Happy Monday!
Hope everyone is doing well. As we take a deep look into Cardiology, this week we will be exploring the role of AI in Cardiology!
In modern medicine, clinical decisions are made on the basis of the presented clinical
manifestation, underlying conditions, historical data related to the manifestation, evidence of a clinical intervention, safety and efficacy data of the intervention, and access to new
evidence-based interventions. In addition to considering these complex datasets, clinicians are required to incorporate the patient risk-benefit metrics into every decision step.
Under real world circumstances, the evidence and application of novel interventional strategies are not readily available to physicians. Non-availability of clinical criteria for selecting proper interventional strategies and lack of access to patient’s genomic and pharmacogenomic profiles also hinders the decision making process. Things get more complicated when a cardiologist encounters such problems where life is readily at stake, particularly when patients suffer from cardiac arrest or cardio-vascular strokes. Availability of digital tools like AI or ML algorithms could simplify the clinical decision making process in complex clinical manifestations like a heart attack.
Evidence suggests that AI tools will certainly result in the improvement of the way evidence is produced, knowledge is organized, and then converted into clinical decisions. This integration of artificial intelligence technologies such as machine learning into day-to-day medical decision-making, would improve patient care and clinical outcome especially in Interventional Cardiology. Doctors, however, will have to maintain absolute discretion, keep an eye on individual decisions, and have the power to override algorithms in higher order clinical decisions.
In one study, deep learning algorithms clearly outperformed clinicians in predicting prognosis and future events in patients with pulmonary hypertension [1]. In another study, machine learning helped to develop a clear phenotypic classification of heart failure patients with preserved ejection fraction [2]. Cardiovascular research based on artificial intelligence tools is an ongoing field of research. Due to its potential to change the way we generate knowledge, interpret data, and make decisions, artificial intelligence may trigger uncertainties and reservations among healthcare providers and clinicians [3]. “The future of AI in cardiology and in medicine in general is bright as the collaboration between investigators and clinicians continues to excel [4].”
We hope you learned more about AI in Cardiology. Check back here next week to see more information about cardiology
Stay Safe,
Jasmine Wani - Vice President
Sources
1. Shah SJ et al., (2015). Circulation. 2015;131(3):269–279.
2. Diana Bonderman (2017). Wien Klin Wochenschr. 129(23): 866–868.
3. Mayo Clinic (2020) Algorthims and Bioethics 843-844
4. Dawes TJW, et al, (2017). Radiology. 283(2):381–390.
Commentaires