Abstract 968P
Background
Current guidelines for hepatocellular carcinoma (HCC) screening in patients with chronic liver disease (CLD) recommend ultrasound with or without alpha-fetoprotein (AFP) every 6 months. The sensitivity of AFP and USG are low for early stage HCC. Following our previous study which identified a novel routine blood test signature for HCC, this study aims to develop a high-dimensional data classifier which accounts for the intricate interactions between these blood parameters for the detection of HCC. Its performance is then compared with AFP.
Methods
Records from 2000 to 2018 were retrieved from a population-based clinical database of >200k patients, the Hong Kong Hospital Authority Data Collaboration Laboratory. CLD (hepatitis/ cirrhosis) patients with and without HCC were identified with ICD codes, antiviral drug history, virology test and radiology reports. Decompensated cases were excluded. Blood records within one month before the diagnosis of HCC and CLD patients were retrieved. The records retrieved included all components of CBC, LFT, RFT and clotting profile. Data from 2000-2015 were split into training and testing cohorts in an 8:2 ratio while data from 2016-2018 were used as the validation set. Machine learning models were applied and their performances were compared with AFP.
Results
The cohort yielded 223,862 patients including 31,149 with HCC (45.9% hepatitis-associated) and 192,713 without. Results from the test set (n = 12528; 3279 HCC) showed promise in safely excluding non-HCC patients with a sensitivity of 90% and negative predictive value of 97%. The model’s high sensitivity maintained steady from late to early stage HCC while that of AFP halved. Our model increases HCC detection rate via USG from 19% to 50% compared to current protocol, indicating potential use in imaging prioritization and cost-saving in HCC surveillance.
Conclusions
An AI classifier for HCC detection is developed from routine blood test patient data. Its performance tested using an ultra-large cohort is consistently high without degradation across all stages with marked superiority to AFP for early stage HCC detection. Currently, multicenter prospective validation is being performed in Hong Kong.
Clinical trial identification
Editorial acknowledgement
Legal entity responsible for the study
The Hong Kong University of Science and Technology.
Funding
Has not received any funding.
Disclosure
All authors have declared no conflicts of interest.
Resources from the same session
1009P - Network meta-analysis of first-line systemic therapies for advanced hepatocellular carcinoma: A comparison of objective response rates
Presenter: Gagandeep Kaur
Session: Poster session 18
1010P - A parametric network meta-analysis of first-line systemic therapies for advanced hepatocellular carcinoma related to overall survival
Presenter: Akanksha Sharma
Session: Poster session 18
1011P - A prospective study of TACE combined with lenvatinib plus sintilimab for HCC with portal vein tumor thrombus
Presenter: Xiaoyan Ding
Session: Poster session 18
1012P - First-in-human study of ABSK-011, a novel, highly selective fibroblast growth factor receptor (FGFR) 4 inhibitor for treating advanced hepatocellular carcinoma (HCC) with FGF19 overexpression
Presenter: Ann-Lii Cheng
Session: Poster session 18
1013TiP - Refinement and validation of a comprehensive clinical diagnostic model (GAMAD) for early detection of hepatocellular carcinoma: A multicenter, prospective study protocol
Presenter: Tian Yang
Session: Poster session 18
1014TiP - Efficacy and safety of recombinant human adenovirus type 5 injection combined with transhepatic arterial embolization sequential thermal ablation for medium-and high-risk recurrent liver cancer: a prospective, open-label, randomized controlled study
Presenter: Jianjun Li
Session: Poster session 18
1015TiP - A Prospective, phase II clinical study of tislelizumab monotherapy or in combination with lenvatinib for neoadjuvant treatment of resectable hepatocellular carcinoma
Presenter: Tianqiang Song
Session: Poster session 18