Electronic Health Record Mortality Prediction Model for Targeted Palliative Care Among Hospitalized Medical Patients: a Pilot Quasi-experimental Study

Development of electronic health record (EHR) prediction models to improve palliative care delivery is on the rise, yet the clinical impact of such models has not been evaluated. To assess the clinical impact of triggering palliative care using an EHR prediction model. Pilot prospective before-after study on the general medical wards at an urban academic medical center. Adults with a predicted probability of 6-month mortality of ≥ 0.3. Triggered (with opt-out) palliative care consult on hospital day 2. Frequencies of consults, advance care planning (ACP) documentation, home palliative care and hospice referrals, code status changes, and pre-consult length of stay (LOS). The control and intervention periods included 8 weeks each and 138 admissions and 134 admissions, respectively. Characteristics between the groups were similar, with a mean (standard deviation) risk of 6-month mortality of 0.5 (0.2). Seventy-seven (57%) triggered consults were accepted by the primary team and 8 consults were requested per usual care during the intervention period. Compared to historical controls, consultation increased by 74% (22 [16%] vs 85 [63%], P < .001), median (interquartile range) pre-consult LOS decreased by 1.4 days (2.6 [1.1, 6.2] vs 1.2 [0.8, 2.7], P = .02), ACP documentation increased by 38% (23 [17%] vs 37 [28%], P = .03), and home palliative care referrals increased by 61% (9 [7%] vs 23 [17%], P = .01). There were no differences between the control and intervention groups in hospice referrals (14 [10] vs 22 [16], P = .13), code status changes (42 [30] vs 39 [29]; P = .81), or consult requests for lower risk (< 0.3) patients (48/1004 [5] vs 33/798 [4]; P = .48). Targeting hospital-based palliative care using an EHR mortality prediction model is a clinically promising approach to improve the quality of care among seriously ill medical patients. More evidence is needed to determine the generalizability of this approach and its impact on patient- and caregiver-reported outcomes.

[1]  Skipper Seabold,et al.  Statsmodels: Econometric and Statistical Modeling with Python , 2010, SciPy.

[2]  S Lemeshow,et al.  Factors affecting the performance of the models in the Mortality Probability Model II system and strategies of customization: a simulation study. , 1996, Critical care medicine.

[3]  D. Asch,et al.  Harnessing the power of default options to improve health care. , 2007, The New England journal of medicine.

[4]  M. Ersek,et al.  Associations between Timing of Palliative Care Consults and Family Evaluation of Care for Veterans Who Die in a Hospice/Palliative Care Unit. , 2017, Journal of palliative medicine.

[5]  S. Meghani,et al.  Palliative Care Consultation for Goals of Care and Future Acute Care Costs: A Propensity-Matched Study , 2018, The American journal of hospice & palliative care.

[6]  Andrew Y. Ng,et al.  Improving palliative care with deep learning , 2017, 2017 IEEE International Conference on Bioinformatics and Biomedicine (BIBM).

[7]  J. Eickhoff,et al.  A Quantitative Study of Triggered Palliative Care Consultation for Hospitalized Patients With Advanced Cancer. , 2015, Journal of pain and symptom management.

[8]  Ewout W. Steyerberg,et al.  Big Data and Predictive Analytics: Recalibrating Expectations , 2018, JAMA.

[9]  S. Halpern,et al.  A Research Agenda for High-Value Palliative Care , 2018, Annals of Internal Medicine.

[10]  L. Deliens,et al.  Referral to palliative care in COPD and other chronic diseases: a population-based study. , 2013, Respiratory medicine.

[11]  D. Meier,et al.  Outcomes That Define Successful Advance Care Planning: A Delphi Panel Consensus. , 2018, Journal of pain and symptom management.

[12]  C. Hartog,et al.  Goal-concordant care in the ICU: a conceptual framework for future research , 2017, Intensive Care Medicine.

[13]  Gloria P. Lipori,et al.  MySurgeryRisk: Development and Validation of a Machine-learning Risk Algorithm for Major Complications and Death After Surgery , 2019, Annals of surgery.

[14]  V. Allgar,et al.  Triggers in advanced neurological conditions: prediction and management of the terminal phase , 2013, BMJ Supportive & Palliative Care.

[15]  I. Kohane,et al.  Big Data and Machine Learning in Health Care. , 2018, JAMA.

[16]  D. Lupu.  Estimate of current hospice and palliative medicine physician workforce shortage. , 2010, Journal of pain and symptom management.

[17]  D. Meier,et al.  Identifying patients in need of a palliative care assessment in the hospital setting: a consensus report from the Center to Advance Palliative Care. , 2011, Journal of palliative medicine.

[18]  Alona Muzikansky,et al.  Early palliative care for patients with metastatic non-small-cell lung cancer. , 2010, The New England journal of medicine.

[19]  S. H. Regli,et al.  Machine Learning Approaches to Predict 6-Month Mortality Among Patients With Cancer , 2019, JAMA network open.

[20]  Spencer S. Jones,et al.  Development and Evaluation of an Automated Machine Learning Algorithm for In-Hospital Mortality Risk Adjustment Among Critical Care Patients* , 2018, Critical care medicine.

[21]  D. Meier,et al.  Impact of Staffing on Access to Palliative Care in U.S. Hospitals. , 2015, Journal of palliative medicine.

[22]  D. Meier,et al.  A National Strategy For Palliative Care. , 2017, Health affairs.

[23]  V. Chopra,et al.  A Model to Improve Hospital-Based Palliative Care: The Palliative Care Redistribution Integrated System Model (PRISM) , 2018, Journal of hospital medicine.

[24]  L. Yessayan,et al.  Preliminary Analysis of a Modified Screening Tool to Increase the Frequency of Palliative Care Consults , 2018, The American journal of hospice & palliative care.

[25]  Maggie M Rogers,et al.  The Growth of Palliative Care in U.S. Hospitals: A Status Report , 2016, Journal of palliative medicine.

[26]  K. Todd,et al.  A rapid two-stage screening protocol for palliative care in the emergency department: a quality improvement initiative. , 2011, Journal of pain and symptom management.

[27]  J. Tulsky,et al.  Achieving Goal-Concordant Care: A Conceptual Model and Approach to Measuring Serious Illness Communication and Its Impact. , 2018, Journal of palliative medicine.

[28]  Dylan S. Small,et al.  Rationale and Design of the Randomized Evaluation of Default Access to Palliative Services (REDAPS) Trial. , 2016, Annals of the American Thoracic Society.

[29]  J. Quinn,et al.  Validation of the Social Security Death Index (SSDI): An Important Readily-Available Outcomes Database for Researchers , 2008, The western journal of emergency medicine.

[30]  Kathie S Zimbro,et al.  Making the Case for Palliative Care at the System Level: Outcomes Data. , 2016, Journal of palliative medicine.

[31]  Guanhua Chen,et al.  Calibration Drift Among Regression and Machine Learning Models for Hospital Mortality , 2017, AMIA.

[32]  S. Halpern.  Using Default Options and Other Nudges to Improve Critical Care , 2018, Critical care medicine.

[33]  S. Morton,et al.  Association Between Palliative Care and Patient and Caregiver Outcomes , 2016 .

[34]  H. Gruhler,et al.  Determining Palliative Care Penetration Rates in the Acute Care Setting. , 2017, Journal of pain and symptom management.

[35]  Maryam Behta,et al.  The Impact of Inpatient Palliative Care Consultations on 30-Day Hospital Readmissions. , 2015, Journal of palliative medicine.

[36]  R. Morrison,et al.  Economics of Palliative Care for Hospitalized Adults With Serious Illness: A Meta-analysis , 2018, JAMA internal medicine.

[37]  D. Meier,et al.  Increased access to palliative care and hospice services: opportunities to improve value in health care. , 2011, The Milbank quarterly.

[38]  J. Spetz,et al.  Few Hospital Palliative Care Programs Meet National Staffing Recommendations. , 2016, Health affairs.

[39]  Ruben Amarasingham,et al.  The legal and ethical concerns that arise from using complex predictive analytics in health care. , 2014, Health affairs.

[40]  Benjamin French,et al.  Development, implementation, and impact of an automated early warning and response system for sepsis. , 2015, Journal of hospital medicine.

[41]  R. Kohli-Seth,et al.  Developing triggers for the surgical intensive care unit for palliative care integration. , 2016, Journal of critical care.

[42]  R. O'ConnorNina,et al.  Which Patients Need Palliative Care Most? Challenges of Rationing in Medicine's Newest Specialty. , 2016 .

[43]  M. Howell,et al.  Ensuring Fairness in Machine Learning to Advance Health Equity , 2018, Annals of Internal Medicine.

[44]  Judd B. Kessler,et al.  Using Behavioral Economics to Design Physician Incentives That Deliver High-Value Care , 2016, Annals of Internal Medicine.

[45]  L. Ungar,et al.  Inclusion of Unstructured Clinical Text Improves Early Prediction of Death or Prolonged ICU Stay* , 2018, Critical care medicine.

[46]  E. Bruera,et al.  Automatic referral to standardize palliative care access: an international Delphi survey , 2017, Supportive Care in Cancer.

[47]  Alexander K. Smith,et al.  The diverse landscape of palliative care clinics. , 2013, Journal of palliative medicine.

[48]  György J. Simon,et al.  Development and Validation of Machine Learning Models for Prediction of 1-Year Mortality Utilizing Electronic Medical Record Data Available at the End of Hospitalization in Multicondition Patients: a Proof-of-Concept Study , 2018, Journal of General Internal Medicine.

[49]  D. Meier,et al.  Cost savings associated with US hospital palliative care consultation programs. , 2008, Archives of internal medicine.