Issue link: https://beckershealthcare.uberflip.com/i/1191144
42 DATA ANALYTICS & AI Physician viewpoint: 10 areas in which AI will transform primary care By Andrea Park T hough the integration of artificial intelligence into healthcare is mov- ing at a cautious rate, the technolo- gy continues to offer massive potential to revolutionize care delivery and outcomes. In a recent article in the Journal of Gen- eral Internal Medicine, Steven Lin, MD, and Megan Mahoney, MD, both from Stanford University, and Christine Sinsky, MD, the American Medical Association's vice president for professional satisfac- tion, described 10 areas of primary care that stand to be most enhanced by AI. Primary care, they explained, is where the technology is likely to have an impact of the "broadest and most ambitious scale." "We propose how these AI-powered innovations must augment, not subvert, the patient-physician relationship for physicians and patients to accept them," they wrote. "AI implemented poorly risks pushing humanity to the margins; done wisely, AI can free up physicians' cogni- tive and emotional space for patients, and shi the focus away from transactional tasks to personalized care." e 10 areas identified in the article are: 1. Risk prevention and intervention. 2. Population health management. 3. Medical advice and triage. 4. Risk-adjusted paneling and resourcing. 5. Device integration. 6. Digital health coaching. 7. Chart review and documentation. 8. Diagnostics 9. Clinical decision-making. 10. Practice management. n AHA: 6 crucial components for integrating AI into healthcare workforce By Andrea Park W ith the vast majority of healthcare executives citing as a major pri- ority the hiring and training of employees to take full advantage of artificial intelligence offerings, it is only a matter of time before AI completely reshapes the healthcare workforce. A report from the American Hospital Association's Center for Health Innovation, "AI and the Healthcare Workforce," describes the many ways in which AI will impact healthcare workers. The report also offers executives advice for proactively address- ing challenges associated with AI adoption, and outlines six components that will de- termine the success or failure of integrating automated processes into the workforce. "Absent these six critical success factors, even the most powerful AI technolo- gies will fail at a hospital or health system," the report notes. The list was drawn from the insights of the Center for Health Innovation's expert panel, which includes leaders from Philadelphia-based Penn Medicine; Somerville, Mass.- based Partners HealthCare; Danville, Pa.-based Geisinger; Eden Prairie, Minn.- based Optum and more. Here are those six "critical success factors": 1. Multidisciplinary team management 2. Change management 3. Culture 4. Partnering with AI consultants and vendors 5. Workflow integration 6. Project identification n AI can significantly reduce ICU false alarms, study finds Andrea Park A three-part system using machine learning was able to greatly reduce the number of false alarms caused by bedside monitors in the intensive care unit, a study shows. Researchers from Massachusetts General Hospital in Boston developed a system to improve ICU alarms, as described in npj Digital Medicine. In some cases, nearly 90 percent of these alarms have been found to be false positives, resulting in "noise disturbance, desensitization and decreased quality of care," according to the study's authors. The system was comprised of three stages: signal processing, to ensure proper an- notation of vital signs; feature extraction, to distinguish between benign noise and alarm-worthy physiological signals; and optimized machine learning, to reduce the complexity of the bedside monitors' internal models and thus improve their accuracy in deciding whether an alarm is necessary. The system was applied to a dataset previously used in the 2015 PhysioNet/ Computing in Cardiology Challenge. The researchers achieved a score on the challenge higher than those of all other previously published methods. In con- clusion, they wrote, "Such an approach therefore has the promise to improve the ICU environment for patients and healthcare providers alike." n