How AI drives innovation in cardiovascular medicine.

Medicine is entering a new era in which artificial intelligence (AI) and deep learning have a measurable impact on patient care. This impact is especially evident in cardiovascular medicine. While the purpose of this short opinion paper is not to provide an in-depth review of the many applications of AI in cardiovascular medicine, we summarize some of the important advances that have taken place in this domain.

Moving towards vertically integrated artificial intelligence development.

Substantial interest and investment in clinical artificial intelligence (AI) research has not resulted in widespread translation to deployed AI solutions. Current attention has focused on bias and explainability in AI algorithm development, external validity and model generalisability, and lack of equity and representation in existing data. While of great importance, these considerations also reflect a model-centric approach seen in published clinical AI research, which focuses on optimising architecture and performance of an AI model on best available datasets. However, even robustly built models using state-of-the-art algorithms may fail once tested in realistic environments due to unpredictability of real-world conditions, out-of-dataset scenarios, characteristics of deployment infrastructure, and lack of added value to clinical workflows relative to cost and potential clinical risks. In this perspective, we define a vertically integrated approach to AI development that incorporates early, cross-disciplinary, consideration of impact evaluation, data lifecycles, and AI production, and explore its implementation in two contrasting AI development pipelines: a scalable "AI factory" (Mayo Clinic, Rochester, United States), and an end-to-end cervical cancer screening platform for resource poor settings (Paps AI, Mbarara, Uganda). We provide practical recommendations for implementers, and discuss future challenges and novel approaches (including a decentralised federated architecture being developed in the NHS (AI4VBH, London, UK)). Growth in global clinical AI research continues unabated, and introduction of vertically integrated teams and development practices can increase the translational potential of future clinical AI projects.

Addressing racial disparities in surgical care with machine learning.

There is ample evidence to demonstrate that discrimination against several population subgroups interferes with their ability to receive optimal surgical care. This bias can take many forms, including limited access to medical services, poor quality of care, and inadequate insurance coverage. While such inequalities will require numerous cultural, ethical, and sociological solutions, artificial intelligence-based algorithms may help address the problem by detecting bias in the data sets currently being used to make medical decisions. However, such AI-based solutions are only in early development. The purpose of this commentary is to serve as a call to action to encourage investigators and funding agencies to invest in the development of these digital tools.

A proposal for developing a platform that evaluates algorithmic equity and accuracy.

We are at a pivotal moment in the development of healthcare artificial intelligence (AI), a point at which enthusiasm for machine learning has not caught up with the scientific evidence to support the equity and accuracy of diagnostic and therapeutic algorithms. This proposal examines algorithmic biases, including those related to race, gender and socioeconomic status, and accuracy, including the paucity of prospective studies and lack of multisite validation. We then suggest solutions to these problems. We describe the Mayo Clinic, Duke University, Change Healthcare project that is evaluating 35.1 billion healthcare records for bias. And we propose 'Ingredients' style labels and an AI evaluation/testing system to help clinicians judge the merits of products and services that include algorithms. Said testing would include input data sources and types, dataset population composition, algorithm validation techniques, bias assessment evaluation and performance metrics.

Understanding the role of digital platforms in technology readiness.

State-of-the-art digital tools that take advantage of machine learning-derived algorithms and advanced data analytics have the potential to transform regenerative medicine by enabling investigators and clinicians to extract intelligence and actionable insights from published studies, electronic health records, pathology images and a variety of other sources. Used in isolation, however, these tools are not as effective as they can be integrated into a comprehensive strategy - a platform. We discuss the value of a platform strategy by summarizing several initiatives that have been launched at Mayo Clinic, including a clinical data analytics platform, a remote diagnostics and management platform and a virtual care system.

Redesigning COVID-19 Care With Network Medicine and Machine Learning.

Emerging evidence regarding COVID-19 highlights the role of individual resistance and immune function in both susceptibility to infection and severity of disease. Multiple factors influence the response of the human host on exposure to viral pathogens. Influencing an individual's susceptibility to infection are such factors as nutritional status, physical and psychosocial stressors, obesity, protein-calorie malnutrition, emotional resilience, single-nucleotide polymorphisms, environmental toxins including air pollution and firsthand and secondhand tobacco smoke, sleep habits, sedentary lifestyle, drug-induced nutritional deficiencies and drug-induced immunomodulatory effects, and availability of nutrient-dense food and empty calories. This review examines the network of interacting cofactors that influence the host-pathogen relationship, which in turn determines one's susceptibility to viral infections like COVID-19. It then evaluates the role of machine learning, including predictive analytics and random forest modeling, to help clinicians assess patients' risk for development of active infection and to devise a comprehensive approach to prevention and treatment.

An FP's guide to AI-enabled clinical decision support.

To better understand the capabilities and challenges of artificial intelligence and machine learning, we look at the role they can play in screening for retinopathy and colon cancer.

Targeting depressive symptoms with technology.

Interest in digital mental health, driven largely by the need to increase access to mental health services, presents new opportunities as well as challenges. This article provides a selective overview of several new approaches, including chatbots and apps, with a focus on exploring their unique characteristics. To understand the broader issues around digital mental health apps, we discuss recent reviews in this space in the context of how they can inform care today, and how these apps fail to address several important gaps. Framing apps as either tools to augment versus deliver care, we explore ongoing struggles in this space that will determine how apps are used, regulated, and reimbursed for. Realizing that many mental health apps today exist in this still undefined space and often possess no evidence, we conclude with an overview of the American Psychiatric Association (APA)'s app evaluation framework with the goal of offering a more informed approach to these digital tools.