Using Electronic Health Record Mortality Data to Promote Goals-of-Care Discussions in Seriously Ill Transferred Patients: A Pilot Study

Abstract

Background Mortality prediction data may aid in identifying seriously ill transferred patients at high risk of dying and facilitate early goals-of-care discussions (GOCD); however, this is rarely evaluated. We recently developed a model for predicting 30-day inpatient mortality, which may be useful for promoting early GOCD.

Objectives Our objectives were to examine the effects of sharing model-generated mortality risk with hospitalists by assessing (1) if hospitalists agreed with the mortality risk prediction, (2) if they planned to conduct GOCD or consult palliative care within 72 hours of transfer, and (3) if the communication alert affected GOCD timing and other clinical outcomes. We also aimed to measure the association between both the model-generated and hospitalists' stratified risk assessments with patient mortality.

Methods This was a nonrandomized quasi-experimental pilot study with a historical control group. On the second day of hospitalization, the model-generated risk was communicated to the hospitalists. Hospitalists were asked to answer questions via a HIPAA (Health Insurance Portability and Accountability Act)-compliant mobile communication system, and clinical outcomes were extracted via chart review.

Results Eighty-four patients (42 in the control and 42 in the intervention group) were included in this study. Hospitalists agreed that all patients in the intervention group were at risk for inpatient mortality. Hospitalists were more likely to indicate a plan to conduct GOCD in the intervention group (n = 9) compared with the control group (n = 4, p < 0.001). In this subset of patients, GOCD was completed within 72 hours in 78% of intervention patients (n = 7) as compared with 50% in the control group (n = 2). The greater absolute value of the model-generated mortality risk was significantly associated with deaths (p = 0.01), similar to the hospitalists' prediction of the mortality risk (p = 0.02).

Conclusion Communicating model-generated mortality risk to hospitalists is a promising approach to promote timely GOCD.

Keywords

goals-of-care discussions - inpatient mortality model - mortality risk stratification - clinical decision support - electronic health records

• References

• 1 Bharadwaj P, Helfen KM, Deleon LJ. et al. Making the case for palliative care at the system level: outcomes data. J Palliat Med 2016; 19 (03) 255-258
• 2 May P, Normand C, Cassel JB. et al. Economics of palliative care for hospitalized adults with serious illness: a meta-analysis. JAMA Intern Med 2018; 178 (06) 820-829
• 3 Beernaert K, Cohen J, Deliens L. et al. Referral to palliative care in COPD and other chronic diseases: a population-based study. Respir Med 2013; 107 (11) 1731-1739
• 4 Brooten JK, Buckenheimer AS, Hallmark JK. et al. Risky behavior: hospital transfers associated with early mortality and rates of goals of care discussions. West J Emerg Med 2020; 21 (04) 935-942
• 5 Rosenberg LB, Jacobsen JC. Chasing hope: when are requests for hospital transfer a place for palliative care integration?. J Hosp Med 2020; 14 (04) 250-251
• 6 Hallen SA, Hootsmans NA, Blaisdell L, Gutheil CM, Han PK. Physicians' perceptions of the value of prognostic models: the benefits and risks of prognostic confidence. Health Expect 2015; 18 (06) 2266-2277
• 7 Moja L, Liberati EG, Galuppo L. et al. Barriers and facilitators to the uptake of computerized clinical decision support systems in specialty hospitals: protocol for a qualitative cross-sectional study. Implement Sci 2014; 9: 105
• 8 Abedini NC, Chopra V. A model to improve hospital-based palliative care: the Palliative Care Redistribution Integrated System Model (PRISM). J Hosp Med 2018; 13 (12) 868-871
• 9 Hui D, Mori M, Meng YC. et al. Automatic referral to standardize palliative care access: an international Delphi survey. Support Care Cancer 2018; 26 (01) 175-180
• 10 Courtright KR, Chivers C, Becker M. et al. Electronic health record mortality prediction model for targeted palliative care among hospitalized medical patients: a pilot quasi-experimental study. J Gen Intern Med 2019; 34 (09) 1841-1847
• 11 Cardona M, Lewis ET, Kristensen MR. et al. Predictive validity of the CriSTAL tool for short-term mortality in older people presenting at emergency departments: a prospective study. Eur Geriatr Med 2018; 9 (06) 891-901
• 12 Van Calster B, Wynants L, Timmerman D, Steyerberg EW, Collins GS. Predictive analytics in health care: how can we know it works?. J Am Med Inform Assoc 2019; 26 (12) 1651-1654
• 13 Dhar V. Big data and predictive analytics in health care. Big Data 2014; 2 (03) 113-116
• 14 Delahanty RJ, Kaufman D, Jones SS. Development and evaluation of an automated machine learning algorithm for in-hospital mortality risk adjustment among critical care patients. Crit Care Med 2018; 46 (06) e481-e488
• 15 Soffer S, Klang E, Barash Y, Grossman E, Zimlichman E. Predicting in-hospital mortality at admission to the medical ward: a big-data machine learning model. Am J Med 2021; 134 (02) 227-234.e4
• 16 Manz CR, Zhang Y, Chen K. et al. Long-term effect of machine learning-triggered behavioral nudges on serious illness conversations and end-of-life outcomes among patients with cancer: a randomized clinical trial. JAMA Oncol 2023; 9 (03) 414-418
• 17 Escobar GJ, Gardner MN, Greene JD, Draper D, Kipnis P. Risk-adjusting hospital mortality using a comprehensive electronic record in an integrated health care delivery system. Med Care 2013; 51 (05) 446-453
• 18 Rajkomar A, Oren E, Chen K. et al. Scalable and accurate deep learning with electronic health records. NPJ Digit Med 2018; 1: 18
• 19 Schwartz N, Sakhnini A, Bisharat N. Predictive modeling of inpatient mortality in departments of internal medicine. Intern Emerg Med 2018; 13 (02) 205-211
• 20 Nakas CT, Schütz N, Werners M, Leichtle AB. Accuracy and calibration of computational approaches for inpatient mortality predictive modeling. PLoS One 2016; 11 (07) e0159046
• 21 Cohen IG, Amarasingham R, Shah A, Xie B, Lo B. The legal and ethical concerns that arise from using complex predictive analytics in health care. Health Aff (Millwood) 2014; 33 (07) 1139-1147
• 22 Shah ND, Steyerberg EW, Kent DM. Big data and predictive analytics: recalibrating expectations. JAMA 2018; 320 (01) 27-28
• 23 Beam AL, Kohane IS. Big data and machine learning in health care. JAMA 2018; 319 (13) 1317-1318
• 24 Mahendraker N, Flanagan M, Azar J, Williams LS. Development and validation of a 30-day in-hospital mortality model among seriously ill transferred patients: a retrospective cohort study. J Gen Intern Med 2021; 36 (08) 2244-2250
• 25 Bhaskaran K, Dos-Santos-Silva I, Leon DA, Douglas IJ, Smeeth L. Association of BMI with overall and cause-specific mortality: a population-based cohort study of 3·6 million adults in the UK. Lancet Diabetes Endocrinol 2018; 6 (12) 944-953
• 26 Lupu D, Quigley L, Mehfoud N, Salsberg ES. The growing demand for hospice and palliative medicine physicians: will the supply keep up?. J Pain Symptom Manage 2018; 55 (04) 1216-1223
• 27 Haley EM, Meisel D, Gitelman Y, Dingfield L, Casarett DJ, O'Connor NR. Electronic goals of care alerts: an innovative strategy to promote primary palliative care. J Pain Symptom Manage 2017; 53 (05) 932-937
• 28 Colunga-Lozano LE, Foroutan F, Rayner D. et al. Clinical judgment shows similar and sometimes superior discrimination compared to prognostic clinical prediction models: a systematic review. J Clin Epidemiol 2024; 165: 111200
• 29 Orlovic M, Droney J, Vickerstaff V. et al. Accuracy of clinical predictions of prognosis at the end-of-life: evidence from routinely collected data in urgent care records. BMC Palliat Care 2023; 22 (01) 51
• 30 Richardson S, Dauber-Decker K, Solomon J. et al. Nudging health care providers' adoption of clinical decision support: protocol for the user-centered development of a behavioral economics-inspired electronic health record tool. JMIR Res Protoc 2023; 12: e42653
• 31 Embi PJ. Algorithmovigilance-advancing methods to analyze and monitor artificial intelligence-driven health care for effectiveness and equity. JAMA Netw Open 2021; 4 (04) e214622
• 32 Auerbach AD, Pantilat SZ. End-of-life care in a voluntary hospitalist model: effects on communication, processes of care, and patient symptoms. Am J Med 2004; 116 (10) 669-675
• 33 Choi DT, Sada YH, Sansgiry S. et al. Using telemedicine to facilitate patient communication and treatment decision-making following multidisciplinary tumor board review for patients with hepatocellular carcinoma. J Gastrointest Cancer 2023; 54 (02) 623-631
• 34 Oliver DP, Demiris G, Wittenberg-Lyles E, Washington K, Day T, Novak H. A systematic review of the evidence base for telehospice. Telemed J E Health 2012; 18 (01) 38-47