IMPORTANCE Accurate surgical scheduling affects patients, clinical staff, and use of physical resources. Although numerous retrospective analyses have suggested a potential for improvement, the real-world outcome of implementing a machine learning model to predict surgical case duration appears not to have been studied. OBJECTIVESTo assess accuracy and real-world outcome from implementation of a machine learning model that predicts surgical case duration. DESIGN, SETTING, AND PARTICIPANTSThis randomized clinical trial was conducted on 2 surgical campuses of a cancer specialty center. Patients undergoing colorectal and gynecology surgery at Memorial Sloan Kettering Cancer Center who were scheduled more than 1 day before surgery between April 7, 2018, and June 25, 2018, were included. The randomization process included 29 strata (11 gynecological surgeons at 2 campuses and 7 colorectal surgeons at a single campus) to ensure equal chance of selection for each surgeon and each campus. Patients undergoing more than 1 surgery during the study's timeframe were enrolled only once. Data analyses took place from July 2018 to November 2018. INTERVENTIONSCases were assigned to machine learning-assisted surgical predictions 1 day before surgery and compared with a control group. MAIN OUTCOMES AND MEASURESThe primary outcome measure was accurate prediction of the duration of each scheduled surgery, measured by (arithmetic) mean (SD) error and mean absolute error. Effects on patients and systems were measured by start time delay of following cases, the time between cases, and the time patients spent in presurgical area.RESULTS A total of 683 patients were included (mean [SD] age, 55.8 [13.8] years; 566 women [82.9%]); 72 were excluded. Of the 683 patients included, those assigned to the machine learning algorithm had significantly lower mean (SD) absolute error (control group, 59.3 [72] minutes; intervention group, 49.5 [66] minutes; difference, −9.8 minutes; P = .03) compared with the control group. Mean start-time delay for following cases (patient wait time in a presurgical area), dropped significantly: 62.4 minutes (from 70.2 minutes to 7.8 minutes) and 16.7 minutes (from 36.9 minutes to 20.2 minutes) for patients receiving colorectal and gynecology surgery, respectively. The overall mean (SD) reduction of wait time was 33.1 minutes per patient (from 49.4 minutes to 16.3 minutes per patient). Improved accuracy did not adversely inflate time between cases (surgeon wait time). There was marginal improvement (1.5 minutes, from a mean of 70.6 to 69.1 minutes) in time between the end of cases and start of to-follow cases using the predictive model, compared with the control group. Patients spent a mean of 25.2 fewer minutes in the facility before surgery (173.3 minutes vs 148.1 minutes), indicating a potential benefit vis-à-vis available resources for other patients before and after surgery.CONCLUSIONS AND RELEVANCE Implementing machine learning-generated predictions for surgical case durations may improve case duration accura...

The ability to accurately measure and assess current and potential health care system capacities is an issue of local and national significance. Recent joint statements by the Institute of Medicine and the Agency for Healthcare Research and Quality have emphasized the need to apply industrial and systems engineering principles to improving health care quality and patient safety outcomes. To address this need, a decision support tool was developed for planning and budgeting of current and future bed capacity, and evaluating potential process improvement efforts. The Strategic Bed Analysis Model (StratBAM) is a discrete-event simulation model created after a thorough analysis of patient flow and data from Geisinger Health System's (GHS) electronic health records. Key inputs include: timing, quantity and category of patient arrivals and discharges; unit-level length of care; patient paths; and projected patient volume and length of stay. Key outputs include: admission wait time by arrival source and receiving unit, and occupancy rates. Electronic health records were used to estimate parameters for probability distributions and to build empirical distributions for unit-level length of care and for patient paths. Validation of the simulation model against GHS operational data confirmed its ability to model real-world data consistently and accurately. StratBAM was successfully used to evaluate the system impact of forecasted patient volumes and length of stay in terms of patient wait times, occupancy rates, and cost. The model is generalizable and can be appropriately scaled for larger and smaller health care settings.

The 3-day REDD model predicts high-risk patients with fair discriminative power. The discriminative power of the 30-day REDD model is also better than the previously reported models under similar settings. The 3-day REDD model has been implemented and is being used to identify patients at risk for AEs.

researchers and practitioners reserve CT as a secondary test following only indeterminate results of other diagnostic tests. 2,3 Such strategies should be carefully attempted while maintaining excellent overall diagnostic accuracy. 3 As Hu et al pointed out, magnetic resonance imaging is promising; however, it is yet to be determined if the study results can be generalized to average hospitals and to different health care systems.The diagnosis of appendicitis is one of few indications of low-dose CT techniques established with high-level evidence. 4 However, the adoption of low-dose CT is disappointingly slow, and the variation in CT radiation dose used for the diagnosis of appendicitis is surprisingly wide across regions and hospitals. 5,6 The variation is partly attributable to the use of multiphase scanning, which has no rationale for the diagnosis of appendicitis.As Schaps et al pointed out, our observation is perhaps just one piece of a complex puzzle on the carcinogenic risk of CT radiation. Unless there are conclusive experimental data, it would be prudent not to ignore the carcinogenic risk but to adhere to the As Low As Reasonably Achievable (ALARA) principle: first, use CT only when clinically necessary and second, keep the radiation dose as low as possible.

No abstract