AI Can Identify Trauma Patients Who Misuse Alcohol | Loyola Medicine
Friday, February 22, 2019

Artificial Intelligence Can Identify Trauma Patients Who Misuse Alcohol

 
MAYWOOD, IL – A first-of-its kind study has demonstrated that an artificial intelligence technique can be used to identify trauma patients who misuse alcohol.
 
Researchers from Loyola Medicine and Loyola University Chicago used the technique, natural language processing, to identify alcohol misusers from clinician notes in electronic health records.
 
In 78 percent of cases, the technique was able to differentiate between patients who misused alcohol and those who did not. Corresponding author Majid Afshar, MD, MSCR, and colleagues published their findings in the Journal of the American Medical Informatics Association.
 
Dr. Afshar, a Loyola Medicine critical care physician, is an assistant professor in the Division of Pulmonary and Critical Care Medicine and Department of Public Health Sciences of Loyola University Chicago Stritch School of Medicine.
 
The study was a cross-campus collaboration that included researchers from Loyola's Burn and Shock Trauma Research Institute, Center for Health Outcomes and Informatics Research, Department of Public Health Sciences, Department of Computer Science, Department of Medicine and Department of Surgery.
 
As many as 1 in 3 trauma patients misuse alcohol, and many trauma cases are alcohol related. Previous research has shown that a traumatic injury provides an opportunity for a teachable moment. Screening, brief intervention and referral to treatment (SBIRT) can reduce subsequent alcohol consumption, decrease injury recurrence by nearly 50 percent and reduce rates of DUI arrests.
 
The brief intervention typically includes providing information on the link between drinking and injury, encouraging patients to think about how drinking may have contributed to their injuries and giving professional advice about the need to reduce risk by cutting down or quitting drinking.
 
Current screening methods employ the 10-item Alcohol Use Disorders Identification Test (AUDIT). But there are drawbacks to this screening test. Patients may not be honest when answering questions about their alcohol use or may not be able to communicate at all. Staff may not be available to administer the test, especially during nights and weekends. In addition, screening is a "resource-intensive process that imposes significant costs on a health system," Dr. Afshar and colleagues wrote.
 
Using artificial intelligence to screen for alcohol misusers potentially could overcome these problems. To test this idea, researchers sifted through electronic health records using natural language processing and machine learning. The artificial intelligence technique employs computational methods that help computers understand human language.
 
The study included records of 1,422 adult patients admitted to Loyola's Level 1 trauma center over 3 ½ years. The data included 91,045 clinician notes in electronic health records. The notes contained 16,091 medical concepts. Using natural language processing, researchers identified 16 medical concepts that predict for alcohol misuse.
 
The concepts include intoxication, neglect, drinking problems, liver imaging, sexually active, marijuana and the B1 vitamin thiamine. (Hospital patients with alcohol dependence commonly are treated for thiamine deficiency.)
 
The artificial intelligence technique likely would be affordable to trauma centers that have the expertise to use it, Dr. Afshar said. He noted that the open-source programming and linguistics software used by researchers would be free to any user. 
 
Natural language processing "has adequate predictive validity for identifying alcohol misuse in the trauma setting," Dr. Afshar and colleagues concluded. The technique "provides an automated approach to potentially overcome staffing and patient barriers for SBIRT programs at trauma centers."
 
The study was supported by grants from the National Institute of Alcoholism and Alcohol Abuse, National Institute of Drug Abuse and Loyola's Center for Health Outcomes and Informatics Research.
 
Dr. Afshar's Loyola co-authors are Andrew Phillips, MS, Jeanne Mueller, RN, Daniel To, Richard Gonzalez , MD, Ron Price, Richard Cooper, MD, Cara Joyce, PhD and Dmitriy Dligach, PhD. An additional co-author is Niranjan Karnik, MD, PhD of Rush University Medical Center.
 
The study is titled "Natural language processing and machine learning to identify alcohol misuse from the electronic health record in trauma patients: development and internal validation."
 

About Loyola Medicine

Loyola Medicine is a quaternary care system based in the western suburbs of Chicago that includes Loyola University Medical Center (LUMC) in Maywood, Gottlieb Memorial Hospital (GMH) in Melrose Park, MacNeal Hospital in Berwyn and convenient locations offering primary and specialty care services from more than 1,750 physicians throughout Cook, Will and DuPage counties. LUMC is a 547-licensed-bed hospital that includes the William G. and Mary A. Ryan Center for Heart & Vascular Medicine, the Cardinal Bernardin Cancer Center, a Level 1 trauma center, Illinois's largest burn center, a certified comprehensive stroke center and a children’s hospital. The medical center campus is also home to Loyola University Chicago Stritch School of Medicine, Loyola University Chicago Marcella Niehoff School of Nursing and the Loyola Center for Fitness. GMH is a 247-licensed-bed community hospital with 150 physician offices, an adult day care program, the Gottlieb Center for Fitness, the Loyola Center for Metabolic Surgery and Bariatric Care and the Loyola Cancer Care & Research at the Marjorie G. Weinberg Cancer Center at Melrose Park. MacNeal Hospital is a 374-bed teaching hospital with advanced inpatient and outpatient medical, surgical and psychiatric services, advanced diagnostics and treatments in a convenient community setting at eight locations. Loyola Medicine is a member of Trinity Health, one of the nation’s largest health systems with 94 hospitals in 22 states.

About Trinity Health

Trinity Health is one of the largest multi-institutional Catholic health care delivery systems in the nation, serving diverse communities that include more than 30 million people across 22 states. Trinity Health includes 93 hospitals, as well as 122 continuing care programs that include PACE, senior living facilities, and home care and hospice services. Its continuing care programs provide nearly 2.5 million visits annually. Based in Livonia, Mich., and with annual operating revenues of $17.6 billion and assets of $23.4 billion, the organization returns $1.1 billion to its communities annually in the form of charity care and other community benefit programs. Trinity Health employs about 131,000 colleagues, including 7,500 employed physicians and clinicians. Committed to those who are poor and underserved in its communities, Trinity Health is known for its focus on the country's aging population. As a single, unified ministry, the organization is the innovator of Senior Emergency Departments, the largest not-for-profit provider of home health care services — ranked by number of visits — in the nation, as well as the nation’s leading provider of PACE (Program of All Inclusive Care for the Elderly) based on the number of available programs. For more information, visit www.trinity-health.org. You can also follow @TrinityHealthMI on Twitter.