# Risk Stratification for and Early Detection of Liver Cancer

> **NIH NIH U01** · BAYLOR COLLEGE OF MEDICINE · 2024 · $433,960

## Abstract

The Translational Research Center (TRC) includes a diverse team of clinical and translational researchers with
a strong track record of working together to reduce hepatocellular cancer (HCC). The TRC uses data from a
unique group of patients with cirrhosis who are being recruited from eight different sites throughout Texas (the
TRC cohort). Our TRC cohort currently includes > 3700 patients with cirrhosis (>10,000 follow up surveillance
visits and >190 HCC cases) who have diverse risk factors, including cured HCV and non-alcoholic fatty liver
disease. These patients are under routine HCC surveillance and their biological samples and clinical and
radiological data for each visit is stored; it is a valuable resource for our research and other Consortium projects.
We also launched a separate prospective cohort of patients with indeterminate liver nodules, which is a high risk
and high priority group for HCC risk stratification and early detection. We are collecting surveys, clinical data,
images and biospecimens from this cohort. The catalytic effects of our TRC are seen in the productivity of our
junior investigators, who started innovative new initiatives and programs. Our work had a broad impact, including
helping develop various society guidelines on HCC surveillance. Using data and the strong network of
investigators and institutions collaborating with our TRC, we have already generated important data on risk
factors and risk stratification for HCC. We also developed and demonstrated the framework for adding patient-
and liver disease-related factors to new blood-biomarker profiles to improve early HCC detection. Here, we
propose to build a novel imaging repository, including MRI images from our cohort. We will annotate and
incorporate data from abdominal ultrasound reports for our TRC cohort using novel, scalable machine learning
pipelines. We will also strengthen our data by appending information from the State cancer registries. Using data
from different sources available to us, we will develop and test new personalized methods to stratify risk that
blends information from clinical factors, blood-based biomarkers, and imaging (radiomics) to predict future
development of HCC in patients with cirrhosis across diverse risk factors (Aim 1). We showed that the HCC
Early Detection Screening (HES) algorithm, when combined with HCC blood-based biomarkers (AFP‐L3, DCP)
in HES version 2.0 (HES v2.0), substantially improved early detection. We will validate and compare HES v2.0
with GALAD, another early detection algorithm, and evaluate their performance versus the current standard
ultrasound-based surveillance (Aim 2). In Aim 3, we will develop a new mathematical model to look at how
useful current and emerging biomarkers are for detecting HCC. We will also assess the risks, costs, and benefits
of HCC surveillance using different cutoffs of existing and novel blood and imaging biomarkers. We will develop
and disseminate an online Simulator so that othe...

## Key facts

- **NIH application ID:** 10931490
- **Project number:** 5U01CA230997-07
- **Recipient organization:** BAYLOR COLLEGE OF MEDICINE
- **Principal Investigator:** Jagpreet Chhatwal
- **Activity code:** U01 (R01, R21, SBIR, etc.)
- **Funding institute:** NIH
- **Fiscal year:** 2024
- **Award amount:** $433,960
- **Award type:** 5
- **Project period:** 2018-09-13 → 2028-08-31

## Primary source

NIH RePORTER: https://reporter.nih.gov/project-details/10931490

## Citation

> US National Institutes of Health, RePORTER application 10931490, Risk Stratification for and Early Detection of Liver Cancer (5U01CA230997-07). Retrieved via AI Analytics 2026-06-01 from https://api.ai-analytics.org/grant/nih/10931490. Licensed CC0.

---

*[NIH grants dataset](/datasets/nih-grants) · CC0 1.0*