analiza aiqbench
This paper addresses a critical limitation in current clinical search systems by reframing longitudinal retrieval as an evidence allocation problem rather than simple relevance ranking. The authors demonstrate that standard similarity-based retrievers fail to capture unique temporal transitions in patient histories due to redundant documentation, proposing a new framework to optimize how limited evidence budgets are distributed across time. While the study highlights significant technical challenges in validating these methods without expert reference timelines, it establishes a clear research agenda for improving AI-driven retrieval in electronic health records.
Temporal Evidence Allocation For Longitudinal Clinical Retrieval: A Position And Technical Report
arXiv:2610.27682v1 Announce Type: new Abstract: Electronic health records are written to support care, not retrieval. Across years of oncology notes, the primary diagnosis is restated in report after report, while the events that shape a patient's course, such as a recurrence or a change in therapy, may be recorded only once. A retriever that ranks passages by similarity to the query keeps returning the repeated material and can miss these transitions, that is, it exhibits temporal redundancy across historical narratives. We argue that longitudinal clinical retrieval should be treated as allocating a limited evidence budget across time, not just ranking by relevance. We separate the task into three objectives: temporal evidence allocation, candidate reconstruction, and clinical validation. In Study A (13 clinical queries over 20 patient records, with two-stage reconstruction), the Temporal-15 configuration reaches a milestone slot recall of 0.538, compared with 0.388 for the Global-50 baseline. However, it also retrieves far more evidence (496 versus 50 indexed units per query), so the gain cannot be credited to allocation alone. When evidence is held fixed, removing prompted precedence rules raises schema-order reversals from 0.010 to 0.080. A five-patient, single-query pilot with fixed budgets finds that wider temporal coverage does not reliably yield more dated milestones. Together, these results suggest that how much a record says about a period is a poor guide to how useful that period is as evidence. Because no expert reference timelines are available, our measurements describe retrieval behavior rather than clinical accuracy. This position and technical report presents the retrieval analysis behind the Onco-CONSTRUE framework and sets out a research agenda for budget-constrained longitudinal clinical retrieval.
Abstract:Electronic health records are written to support care, not retrieval. Across years of oncology notes, the primary diagnosis is restated in report after report, while the events that shape a patient's course, such as a recurrence or a change in therapy, may be recorded only once. A retriever that ranks passages by similarity to the query keeps returning the repeated material and can miss these transitions, that is, it exhibits temporal redundancy across historical narratives. We argue that longitudinal clinical retrieval should be treated as allocating a limited evidence budget across time, not just ranking by relevance. We separate the task into three objectives: temporal evidence allocation, candidate reconstruction, and clinical validation. In Study A (13 clinical queries over 20 patient records, with two-stage reconstruction), the Temporal-15 configuration reaches a milestone slot recall of 0.538, compared with 0.388 for the Global-50 baseline. However, it also retrieves far more evidence (496 versus 50 indexed units per query), so the gain cannot be credited to allocation alone. When evidence is held fixed, removing prompted precedence rules raises schema-order reversals from 0.010 to 0.080. A five-patient, single-query pilot with fixed budgets finds that wider temporal coverage does not reliably yield more dated milestones. Together, these results suggest that how much a record says about a period is a poor guide to how useful that period is as evidence. Because no expert reference timelines are available, our measurements describe retrieval behavior rather than clinical accuracy. This position and technical report presents the retrieval analysis behind the Onco-CONSTRUE framework and sets out a research agenda for budget-constrained longitudinal clinical retrieval.
Artificial Intelligence (cs.AI)
arXiv:2610.27682 [cs.AI]
(or arXiv:2610.27682v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2610.27682 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 359 cuvinte
Subiecte conexe
HALO: Hierarchical Evidence Selection and Reinforcement Learning for Allocating Budgeted Label Optimization from Longitudinal Clinical Records
arXiv · 3 nov. 2026
DART: A DAG-Based Reputation and Incentive Framework via Blockchain-Enabled Governance for Trustworthy LLM Multi-Agent Collaboration
arXiv · 9 sept. 2026
Qoro Quantum Opens Cloud GPU Simulation Tier to Accelerate Large-Scale Circuit Emulation
Quantum Computing Report · 4 nov. 2026
Expert-Driven Survival Machines: Improving Stratification and Interpretability in Multiple Clinical Cohorts
arXiv · 15 iun. 2026