Public Health & Policy

Gradient boosting for extremes: sampling theory and application to insurance

We develop a statistical learning theory for gradient boosting applied to the estimation of covariate-dependent Generalized Pareto (GP) distributions in the context of Peaks-over-Threshold modeling. After an orthogonal reparametrization of the GP likelihood that diagonalizes its Fisher information matrix, we cast the estimation problem within the Empirical Risk Minimization (ERM) framework and der...

Heterogeneity of Treatment Effect of Aspirin and Clinically Significant Bleeding in Older Adults

Aim: The global population of older adults is growing, and older age is linked to higher bleeding risk. Although guidelines discourage aspirin for primary prevention in healthy older adults due to bleeding harms outweighing benefits, many continue taking it without a clear indication. It remains unclear whether all older adults face uniform aspirin-related bleeding risk or if certain subgroups are...

Augmentation techniques for video surveillance in the visible and thermal spectral range

In intelligent video surveillance, cameras record image sequences during day and night. Commonly, this demands different sensors. To achieve a better ...

Revisiting Vehicle Color Recognition in Long-Tailed Surveillance Scenarios

Vehicle color recognition is an important cue for vehicle identification in surveillance systems, especially when license plates are illegible due to ...

A Decade of the Center for Disease Control and Prevention's FluSight Influenza Forecasting

Since the U.S. 2013/14 influenza season, the CDC's FluSight Challenge has provided a platform for evaluating influenza forecasting models and fosterin...

Synthetic but Not Realistic: The Evaluation Challenge in Generative Modelling for Structured Electronic Medical Records

Synthetic healthcare data are widely proposed as privacy-preserving substitutes for real patient data, yet their evaluation remains dominated by stati...

NutriMLLM: Multimodal Large Language Models for Dietary Micronutrient Analysis

Comprehensive estimation of dietary micronutrients from food images could improve clinical nutrition care, but training such models requires large mul...

Routine laboratory trajectories encode the onset of organ-level complications in cancer

Routine laboratory panels drawn during cancer treatment constitute longitudinal physiological recordings of organ function, yet their temporal structu...

Real-Time Threat Detection from Surveillance Cameras using Machine Learning

Ensuring public safety in densely populated urban environments remains a critical challenge, necessitating the deployment of intelligent and automated...

Hybrid CNN-LSTM Framework for Intelligent Cyber Attack Detection and Prevention in U.S. Critical Digital Infrastructure: A Comparative Machine Learning Evaluation on CSE-CIC-IDS2018

Digital infrastructure is growing at a rapid pace in the United States, and as a result, exposure to advanced cyber threats to critical sectors includ...

KESOZI Digital Twin: Physics-Informed Neural Network for Independent Estimation and Prediction of Childhood Diarrheal Disease Burden in Kenya, Somaliland, and Zimbabwe

Childhood diarrheal disease remains a leading cause of morbidity and mortality among children under five years in sub-Saharan Africa, particularly in ...

Simple cumulative weighting of routine surveillance data identifies epidemic wave origins more accurately than a large language model: evidence from eight COVID-19 waves in Japan

Identifying the origin of an emerging epidemic wave within days of onset could enable targeted response before national spread, yet current methods re...

Comfort with AI for HIV Prevention Among Cisgender Women in New York City

Background: Long-acting pre-exposure prophylaxis (PrEP) expands HIV prevention options for women. However, PrEP impact depends on addressing persisten...

The AFRIDIARRHEA multimodal fusion framework for Estimating the Burden of Diarrheal Diseases Among Children Under Five in Kenya, Zimbabwe, and Somaliland

Background: Accurate estimation of childhood diarrheal disease burden in Africa remains challenging because of limited surveillance, incomplete mortal...

SchistoTrackNet: machine learning for diagnosis of schistosomiasis-associated periportal fibrosis from ultrasound images

Liver fibrosis is a major cause of death in low- and middle-income country contexts. In rural, poor areas of sub-Saharan Africa, schistosomiasis is an...

Stigmatizing Language Detection in Opioid Use Disorder Patient-Directed Discharge Clinical Documentation: A Privacy-Preserving Analysis Using a Locally Deployed Large Language Model

Objective: Stigmatizing language in the electronic health record (EHR) has been associated with adverse patient experience in substance use disorder c...

Sensitive Glioma Detection and Recurrence Monitoring Using a Machine Learning Model Based on Circulating Monocytes

Background: Non-invasive diagnosis, reliable recurrence surveillance remain critical unmet needs in gliomas. Glioma induces profound systemic immune a...

Development and Validation of a Machine Learning Model to Predict Prognosis in Patients with Advanced Head and Neck Cancer

Importance Prognostic tools beyond staging are needed to guide treatment and counseling in head and neck squamous cell carcinoma (HNSCC). Objective To...

AI Adoption for NCDs in Kenya: A Qualitative Study

Background: Non-communicable diseases (NCDs) represent a critical public health challenge in Kenya, responsible for over 50% of inpatient admissions a...

Future Pandemics: AI-Designed Diagnostic Assays for Detection of Andes Orthohantavirus (ANDV) Associated with the 2026 MV Hondius Outbreak

Andes orthohantavirus (ANDV), the primary etiological agent of hantavirus pulmonary syndrome (HPS) in South America, is uniquely capable of limited hu...