{"version":1,"type":"story","url":"https://digestai.news/story/researchers-propose-longinus-framework-for-next-visit-diagnosis-predic","json":"https://digestai.news/story/researchers-propose-longinus-framework-for-next-visit-diagnosis-predic.json","markdown":"https://digestai.news/story/researchers-propose-longinus-framework-for-next-visit-diagnosis-predic.md","slug":"researchers-propose-longinus-framework-for-next-visit-diagnosis-predic","headline":"Researchers propose longinus framework for Next-Visit diagnosis prediction","summary":"A new paper on arXiv introduces **LONGINUS**, a retrieval-memory multi-agent system designed to improve next-visit diagnosis prediction in healthcare. The authors argue that current methods fail to account for variability in diagnosis sets, temporal changes (persistent, new, or recurrent diagnoses), and varying patient history depth. Their evaluation framework compares rule-based heuristics, LLM prompting, retrieval, memory, and multi-agent approaches, finding that simple repetition of the last visit often outperforms LLM-based methods despite predicting no new diagnoses.\n\nLONGINUS combines retrieved patient record evidence with structured memory of the patient’s trajectory, using cross-view agreement to adjudicate disagreements without exposing their sources. Tests on **MIMIC-III** and **MIMIC-IV** datasets with four LLM backbones show it achieves the highest transition-specific performance among LLM-based methods in nearly all scenarios while maintaining competitiveness on aggregate metrics. The work highlights the need for more nuanced evaluation frameworks in clinical prediction tasks.","keyPoints":["LONGINUS framework combines retrieval and memory for next-visit diagnosis prediction, outperforming LLM-only methods in transition-specific cases","Researchers find simple repetition of last-visit diagnoses often surpasses LLM-based approaches despite limited predictive power","Tests on MIMIC-III and MIMIC-IV datasets with four LLM backbones show LONGINUS leads in transition-specific performance"],"whyItMatters":"This work could shift clinical prediction models toward more accurate, interpretable, and context-aware systems by addressing temporal and distributional challenges in diagnosis prediction.","category":{"slug":"research","name":"Research","url":"https://digestai.news/category/research"},"entities":{"companies":[],"models":["LONGINUS"],"people":[]},"firstPublishedAt":"2026-11-04T05:00:00Z","updatedAt":"2026-11-04T05:00:00Z","sourceCount":1,"hasPrimarySource":true,"sources":[{"outlet":"arXiv cs.CL","title":"Rethinking Next-Visit Diagnosis Prediction Beyond Aggregate Metrics: Retrieval--Memory Multi-Agent Adjudication","url":"https://arxiv.org/abs/2611.03826","publishedAt":"2026-11-04T05:00:00Z","type":"primary","primary":true,"lead":true}],"sourceNotes":null,"discussions":[],"thread":null,"cite":{"text":"Digest AI, \"Researchers propose longinus framework for Next-Visit diagnosis prediction\", 4 November 2026, https://digestai.news/story/researchers-propose-longinus-framework-for-next-visit-diagnosis-predic","publisher":"Digest AI","title":"Researchers propose longinus framework for Next-Visit diagnosis prediction","datePublished":"2026-11-04T05:00:00Z","url":"https://digestai.news/story/researchers-propose-longinus-framework-for-next-visit-diagnosis-predic"},"generatedBy":"Written by Digest AI's editorial model from the linked sources; the sources are the record.","license":"Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse"}