Towards Precision Therapy in Hepatocellular Carcinoma: A Clinical-Reasoning LLM for Risk Stratification and Treatment Guidance

Source

Source name: arXiv
Source kind: paper
Authors / organization: Peng Cui, Jitao Wang, Siyan Xue, Yao Huang, Haoming Xia, Dong Li, Dengxiang Liu, Weilin Wang, Liping Liu, Leida Zhang, Yunfu Cui, Tao Peng, Daolin Ji, Haitao Zhao, Wei Zhang, Xiaojuan Wang, Weijie Ma, Zongren Ding, Jinlong Li, Yuan Ding, Jiajing Zhao, Zhiyu Chen, Chengkun Yang, Ziyue Huang, Jiaqi Liu, Fusheng Liu, Yang Zhou, Xiaojuan Wang, Zhongquan Sun, Shiyun Bao, Xiaojun Wang, Ming Yang, Guangxin Li, Bin Shu, Yong Liao, Hongxuan Li, Yao Tang, Shizhong Yang, Yongyi Zeng, Yufeng Yuan, Yinpeng Dong, Jihui Hao, Jun Zhu, Jiahong Dong
Venue: arXiv: cs.AI
Published: 2026-07-09
Collected: 2026-07-10
URL: http://arxiv.org/abs/2607.08602v1
PDF: https://arxiv.org/pdf/2607.08602v1
DOI: UNKNOWN

Plain-Language Brief

A large language model named HCC-STAR has been developed to provide personalized treatment recommendations, risk scores, and survival estimates for patients with Hepatocellular Carcinoma (HCC). The model reads through electronic medical records (EMRs) and is validated by clinicians. It outperforms existing clinical guidelines and other models in treatment recommendation and risk stratification, as shown in a multi-center study in China. The use of HCC-STAR could potentially improve the accuracy of decisions made by physicians.

What the Document Says

Hepatocellular Carcinoma (HCC) is a type of cancer with high mortality rate.
Current guidelines and staging systems for HCC have limitations in addressing within-stage heterogeneity and clinical context in EMRs.
A model named HCC-STAR has been developed to address these limitations. It reads EMR narratives and outputs risk score-based staging, treatment recommendations with evidence-based rationales, and individualized survival estimates.
The model was trained on a corpus of about 30,000 HCC cases curated from SEER and expanded into EMR-style narrative training data using a clinician-validated prompt-based augmentation workflow.
HCC-STAR uses a knowledge-aligned reasoning framework optimized with a step-verifiable composite reward to move beyond text-level memorization of clinical guidelines.
In a multi-center study, HCC-STAR achieved superior performance in treatment recommendation and risk stratification compared to clinical guidelines and competitive models like GPT-5 and Gemini-2.5 Pro.
The model showed potential for improving the accuracy of decisions made by physicians in clinician-centric evaluations.
In hypothetical overall-survival analysis, patients under HCC-STAR recommendations had a median survival of 51 months, compared to 29 and 32 months under BCLC and CNLC respectively.
Blinded hepatobiliary specialists rated the reasoning and evidence-based justifications of HCC-STAR as trustworthy.

Key Concepts Mentioned

Hepatocellular Carcinoma
electronic medical records
HCC-STAR
risk score-based staging
treatment recommendations
evidence-based rationales
individualized survival estimates
clinical guidelines
GPT-5
Gemini-2.5 Pro

Claims Made by the Document

HCC-STAR outperforms existing clinical guidelines and competitive models in treatment recommendation and risk stratification.
The use of HCC-STAR could potentially improve the accuracy of decisions made by physicians.

Evidence Used

Comparative performance data from a multi-center study
Findings from clinician-centric evaluations

Methods / Approach

Development of a large language model
Optimization of the model with a step-verifiable composite reward
Training on a corpus of about 30,000 HCC cases
Clinician validation of the model

Limitations Stated by the Authors

UNKNOWN

Limitations Noted by the Agent

Agent interpretation — not from the source.

The model's performance may be affected by the quality and quantity of the data it was trained on. It is also dependent on the accuracy and completeness of the information in the electronic medical records.

Open Questions

What is the exact training process for HCC-STAR?
How does HCC-STAR handle cases not covered by the clinical guidelines?

Notes for Future Q&A

May include interpretation. Labeled where it does.

The text provides details about the development and validation of the model, but it doesn't go into specifics about the training process.
The text mentions that the model is based on clinical guidelines, but it does not clarify how it handles cases where those guidelines do not apply.

Raw Abstract / Excerpt

Hepatocellular carcinoma (HCC) is a common malignancy and a leading cause of cancer-related mortality. Current guidelines and staging systems provide coarse categories, but often miss within-stage heterogeneity and the clinical context in electronic medical records (EMRs). We present HCC-STAR (Hepatocellular Carcinoma Staging, Treatment And pRognosis), a clinically aligned large language model that reads routine EMR narratives and jointly outputs risk score-based staging, ranked guideline-consistent treatments with evidence-based rationales, and individualized survival estimates. We curated about 30,000 HCC cases from SEER and expanded them into EMR-style narrative training data using a clinician-validated, prompt-based augmentation workflow. On this corpus, we developed a knowledge-aligned reasoning framework optimized with a step-verifiable composite reward, moving beyond text-level memorization of clinical guidelines. In a multi-center cohort of 6,668 patients from 12 hospitals in China, HCC-STAR achieved state-of-the-art performance in treatment recommendation and risk stratification compared with clinical guidelines and competitive models, including GPT-5 and Gemini-2.5 Pro. Hypothetical overall-survival analysis showed a median survival of 51 months under adherence to HCC-STAR recommendations, compared with 29 and 32 months under BCLC and CNLC. In clinician-centric evaluations, blinded hepatobiliary specialists rated HCC-STAR's reasoning and evidence-based justifications as trustworthy. The model surpassed resident and attending physicians in treatment accuracy and helped physicians make more accurate decisions faster when used as an assistant. These findings support HCC-STAR as a reliable and verifiable decision-support system for risk stratification and precision therapy in HCC.