Microsoft Health Futures
Nouvelles et reportages
Advancing biomedical discovery: Overcoming data challenges in precision medicine
| Mandi Hall
Our recent study in Nature Scientific Reports identified key challenges in the biomedical data lifecycle and offered 7 actionable recommendations.
This panel explores the transformative potential of generative AI in learning the language of nature and patients for precision health, from proteins to medical imaging, from electronic medical records to home health monitoring.
Hoifung Poon introduces an agenda in precision health, utilizing generative AI to pretrain high-fidelity patient embeddings from multimodal, longitudinal patient journeys. This approach unlocks population-scale real-world evidence, optimizing clinical care and accelerating biomedical discovery.
Dans l’actualité | ConSalud
Microsoft Health Futures: The future of medicine powered by artificial intelligence
Microsoft’s generative artificial intelligence is making it possible to identify patterns in large populations, structure clinical information and simulate clinical trials, optimizing the development of new treatments.
BiomedParse: A foundation model for smarter, all-in-one biomedical image analysis
| Hoifung Poon, Theodore Zhao, Aiden Gu, Mu Wei, et Sheng Wang
BiomedParse reimagines medical image analysis, integrating advanced AI to capture complex insights across imaging types—a step forward for diagnostics and precision medicine.
Dans l’actualité | Providence
Comprehensive Genomic Profiling leads to better patient outcomes, new joint study says
New real-world data from Providence, Illumina (NASDAQ: ILMN), and Microsoft Research reveals that Comprehensive Genomic Profiling (CGP), when done early in a cancer patient’s diagnosis, leads to better personalized treatment and patient outcomes. The findings come out of the first…
Dans l’actualité | AAMC
Can AI fundamentally improve patient care?
Microsoft exec and Learn Serve Lead 2024 speaker James Weinstein, DO, says the technology could eventually expand access and quality, but privacy concerns remain. While artificial intelligence (AI) tools are drawing attention for their potential to improve doctor-patient dynamics —…
Stress-testing biomedical vision models with RadEdit: A synthetic data approach for robust model deployment
| Max Ilse, Daniel Coelho de Castro, et Javier Alvarez-Valle
RadEdit stress-tests biomedical vision models by simulating dataset shifts through precise image editing. It uses diffusion models to create realistic, synthetic datasets, helping to identify model weaknesses and evaluate robustness.
Microsoft Research Forum Episode 4: The future of multimodal models, a new “small” language model, and other AI updates
Explore multimodal & small language models, plus advanced benchmarks for AI evaluation. Microsoft researchers are working on breakthroughs in weather prediction, materials design, even a new kind of computer for AI inference and hard optimization problems.