Development and Validation of a Machine Learning Model to Aid Discharge Processes for Inpatient Surgical Care

Abstract

IMPORTANCE Inpatient overcrowding is associated with delays in care, including the deferral of surgical care until beds are available to accommodate postoperative patients. Timely patient discharge is critical to address inpatient overcrowding and requires coordination among surgeons, nurses, case managers, and others. This is difficult to achieve without early identification and systemwide transparency of discharge candidates and their respective barriers to discharge. OBJECTIVE To validate the performance of a clinically interpretable feedforward neural network model that could improve the discharge process by predicting which patients would be discharged within 24 hours and their clinical and nonclinical barriers. DESIGN, SETTING, AND PARTICIPANTS This prognostic study included adult patients discharged from inpatient surgical care from May 1, 2016, to August 31, 2017, at a quaternary care teaching hospital. Model performance was assessed with standard cross-validation techniques. The model's performance was compared with a baseline model using historical procedure median length of stay to predict discharges. In prospective cohort analysis, the feedforward neural network model was used to make predictions on general surgical care floors with 63 beds. If patients were not discharged when predicted, the causes of delay were recorded. MAIN OUTCOMES AND MEASURES The primary outcome was the out-of-sample area under the receiver operating characteristic curve of the model. Secondary outcomes included the causes of discharge delay and the number of avoidable bed-days. RESULTS The model was trained on 15 201 patients (median [interquartile range] age, 60 [46-70] years; 7623 [50.1%] men) discharged from inpatient surgical care. The estimated out-of-sample area under the receiver operating characteristic curve of the model was 0.840 (SD, 0.008; 95% CI, 0.839-0.844). Compared with the baseline model, the neural network model had higher sensitivity (52.5% vs 56.6%) and specificity (51.7% vs 82.6%). The neural network model identified 65 barriers to discharge. In the prospective study of 605 patients, causes of delays included clinical barriers (41 patients [30.1%]), variation in clinical practice (30 patients [22.1%]), and nonclinical reasons (65 patients [47.8%]). Summing patients who were not discharged owing to variation in clinical practice and nonclinical reasons, 128 bed-days, or 1.2 beds per day, were classified as avoidable. CONCLUSIONS AND RELEVANCE This cohort study found that a neural network model could predict daily inpatient surgical care discharges and their barriers. The model identified systemic causes of discharge delays. Such models should be studied for their ability to increase the timeliness of discharges.

Predicting Length of Stay and Discharge Destination for Surgical Patients: A Cohort Study

“…Those topics have been the object of reviews [ 13 ], and also, governments have tried to tackle this issue, creating useful toolkits for professionals [ 14 ]. With the development of machine learning and neural systems, they have also been used and applied to predict the LOS [ 15 ], and this will be even more common in the future. Moreover, the recent year showed us how in stress situations such as COVID-19, good bed management may help the endurance of the healthcare system [ 16 ], so understanding those factors is crucial.…”

Artificial intelligence in thoracic surgery: past, present, perspective and limits

“…Electronic health records are a source of big data that are continuously updated by surgeons, nurses, nutritionists and physical therapists. SAFAVI et al [41] used electronic health records to develop a machine learning model to aid discharge processes for inpatient surgical care, including for thoracic surgery patients. The estimated out-of-sample area under the receiver operating characteristic curve of the model was 0.84 (SD 0.008; 95% CI 0.839-0.844).…”

Predicting inpatient flow at a major hospital using interpretable analytics

“…Scope Predicted outcome Methodology Tabak et al (2014) All inpatients Mortality Linear regression Van Walraven and Forster (2017) All inpatients Discharge volume Survival analysis McCoy et al (2018) Hospital level Discharge volume Time series Rajkomar et al (2018) All inpatients Mortality, overall LOS > 7 days Deep learning Safavi et al (2019) Surgical inpatients Remaining LOS < 1 day Deep learning most severe patients. Patients who cannot be admitted to an ICU due to congestion have to be admitted to a general care bed, leading to increased length of stay and readmission risk (Kim et al 2016).…”