By Carol Marin-Vargas, National Accounts Sales Manager, Creo Wellness
Amazon does it, as does Netflix and even Yelp. Machine learning has woven itself into the fabric of shopping, eating out, entertainment and now healthcare. What has facilitated this explosion in computers capable of autonomous action and decision-making? Several important factors:
First, the unprecedented availability of massive amounts of data generated by both consumer and mobile health devices creates a fertile field of inquiry for IT developers. Mobile devices, measuring stations, hand-held or wearable technology, and electronic medical records are just a few examples of these new data sets, with more arriving on the scene daily.
Second, the continuing evolution of software enables previously unimaginable insights to be pulled from data between data sets from disparate sources. Software developers use APIs to aggregate data from native IT, mobile applications, and devices. Algorithms applied to the data that can discover new patterns of information.
Finally, the ubiquitous nature of smart applications in consumer-facing tech, as mentioned in the lead-in about Amazon, has transmuted the concept of “artificial intelligence” from scary sci-fi to an expected component of the consumer/user experience.
A recent article in Modern Healthcare magazine explored the blossoming of machine learning in the healthcare field. One of the biggest challenges, author Beth Kutscher states, is that healthcare presents
a large and complex data set—but also a highly valuable one. Buried within it are the answers to a multitude of questions that vex doctors and administrators: How can we shorten length of stay after colon surgery? Why are we seeing so many insurance denials? What is a cardiac patient’s risk of having another heart attack?
Machine learning shows promise for improving clinical care, including reducing negative drug interactions and the blossoming of genetically targeted treatments for cancer and other diseases. As algorithms are developed that can sift through heterogeneous data sets and highlight patterns, better treatment plans become available.
Here are a few examples of machine learning in action within a clinical healthcare setting:
1. Ensuring compliance for better research: One of the most important contributions of machine learning to the field of medicine and healthcare is the ability to analyze data from disparate sources in real time. An intriguing example of this in the field of pharmaceuticals is AiCure, a tech company that uses machine learning to confirm medicine ingestion for subjects of clinical drug trials. This software works through the camera function of smartphone technology to capture and confirm study compliance resulting in the increased accuracy of study outcome data.
2. Preventing medical error: Medaware, founded in 2012 and inspired by the tragic death of a nine-year-old boy prescribed the wrong drug, uses proprietary algorithms to identify and prevent prescription error. Medaware gathers patient and prescription data and compares them to historical data in real time, flagging outliers. Data generated from individual cases are also aggregated into reports that allow for institutional, patient, and physician risk mapping.
3. Better Population Health Management: Creo Wellness uses a proprietary algorithm to analyze clinical, user, and population data to create individualized wellness programs. Once risk is assessed, the Creo Wellness application delivers specific interventions tailored for each individual based on their risk. The Creo program “learns” from the behavior of each individual user and then caters further recommendations, prompts and responses to each unique profile and behavior pattern.
It may be an oversimplification, but machine learning in some ways works like a mini-medical conference, allowing for the convergence of expertise from an infinite number of fields (imaging, pharma, research, epidemiology, robotics, surgery, rehab, etc.) while pulling new insights out of the noise in real time.
Contact us for a better understanding of how to put technology to work for better health.
Creo was founded by an innovative, cross-disciplinary team of laboratory diagnostic, business finance and health care management veterans. Contact us to learn how our advanced blood testing, precision analytics, health coaching and technology build employee plans that are personalized and effective—delivering real health improvements with measurable reductions in long-term health plan costs to employers.