Evidence map›Paper›PMID 41867215›Full record

ArticlemedRxiv : the preprint server for health sciences2026

An agentic AI system enhances clinical detection of immunotherapy toxicities: a multi-phase validation study.

Jack Gallifant, Shan Chen, Kee-Young Shin, Katherine C Kellogg, Patrick F Doyle, Joyce Guo, Bingyang Ye, Andrew Warrington, Bingxue K Zhai, Matthew J Hadfield and 17 more

Abstract readPreprint
PubMed Full text at PMC Publisher
In one paragraph

Article in medRxiv : the preprint server for health sciences, 2026. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Not yet cited in PubMed.

0numbers the graph read from it
0cells of the map it votes in
0citing papers in PubMed
–field-weighted citation impact
1 · What the graph read from it

What it found

Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.

The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.

2 · The registry

The trial behind it

Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.

Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.

3 · Its place in the literature

Who cites it

0 citing papers in PubMed.

No citing paper in PubMed yet.

4 · The record

Corrections and comments

PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.

5 · Who and what money

Authors and funding

27 authors.

Jack GallifantMass General Brigham, MA, USA.
Shan ChenMass General Brigham, MA, USA.
Kee-Young ShinHarvard Medical School, MA, USA.
Katherine C KelloggMIT Sloan School of Management, MA, USA.
Patrick F DoyleMass General Brigham, MA, USA.
Joyce GuoMass General Brigham, MA, USA.
Bingyang YeBrown University Health, RI, USA.
Andrew WarringtonMass General Brigham, MA, USA.
Bingxue K ZhaiMass General Brigham, MA, USA.
Matthew J HadfieldCenter for Clinical Cancer Informatics and Data Science, Legorreta Cancer Center, Brown University, Providence, RI, USA.
Alexander GusevHarvard Medical School, MA, USA.
Biagio RicciutiHarvard Medical School, MA, USA.
David C ChristianiMass General Brigham, MA, USA.
Hugo Jwl AertsMass General Brigham, MA, USA.
Benjamin H KannMass General Brigham, MA, USA.
Raymond H MakMass General Brigham, MA, USA.
Tanna L NelsonCenter for Biomedical Informatics & Information Technology, National Cancer Institute, NIH, MD, USA.
Paul NguyenMass General Brigham, MA, USA.
Jonathan D SchoenfeldMass General Brigham, MA, USA.
Umit TopalogluCenter for Biomedical Informatics & Information Technology, National Cancer Institute, NIH, MD, USA.
Paul CatalanoHarvard Medical School, MA, USA.
Harry HochheiserUniversity of Pittsburgh, PA, USA.
Jeremy L WarnerCenter for Clinical Cancer Informatics and Data Science, Legorreta Cancer Center, Brown University, Providence, RI, USA.
Elad SharonHarvard Medical School, MA, USA.
David E KozonoMass General Brigham, MA, USA.
Guergana K SavovaHarvard Medical School, MA, USA.
Danielle S BittermanMass General Brigham, MA, USA.ORCID 0000-0003-0345-2232

Funding

The Boston Lung Cancer Survival CohortU01CA209414 · NCI · HARVARD UNIVERSITY D/B/A HARVARD SCHOOL OF PUBLIC HEALTH · PI David C Christiani · 2017 to 2026
$12.2M
Shared Resource Core 2: Clinical Artificial Intelligence CoreU54CA274516 · NCI · DANA-FARBER CANCER INST · PI Ross I. Berbeco · 2023 to 2026
$8.1M
Cancer Deep Phenotyping from Electronic Medical RecordsU24CA248010 · NCI · BOSTON CHILDREN'S HOSPITAL · PI HARRY S HOCHHEISER, GUERGANA K. SAVOVA · 2020 to 2026
$6.1M
Informatics strategies to improve immune-related adverse event detection in cancer patientsR01CA294033 · NCI · BRIGHAM AND WOMEN'S HOSPITAL · PI Hugo Aerts · 2024 to 2026
$1.3M
NCI NIH HHS R01 CA294033NCI NIH HHS U01 CA209414NCI NIH HHS U24 CA248010NCI NIH HHS U54 CA274516
6 · The paper itself

Abstract

Immune-related adverse events (irAEs) affect up to 40% of patients receiving immune checkpoint inhibitors, yet their identification depends on laborious and inconsistent manual chart review. Here we developed and evaluated an agentic large language model system to extract the presence, temporality, severity grade, attribution, and certainty of six irAE types from clinical notes. Retrospectively (263 notes), the system achieved macro-averaged F1 of 0.92 for detection and 0.66 for multi-class severity grading; self-consistency improved F1 by 0.14. The best-performing configuration cost approximately $0.02 per note. In prospective silent deployment over three months (884 notes), detection F1 was 0.72-0.79. In a randomized crossover study of clinical trial staff (17 participants, 316 observations), agentic assistance reduced annotation time by 40% (P < 0.001), increased complete-match accuracy (OR 1.45; 95% CI 1.01-2.09; P = 0.045), and improved inter-annotator agreement (Krippendorff's α from 0.22-0.51 to 0.82-0.85). These results demonstrate that agentic AI coupled with human verification could enhance efficiency, performance, and consistency for irAE assessment.

Indexed as

Clinical Decision SupportElectronic Health RecordsHuman-Computer InteractionImmune-Related Adverse EventsImmunotherapyLarge Language ModelsNatural Language Processing

Identifiers

PMID41867215
PMCPMC13004146

What OpenQuestion holds

Textmetadata
LicenceCC BY-NC
Read underepoch 390

Registered trials

None linked

Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.