Big health data: the new frontier for cardiovascular disease

Despite improvement in diagnosis and management, cardiovascular disease (CVD) is the leading cause of death and hospitalization throughout the world. The expansion of digital cardiology presents outstanding opportunities for clinicians, researchers, and health care administrators to improve outcomes and sustainability of health systems. Electronic big health data combining electronic health records (EHRs) from diverse individuals across a wide variety of platforms may provide a real-time solution to questions and problems relating to health. Very large population studies based on EHR are efficient and cost-effective, and offer an alternative to traditional research approaches. Indeed, digital cardiology can help researchers to enhance, diagnose, and manage CVD using dedicated algorithms that allow targeted and personalized CVD treatments

Social media influencers in cardiology/metabolism—a force for good or evil?

Social media use within medicine has undeniably risen within the last decade, paralleling a trend in wider society. Twitter, with its threads and quiz elements, has become a prominent and accessible route of information distribution and debate in medicine. But is it a force for good or for harm?

The implantable loop recorder in high-risk syncope

: Syncope is a common presentation, with the main challenge being identification of higher-risk patients. Often, treatment decisions are complex and require close monitoring prior to making a definitive management plan. This is particularly the case in those presenting with ventricular arrhythmia (VA). We describe a case of a 64-year-old male who presents with presyncope and probable VA. The patient subsequently had an implantable loop recorder (ILR) placed, which guided the final decision to insert an implantable cardioverter defibrillator. This case illustrates the general approach to patients presenting with syncope and VA and the use of newer technology, such as the ILR, in guiding definitive management strategies.

Artificial intelligence in cardiology

In the first wave of artificial intelligence (AI), rule-based expert systems were developed, with modest success, to help generalists who lacked expertise in a specific domain. The second wave of AI, originally called artificial neural networks but now described as machine learning, began to have an impact with multilayer networks in the 1980s. Deep learning, which enables automated feature discovery, has enjoyed spectacular success in several medical disciplines, including cardiology, from automated image analysis to the identification of the electrocardiographic signature of atrial fibrillation during sinus rhythm. Machine learning is now embedded within the NHS Long-Term Plan in England, but its widespread adoption may be limited by the “black-box” nature of deep neural networks.

Which app is right for my CVD patient?

Cardiovascular disease is a leading cause of mortality and morbidity, and despite efforts to identify and control cardiovascular risk factors, significant disease burden remains. As traditional strategies to reduce cardiovascular risk are challenged by lack of resources and growing populations, new strategies are deployed, including the use of smartphone applications (apps) designed to help patients manage their risk factors. For cardiovascular disease, some apps specifically address one risk factor, but others include a more holistic approach to manage multiple risk factors at once for primary and secondary prevention, whereas others serve as virtual cardiac rehabilitation intervention support. App stores show thousands of options in each app category, making it difficult to select the appropriate ones to recommend to patients. Very few apps in the app stores are rigorously validated for clinical efficacy or safety, making selection even more challenging. To address this, health organizations worldwide have created platforms to examine and appraise mobile health apps using standardized criteria to support clinician and patient app selection decisions. Now, with the rise of the COVID-19 pandemic, prolonged lockdowns have challenged traditional models of care. Telemedicine for cardiovascular disease patients is advancing virtual cardiac rehabilitation models to replace or improve traditional care.

Avoiding big data pitfalls

Clinical decisions are based on a combination of inductive inference built on experience (ie, statistical models) and on deductions provided by our understanding of the workings of the cardiovascular system (ie, mechanistic models). In a similar way, computers can be used to discover new hidden patterns in the (big) data and to make predictions based on our knowledge of physiology or physics. Surprisingly, unlike humans through history, computers seldom combine inductive and deductive processes. An explosion of expectations surrounds the computer’s inductive method, fueled by the “big data” and popular trends. This article reviews the risks and potential pitfalls of this computer approach, where the lack of generality, selection or confounding biases, overfitting, or spurious correlations are among the commonplace flaws. Recommendations to reduce these risks include an examination of data through the lens of causality, the careful choice and description of statistical techniques, and an open research culture with transparency. Finally, the synergy between mechanistic and statistical models (ie, the digital twin) is discussed as a promising pathway toward precision cardiology that mimics the human experience.

Wearable devices in cardiology

Wearables—sensors that are externally applied to the body to measure a signal and transmit or record the data for further analysis—are an industry worth billions of dollars annually. It is technically feasible to measure activity, blood pressure, and pulse, and to detect arrhythmia and potential heart failure decompensation via wearables. Relatively few studies have assessed the clinical value of wearables, and many remain curiosities or consumer “toys.” However, through attention to demonstrating accuracy and added value, it is possible for some technologies to be incorporated into diagnostic and treatment decision-making. Barriers to such transition include patient and physician acceptability, difficulties in incorporating the data into electronic medical records, and lack of reimbursement or regulatory approval. Cardiologists are becoming increasingly familiar with this developing field, but pressure for implementation may come more from the consumer than from the health care system.

Applications of artificial intelligence in echocardiography

Artificial intelligence (AI) is a significant technological advance that underlies many aspects of modern life. Computer-aided detection is increasingly being applied to cardiovascular imaging such as echocardiography. AI improves the accuracy and reliability of echocardiographic measurements, reduces diagnostic errors, and minimizes interobserver variability. Research of, access to, and investment in AI-enhanced echocardiography has the potential to improve the diagnosis of cardiovascular disease (CVD), particularly in regional and remote areas, and allows for prognostication and risk stratification of age-related CV events. This review describes how AI-enhanced echocardiography can lead to improvements in image interpretation and in the diagnosis and prognostication of CVD. It also outlines the challenges precluding widespread adoption of AI tools in echocardiographic practice at the current time.