Lubna Pinky

Malaria elimination is shaped by complex interactions among climatic, environmental, socioeconomic, demographic, health-system, and intervention-related factors. However most studies examine only subsets of these drivers, limiting understanding of their combined influence on epidemiological risks. In this study, we integrated 25 years of data from 44 African countries on malaria burden and control, climate, environmental and land-use conditions, socioeconomic and demographic characteristics, and health-system capacity within a unified geospatial, explainable machine-learning, and forecasting framework to characterize spatiotemporal patterns of malaria, quantify the relative contributions of key determinants, and generate 10-year Africa-wide and country-specific forecasts of malaria incidence and mortality rates per 1,000 people at risk. We identified and mapped malaria incidence and mortality hotspots using the Getis-Ord Gi* statistic. Our analyses showed that both incidence and mortality burden remained highly heterogeneous across Africa, with persistent hotspots concentrated in the West and Central Africa. The explainable machine-learning model, that achieved high predictive performance (i.e., XGBoost for incidence, holdout R$^2$ = 0.92; Random Forest for mortality, holdout R$^2$ = 0.91), identified lower availability of hospital beds (per 1,000 people), higher mortality rate attributed to unsafe WASH (per 100,000), and lower percentage (\%) of people using handwashing facilities as the top three most influential determinants of higher risk of infection across Africa whereas higher mortality rate attributed to unsafe WASH (per 100,000), lower \% of people using at least basic sanitation services, and access to electricity (\%) were associated with worse mortality outcomes. Forecasting models also demonstrated strong predictive accuracy (Naive persistence and Elastic Net, holdout R$^2$ = 0.98 for incidence and 0.97 for mortality). Assuming current intervention and structural conditions persist, Africa-wide malaria incidence was projected to remain broadly stable, with a modest upward trend by 2035, whereas mortality was projected to decline initially and subsequently remain relatively unchanged. However, substantial country-level heterogeneity showed both emerging transmission hotspots and persistently high-burden countries. this suggests there is a need for sustained control and accelerated elimination efforts. Overall, this study demonstrates that integrating geospatial analysis, explainable machine learning, and forecasting provides a robust framework for understanding malaria dynamics, identifying the key determinants of burden, anticipating future trends, and supporting geographically targeted malaria control across Africa. Beyond malaria, our analyses can be applied as a generalizable approach for infectious disease surveillance, early-warning systems, hotspot detection, resource prioritization, and precision public health using large-scale longitudinal health data.

Background/Objectives: This review paper summarizes and critically analyzes different Machine Learning (ML) and Artificial Intelligence (AI)-based predictive modeling techniques in early detection and personalized treatment for Kidney diseases, specifically diabetic kidney disease (DKD), chronic kidney disease (CKD), and end-stage renal disease (ESRD). This manuscript focuses on integrating electronic medical record (EMR) data with multi-omics biomarkers to enhance clinical decision-making. Method: A systematic database search retrieved 43 peer-reviewed articles from PubMed, Google Scholar, and ScienceDirect. These works were critically analyzed based on methodological rigor, model interpretability, and translational potential. Review: This paper examined a series of advanced AI and ML models, including but not limited to Random Forests (RF), Extreme Gradient Boosting (XGBoost), deep neural networks, and artificial neural networks, among others. Additionally, this paper explicitly explored validated approaches for fibrosis staging, dialysis prediction, and mortality risk assessment. Conclusions: The paper shows how leveraging AI models for patient-specific biomarker and EMR data presents substantial promise for facilitating preventative interventions, guiding timely nephrology referrals, and optimizing individualized treatment regimens. These state-of-the-art tools will ultimately improve long-term renal outcomes and reduce healthcare burdens. The study further addresses ethical challenges and potential adverse implications associated with the use of AI in clinical settings.

Prostate cancer remains one of the most prevalent malignancies and a leading cause of cancer-related deaths among men worldwide. Despite advances in traditional diagnostic methods such as Prostate-specific antigen testing, digital rectal examination, and multiparametric Magnetic resonance imaging, these approaches remain constrained by modality-specific limitations, suboptimal sensitivity and specificity, and reliance on expert interpretation, which may introduce diagnostic inconsistency. Multimodal deep learning and machine learning fusion, which integrates diverse data sources including imaging, clinical, and molecular information, has emerged as a promising strategy to enhance the accuracy of prostate cancer classification. This review aims to outline the current state-of-the-art deep learning and machine learning based fusion techniques for prostate cancer classification, focusing on their implementation, performance, challenges, and clinical applicability. Following the PRISMA guidelines, a total of 131 studies were identified, of which 27 met the inclusion criteria for studies published between 2021 and 2025. Extracted data included input techniques, deep learning architectures, performance metrics, and validation approaches. The majority of the studies used an early fusion approach with convolutional neural networks to integrate the data. Clinical and imaging data were the most commonly used modalities in the reviewed studies for prostate cancer research. Overall, multimodal deep learning and machine learning-based fusion significantly advances prostate cancer classification and outperform unimodal approaches.

Respiratory viral infections are a leading global cause of disease with multiple viruses detected in 20–30% of cases, and several viruses simultaneously circulating. Some infections with unique viral copathogens result in reduced pathogenicity, while other viral pairings can worsen disease. The mechanisms driving these dichotomous outcomes are likely variable and have only begun to be examined in the laboratory and clinic. To better understand viral–viral coinfections and predict potential mechanisms that result in distinct disease outcomes, we first systematically fit mathematical models to viral load data from ferrets infected with respiratory syncytial virus (RSV), followed by influenza A virus (IAV) after 3 days. The results suggest that IAV reduced the rate of RSV production, while RSV reduced the rate of IAV infected cell clearance. We then explored the realm of possible dynamics for scenarios that had not been examined experimentally, including a different infection order, coinfection timing, interaction mechanisms, and viral pairings. IAV coinfection with rhinovirus (RV) or SARS-CoV-2 (CoV2) was examined by using human viral load data from single infections together with murine weight-loss data from IAV-RV, RV-IAV, and IAV-CoV2 coinfections to guide the interpretation of the model results. Similar to the results with RSV-IAV coinfection, this analysis shows that the increased disease severity observed during murine IAV-RV or IAV-CoV2 coinfection was likely due to the slower clearance of IAV-infected cells by the other viruses. The improved outcome when IAV followed RV, on the other hand, could be replicated when the rate of RV infected cell clearance was reduced by IAV. Simulating viral–viral coinfections in this way provides new insights about how viral–viral interactions can regulate disease severity during coinfection and yields testable hypotheses ripe for experimental evaluation.

We present promor, a comprehensive, user-friendly R package that streamlines label-free quantification proteomics data analysis and building machine learning-based predictive models with top protein candidates. promor is freely available as an open source R package on the Comprehensive R Archive Network (CRAN) (https://CRAN.R-project.org/package=promor) and distributed under the Lesser General Public License (version 2.1 or later). Development version of promor is maintained on GitHub (https://github.com/caranathunge/promor) and additional documentation and tutorials are provided on the package website (https://caranathunge.github.io/promor/). Supplementary data are available at Bioinformatics Advances online.

Human parainfluenza viruses (HPIVs) are a leading cause of acute respiratory infection hospitalization in children, yet little is known about how dose, strain, tissue tropism, and individual heterogeneity affects the processes driving growth and clearance kinetics. Longitudinal measurements are possible by using reporter Sendai viruses, the murine counterpart of HPIV 1, that express luciferase, where the insertion location yields a wild-type (rSeV-luc(M-F*)) or attenuated (rSeV-luc(P-M)) phenotype. Bioluminescence from individual animals suggests that there is a rapid increase in expression followed by a peak, biphasic clearance, and resolution. However, these kinetics vary between individuals and with dose, strain, and whether the infection was initiated in the upper and/or lower respiratory tract. To quantify the differences, we translated the bioluminescence measurements from the nasopharynx, trachea, and lung into viral loads and used a mathematical model together a nonlinear mixed effects approach to define the mechanisms distinguishing each scenario. The results confirmed a higher rate of virus production with the rSeV-luc(M-F*) virus compared to its attenuated counterpart, and suggested that low doses result in disproportionately fewer infected cells. The analyses indicated faster infectivity and infected cell clearance rates in the lung and that higher viral doses, and concomitantly higher infected cell numbers, resulted in more rapid clearance. This parameter was also highly variable amongst individuals, which was particularly evident during infection in the lung. These critical differences provide important insight into distinct HPIV dynamics, and show how bioluminescence data can be combined with quantitative analyses to dissect host-, virus-, and dose-dependent effects.

The novel coronavirus severe acute respiratory syndrome coronavirus 2 (SARS‐CoV‐2) has rapidly spread around the world, causing serious illness and death and creating a heavy burden on the healthcare systems of many countries. Since the virus first emerged in late November 2019, its spread has coincided with peak circulation of several seasonal respiratory viruses, yet some studies have noted limited coinfections between SARS‐CoV‐2 and other viruses. We use a mathematical model of viral coinfection to study SARS‐CoV‐2 coinfections, finding that SARS‐CoV‐2 replication is easily suppressed by many common respiratory viruses. According to our model, this suppression is because SARS‐CoV‐2 has a lower growth rate (1.8/d) than the other viruses examined in this study. The suppression of SARS‐CoV‐2 by other pathogens could have implications for the timing and severity of a second wave.

Many mathematical models of respiratory viral infections do not include regeneration of cells within the respiratory tract, arguing that the infection is resolved before there is significant cellular regeneration. However, recent studies have found that ∼40% of patients hospitalized with influenza-like illness are infected with at least two different viruses, which could potentially lead to longer-lasting infections. In these longer infections, cell regeneration might affect the infection dynamics, in particular, allowing for the possibility of chronic coinfections. Several mathematical models have been used to describe cell regeneration in infection models, though the effect of model choice on the predicted time course of viral coinfections is not clear. We investigate four mathematical models incorporating different mechanisms of cell regeneration during respiratory viral coinfection to determine the effect of cell regeneration on infection dynamics. We perform linear stability analysis for each of the models and find the steady states analytically. The analysis suggests that chronic illness is possible but only with one viral species; chronic coexistence of two different viral species is not possible with the regeneration models considered here.