Narrative review of the role of artificial intelligence to improve aortic valve disease management

Abstract

Valvular heart disease (VHD) is a chronic progressive condition with an increasing prevalence in the Western world due to aging populations. VHD is often diagnosed at a late stage when patients are symptomatic and the outcomes of therapy, including valve replacement, may be sub-optimal due the development of secondary complications, including left ventricular (LV) dysfunction. The clinical application of artificial intelligence (AI), including machine learning (ML), has promise in supporting not only early and more timely diagnosis, but also hastening patient referral and ensuring optimal treatment of VHD. As physician auscultation lacks accuracy in diagnosis of significant VHD, computer-aided auscultation (CAA) with the help of a commercially available digital stethoscopes improves the detection and classification of heart murmurs. Although used little in current clinical practice, CAA can screen large populations at low cost with high accuracy for VHD and faciliate appropriate patient referral. Echocardiography remains the next step in assessment and planning management and AI is delivering major changes in speeding training, improving image quality by pattern recognition and image sorting, as well as automated measurement of multiple variables, thereby improving accuracy. Furthermore, AI then has the potential to hasten patient disposal, by automated alerts for red-flag findings, as well as decision support in dealing with results. In management, there is great potential in ML-enabled tools to support comprehensive disease monitoring and individualized treatment decisions. Using data from multiple sources, including demographic and clinical risk data to image variables and electronic reports from electronic medical records, specific patient phenotypes may be identified that are associated with greater risk or modeled to the estimate trajectory of VHD progression. Finally, AI algorithms are of proven value in planning intervention, facilitating transcatheter valve replacement by automated measurements of anatomical dimensions derived from imaging data to improve valve selection, valve size and method of delivery.

Integration of Artificial Intelligence, Blockchain, and Wearable Technology for Chronic Disease Management: A New Paradigm in Smart Healthcare

“…In the past few years, the use of AI in the diagnosis and treatment of cardiovascular disease has grown, which has improved the quality of care, cost-effectiveness, and mortality in patients with heterogeneous diseases, such as pulmonary hypertension, coronary artery disease, heart failure, and cardiomyopathy [30] . AI enables continuous real-time monitoring, whether in the home or medical settings and has built-in methods of care that can be upgraded and intervened upon demand, ultimately enabling patients to self-manage their condition and to improve their prognosis.…”

“…Moreover, combined with the widespread availability of broadband technology, the rapid development and low cost of hand-held echocardiography devices have brought new opportunities for screening and early diagnosis of valvular heart disease in the community. Once images have been acquired, the AI-based system can accelerate appropriate intervention in valvular heart disease, and the automated alerts from an integrated hand-held echocardiogram device with electronic sensors can be delivered directly to healthcare providers [29,30] . This form of convenient data relay can significantly improve the timeliness of clinical treatment.…”

“…In treatment planning, as recommended by the guidelines, the most appropriate treatment should be determined by a multidisciplinary heart team, usually taking into account patient comorbidities, age, degree of weakness, degree of independence, anatomic conditions, preoperative mortality, and patient preferences [31] . Clinical decision support systems based on AI have been proven to assist preoperative planning by incorporating imaging data from echocardiography or computed tomography into algorithms that help to determine the appropriate valve size (and even the valve type) for interventional therapy in a fast and reliable manner [28][29][30][31] .…”

“…In some cases, machine learning often encounters bottlenecks due to the difficulty of obtaining sufficient physiological health data. The challenge is to compile health information from diverse sources, such as wearable devices, portable ECG monitors, existing hospital-based electronic medical records, biobanks, and nonmedical data from social media and activity logs [30] . Based on blockchain technology, a natural foundation can be formed to standardize the health data structure for AI training, clinical trials, and supervision.…”

“…The second part is to make a comparative analysis and to evaluate the intelligent algorithm model in cardiovascular disease [31] . Blockchain technology provides the capacity to trace independent block (record) types and dissect granular data [25,30,31] . By integrating blockchain and AI, the complementary advantages can be achieved at the technical level, which can promote the quality of personalized cardiovascular treatment by greatly improving the availability of data for AI development and training, sharing proprietary algorithms for promotion, decentralizing databases of different providers or medical systems, and motivating solutions that improve results compared to other providers or medical systems [32] .…”