Department of Surgery, University of California, San Diego, 9300 Campus Point Drive, #7220, La Jolla, CA, 92037, USA.
Department of Medicine, Division of Biomedical Informatics, University of California, San Diego, La Jolla, CA, USA.
J Med Syst. 2019 Jan 5;43(2):32. doi: 10.1007/s10916-018-1151-y.
Robot-assisted surgery (RAS) requires a large capital investment by healthcare organizations. The cost of a robotic unit is fixed, so institutions must maximize use of each unit by utilizing all available operating room block time. One way to increase utilization is to accurately predict case durations. In this study, we sought to use machine learning to develop an accurate predictive model for RAS case duration. We analyzed a random sample of robotic cases at our institution from January 2014 to June 2017. We compared the machine learning models to the baseline model, which is the scheduled case duration (determined by previous case duration averages and surgeon adjustments). Specifically, we used: 1) multivariable linear regression, 2) ridge regression, 3) lasso regression, 4) random forest, 5) boosted regression tree, and 6) neural network. We found that all machine learning models decreased the average root-mean-squared error (RMSE) as compared to the baseline model. The average RMSE was lowest with the boosted regression tree (80.2 min, 95% CI 74.0-86.4), which was significantly lower than the baseline model (100.4 min, 95% CI 90.5-110.3). Using boosted regression tree, we can increase the number of accurately booked cases from 148 to 219 (34.9% to 51.7%, p < 0.001). This study shows that using various machine learning approaches can improve the accuracy of RAS case length predictions, which will increase utilization of this limited resource. Further work is needed to operationalize these findings.
机器人辅助手术 (RAS) 需要医疗机构进行大量的资本投资。机器人单元的成本是固定的，因此机构必须通过充分利用所有可用的手术室块时间来最大限度地利用每个单元。增加利用率的一种方法是准确预测手术持续时间。在这项研究中，我们试图使用机器学习来开发一种准确的 RAS 手术持续时间预测模型。我们分析了我们机构 2014 年 1 月至 2017 年 6 月的随机机器人手术案例。我们将机器学习模型与基线模型进行了比较，基线模型是预定的手术持续时间（由之前的手术持续时间平均值和外科医生调整确定）。具体来说，我们使用了：1）多变量线性回归，2）岭回归，3）套索回归，4）随机森林，5）增强回归树和 6）神经网络。我们发现与基线模型相比，所有机器学习模型都降低了平均均方根误差 (RMSE)。增强回归树的平均 RMSE 最低（80.2 分钟，95%CI 74.0-86.4），明显低于基线模型（100.4 分钟，95%CI 90.5-110.3）。使用增强回归树，我们可以将准确预订的病例数从 148 例增加到 219 例（34.9%至 51.7%，p<0.001）。这项研究表明，使用各种机器学习方法可以提高 RAS 手术长度预测的准确性，从而提高这种有限资源的利用率。需要进一步的工作来实现这些发现。
