Accurate malaria diagnosis with precise identification of Plasmodium species is crucial for an effective treatment. While microscopy is still the gold standard in malaria diagnosis, it relies heavily on trained personnel. Artificial intelligence (AI) advances, particularly convolutional neural networks (CNNs), have significantly improved diagnostic capabilities and accuracy by enabling the automated analysis of medical images. Previous models efficiently detected malaria parasites in red blood cells but had difficulty differentiating between species. We propose a CNN-based model for classifying cells infected by P. falciparum, P. vivax, and uninfected white blood cells from thick blood smears. Our best-performing model utilizes a seven-channel input and correctly predicted 12,876 out of 12,954 cases. We also generated a cross-validation confusion matrix that showed the results of five iterations, achieving 63,654 out of 64,126 true predictions. The model’s accuracy reached 99.51%, a precision of 99.26%, a recall of 99.26%, a specificity of 99.63%, an F1 score of 99.26%, and a loss of 2.3%. We are now developing a system based on real-world quality images to create a comprehensive detection tool for remote regions where trained microscopists are unavailable.

Objetivo Describir y analizar la actividad científica sobre la COVID-19 en Latinoamérica.Materiales y Métodos Mediante una revisión sistemática de la literatura en PubMed, LILACS y los repositorios preimpresos BioRxiv y medRxiv, se recuperaron todos los documentos disponibles sobre la COVID-19 en Latinoamérica desde el primero de enero hasta el 24 de abril de 2020, para su análisis bibliométrico.Resultados Un total de 29 publicaciones fueron incluidas en el análisis. El país con más producción científica fue Brasil (10/29; 34,4%), seguido de Colombia (6/29; 20,6%) y México (6/29; 20,6%). La universidad con más artículos fue la Universidad Tecnológica de Pereira, Colombia (5/29; 17,24%). El 41,3% de las publicaciones fueron documentos preimpresos. La mayoría de los estudios excluidos fueron comentarios editoriales u opiniones de expertos. Tres de cada cuatro investigaciones tenían un enfoque epidemiológico (21/29; 72,4%); limitados estudios sobre el diagnóstico (5/29; 17,2%), la fisiopatogenia (2/29; 2,8%) y los aspectos terapéuticos (1/29; 3,4%) fueron encontrados.Conclusión Pese al crecimiento exponencial de publicaciones en el mundo, existe una limitada cantidad de información sobre el comportamiento de esta infección en Latinoamérica. Se requiere la publicación de estudios con alta calidad metodológica, que aporten conocimiento sobre el impacto de la pandemia en la región.

Background: Malaria remains a leading public health problem worldwide. Co-infections with other pathogens complicate its diagnosis and may modify the disease’s clinical course and management. Similarities in malaria clinical presentation with other infections and overlapping endemicity result in underdiagnosis of co-infections and increased mortality. Thus, the aim of this study was to determine the seroprevalence of viral and bacterial pathogens among diagnosed malaria patients in malaria-endemic areas in Venezuela. Methods: A cross-sectional study was conducted on malaria patients attending three reference medical centres in Ciudad Bolivar, Venezuela. Clinical evaluation and laboratory tests for dengue virus (DENV), chikungunya virus (CHIKV), viral hepatitis [hepatitis A virus (HAV), hepatitis B virus (HBV), and hepatitis C virus (HCV)], and leptospirosis (LEP) were performed by enzyme-linked immunosorbent assays. Previous exposure to these pathogens was defined by the presence of specific immunoglobulin (Ig) G, and co-infection or recent exposure (CoRE) was determined by the presence of specific IgM alone or IgM + IgG. Data analysis considered descriptive statistics. Parameter distribution was statistically evaluated using Kolmogorov–Smirnov test and the necessary comparison tests. Odds ratio (OR) for complications was determined according to CoRE presence with a 95% confidence interval (CI). Results: A total of 161 malaria patients were studied, 66% infected with Plasmodium vivax, 27% with P. falciparum, and 7.5% harboured P. vivax/P. falciparum mixed infection. Previous exposure to DENV (60%) and CHIKV (25%) was frequent. CoRE was confirmed in 55 of the 161 malaria patients (34%) and were more frequent in P. falciparum (49%) than in P. vivax (29%) and mixed malaria patients (25%) (OR = 2.43, 95% CI: 1.39–4.25, P = 0.018). The most frequent CoRE was DENV (15%), followed by HAV (12%), HBV (6.2%), CHIKV (5.5%), and LEP (3.7%); HCV CoRE was absent. Complicated malaria was significantly more frequent in patients with CoRE (56%) than those without CoRE (36%; OR = 2.31, 95% CI: 1.18–4.92, P = 0.013). Conclusions: We found high CoRE prevalence in malaria patients as determined by serology in the study region; cases were associated with a worse clinical outcome. Further prospective studies with samples from different infection sites and the use of molecular tools are needed to determine the clinical significance of these findings. Graphical

Background: Malaria‐endemic areas are not spared from the impact of coronavirus disease 2019 (COVID-19), leading to co-infection scenarios where overlapping symptoms impose serious diagnostic challenges. Current knowledge on Plasmodium spp. and severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) co‐infection in pregnant women remains limited, especially in Latin America, where Plasmodium vivax infection is highly prevalent. Methods: This is a case series of five pregnant women with P. vivax and SARS-CoV-2 co-infection hospitalized in two main malaria referral centers of the Capital District and Bolivar state, Venezuela between March 13, 2020 and December 31, 2021. Results: Clinical and laboratory data from five pregnant women with a mean age of 22 years were analyzed; three of them were in the third trimester of pregnancy. Comorbidities included obesity in two cases, hypertension in one, and asthma in one. Three out of five patients had severe to critical COVID-19 disease. Dry cough, fever, chills, and headache were the most frequent symptoms reported. Laboratory analyses showed elevated aspartate/alanine aminotransferase and creatinine levels, thrombocytopenia, and severe anemia as the most relevant abnormalities. The mean period between symptom onset and a positive molecular test for SARS-CoV-2 infection or positive microscopy for Plasmodium spp. was 4.8 ± 2.5 days and 2.8 ± 1.6 days, respectively. The mean hospital stay was 5.4 ± 7 days. Three women recovered and were discharged from the hospital. Two women died, one from cerebral malaria and one from respiratory failure. Three adverse fetal outcomes were registered, two miscarriages and one stillbirth. Conclusion: This study documented a predominance of severe/critical COVID-19 disease and a high proportion of adverse maternal–fetal outcomes among pregnant women with malaria and COVID-19 co-infection. More comprehensive prospective cohort studies are warranted to explore the risk factors, management challenges, and clinical outcomes of pregnant women with this co-infection.

We have here assessed the impact of demographic, clinical, and treatment compliance characteristics on health-related quality of life (HRQoL) of Venezuelan patients with systemic lupus erythematosus (SLE). We have used a disease-specific questionnaire, the Lupus Quality of Life (LupusQoL), validated in our patient population, to measure HRQoL. A cross-sectional study was conducted among 100 patients with SLE from outpatient clinics. Patients completed a form with demographic, clinical, and treatment compliance data, and the LupusQoL questionnaire. HRQoL was classified as better or worse according to previously established cut-off points for this patient population. Spearman’s r test was used to determine the correlations between age, years of education, disease duration, SLEDAI, and SLICC-DI with the eight domains of the LupusQoL. Mann–Whitney U test was used to compare the HRQoL between the two groups of patients according to treatment compliance. Binomial logistic regression using the backward stepwise selection method was performed to identify the risk factors associated with each of the eight domains of the LupusQoL among patients with inactive (SLEDAI < 4) and active (SLEDAI ≥ 4) SLE. HRQoL of our patients was classified as better in all domains of the LupusQoL. Age correlated negatively with all domains of the LupusQoL, except with “burden to others”, and disease activity correlated negatively with all domains of the LupusQoL, except with “intimate relationships” and “burden to others” (p < 0.05). Patients who fully complied with indicated treatment had higher scores in “physical health” domain compared to patients who did not comply with at least one of the prescribed medications (p < 0.05). In patients with active SLE, a risk factor associated with worse “planning” and “intimate relationships” was advanced age, while having had SLE flare-ups in the previous six months was a risk factor associated with worse “physical health” (p < 0.05). Age and disease activity were negatively correlated with almost all domains of the LupusQoL, and treatment compliance was associated with higher score in the “physical health” domain. Disease control and treatment compliance should be the main goals for a better HRQoL in our patients with SLE.