Canonical text (the exact bytes fingerprinted)

TRUVACE RECORD VERSION
record: TRV-2026-1596
version: 1
kind: certified
reason: Certified into the record
timestamp: 2026-10-16T18:13:18.317806Z
status: published
lens: g_space
sector: health
headline: TrajOnco: a multi-agent framework for temporal reasoning over longitudinal EHR for multi-cancer early detection
dek: Abstract Accurate estimation of cancer risk from longitudinal electronic health records (EHRs) could support earlier detection and improved care, but modeling such complex patient trajectories remains challenging. We present TrajOnco, a training-free, multi-agent large language model (LLM) framework designed for scalable multi-cancer early detection. Using a chain-of-agents architecture with long-term memory, TrajOnco performs temporal reasoning over sequential clinical events to generate patient-level summaries…
gain_title: A training-free multi-agent LLM system predicted 1-year cancer diagnosis risk from longitudinal health records, reaching AUROCs of 0.64–0.80 and matching supervised machine learning in a lung cancer benchmark.
problem_title: (none)
trace_subject: (none)
gain_reading: A training-free multi-agent LLM system predicted 1-year cancer diagnosis risk from longitudinal health records, reaching AUROCs of 0.64–0.80 and matching supervised machine learning in a lung cancer benchmark.
gain_evidence: performing comparably to supervised machine learning in a lung cancer benchmark
problem_reading: (none)
problem_evidence: (none)
quick_read: Researchers built TrajOnco, a chain-of-agents large language model framework that reads sequences of clinical events in electronic health records and produces patient-level summaries, rationales linked to evidence, and risk scores. It was tested on de-identified Truveta data using matched case-control cohorts for 15 cancer types, predicting diagnosis within one year.

The work suggests that LLM agents could support scalable multi-cancer early detection without task-specific training, while also offering interpretable reasoning that clinicians can inspect. The abstract describes retrospective evaluation on matched cohorts, so real-world screening benefit has not been shown, and the lower end of the AUROC range indicates uneven performance across cancers.
limitation: The evaluation used matched case-control cohorts, and performance varied across cancer types with AUROCs from 0.64 to 0.80, so prospective screening performance remains untested.
tag: Evidence-backed gain
key_points: The framework is training-free and uses multiple LLM agents with long-term memory to reason over patient event timelines. | In zero-shot tests across 15 cancer types, AUROCs ranged from 0.64 to 0.80. | It performed comparably to supervised machine learning in a lung cancer benchmark and showed better temporal reasoning than single-agent LLMs. | Smaller models such as GPT-4.1-mini could still carry out effective temporal reasoning in the multi-agent design. | Human evaluation supported the groundedness of outputs, and aggregated rationales matched established clinical knowledge on population-level risk patterns.
rundown: TrajOnco uses a chain-of-agents architecture in which agents process sequential clinical events and keep long-term memory. Each patient receives a summary, rationales tied to evidence in the record, and a predicted risk score for cancer diagnosis at one year.

The evaluation used de-identified Truveta EHR data and matched case-control cohorts covering 15 cancer types. Under zero-shot conditions, the system was compared with supervised machine learning on lung cancer and with single-agent LLMs on temporal reasoning.

The authors also report that the multi-agent design allowed smaller-capacity models to reason effectively, and that human reviewers found outputs grounded. Aggregating the reasoning outputs revealed population-level risk patterns consistent with established clinical knowledge, pointing to a use for clinical insight generation.
sources:
- peer_reviewed | npj Digital Medicine | https://doi.org/10.1038/s41746-026-03377-9 | 2026-10-15
prev: 0000000000000000000000000000000000000000000000000000000000000000

sha256

c56219a9809d9e24fcd56226c7f14bd5d661d88c9a21e313b44c37b2530da55d

previous

0000000000000000000000000000000000000000000000000000000000000000