-positive results (induration ≥ 5 mm), and the smears of those with smaller induration (LST < 19 mm) gave a higher proportion of positive PCR results. This study determined that smear age did not affect PCR positivity, which allows retrospective analyzes and suggests smears might be useful for molecular complementary diagnosis. Because Leishmania (Viannia) braziliensis is the main circulating species in the study area, determining Viannia subgenus in all analyzed samples confirms previous findings. PCR positivity showed statistically significant differences according to semiquantitative microscopy, highlighting the importance of parasite burden in the diagnostic sensitivity of the method. Considering that smears of patients with smaller LST induration were more positive in PCR, a negative smear from patients with positive LST response, but < 19 mm, could actually represent a false-negative result.