Development, Deployment, and Implementation of a Machine Learning Surgical Case Length Prediction Model and Prospective Evaluation.

OBJECTIVE: To implement a machine learning model using only the restricted data available at case creation time to predict surgical case length for multiple services at different locations. BACKGROUND: The operating room is one of the most expensive resources in a health system, estimated to cost $22 to $133 per minute and generate about 40% of hospital revenue. Accurate prediction of surgical case length is necessary for efficient scheduling and cost-effective utilization of the operating room and other resources. METHODS: We introduced a similarity cascade to capture the complexity of cases and surgeon influence on the case length and incorporated that into a gradient-boosting machine learning model. The model loss function was customized to improve the balance between over- and under-prediction of the case length. A production pipeline was created to seamlessly deploy and implement the model across our institution. RESULTS: The prospective analysis showed that the model output was gradually adopted by the schedulers and outperformed the scheduler-predicted case length from August to December 2022. In 33,815 surgical cases across outpatient and inpatient platforms, the operational implementation predicted 11.2% fewer underpredicted cases and 5.9% more cases within 20% of the actual case length compared with the schedulers and only overpredicted 5.3% more. The model assisted schedulers to predict 3.4% more cases within 20% of the actual case length and 4.3% fewer underpredicted cases. CONCLUSIONS: We created a unique framework that is being leveraged every day to predict surgical case length more accurately at case posting time and could be potentially utilized to deploy future machine learning models.

Implementing venous leg ulcer education and clinical decision support: a quality improvement project.

BACKGROUND: Venous leg ulcers (VLU) require early identification and treatment to prevent further harm. Health care providers often fail to initiate evidenced-based VLU treatment promptly because of a lack of knowledge of VLU guidelines. PURPOSE: To improve early treatment for patients with VLUs presenting to outpatient clinic settings. METHODS: Plan-Do-Study-Act cycles were used for this quality improvement project. Virtual education and a comprehensive clinical decision support (CDS) order set were implemented. Outcome metrics included the rate of ankle-brachial index (ABI) testing, mechanical compression therapy, and home health service referrals for patients with VLUs. The frequency with which the CDS order set was used was also measured. RESULTS: Forty health care providers attended the virtual education sessions among 3 outpatient clinics. There was an increase in ankle-brachial index testing from pre (n = 7; 15.9%) to post (n = 10; 18.2%) (P = .796), but there was a decline in mechanical compression therapy from pre (n = 15; 34.1%) to post (n = 4; 7.3%) (P = .002) and home health service referrals from pre (n = 11; 25%) to post (n = 9; 16.4%) (P = .322). The CDS order set was used 9 times over 13 weeks. CONCLUSION: Future Plan-Do-Study-Act cycles will include completing in-person education and reducing the VLU CDS order set length. Future projects should consider these approaches when implementing evidence-based VLU guidelines.

Influence of electronic medical record implementation on provider retirement at a major academic medical centre.

RATIONALE, AIMS AND OBJECTIVES: The push for electronic medical record (EMR) implementation is grounded on increasing efficiency and cost savings. Our objective was to investigate the effect of EMR implementation on provider attrition. METHODS: We completed a retrospective study investigating whether medical provider attrition, clinical MD or equivalent, coincided with EMR implementation. We analysed monthly provider attrition rates and mean age at attrition 24 months preceding the EMR 'go-live' date at our institution and 12 months after. RESULTS: 208 provider departures occurred between July 2011 and June 2014. The attrition categories were classified as 'departure' (n = 137, 65.9%), 'emeritus' (n = 30; 14.4%), 'no specified reason' (n = 26; 12.5%) and 'not reappointed' (n = 15; 7.2). The most common degree held by departing providers was 'MD' (n = 170; 81.7%). Most departures occurred in June 2013 (n = 24). The mean provider age at departure was 46.4 years ± 2.9 years for June 2012, 48.1 years ± 2.5 years for June 2013 and 45.0 years ± 4.1 years for June 2014. Our data indicate a trend for both an increase in number of departing providers, as well as an increased mean age in the month immediately prior to EMR implementation. CONCLUSION: To date, no other investigation of the effect of EMR implementation of provider retirements have been published. We demonstrate a peak in provider attrition in the month prior to EMR implementation that may not be explained by normal attrition patterns with an academic calendar. LEVEL OF EVIDENCE: Level 5 - qualitative or descriptive study.

The found down patient: A Western Trauma Association multicenter study.

BACKGROUND: Unconscious patients who present after being "found down" represent a unique triage challenge. These patients are selected for either trauma or medical evaluation based on limited information and have been shown in a single-center study to have significant occult injuries and/or missed medical diagnoses. We sought to further characterize this population in a multicenter study and to identify predictors of mistriage. METHODS: The Western Trauma Association Multicenter Trials Committee conducted a retrospective study of patients categorized as found down by emergency department triage diagnosis at seven major trauma centers. Demographic, clinical, and outcome data were collected. Mistriage was defined as patients being admitted to a non-triage-activated service. Logistic regression was used to assess predictors of specified outcomes. RESULTS: Of 661 patients, 33% were triaged to trauma evaluations, and 67% were triaged to medical evaluations; 56% of all patients had traumatic injuries. Trauma-triaged patients had significantly higher rates of combined injury and a medical diagnosis and underwent more computed tomographic imaging; they had lower rates of intoxication and homelessness. Among the 432 admitted patients, 17% of them were initially mistriaged. Even among properly triaged patients, 23% required cross-consultation from the non-triage-activated service after admission. Age was an independent predictor of mistriage, with a doubling of the rate for groups older than 70 years. Combined medical diagnosis and injury was also predictive of mistriage. Mistriaged patients had a trend toward increased late-identified injuries, but mistriage was not associated with increased length of stay or mortality. CONCLUSION: Patients who are found down experience significant rates of mistriage and triage discordance requiring cross-consultation. Although the majority of found down patients are triaged to nontrauma evaluation, more than half have traumatic injuries. Characteristics associated with increased rates of mistriage, including advanced age, may be used to improve resource use and minimize missed injury in this vulnerable patient population. LEVEL OF EVIDENCE: Epidemiologic study, level III.