Hospital length of stay following radical cystectomy for muscle-invasive bladder cancer: Development and validation of a population-based prediction model

Effect of Early Postoperative Rehabilitation on Length of Hospital Stay after Robot-assisted Radical Prostatectomy

Objectives

: This study assessed how early postoperative rehabilitation interventions affected the duration of hospital stay in patients with prostate cancer who had radical prostatectomy with robotic assistance.

Methods

: From the Japanese Diagnosis Procedure Combination database, we extracted case data for patients discharged between April 2014 and March 2020. Patients were recognized by code C61 from the International Classification of Diseases, 10th Edition. We ran a multilevel linear regression analysis to investigate the impact of early rehabilitation on the duration of hospital stay.

Results

: There were 2151 participants in the trial. In patients with prostate cancer who had resection utilizing robotic-assisted devices, early rehabilitation was related to a substantial decrease in duration of hospital stay (coefficient, -0.86; 95% CI, -1.64 to -0.07; P=0.032).

Conclusions

: Early postoperative rehabilitation may contribute to shorter hospital stays in patients with prostate cancer at high risk of both postoperative complications and a decline in their ability to perform activities of daily living.

Retrospective Evaluation of a Single Surgeon's Learning Curve of Robot-Assisted Radical Cystectomy with Intracorporeal Urinary Diversion via Ileal Conduit

Robot-assisted radical cystectomy with intracorporeal urinary diversion (iRARC) is increasingly being performed instead of open surgery. A criticism of this technique is the long learning curve, but limited data are available on this topic. At our center, the transition from open radical cystectomy (ORC) to iRARC began in May 2017. A retrospective analysis was conducted on the initial 53 cases of robot-assisted cystectomy with intracorporeal urinary diversion via ileal conduit, which were performed by one single surgeon. The patients were divided into four consecutive groups according to the surgeon's increasing experience, and perioperative parameters were analyzed as a surrogate for the learning curve. Over the course of the learning curve, a decline in median operation time from 415 to 361 min (p = 0.02), blood loss from 400 to 200 mL (p = 0.01), and minor complications from 71% to 15% (p = 0.02) was observed. No significant difference in overall and major complications, length of hospital stay, and total lymph node yield was shown. During the initial period of the learning curve, only the less complex cases were operated on using robotic surgery, while the more challenging ones were handled through open surgery. After experience with 28 cases, no more cystectomies were performed through open surgery. This led to an increase in operation time and length of hospital stay, as well as a higher incidence of both minor and overall complications among cases 28-40. After 40 cases, a significant decrease in these parameters was observed again. Our analysis demonstrated that operation time, blood loss, and minor complications decrease with increasing surgical experience in iRARC, while suggesting that technically challenging cases should be operated on after experience with 40 robotic cystectomies.

Preoperative predictors of prolonged length of stay in radical cystectomy: a retrospective study using the American College of Surgeons-National Surgical Quality Improvement Program Dataset

Background

Radical cystectomy (RC) is considered a complex procedure that entails significant morbidity and mortality.

Objectives

We aimed to determine pre-operative patient characteristics that help predict a prolonged length of hospital stay (PLOS) following RC.

Design and Methods

The American College of Surgeons-National Surgical Quality Improvement Program (ACS-NSQIP) database was used to select patients who underwent RC between the years 2011 and 2020. Prolonged length of stay was defined as a hospital stay ⩾9 days. We compared patient demographics, pre-operative labs, surgical characteristics, and medical history between patients with or without PLOS. Multivariable logistic regression models controlling for pre-operative characteristics and propensity score matching for post-operative complications were conducted to control for possible confounders.

Results

The analysis yielded details of 19,158 RC patients of which 6007 (31%) patients had a PLOS. Patients with PLOS were more likely to have post-operative complications that could serve as predictors for the PLOS rather than their pre-operative characteristics. Hence, we matched our cohort for these complications. After matching, patient pre-operative characteristics that predict PLOS included female gender (Odds Ratio (OR) = 5.91), 10-year increase in age (OR = 1.15), non-White race (OR = 1.98), partially or totally dependent functional health status (OR = 2.86), bleeding disorders (OR = 4.67), congestive heart failure (OR = 1.59), pre-operative transfusion (OR = 3.03), and a 20-min increase in operative time (OR = 1.01) (p < 0.046).

Conclusion

Patient demographics and pre-operative factors can help predict PLOS in RC patients. These predictors could serve as tools for patient counseling and risk stratification.

Optimization of Tree-Based Machine Learning Models to Predict the Length of Hospital Stay Using Genetic Algorithm

The length of hospital stay (LOS) is a significant indicator of the quality of patient care, hospital efficiency, and operational resilience. Considering the importance of LOS in hospital resource management, this research aims to improve the accuracy of LOS prediction using hyperparameter optimization (HPO). Expert physicians and related studies were reviewed to determine the variables affecting LOS. The electronic medical records of 200 patients in the department of internal medicine of a hospital in Iran were collected randomly. As the performance of machine learning (ML) models can vary based on the characteristics of the features, several models were applied and evaluated in this study. In particular, k-nearest neighbors (KNN), multivariate regression, decision tree (DT), random forest (RF), artificial neural network (ANN), and XGBoost have been evaluated and improved. The genetic algorithm (GA) was applied to optimize the tree-based models. In addition, the dummy coding technique, sometimes called the One-Hot encoding, was used to encode categorical features to increase prediction accuracy. Compared with other algorithms, the XGBoost model optimized by GA (XGB_GA) achieved higher accuracy and better prediction performance. The mean and median of absolute errors in the test dataset for this model were 1.54 and 1.14 days, respectively. In other words, the XGB_GA model reduced the mean absolute error by 37%, which is beneficial in the reliable design of a clinical decision support system.

Preoperative MELD score predicts mortality and adverse outcomes following radical cystectomy: analysis of American College of Surgeons National Surgical Quality Improvement Program

BACKGROUND

The model for end-stage liver disease (MELD) has been widely used to predict the mortality and morbidity of various surgical procedures.

OBJECTIVES

We aimed to correlate a high preoperative MELD score with adverse 30-day postoperative complications following radical cystectomy.

DESIGN AND METHODS

Patients who underwent elective, non-emergency radical cystectomy were identified from the American College of Surgeons-National Surgical Quality Improvement Program (ACS-NSQIP) database from 2005 to 2017. Patients were categorized according to a calculated MELD score. The primary outcomes of this study were 30-day postoperative mortality, morbidity, and length of hospital stay following radical cystectomy. For further sensitivity analysis, propensity score matching was used to yield a total of 1387 matched pairs and primary outcomes were also assessed in the matched cohort.

RESULTS

Compared with patients with a MELD < 10, those with MELD ⩾ 10 had significantly higher rates of mortality [odds ratio (OR) = 1.71, p = 0.004], major complications (OR = 1.42, p < 0.001), and prolonged hospital stay (OR = 1.29, p < 0.001) on multivariate analysis. Following risk-adjustment for race, propensity-matched groups revealed that patients with MELD score ⩾ 10 were significantly associated with higher mortality (OR = 1.85, p = 0.008), major complications (OR = 1.34, p < 0.001), yet similar length of hospital stay (OR = 1.17, p = 0.072).

CONCLUSION

MELD score ⩾ 10 is associated with higher mortality and morbidity in patients undergoing radical cystectomy compared with lower MELD scores. Risk-stratification using MELD score may assist clinicians in identifying high-risk patients to provide adequate preoperative counseling, optimize perioperative conditions, and even consider nonsurgical alternatives.

Hospital Length of Stay Prediction Methods: A Systematic Review

OBJECTIVE

This systematic review sought to establish a picture of length of stay (LOS) prediction methods based on available hospital data and study protocols designed to measure their performance.

MATERIALS AND METHODS

An English literature search was done relative to hospital LOS prediction from 1972 to September 2019 according to the PRISMA guidelines. Articles were retrieved from PubMed, ScienceDirect, and arXiv databases. Information were extracted from the included papers according to a standardized assessment of population setting and study sample, data sources and input variables, LOS prediction methods, validation study design, and performance evaluation metrics.

RESULTS

Among 74 selected articles, 98.6% (73/74) used patients' data to predict LOS; 27.0% (20/74) used temporal data; and 21.6% (16/74) used the data about hospitals. Overall, regressions were the most popular prediction methods (64.9%, 48/74), followed by machine learning (20.3%, 15/74) and deep learning (17.6%, 13/74). Regarding validation design, 35.1% (26/74) did not use a test set, whereas 47.3% (35/74) used a separate test set, and 17.6% (13/74) used cross-validation. The most used performance metrics were R2 (47.3%, 35/74), mean squared (or absolute) error (24.4%, 18/74), and the accuracy (14.9%, 11/74). Over the last decade, machine learning and deep learning methods became more popular (P=0.016), and test sets and cross-validation got more and more used (P=0.014).

CONCLUSIONS

Methods to predict LOS are more and more elaborate and the assessment of their validity is increasingly rigorous. Reducing heterogeneity in how these methods are used and reported is key to transparency on their performance.