Parallel Session 5 - Artificial Intelligence

To foster the healthcare transformation in HA, Artificial Intelligence (AI) is adopted together with machine learning and data analytics to drive innovations for data-driven care, service quality improvement and automation.  AI-enabled solutions are able to enhance the quality & safety of care, reduce human errors and relieving workload of frontline staff, by providing clinical decision support, early detection of conditions as well as streamlining the workflows in both clinical and non-clinical aspects.
Over the past few years, a wide range of AI initiatives have been developed and deployed, from clinical to non-clinical applications, from in-house to co-delivered vendor solutions. With the support from frontline staff and Head Office Divisions, a governance structure was set up to oversee the strategic planning, development and execution of AI initiatives. To put forward AI researches and technology ideas into service benefits, the HA AI Lab which equipped with advanced AI computing infrastructure was established in 2021. By collaborating with various stakeholders, more insightful AI initiatives will be rolled out to pave the AI journey in HA, as well as support HA’s strategic goals for the provision of Smart Care and the development of Smart Hospitals.

Using Artificial Intelligence in health care seems like a futuristic technology, but it is something that's being used to complement and support clinical workflow. Radiology has had the lead, partly because Artificial Intelligence is driven by data and radiology has a lot of digital data already ready to be used by Artificial Intelligence. Imaging Artificial Intelligence is mainly implemented in radiology worldwide. With a well-established pipeline, the support from radiology and imaging Artificial Intelligence can be extended to frontline clinicians especially hospitals and clinics under Hong Kong Hospital Authority. There has been a good start in imaging Artificial Intelligence journey in Hospital Authority, as one of the leader in the journey, the development and implementation should address clinical workflow with quality and safety gets balanced. Artificial Intelligence has shown impressive accuracy and sensitivity in the identification of image abnormalities. On the other hand, detection of subtle changes of indeterminate significance will occur with improved sensitivity, navigating between subtle detection and over-diagnosis is never an easy task. The development, implementation and challenges of translating Artificial Intelligence technology for Chest X-ray and Hip X-ray into clinical practice will be shared. Other onboarding clinical Artificial Intelligence to support our frontline clinicians will be also included.

Hepatocellular carcinoma (HCC) is the deadliest complications of chronic viral hepatitis. Precise HCC risk prediction facilitates appropriate surveillance strategy and reduces cancer mortality. Various novel machine-learning (ML) and artificial intelligence (AI) models are being developed and validated to predict HCC. Our team has the privilege to leverage the terrific Hospital Authority data to carry out a territory-wide study in Hong Kong from year 2000 to 2018 identified based on comprehension clinical data, namely viral markers, diagnosis codes and antiviral treatment for chronic viral hepatitis. The cohort was randomly split into training and validation cohorts in 7:3 ratio. Five state-of-the-art ML methods including logistic regression, ridge regression, AdaBoost, decision tree and random forest were compared for the best prediction model. We included 124,006 patients with chronic viral hepatitis and complete data to build the models. In the training cohort (n=86,804, 6,821 HCC), ridge regression (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 accuracies and significantly higher than 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. Low cut-off (0.07) of HCC ridge score (HCC-RS) achieved 90.0% sensitivity and 98.6% negative predictive values (NPV) in the validation cohort. High cut-off (0.15) of HCC-RS achieved high specificity (90.0%) and NPV (95.6%); 31.1% of patients remained indeterminate. In conclusion, HCC-RS from ridge regression machine-learning model accurately predicts HCC in CVH patients. These machine-learning models may be developed as built-in functional keys or calculators in the electronic health systems to reduce cancer mortality. Our study is one of the most recent examples of how to apply ML and AI in HCC risk prediction. Some other AI models make good use of radiomics and clinical data through the Convolutional Neural Network (CNN)-based modelling to predict HCC risk. ML and AI models would facilitate the prediction of HCC risk, assist but not replace our clinical judgment and decision-making process.