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
842P - Multicenter real-world study of newly diagnosed advanced-stage extranodal natural killer/T cell lymphoma (ENKTL): Proposal for intensive therapy
Presenter: Yu-Ce Wei
Session: Poster session 18
844P - Progression -free survival prediction of multiple myeloma patients in five European countries using machine learning models
Presenter: Maria Luisa Pleguezuelo Witte
Session: Poster session 18
845P - A machine learning based clinical platform for cancer subtyping and data integration in hematological malignancies
Presenter: Michelle Tang
Session: Poster session 18
846P - Artificial intelligence-driven identification of onco-hematology patients who may develop severe COVID-19
Presenter: Souad Assaad
Session: Poster session 18
847P - Fatal infections among leukemia patients
Presenter: Huijie Zhou
Session: Poster session 18
848P - Mortality after rasburicase vs allopurinol anti-hyperuricemia monotherapy in patients with liquid tumors
Presenter: Mitchell Cairo
Session: Poster session 18
849P - Long non-coding RNA signatures and their role in the progression of childhood T cell acute lymphoblastic leukemia
Presenter: Pankaj Sharma
Session: Poster session 18
850P - A zebrafish model of MYC-driven acute myeloid leukemia reveals that neutrophil resistance to oncogenic transformation depends on their ability to promote PP2A-mediated MYC proteasomal degradation
Presenter: Anna Maria Luciano
Session: Poster session 18
851P - Characterization of a zebrafish model of MYC-driven acute myeloid leukemia
Presenter: Anna Maria Luciano
Session: Poster session 18
852P - c-MAF-driven metabolic reprogramming mediates H3K27 hyperacetylation to regulate super enhancer-associated genes
Presenter: Phyllis SY Chong
Session: Poster session 18