Boston Hospitals Use Machine Learning to Manage Most-Expensive Illnesses

Algorithms predict hospitalizations for heart disease or diabetes one year in advance

While debate drags on about legislation, regulations, and other measures to improve the U.S. health care system, a new wave of analytics and technology could help cut costly and unnecessary hospitalizations while improving outcomes for patients, according to an article in the Harvard Business Review.

In an ongoing effort with Boston-area hospitals, including the Boston Medical Center and Brigham and Women’s Hospital, Dr. Yannis Paschalidis and his colleagues at Boston University’s Center for Information and Systems Engineering found that they could use machine-learning algorithms to predict hospitalizations due to heart disease or diabetes approximately one year in advance with an accuracy rate of up to 82%. The team is also working with the Department of Surgery at the Boston Medical Center and can predict readmissions within 30 days of general surgery.

The hospitals provide Paschalidis and his colleagues with patients’ anonymous electronic health records, which include information on demographics, diagnoses, admissions, procedures, vital signs at doctor visits, prescribed medications, and laboratory results. The investigators then use their algorithms to predict who might have to be hospitalized. This gives the hospital a chance to intervene, to treat the disease more aggressively in an outpatient setting, and to avoid a costly hospitalization while improving the patient’s condition, according to Paschalidis.

The potential benefits from applying machine-learning analytics in health care are enormous, Paschilidis says. Based on a study of one year’s worth of hospital admissions in the U.S., the Agency for Healthcare Research and Quality estimated that 4.4 million of those admissions––totaling $30.8 billion in costs––could have been prevented. Of the $30.8 billion, $9.0 billion was for patients with heart diseases, and $5.8 billion was for patients with complications from diabetes.

“That’s half of all unnecessary hospitalizations,” Paschalidis points out.

Ongoing U.S. reforms in health care that link payments with outcomes are forcing hospitals to assume more financial risks, he says. In response, hospitals are increasingly making analytics and new technologies a key part of their operations. Business analytics widely used in the transportation industry by airlines and shipping companies are beginning to be employed to schedule operating rooms and staffing. Other algorithms are being developed to assist physicians in making diagnoses. For example, Paschalidis and his team have developed methods to automatically titrate medications in intensive care units in response to the patients’ conditions.

Paschalidis acknowledges that analytics and data-driven personalized medicine and health monitoring have risks. “Do we want our employers and health insurers to know the status of our health and the risks we face?” he asks. The privacy, security, and reliability of new systems and methods are also critical concerns. But algorithms—the foundation of encryption methods, privacy-preserving data processing, and intrusion- and fraud-detection systems—could help alleviate those problems, Pashaclidis says.

Source: Harvard Business Review; May 31, 2017.