Using the Electronic Medical Record to Identify Patients at High Risk for Frequent Emergency Department Visits and High System Costs.

BACKGROUND A small proportion of patients account for a high proportion of healthcare use. Accurate preemptive identification may facilitate tailored intervention. We sought to determine whether machine learning techniques using text from a family practice electronic medical record can be used to predict future high emergency department use and total costs by patients who are not yet high emergency department users or high cost to the healthcare system. METHODS Text from fields of the cumulative patient profile within an electronic medical record of 43,111 patients was indexed. Separate training and validation cohorts were created. After processing, 11,905 words were used to fit a logistic regression model. The primary outcomes of interest in the 12 months after prediction were 3 or more emergency department visits and being in the top 5% in healthcare expenditures. Outcomes were assessed through linkage to administrative databases housed at the Institute for Clinical Evaluative Sciences. RESULTS In the model to predict frequent emergency department visits, after excluding patients who were high emergency department users in the previous year, the area under the receiver operating characteristic curve was 0.71. By using the same methodology, the model to predict the top 5% in total system costs had an area under the receiver operating characteristic curve of 0.76. CONCLUSIONS Machine learning techniques can be applied to analyze free text contained in electronic medical records. This dataset is more predictive of patients who will generate future high costs than future emergency department visits. It remains to be seen whether these predictions can be used to reduce costs by early interventions in this cohort of patients.

[1]  P. Donnan,et al.  Development and validation of a model for predicting emergency admissions over the next year (PEONY): a UK historical cohort study. , 2008, Archives of internal medicine.

[2]  Walter P Wodchis,et al.  Looking Beyond Income and Education: Socioeconomic Status Gradients Among Future High-Cost Users of Health Care. , 2015, American journal of preventive medicine.

[3]  A. Beck,et al.  Using a Mailed Survey to Predict Hospital Admission Among Patients Older than 80 , 1996, Journal of the American Geriatrics Society.

[4]  L. Rosella,et al.  High-cost health care users in Ontario, Canada: demographic, socio-economic, and health status characteristics , 2014, BMC Health Services Research.

[5]  Wei Luo,et al.  Risk stratification using data from electronic medical records better predicts suicide risks than clinician assessments , 2014, BMC Psychiatry.

[6]  Richard Kaplan,et al.  An Electronic Medical Record-Based Model to Predict 30-Day Risk of Readmission and Death Among HIV-Infected Inpatients , 2012, Journal of acquired immune deficiency syndromes.

[7]  S. Rana,et al.  Predicting unplanned readmission after myocardial infarction from routinely collected administrative hospital data. , 2014, Australian health review : a publication of the Australian Hospital Association.

[8]  Ying Ma,et al.  Electronic medical record-based multicondition models to predict the risk of 30 day readmission or death among adult medicine patients: validation and comparison to existing models , 2015, BMC Medical Informatics and Decision Making.

[9]  Geraint Lewis,et al.  "Impactibility models": identifying the subgroup of high-risk patients most amenable to hospital-avoidance programs. , 2010, The Milbank quarterly.

[10]  Emmett Keeler,et al.  Development of a Method to Identify Seniors at High Risk for High Hospital Utilization , 2002, Medical care.

[11]  S Purdey,et al.  Predicting and preventing avoidable hospital admissions: a review. , 2013, The journal of the Royal College of Physicians of Edinburgh.

[12]  Christian Weber,et al.  Using individualized predictive disease modeling to identify patients with the potential to benefit from a disease management program for diabetes mellitus. , 2006, Disease management : DM.

[13]  Walter P. Wodchis,et al.  A 3-year study of high-cost users of health care , 2016, Canadian Medical Association Journal.

[14]  Debra Butt,et al.  Are family physicians comprehensively using electronic medical records such that the data can be used for secondary purposes? A Canadian perspective , 2015, BMC Medical Informatics and Decision Making.

[15]  K. O'Brien,et al.  Cost-effectiveness of clinical case management for ED frequent users: results of a randomized trial. , 2008, The American journal of emergency medicine.

[16]  N. Adler,et al.  Patients in context--EHR capture of social and behavioral determinants of health. , 2015, The New England journal of medicine.

[17]  Steve Taylor,et al.  Predicting the likelihood of emergency admission to hospital of older people: development and validation of the Emergency Admission Risk Likelihood Index (EARLI). , 2007, Family practice.

[18]  E. Kinney,et al.  Health Insurance Coverage in the United States , 2002 .

[19]  Michael F. Kamali,et al.  Emergency department waiting room: many requests, many insured and many primary care physician referrals , 2013, International Journal of Emergency Medicine.

[20]  Dante Morra,et al.  Effect of a postdischarge virtual ward on readmission or death for high-risk patients: a randomized clinical trial. , 2014, JAMA.

[21]  Brian W. Powers,et al.  ACOs and High-Cost Patients. , 2016, The New England journal of medicine.

[22]  S. Lewis A system in name only--access, variation, and reform in Canada's provinces. , 2015, The New England journal of medicine.

[23]  D. Wennberg,et al.  Case finding for patients at risk of readmission to hospital: development of algorithm to identify high risk patients , 2006, BMJ : British Medical Journal.

[24]  R. Tibshirani Regression Shrinkage and Selection via the Lasso , 1996 .

[25]  Karen Tu,et al.  Evaluation of Electronic Medical Record Administrative data Linked Database (EMRALD). , 2014, The American journal of managed care.

[26]  Michael R Gionfriddo,et al.  Preventing 30-day hospital readmissions: a systematic review and meta-analysis of randomized trials. , 2014, JAMA internal medicine.

[27]  Azeem Majeed,et al.  Identifying patients at high risk of emergency hospital admissions: a logistic regression analysis. , 2006, Journal of the Royal Society of Medicine.

[28]  Joshua A. Doherty,et al.  Early prediction of septic shock in hospitalized patients. , 2010, Journal of hospital medicine.

[29]  Walter P. Wodchis,et al.  Guidelines on Person-Level Costing Using Administrative Databases in Ontario , 2013 .

[30]  Robert Gibbons,et al.  Using Electronic Health Record Data to Develop and Validate a Prediction Model for Adverse Outcomes in the Wards* , 2012, Critical care medicine.

[31]  Stuart Parker,et al.  Follow up of people aged 65 and over with a history of emergency admissions: analysis of routine admission data , 2005, BMJ : British Medical Journal.