A Liver Stiffness-Based Etiology-Independent Machine Learning Algorithm to Predict Hepatocellular Carcinoma

BACKGROUND & AIMS

The existing hepatocellular carcinoma (HCC) risk scores have modest accuracy, and most are specific to chronic hepatitis B infection. In this study, we developed and validated a liver stiffness-based machine learning algorithm (ML) for prediction and risk stratification of HCC in various chronic liver diseases (CLDs).

METHODS

MLs were trained for prediction of HCC in 5155 adult patients with various CLDs in Korea and further tested in 2 prospective cohorts from Hong Kong (HK) (N = 2732) and Europe (N = 2384). Model performance was assessed according to Harrell's C-index and time-dependent receiver operating characteristic (ROC) curve.

RESULTS

We developed the SMART-HCC score, a liver stiffness-based ML HCC risk score, with liver stiffness measurement ranked as the most important among 9 clinical features. The Harrell's C-index of the SMART-HCC score in HK and Europe validation cohorts were 0.89 (95% confidence interval, 0.85-0.92) and 0.91 (95% confidence interval, 0.87-0.95), respectively. The area under ROC curves of the SMART-HCC score for HCC in 5 years was ≥0.89 in both validation cohorts. The performance of SMART-HCC score was significantly better than existing HCC risk scores including aMAP score, Toronto HCC risk index, and 7 hepatitis B-related risk scores. Using dual cutoffs of 0.043 and 0.080, the annual HCC incidence was 0.09%-0.11% for low-risk group and 2.54%-4.64% for high-risk group in the HK and Europe validation cohorts.

CONCLUSIONS

The SMART-HCC score is a useful machine learning-based tool for clinicians to stratify HCC risk in patients with CLDs.

Non-invasive biomarkers for liver inflammation in non-alcoholic fatty liver disease: present and future

Inflammation is the key driver of liver fibrosis progression in non-alcoholic fatty liver disease (NAFLD). Unfortunately, it is often challenging to assess inflammation in NAFLD due to its dynamic nature and poor correlation with liver biochemical markers. Liver histology keeps its role as the standard tool, yet it is well-known for substantial sampling, intraobserver, and interobserver variability. Serum proinflammatory cytokines and apoptotic markers, namely cytokeratin-18, are well-studied with reasonable accuracy, whereas serum metabolomics and lipidomics have been adopted in some commercially available diagnostic models. Ultrasound and computed tomography imaging techniques are attractive due to their wide availability; yet their accuracies may not be comparable with magnetic resonance imaging-based tools. Machine learning and deep learning models, be they supervised or unsupervised learning, are promising tools to identify various subtypes of NAFLD, including those with dominating liver inflammation, contributing to sustainable care pathways for NAFLD.

Artificial intelligence in prediction of non-alcoholic fatty liver disease and fibrosis

Artificial intelligence (AI) has become increasingly widespread in our daily lives, including healthcare applications. AI has brought many new insights into better ways we care for our patients with chronic liver disease, including non-alcoholic fatty liver disease and liver fibrosis. There are multiple ways to apply the AI technology on top of the conventional invasive (liver biopsy) and noninvasive (transient elastography, serum biomarkers, or clinical prediction models) approaches. In this review article, we discuss the principles of applying AI on electronic health records, liver biopsy, and liver images. A few common AI approaches include logistic regression, decision tree, random forest, and XGBoost for data at a single time stamp, recurrent neural networks for sequential data, and deep neural networks for histology and images.

Machine learning model to predict recurrent ulcer bleeding in patients with history of idiopathic gastroduodenal ulcer bleeding

BACKGROUND

Patients with a history of Helicobacter pylori-negative idiopathic bleeding ulcers have an increased risk of recurring ulcer complications.

AIM

To build a machine learning model to identify patients at high risk for recurrent ulcer bleeding.

METHODS

Data from a retrospective cohort of 22 854 patients (training cohort) diagnosed with peptic ulcer disease in 2007-2016 were analysed to build a model (IPU-ML) to predict recurrent ulcer bleeding. We tested the IPU-ML in all patients with a diagnosis of gastrointestinal bleeding (n = 1265) in 2008-2015 from a different catchment population (independent validation cohort). Any co-morbid conditions which had occurred in >1% of study population were eligible as predictors.

RESULTS

Recurrent ulcer bleeding developed in 4772 patients (19.5%) in the training cohort, during a median follow-up period of 2.7 years. IPU-ML model built on six parameters (age, baseline haemoglobin, and presence of gastric ulcer, gastrointestinal diseases, malignancies, and infections) identified patients with bleeding recurrence within 1 year with an area under the receiver operating characteristic curve (AUROC) of 0.648. When we set the IPU-ML cutoff value at 0.20, 27.5% of patients were classified as high risk for rebleeding with a sensitivity of 41.4%, specificity of 74.6%, and a negative predictive value of 91.1%. In the validation cohort, the IPU-ML identified patients with a recurrence ulcer bleeding within 1 year with an AUROC of 0.775, and 84.3% of overall accuracy.

CONCLUSION

We developed a machine-learning model to identify those patients with a history of idiopathic gastroduodenal ulcer bleeding who are not at high risk for recurrent ulcer bleeding.

A Hybrid Residual Network and Long Short-Term Memory Method for Peptic Ulcer Bleeding Mortality Prediction

The prediction of patient mortality, which can detect high-risk patients, is a significant yet challenging problem in medical informatics. Thanks to the wide adoption of electronic health records (EHRs), many data-driven methods have been proposed to forecast mortality. However, most existing methods do not consider correlations between static and dynamic data, which contain significant information about mutual influences between these data. In this paper, we utilize a deep Residual Network (ResNet) consisting of many convolution units, which can jointly analyze different variables, to capture correlation information in and between static and dynamic variables. Furthermore, the Long Short-Term Memory (LSTM) method is used to extract temporal dependencies information from dynamic data. Finally, a deep fusion method is used to integrate these different types of information to improve mortality prediction. Experiment results on Peptic Ulcer Bleeding (PUB) mortality prediction show that the proposed method outperforms existing methods and achieves an AUC (area under the receiver operating characteristic curve) score of 0.9353.

Regularized color clustering in medical image database

A regularized color clustering algorithm is proposed to solve the color clustering problem in medical image database. By incorporating both measures of cluster separability and cluster compactness, regularized color clustering allows the automatic extraction of significant color groups with varying populations. Experimental results in different color spaces show that the regularized color clustering gives superior results in extracting significant distinct/abnormal color clusters without significant increases in cluster compactness. Furthermore, results of color clustering in different color spaces show that the LUV color space is more suitable for color clustering. Methods for selecting the regularization constants have also been suggested.