Navigation Links
Can computers save health care? IU research shows lower costs, better outcomes

New research from Indiana University has found that machine learning - the same computer science discipline that helped create voice recognition systems, self-driving cars, and credit card fraud detection systems - can drastically improve both the cost and quality of health care in the United States.

Using an artificial intelligence framework combining Markov Decision Processes and Dynamic Decision Networks, IU School of Informatics and Computing researchers Casey Bennett and Kris Hauser show how simulation modeling that understands and predicts the outcomes of treatment could reduce health care costs by over 50 percent while also improving patient outcomes by nearly 50 percent.

The work by Hauser, an assistant professor of computer science, and Ph.D. student Bennett improves upon their earlier work that showed how machine learning could determine the best treatment at a single point in time for an individual patient.

By using a new framework that employs sequential decision-making, the previous single-decision research can be expanded into models that simulate numerous alternative treatment paths out into the future, maintain beliefs about patient health status over time even when measurements are unavailable or uncertain, and continually plan/re-plan as new information becomes available. In other words, it can "think like a doctor."

"The Markov Decision Processes and Dynamic Decision Networks enable the system to deliberate about the future, considering all the different possible sequences of actions and effects in advance, even in cases where we are unsure of the effects," Bennett said.

Moreover, the approach is non-disease-specific - it could work for any diagnosis or disorder, simply by plugging in the relevant information.

The new work addresses three vexing issues related to health care in the U.S.: rising costs expected to reach 30 percent of the gross domestic product by 2050; a quality of care where patients receive correct diagnosis and treatment less than half the time on a first visit; and a lag time of between 13 and 17 years between research and practice in clinical care.

"We're using modern computational approaches to learn from clinical data and develop complex plans through the simulation of numerous, alternative sequential decision paths," Bennett said. "The framework here easily out performs the current treatment-as-usual, case-rate/fee-for-service models of healthcare."

Bennett is also a data architect and research fellow with Centerstone Research Institute, the research arm of Centerstone, the nation's largest not-for-profit provider of community-based behavioral health care. The two researchers had access to clinical data, demographics, and other information on over 6,700 patients who had major clinical depression diagnoses, of which about 65-70 percent had co-occurring chronic physical disorders like diabetes, hypertension, and cardiovascular disease.

Using 500 randomly selected patients from that group for simulations, the two compared actual doctor performance and patient outcomes against sequential decision-making models, all using real patient data. They found great disparity in the cost per unit of outcome change when the artificial intelligence model's cost of $189 was compared to the treatment-as-usual cost of $497.

"This was at the same time that the AI approach obtained a 30 to 35 percent increase in patient outcomes," Bennett said. "And we determined that tweaking certain model parameters could enhance the outcome advantage to about 50 percent more improvement at about half the cost."

While most medical decisions are based on case-by-case, experience-based approaches, there is a growing body of evidence that complex treatment decisions might best be handled through modeling rather than intuition alone.

"Modeling lets us see more possibilities out to a further point, which is something that is hard for a doctor to do," Hauser said. "They just don't have all of that information available to them."

Using the growing availability of electronic health records, health information exchanges, large public biomedical databases, and machine learning algorithms, the researchers believe the approach could serve as the basis for personalized treatment through integration of diverse, large-scale data passed along to clinicians at the time of decision-making for each patient. Centerstone alone, Bennett noted, has access to health information on over one million patients each year.

"Even with the development of new AI techniques that can approximate or even surpass human decision-making performance, we believe that the most effective long term path could be combining artificial intelligence with human clinicians," Bennett said. "Let humans do what they do well, and let machines do what they do well. In the end, we may maximize the potential of both."


Contact: Steve Chaplin
Indiana University

Related medicine news :

1. Community health workers help type 2 diabetes care
2. Common Causes of Memory Slips, From the February 2013 Harvard Men's Health Watch
3. Healthentic Welcomes Delta Dental Customers for User Group Conference, Strategy Sessions
4. Yumi Media Encourages Vegetarianism For Heart Health As Reported In the Independent Florida Alligator
5. shifting its focus onto new sustainable weight loss strategies
6. Author, relationship expert Donna Barnes dishes healthy habits
7. Bel Marra Health Reports on a New Study: Mixed Weight Couples are More Likely to Have Unhappy Marriages
8. Everyday Activities May Have Same Health Benefits as Going to Gym
9. Zion Health Announces Release of New Line of Home Remedies: Kanwa Whole Body Detox teas for Stomach Pain, Ulcers, and Skin Allergies Now available at Bee Health E in Doug
10. interview with Dr. Mark Mitchelson on Weight Loss
11. Zane Benefits Publishes New Information on the Individual Health Insurance Mandate Tax Penalty
Post Your Comments:
Related Image:
Can computers save health care? IU research shows lower costs, better outcomes
(Date:11/30/2015)... , ... November 30, 2015 , ... ... – Kreithen”), one of the leading plastic surgery practices in Florida, is proud ... chosen to consult for surgical innovations giant Ethicon Inc., a Johnson & Johnson ...
(Date:11/30/2015)... ... November 30, 2015 , ... The successful filing of an Investigational New ... is so important to this key industry segment, Regis Technologies has decided to sponsor ... December 4th at 11am EST. , Federal law does not allow new drugs to ...
(Date:11/30/2015)... ... November 30, 2015 , ... Healthjump, Inc. announced ... a Healthcare IT consulting, development and support company. The purchase will expand the ... within DataTrade to extend the services currently provided by Healthjump. , ...
(Date:11/30/2015)... ... , ... GKhair & Tibolli team members and artists were excited and proud ... 8th and 9th at the Puerto Rico Convention Center, San Juan Puerto Rico. The ... of the line fashion journalists. The San Juan Beauty Show carries immense credibility among ...
(Date:11/30/2015)... Georgia (PRWEB) , ... November 30, 2015 , ... ... for healthcare professionals worldwide today released the results of a survey of educational ... East and Africa found a growing global demand for high quality online and ...
Breaking Medicine News(10 mins):
(Date:11/30/2015)... YORK , Nov. 30, 2015 Cumberland Pharmaceuticals ... will present live at on December 3, 2015. ... --> TIME: 3:15p.m. ET LINK: ... ET LINK: --> ... online event where investors are invited to ask the company ...
(Date:11/30/2015)... Nov. 30, 2015 Varian Medical Systems (NYSE: VAR ... educational partnership with Apollo Hospitals Group, the largest hospital chain in ... help train radiation technologists in the country. The MoU was signed ... Knowledge, and Ashok Kakkar , Varian,s India ... India , Varian intends to deploy its Access ...
(Date:11/30/2015)... and BOSTON , November 30, 2015 ... develop potential new medicines directed at up to 10 ... --> PFE ) to research and develop ... protein-coupled receptor (GPCR) targets across multiple therapeutic areas. ... drug discovery and development company and wholly-owned subsidiary of ...
Breaking Medicine Technology: