Prospective Evaluation of a Machine-Learning Prediction Model for Missed Radiology Appointments.

The term "no-show" refers to scheduled appointments that a patient misses, or for which she arrives too late to utilize medical resources. Accurately predicting no-shows creates opportunities to intervene, ensuring that patients receive needed medical resources. A machine-learning (ML) model can accurately identify individuals at high no-show risk, to facilitate strategic and targeted interventions. We used 4,546,104 non-same-day scheduled appointments in our medical system from 1/1/2017 through 1/1/2020 for training data, including 631,386 no-shows. We applied eight ML techniques, which yielded cross-validation AUCs of 0.77-0.93. We then prospectively tested the best performing model, Gradient Boosted Regression Trees, over a 6-week period at a single outpatient location. We observed 123 no-shows. The model accurately identified likely no-show patients retrospectively (AUC 0.93) and prospectively (AUC 0.73, p < 0.0005). Individuals in the highest-risk category were three times more likely to no-show than the average of all other patients. No-show prediction modeling based on machine learning has the potential to identify patients for targeted interventions to improve their access to medical resources, reduce waste in the medical system and improve overall operational efficiency. Caution is advised, due to the potential for bias to decrease the quality of service for patients based on race, zip code, and gender.

Assessment of Machine Learning vs Standard Prediction Rules for Predicting Hospital Readmissions.

Importance: Hospital readmissions are associated with patient harm and expense. Ways to prevent hospital readmissions have focused on identifying patients at greatest risk using prediction scores. Objective: To identify the type of score that best predicts hospital readmissions. Design, Setting, and Participants: This prognostic study included 14 062 consecutive adult hospital patients with 16 649 discharges from a tertiary care center, suburban community hospital, and urban critical access hospital in Maryland from September 1, 2016, through December 31, 2016. Patients not included as eligible discharges by the Centers for Medicare & Medicaid Services or the Chesapeake Regional Information System for Our Patients were excluded. A machine learning rank score, the Baltimore score (B score) developed using a machine learning technique, for each individual hospital using data from the 2 years before September 1, 2016, was compared with standard readmission risk assessment scores to predict 30-day unplanned readmissions. Main Outcomes and Measures: The 30-day readmission rate evaluated using various readmission scores: B score, HOSPITAL score, modified LACE score, and Maxim/RightCare score. Results: Of the 10 732 patients (5605 [52.2%] male; mean [SD] age, 54.56 [22.42] years) deemed to be eligible for the study, 1422 were readmitted. The area under the receiver operating characteristic curve (AUROC) for individual rules was 0.63 (95% CI, 0.61-0.65) for the HOSPITAL score, which was significantly lower than the 0.66 for modified LACE score (95% CI, 0.64-0.68; P < .001). The B score machine learning score was significantly better than all other scores; 48 hours after admission, the AUROC of the B score was 0.72 (95% CI, 0.70-0.73), which increased to 0.78 (95% CI, 0.77-0.79) at discharge (all P < .001). At the hospital using Maxim/RightCare score, the AUROC was 0.63 (95% CI, 0.59-0.69) for HOSPITAL, 0.64 (95% CI, 0.61-0.68) for Maxim/RightCare, and 0.66 (95% CI, 0.62-0.69) for modified LACE score. The B score was 0.72 (95% CI, 0.69-0.75) 48 hours after admission and 0.81 (95% CI, 0.79-0.84) at discharge. In directly comparing the B score with the sensitivity at cutoff values for modified LACE, HOSPITAL, and Maxim/RightCare scores, the B score was able to identify the same number of readmitted patients while flagging 25.5% to 54.9% fewer patients. Conclusions and Relevance: Among 3 hospitals in different settings, an automated machine learning score better predicted readmissions than commonly used readmission scores. More efficiently targeting patients at higher risk of readmission may be the first step toward potentially preventing readmissions.