Surgery duration: Optimized prediction and causality analysis

Abstract

Accurate estimation of duration of surgery (DOS) can lead to cost-effective utilization of surgical staff and operating rooms and decrease patients’ waiting time. In this study, we present a supervised DOS nonlinear regression prediction model whose accuracy outperforms earlier results. In addition, unlike previous studies, we identify the features that influence DOS prediction. Further, in difference from others, we study the causal relationship between the feature set and DOS. The feature sets used in prior studies included a subset of the features presented in this study. This study aimed to derive influential effectors of duration of surgery via optimized prediction and causality analysis. We implemented an array of machine learning algorithms and trained them on datasets comprising surgery-related data, to derive DOS prediction models. The datasets we acquired contain patient, surgical staff, and surgery features. The datasets comprised 23,293 surgery records of eight surgery types performed over a 10-year period in a public hospital. We have introduced new, unstudied features and combined them with features adopted from previous studies to generate a comprehensive feature set. We utilized feature importance methods to identify the influential features, and causal inference methods to identify the causal features. Our model demonstrates superior performance in comparison to DOS prediction models in the art. The performance of our DOS model in terms of the mean absolute error (MAE) was 14.9 minutes. The algorithm that derived the model with the best performance was the gradient boosted trees (GBT). We identified the 10 most influential features and the 10 most causal features. In addition, we showed that 40% of the influential features have a significant (p-value = 0.05) causal relationship with DOS. We developed a DOS prediction model whose accuracy is higher than that of prior models. This improvement is achieved via the introduction of a novel feature set on which the model was trained. Utilizing our prediction model, hospitals can improve the efficiency of surgery schedules, and by exploiting the identified causal relationship, can influence the DOS. Further, the feature importance methods we used can help explain the model’s predictions.

Predicting operative time for metabolic and bariatric surgery using machine learning models: a retrospective observational study

“…Our additional subgroup analysis, stratified by surgery type, further highlights the significant influence of sample size on model performance. We also acknowledge that other studies in the literature have reported similar findings, with narrow differences among various ML models in terms of MAE and RMSE 15 , 16 , 33 . Predicting operative time is inherently complex, involving numerous potential factors, many of which may be challenging to quantify in large databases 41 , 42 .…”

“…Similarly, previous studies have shown that boosted trees outperform other models in predicting operative times. A previous study conducted in Israel reported that GBT performed best in predicting the operative time for eight surgery types, with the lowest MAE and RMSE among RF, GBT, and multilayer perception 16 . Another study in the United States also reported that the boosted regression tree performed best in predicting the operative time for robot-assisted surgery, with the lowest RMSE among multivariable linear regression, ridge regression, lasso regression, RF, boosted regression tree, and neural network 33 .…”

“…We selected the variables in the model based on previous studies 16 , 18 , 25 – 28 . Patient characteristic variables included age, sex, race, BMI, smoking status, American Society of Anesthesiologists physical status, functional health status, comorbidities, and previous therapies.…”

“…trained a random forest (RF), gradient-boosted tree (GBT), and multilayer perception for eight surgery types. The results showed that ML models outperformed existing methods used in hospitals, and GBT performed the best among these models 16 . Shadaev et al .…”

Безшовна Склеротомія У Пацієнтів З Відшаруванням Сітківки Після Проведення Вітректомії

“…Тривалий час хірургічного втручання може посилити маніпуляції з тканинами та травму, що призведе до посилення запальних реакцій і сповільненого загоєння ран [7]. Мінімізація тривалості хірургічного втручання за допомогою ефективних методів і інструментів може допомогти зменшити ці ризики та зменшити ймовірність утворення надмірного рубця [8].…”