New AI framework generates synthetic patient data from small cohorts

Researchers have developed a new generative framework called Multiplicity-weighted Stochastic Attention (SA) that utilizes modern Hopfield networks to create synthetic patient data from small longitudinal cohorts. This method stores real patient profiles as memory patterns, allowing for the generation of synthetic data that closely matches the fidelity and characteristics of the original small datasets. The SA framework was successfully applied to longitudinal coagulation data from 23 patients, demonstrating its potential for tasks like mechanistic calibration and hypothesis generation in areas with limited data, such as maternal health and rare diseases. AI

IMPACT Enables more robust AI modeling for rare diseases and small clinical trials by overcoming data scarcity.

RANK_REASON The cluster contains an academic paper detailing a new generative framework for synthetic data. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

• arXiv
• Hopfield Networks
• Langevin dynamics
• polyendocrine metabolic ovarian syndrome
• pre-eclampsia
• Stochastic Attention

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →