Impact of a machine learning algorithm on time to palliative care in a primary care population: protocol for a stepped-wedge pragmatic randomized trial

• DOI: 10.1186/s12904-022-01113-0
• Publication Date: 2023-02-03T11:03:14Z
• Authors: Ethan P. Heinzen; Patrick M. Wilson; Curtis B. Storlie; Gabriel O. Demuth; Shusaku W. Asai; Gavin M. Schaeferle; Mairead M. Bartley; Rachel D. Havyer
• Keywords: Curative care

Abstract Background As primary care populations age, timely identification of palliative need is becoming increasingly relevant. Previous studies have targeted particular patient with life-limiting disease, but few focused on patients in a setting. Toward this end, we propose stepped-wedge pragmatic randomized trial whereby machine learning algorithm identifies empaneled to units at Mayo Clinic (Rochester, Minnesota, United States) high likelihood need. Methods 42 team 9 clusters were 7 wedges, each lasting days. For teams treatment specialists review identified patients, making recommendations providers when appropriate. Care control wedges receive under the standard care. Discussion This therefore integrates into clinical decision making, instead simply reporting theoretical predictive performance. Such integration has possibility decrease time care, improving quality life and symptom burden. Trial registration Clinicaltrials.gov NCT04604457 , restrospectively registered 10/26/2020. Protocol v0.5, dated 9/23/2020