A view from the Center

Deloitte's Life Sciences & Health Care Blog

Machine learning and predictive analytics speeds diagnoses

With headlines about Zika and Ebola getting the public’s attention, speed and efficiency are critical in diagnosing an infectious disease. Traditionally, physicians have to go through a long list of symptoms to rule out everything from influenza to an allergic reaction, but machine learning is advancing techniques and helping physicians make more accurate, timely diagnoses. Machine learning is a type of artificial intelligence (AI) that provides computers with the ability to learn without being explicitly programmed. It is similar to data mining in that both processes search through to data to identify patterns. But, instead of extracting data for humans to understand, the computers use the data to detect patterns and adjust analysis accordingly.

Machine learning is enabling real-time, automated, infectious disease detection and diagnosis through analyzing data from electronic health records, nursing triage forms, and lab results to quickly alert physicians of possible or confirmed cases of many illnesses. Some machine learning systems are able to geographically map where disease outbreaks have occurred, a useful tool for public health officials in containing an outbreak.

Some hospitals, including NorthShore University HealthSystem, Northwestern Memorial Hospital, and Loyola University Medical Center, are using machine learning for faster diagnosis and to predict what patients in the emergency room will likely need hospitalization. UPMC has its own model that merges predictive analytics with claims and local demographic data to help identify which patients are likely to show up in the emergency department in the near future.

Analysis: Machine learning is helping transform health care by automating tasks and enabling health care systems to better predict and prevent future risks. Improving the accuracy and timeliness of diagnoses and potentially improving population health by identifying illness and patterns of behavior are ways that machine learning is aiding in analysis and interventions. In the last several years, interest in machine learning and other types of AI has surged. Venture capital investments in companies developing and commercializing AI-related products and technology are growing, and global investments reached an estimated $55 billion in 2015. The future of machine learning in health care will likely move to the consumer in the form of mobile apps that can diagnose certain conditions, such as skin conditions or insect bites, by analyzing digital photos.

(Sources: David Schatsky, “Machine learning is going mobile,” DU Press, April 2016; Nathan Benaich, “Investing in Artificial Intelligence,” Tech Crunch, December, 2015)

This weekly series explores innovative breakthroughs and new technologies that are driving momentum and change in the life sciences and health care industry.

Author bio

Doug leads Deloitte Consulting LLP’s Life Sciences and Health Care practice. With 24 years of experience, he works closely with multiple top health care organizations on major clinical and enterprise transformation efforts and on large-scale technology implementation projects. Doug has extensive experience in comprehensive quality and patient safety transformations, turnaround and performance improvement in academic medical centers as well as organization/workflow redesign and technology enablement. He has served as the lead on a number of enterprise transformation initiatives with some of Deloitte’s most largest and most complex clients.