Long Article

Can Artificial Intelligence Reshape Cardiac Care?

Today, individual cardiology patients come with their own big datasets for physicians to sort through as molecular profiling, diagnostic imaging, electronic health records, and mobile monitoring devices become mainstream.1,2 Acquiring and integrating each patient’s vast amount of data into coherent, actionable, and personalized treatment in real-time is reaching an unmanageable level of complexity.1

And when the amount of information reaches crosses over the manageability threshold, care delivery becomes highly variable, resulting in increased costs and mortality rates.1 Investigators from one study found 83 percent of patients with a history of atrial fibrillation who experienced an acute ischemic stroke were never prescribed guideline-recommended anticoagulation therapy.1,3 Researchers conducting a separate review of heart failure patients reported only one percent of those who were eligible for simultaneous treatment with all guideline-recommended medications received the target doses.1,4

Although there are many factors that can influence this type of medical failure, one well-studied cause is the breakdown in communication from physician to patient to provide guideline-directed therapy; the root of this problem is most often due to the lack of familiarity with and timely access to critical guideline information and updates.1 But as data analysis becomes increasingly sophisticated, one strategy that physicians could use to effectively combat the overload of health-related data is artificial intelligence (AI).5

Cardiology begins to embrace AI

Through market analysis reports, it's clear that healthcare AI tools are becoming more prominent.6 In 2016, one consulting agency projected that AI in healthcare was expected to grow by 40 percent in six years, with the potential to improve patient outcomes by 30 to 40 percent and reduce treatment costs by up to 50 percent.1,7

One new AI tool, provides streamlined and immediate access to guideline-recommended therapy to ensure a more consistent level of care.1,8 It does this by creating a digital replica, also known as a digital twin, of each patient by combining data from electronic health records, imaging studies, payer databases, and other available data generated by remote monitoring, wearable or implantable devices.1,8 Each patient’s data is analyzed and compared with the most current evidence-based recommendations so that customized, real-time therapy guidance can be formulated and sent directly to the physician, caregiver, or patient.1,8

Future outlook

Implementing AI in cardiology is expected to enhance and increase capabilities through the development of tools that tackle their broad data-rich environments.5 As the quantity of individual patient data grows to include external automatic monitoring of streaming data from IoT and other complex biomedical sources, cardiologists will need to integrate algorithmic methods into clinical practice.5 Doing so will enable physicians to improve patient outcomes because of AI’s ability to process, analyze, and interpret more data more deeply than has ever been humanly possible.5 Ultimately, AI will increase the efficiency, convenience, personalization, and effectiveness of clinical practice being called upon by patients, healthcare systems, and reimbursement policies.5

  1. Outlining How Artificial Intelligence May Help Adhere to Cardiac Care Guidelines. Diagnostic and Interventional Cardiology https://www.dicardiology.com/article/outlining-how-artificial-intelligence-may-help-adhere-cardiac-care-guidelines Accessed 12/21/2018
  2. Lost in Thought — The Limits of the Human Mind and the Future of Medicine. NEJM New England Journal of Medicine. https://www.nejm.org/doi/full/10.1056/NEJMp1705348 Accessed 12/21/2018
  3. Association of Preceding Antithrombotic Treatment With Acute Ischemic Stroke Severity and In-Hospital Outcomes Among Patients With Atrial Fibrillation. Journal of the American Medical Association https://jamanetwork.com/journals/jama/fullarticle/2610336 Accessed 12/21/2018
  4. Medical Therapy for Heart Failure With Reduced Ejection Fraction
    The CHAMP-HF Registry. Journal of the American College of Cardiology http://www.onlinejacc.org/content/72/4/351 Accessed 12/21/2018
  5. Artificial Intelligence in Cardiology. JACC Journal of the American College of Cardiology https://www.sciencedirect.com/science/article/pii/S0735109718344085 Accessed 12/21/2018
  6. Healthcare Artificial Intelligence Market to Top $34B by 2025. Health IT Analytics https://healthitanalytics.com/news/healthcare-artificial-intelligence-market-to-top-34b-by-2025 Accessed 12/21/2018
  7. From $600 M to $6 Billion, Artificial Intelligence Systems Poised for Dramatic Market Expansion in Healthcare. Frost & Sullivan https://ww2.frost.com/news/press-releases/600-m-6-billion-artificial-intelligence-systems-poised-dramatic-market-expansion-healthcare Accessed 12/21/2018
  8. HealthReveal gets $10.8 million to bring machine learning to chronic condition care. MobiHealth News https://www.mobihealthnews.com/content/healthreveal-gets-108-million-bring-machine-learning-chronic-condition-care Accessed 12/21/2018