The evolution and revolution of artificial intelligence in hepatology: From current applications to future paradigms

Background Information technology has shifted paper-based documentation in the health care sector into a digital form, in which patient information is transferred electronically from one place to another. However, there remain challenges and issues to resolve in this domain owing to the lack of proper standards, the growth of new technologies (mobile devices, tablets, ubiquitous computing), and health care providers who are reluctant to share patient information. Therefore, a solid systematic literature review was performed to understand the use of this new technology in the health care sector. To the best of our knowledge, there is a lack of comprehensive systematic literature reviews that focus on Fast Health Interoperability Resources (FHIR)-based electronic health records (EHRs). In addition, FHIR is the latest standard, which is in an infancy stage of development. Therefore, this is a hot research topic with great potential for further research in this domain. Objective The main aim of this study was to explore and perform a systematic review of the literature related to FHIR, including the challenges, implementation, opportunities, and future FHIR applications. Methods In January 2020, we searched articles published from January 2012 to December 2019 via all major digital databases in the field of computer science and health care, including ACM, IEEE Explorer, Springer, Google Scholar, PubMed, and ScienceDirect. We identified 8181 scientific articles published in this field, 80 of which met our inclusion criteria for further consideration. Results The selected 80 scientific articles were reviewed systematically, and we identified open questions, challenges, implementation models, used resources, beneficiary applications, data migration approaches, and goals of FHIR. Conclusions The literature analysis performed in this systematic review highlights the important role of FHIR in the health care domain in the near future.

The application of artificial intelligence (AI) has been considered a revolutionary change in drug discovery and development. In 2020, the AlphaFold computer program predicted protein structures for the whole human genome, which has been considered a remarkable breakthrough in both AI applications and structural biology. Despite the varying confidence levels, these predicted structures could still significantly contribute to structure-based drug design of novel targets, especially the ones with no or limited structural information. In this work, we successfully applied AlphaFold to our end-to-end AI-powered drug discovery engines, including a biocomputational platform PandaOmics and a generative chemistry platform Chemistry42. A novel hit molecule against a novel target without an experimental structure was identified, starting from target selection towards hit identification, in a cost- and time-efficient manner. PandaOmics provided the protein of interest for the treatment of hepatocellular carcinoma (HCC) and Chemistry42 generated the molecules based on the structure predicted by AlphaFold, and the selected molecules were synthesized and tested in biological assays. Through this approach, we identified a small molecule hit compound for cyclin-dependent kinase 20 (CDK20) with a binding constant Kd value of 9.2 ± 0.5 μM ( n = 3) within 30 days from target selection and after only synthesizing 7 compounds. Based on the available data, a second round of AI-powered compound generation was conducted and through this, a more potent hit molecule, ISM042-2-048, was discovered with an average Kd value of 566.7 ± 256.2 nM ( n = 3). Compound ISM042-2-048 also showed good CDK20 inhibitory activity with an IC 50 value of 33.4 ± 22.6 nM ( n = 3). In addition, ISM042-2-048 demonstrated selective anti-proliferation activity in an HCC cell line with CDK20 overexpression, Huh7, with an IC 50 of 208.7 ± 3.3 nM, compared to a counter screen cell line HEK293 (IC 50 = 1706.7 ± 670.0 nM). This work is the first demonstration of applying AlphaFold to the hit identification process in drug discovery. A novel CDK20 small molecule inhibitor discovered by artificial intelligence based on an AlphaFold-predicted structure demonstrates the first application of AlphaFold in hit identification for efficient drug discovery.

Background The diagnosis performance of B-mode ultrasound (US) for focal liver lesions (FLLs) is relatively limited. We aimed to develop a deep convolutional neural network of US (DCNN-US) for aiding radiologists in classification of malignant from benign FLLs. Materials and methods This study was conducted in 13 hospitals and finally 2143 patients with 24,343 US images were enrolled. Patients who had non-cystic FLLs with pathological results were enrolled. The FLLs from 11 hospitals were randomly divided into training and internal validations (IV) cohorts with a 4:1 ratio for developing and evaluating DCNN-US. Diagnostic performance of the model was verified using external validation (EV) cohort from another two hospitals. The diagnosis value of DCNN-US was compared with that of contrast enhanced computed tomography (CT)/magnetic resonance image (MRI) and 236 radiologists, respectively. Findings The AUC of ModelLBC for FLLs was 0.924 (95% CI: 0.889–0.959) in the EV cohort. The diagnostic sensitivity and specificity of ModelLBC were superior to 15-year skilled radiologists (86.5% vs 76.1%, p = 0.0084 and 85.5% vs 76.9%, p = 0.0051, respectively). Accuracy of ModelLBC was comparable to that of contrast enhanced CT (both 84.7%) but inferior to contrast enhanced MRI (87.9%) for lesions detected by US. Interpretation DCNN-US with high sensitivity and specificity in diagnosing FLLs shows its potential to assist less-experienced radiologists in improving their performance and lowering their dependence on sectional imaging in liver cancer diagnosis.