BindingSiteDTI: differential-scale binding site modelling for drug-target interaction prediction.

MOTIVATION: Enhanced by contemporary computational advances, the prediction of drug-target interactions (DTIs) has become crucial in developing de novo and effective drugs. Existing deep learning approaches to DTI prediction are frequently beleaguered by a tendency to overfit specific molecular representations, which significantly impedes their predictive reliability and utility in novel drug discovery contexts. Furthermore, existing DTI networks often disregard the molecular size variance between macro molecules (targets) and micro molecules (drugs) by treating them at an equivalent scale that undermines the accurate elucidation of their interaction. RESULTS: We propose a novel DTI network with a differential-scale scheme to model the binding site for enhancing DTI prediction, which is named as BindingSiteDTI. It explicitly extracts multiscale substructures from targets with different scales of molecular size and fixed-scale substructures from drugs, facilitating the identification of structurally similar substructural tokens, and models the concealed relationships at the substructural level to construct interaction feature. Experiments conducted on popular benchmarks, including DUD-E, human, and BindingDB, shown that BindingSiteDTI contains significant improvements compared with recent DTI prediction methods. AVAILABILITY AND IMPLEMENTATION: The source code of BindingSiteDTI can be accessed at https://github.com/MagicPF/BindingSiteDTI.

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.

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.

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.

Novel machine learning models outperform risk scores in predicting hepatocellular carcinoma in patients with chronic viral hepatitis.

BACKGROUND & AIMS: Accurate hepatocellular carcinoma (HCC) risk prediction facilitates appropriate surveillance strategy and reduces cancer mortality. We aimed to derive and validate novel machine learning models to predict HCC in a territory-wide cohort of patients with chronic viral hepatitis (CVH) using data from the Hospital Authority Data Collaboration Lab (HADCL). METHODS: This was a territory-wide, retrospective, observational, cohort study of patients with CVH in Hong Kong in 2000-2018 identified from HADCL based on viral markers, diagnosis codes, and antiviral treatment for chronic hepatitis B and/or C. The cohort was randomly split into training and validation cohorts in a 7:3 ratio. Five popular machine learning methods, namely, logistic regression, ridge regression, AdaBoost, decision tree, and random forest, were performed and compared to find the best prediction model. RESULTS: A total of 124,006 patients with CVH with complete data were included to build the models. In the training cohort (n = 86,804; 6,821 HCC), ridge regression (area under the receiver operating characteristic curve [AUROC] 0.842), decision tree (0.952), and random forest (0.992) performed the best. In the validation cohort (n = 37,202; 2,875 HCC), ridge regression (AUROC 0.844) and random forest (0.837) maintained their accuracy, which was significantly higher than those of HCC risk scores: CU-HCC (0.672), GAG-HCC (0.745), REACH-B (0.671), PAGE-B (0.748), and REAL-B (0.712) scores. The low cut-off (0.07) of HCC ridge score (HCC-RS) achieved 90.0% sensitivity and 98.6% negative predictive value (NPV) in the validation cohort. The high cut-off (0.15) of HCC-RS achieved high specificity (90.0%) and NPV (95.6%); 31.1% of patients remained indeterminate. CONCLUSIONS: HCC-RS from the ridge regression machine learning model accurately predicted HCC in patients with CVH. These machine learning models may be developed as built-in functional keys or calculators in electronic health systems to reduce cancer mortality. LAY SUMMARY: Novel machine learning models generated accurate risk scores for hepatocellular carcinoma (HCC) in patients with chronic viral hepatitis. HCC ridge score was consistently more accurate than existing HCC risk scores. These models may be incorporated into electronic medical health systems to develop appropriate cancer surveillance strategies and reduce cancer death.

Intra-Rater and Inter-Rater Reliability of Tongue Coating Diagnosis in Traditional Chinese Medicine Using Smartphones: Quasi-Delphi Study.

BACKGROUND: There is a growing trend in the use of mobile health (mHealth) technologies in traditional Chinese medicine (TCM) and telemedicine, especially during the coronavirus disease (COVID-19) outbreak. Tongue diagnosis is an important component of TCM, but also plays a role in Western medicine, for example in dermatology. However, the procedure of obtaining tongue images has not been standardized and the reliability of tongue diagnosis by smartphone tongue images has yet to be evaluated. OBJECTIVE: The first objective of this study was to develop an operating classification scheme for tongue coating diagnosis. The second and main objective of this study was to determine the intra-rater and inter-rater reliability of tongue coating diagnosis using the operating classification scheme. METHODS: An operating classification scheme for tongue coating was developed using a stepwise approach and a quasi-Delphi method. First, tongue images (n=2023) were analyzed by 2 groups of assessors to develop the operating classification scheme for tongue coating diagnosis. Based on clinicians' (n=17) own interpretations as well as their use of the operating classification scheme, the results of tongue diagnosis on a representative tongue image set (n=24) were compared. After gathering consensus for the operating classification scheme, the clinicians were instructed to use the scheme to assess tongue features of their patients under direct visual inspection. At the same time, the clinicians took tongue images of the patients with smartphones and assessed tongue features observed in the smartphone image using the same classification scheme. The intra-rater agreements of these two assessments were calculated to determine which features of tongue coating were better retained by the image. Using the finalized operating classification scheme, clinicians in the study group assessed representative tongue images (n=24) that they had taken, and the intra-rater and inter-rater reliability of their assessments was evaluated. RESULTS: Intra-rater agreement between direct subject inspection and tongue image inspection was good to very good (Cohen κ range 0.69-1.0). Additionally, when comparing the assessment of tongue images on different days, intra-rater reliability was good to very good (κ range 0.7-1.0), except for the color of the tongue body (κ=0.22) and slippery tongue fur (κ=0.1). Inter-rater reliability was moderate for tongue coating (Gwet AC2 range 0.49-0.55), and fair for color and other features of the tongue body (Gwet AC2=0.34). CONCLUSIONS: Taken together, our study has shown that tongue images collected via smartphone contain some reliable features, including tongue coating, that can be used in mHealth analysis. Our findings thus support the use of smartphones in telemedicine for detecting changes in tongue coating.

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.

Incremental linear discriminant analysis for face recognition.

Dimensionality reduction methods have been successfully employed for face recognition. Among the various dimensionality reduction algorithms, linear (Fisher) discriminant analysis (LDA) is one of the popular supervised dimensionality reduction methods, and many LDA-based face recognition algorithms/systems have been reported in the last decade. However, the LDA-based face recognition systems suffer from the scalability problem. To overcome this limitation, an incremental approach is a natural solution. The main difficulty in developing the incremental LDA (ILDA) is to handle the inverse of the within-class scatter matrix. In this paper, based on the generalized singular value decomposition LDA (LDA/GSVD), we develop a new ILDA algorithm called GSVD-ILDA. Different from the existing techniques in which the new projection matrix is found in a restricted subspace, the proposed GSVD-ILDA determines the projection matrix in full space. Extensive experiments are performed to compare the proposed GSVD-ILDA with the LDA/GSVD as well as the existing ILDA methods using the face recognition technology face database and the Carneggie Mellon University Pose, Illumination, and Expression face database. Experimental results show that the proposed GSVD-ILDA algorithm gives the same performance as the LDA/GSVD with much smaller computational complexity. The experimental results also show that the proposed GSVD-ILDA gives better classification performance than the other recently proposed ILDA algorithms.

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.

A novel incremental principal component analysis and its application for face recognition.

Principal component analysis (PCA) has been proven to be an efficient method in pattern recognition and image analysis. Recently, PCA has been extensively employed for face-recognition algorithms, such as eigenface and fisherface. The encouraging results have been reported and discussed in the literature. Many PCA-based face-recognition systems have also been developed in the last decade. However, existing PCA-based face-recognition systems are hard to scale up because of the computational cost and memory-requirement burden. To overcome this limitation, an incremental approach is usually adopted. Incremental PCA (IPCA) methods have been studied for many years in the machine-learning community. The major limitation of existing IPCA methods is that there is no guarantee on the approximation error. In view of this limitation, this paper proposes a new IPCA method based on the idea of a singular value decomposition (SVD) updating algorithm, namely an SVD updating-based IPCA (SVDU-IPCA) algorithm. In the proposed SVDU-IPCA algorithm, we have mathematically proved that the approximation error is bounded. A complexity analysis on the proposed method is also presented. Another characteristic of the proposed SVDU-IPCA algorithm is that it can be easily extended to a kernel version. The proposed method has been evaluated using available public databases, namely FERET, AR, and Yale B, and applied to existing face-recognition algorithms. Experimental results show that the difference of the average recognition accuracy between the proposed incremental method and the batch-mode method is less than 1%. This implies that the proposed SVDU-IPCA method gives a close approximation to the batch-mode PCA method.