Sources
 Fair ultrasound diagnosis via adversarial protected attribute aware perturbations on latent embeddings
npj Digital Medicine - (Saturday May 17, 2025) Deep learning techniques have significantly enhanced the convenience and precision of ultrasound image diagnosis, particularly in the crucial step of lesion segmentation. However, recent studies reveal that both train-from-scratch models and pre-trained models often…  Development and prospective implementation of a large language model based system for early sepsis prediction
npj Digital Medicine - (Saturday May 17, 2025) Sepsis is a dysregulated host response to infection with high mortality and morbidity. Early detection and intervention have been shown to improve patient outcomes, but existing computational models relying on structured electronic health record… |
 Social determinants of health extraction from clinical notes across institutions using large language models
npj Digital Medicine - (Saturday May 17, 2025) Detailed social determinants of health (SDoH) is often buried within clinical text in EHRs. Most current NLP efforts for SDoH have limitations, investigating limited factors, deriving data from a single institution, using specific patient…  FedWeight: mitigating covariate shift of federated learning on electronic health records data through patients re-weighting
npj Digital Medicine - (Saturday May 17, 2025) Federated learning (FL) enables collaborative analysis of decentralized medical data while preserving patient privacy. However, the covariate shift from demographic and clinical differences can reduce model generalizability. We propose FedWeight, a novel FL framework… |
 The DRAGON benchmark for clinical NLP
npj Digital Medicine - (Saturday May 17, 2025) Artificial Intelligence can mitigate the global shortage of medical diagnostic personnel but requires large-scale annotated datasets to train clinical algorithms. Natural Language Processing (NLP), including Large Language Models (LLMs), shows great potential for annotating…  Hybrid machine learning for real-time prediction of edema trajectory in large middle cerebral artery stroke
npj Digital Medicine - (Saturday May 17, 2025) In treating malignant cerebral edema after a large middle cerebral artery stroke, clinicians need quantitative tools for real-time risk assessment. Existing predictive models typically estimate risk at one, early time point, failing to account… |
 Experience of Using Electronic Inhaler Monitoring Devices for Patients With Chronic Obstructive Pulmonary Disease or Asthma: Systematic Review of Qualitative Studies
JMIR mHealth and uHealth - (Friday May 16, 2025) Background: Electronic inhaler monitoring devices (EIMDs) can enhance medication adherence in patients with chronic obstructive pulmonary disease (COPD) and asthma, yet patient perceptions and experiences with these devices vary widely. A systematic qualitative synthesis…  Datavant acquires Aetion to expand RWE platform
MobiHealthNews - (Friday May 16, 2025) Data sharing technology company Datavant announced it will acquire Aetion, a company focused on real-world evidence in healthcare.Aetion will join Datavant to offer an end-to-end real-world evidence (RWE) platform, allowing healthcare and life sciences… |
 Sprinter scores $55M for home healthcare offering
MobiHealthNews - (Friday May 16, 2025) On-demand, in-home care company Sprinter Health secured $55 million in a Series B financing round led by General Catalyst.Andreessen Horowitz (a16z) Bio + Health and other existing investors, including the Regents of the University…  New app streamlines integration of medical data for dental practices
Healthcare IT news - (Friday May 16, 2025) For all the strides made in recent years breaking down the many barriers to data interoperability across the healthcare ecosystem, challenges still remain. One of the biggest is sharing patient information between and among… |
