Information technology is transforming healthcare, increasingly being used to radically improve care and change many of the ways in which organizations have traditionally practiced medicine. Digital approaches are changing how physicians and healthcare systems diagnose diseases, treat patients and monitor their conditions on an ongoing basis. These new iterations are coming rapidly, as technology enables care to become virtual and patient-centric. Various technologies such as artificial intelligence, natural language processing, medical devices connected via the Internet of Things, smartphone-based apps and more are giving doctors myriad options for revamping patient care. This is disrupting common notions of healthcare and, at the same time, counteracting negative perceptions some clinicians may have had about information technology to date, says Lyle Berkowitz, MD, a medical informaticist and IT entrepreneur based in Chicago.
In an era where nearly every consumer good and service -- from books and groceries to babysitting and shared rides -- can be purchased through an electronic transaction on a mobile device, it seems reasonable to think that more and more of our health care can also be managed using apps on mobile devices. Proponents of these apps see the potential of digital technologies to shift care provision from physicians' offices and hospitals to the patient's home or anywhere with reasonable Wi-Fi connectivity. The potential benefits of digital health seem particularly compelling for managing chronic conditions such as diabetes and hypertension. In these cases, providers typically prescribe multipart protocols -- including medications, dietary restrictions, and exercise -- whose success depends on patient compliance and choices that take place on a daily basis outside of the formal health care system. Chronic diseases are prevalent, affecting roughly 120 million Americans, and take a large toll on public health.
Editor's Note: The following is an excerpt from the new book Demand Better! In the following chapter they explore the striking dearth of data and persistent uncertainty that clinicians often face when having to make decisions. Myth: There is a high degree of scientific certainty in modern medicine "In America, there is no guarantee that any individual will receive high-quality care for any particular health problem. The healthcare industry is plagued with overutilization of services, underutilization of services and errors in healthcare practice." Most of us are confident that the quality of our healthcare is the finest, the most technologically sophisticated and the most scientifically advanced in the world. And for good reason--thousands of clinical research studies are published every year that indicate such findings. Hospitals advertise the latest, most dazzling techniques to peer into the human body and perform amazing lifesaving surgeries with the aid of high-tech devices. There is no question that modern medical practices are remarkable, often effective and occasionally miraculous. But there is a wrinkle in our confidence. We believe that the vast majority of what physicians do is backed by solid science.
The next 10 years will likely see a revolution in the use of cognitive technologies for health care. Admittedly, the industry has not been a leader in the use of data and analytics in the past. Multiple disconnected systems, poor data quality, and difficult-to-change patient and provider behaviors have often been part of the challenges related to health care information. "Imprecision medicine" has generally been the rule. But there are clear signs of change in the $3 trillion US health care industry1 that we believe will come to fruition over the next decade.
Adherence can be defined as "the extent to which patients take their medications as prescribed by their healthcare providers"[Osterberg and Blaschke, 2005]. World Health Organization's reports point out that, in developed countries, only about 50% of patients with chronic diseases correctly follow their treatments. This severely compromises the efficiency of long-term therapy and increases the cost of health services. We propose in this paper different models of patient drug consumption in breast cancer treatments. The aim of these different approaches is to predict medication non-adherence while giving insights to doctors of the underlying reasons of these illegitimate drop-outs. Working with oncologists, we show the interest of Machine- Learning algorithms fined tune by the feedback of experts to estimate a risk score of a patient's non-adherence and thus improve support throughout their care path.