Machine learning versus logistic regression for the prediction of complications after pancreatoduodenectomy.

BACKGROUND: Machine learning is increasingly advocated to develop prediction models for postoperative complications. It is, however, unclear if machine learning is superior to logistic regression when using structured clinical data. Postoperative pancreatic fistula and delayed gastric emptying are the two most common complications with the biggest impact on patient condition and length of hospital stay after pancreatoduodenectomy. This study aimed to compare the performance of machine learning and logistic regression in predicting pancreatic fistula and delayed gastric emptying after pancreatoduodenectomy. METHODS: This retrospective observational study used nationwide data from 16 centers in the Dutch Pancreatic Cancer Audit between January 2014 and January 2021. The area under the curve of a machine learning and logistic regression model for clinically relevant postoperative pancreatic fistula and delayed gastric emptying were compared. RESULTS: Overall, 799 (16.3%) patients developed a postoperative pancreatic fistula, and 943 developed (19.2%) delayed gastric emptying. For postoperative pancreatic fistula, the area under the curve of the machine learning model was 0.74, and the area under the curve of the logistic regression model was 0.73. For delayed gastric emptying, the area under the curve of the machine learning model and logistic regression was 0.59. CONCLUSION: Machine learning did not outperform logistic regression modeling in predicting postoperative complications after pancreatoduodenectomy.

The effect of anastomotic leakage on the incidence of recurrence after tri-modality therapy for esophageal adenocarcinomas.

BACKGROUND: Neoadjuvant chemoradiotherapy (nCRTx) reduces the incidence of recurrence, while anastomotic leakage has shown increase the risk of recurrence. The primary objective of this retrospective study was to investigate the incidence and pattern of recurrence and secondary median recurrence-free interval and post-recurrence survival in patients with and without anastomotic leakage after multimodal therapy for esophageal adenocarcinoma. METHODS: Patients with recurrence after multimodal therapy between 2010 and 2018 were included. RESULTS: Six hundred and eighteen patients were included, 91 (14.7%) had leakage and 278 (45.0%) recurrence. Patients with leakage did not develop recurrence more often (48.4%) than those without (44.4%, [p = 0.484]). Recurrence-free interval for patients with (n = 44) and without leakage (n = 234) was 39 and 52 weeks, respectively (p = 0.049). Post-recurrence survival was 11 and 16 weeks, respectively (p = 0.702). Specified by recurrence site, post-recurrence survival for loco-regional recurrences was 27 versus 33 weeks (p = 0.387) for patients with and without leakage, for distant 9 versus 13 (p = 0.999), and for combined 11 versus 18 weeks (p = 0.492). CONCLUSION AND DISCUSSION: No higher incidence of recurrent disease was observed in patients with anastomotic leakage, however it is associated with a shorter recurrence-free interval. This could have implications for surveillance, as early detection of recurrent disease could influence therapeutic options.

Machine learning models in clinical practice for the prediction of postoperative complications after major abdominal surgery.

Complications after surgery have a major impact on short- and long-term outcomes, and decades of technological advancement have not yet led to the eradication of their risk. The accurate prediction of complications, recently enhanced by the development of machine learning algorithms, has the potential to completely reshape surgical patient management. In this paper, we reflect on multiple issues facing the implementation of machine learning, from the development to the actual implementation of machine learning models in daily clinical practice, providing suggestions on the use of machine learning models for predicting postoperative complications after major abdominal surgery.

Short-term outcome for high-risk patients after esophagectomy.

Transthoracic esophagectomy (TTE) for esophageal cancer facilitates mediastinal dissection; however, it has a significant impact on cardiopulmonary status. High-risk patients may therefore be better candidates for transhiatal esophagectomy (THE) in order to prevent serious complications. This study addressed short-term outcome following TTE and THE in patients that are considered to have a higher risk of surgery-related morbidity. This population-based study included patients who underwent a curative esophagectomy between 2011 and 2018, registered in the Dutch Upper GI Cancer Audit. The Charlson comorbidity index was used to assign patients to a low-risk (score ≤ 1) and high-risk group (score ≥ 2). Propensity score matching was applied to produce comparable groups between high-risk patients receiving TTE and THE. Primary endpoint was mortality (in-hospital/30-day mortality), secondary endpoints included morbidity and oncological outcomes. Additionally, a matched subgroup analysis was performed, including only cervical reconstructions. Of 5,438 patients, 945 and 431 high-risk patients underwent TTE and THE, respectively. After propensity score matching, mortality (6.3 vs 3.3%, P = 0.050), overall morbidity, Clavien-Dindo ≥ 3 complications, pulmonary complications, cardiac complications and re-interventions were significantly more observed after TTE compared to THE. A significantly higher mortality after TTE with a cervical reconstruction was found compared to THE (7.0 vs. 2.2%, P = 0.020). Patients with a high Charlson comorbidity index predispose for a complicated postoperative course after esophagectomy, this was more outspoken after TTE compared to THE. In daily practice, these outcomes should be balanced with the lower lymph node yield, but comparable positive node count and radicality after THE.

The prediction of surgical complications using artificial intelligence in patients undergoing major abdominal surgery: A systematic review.

BACKGROUND: Conventional statistics are based on a simple cause-and-effect principle. Postoperative complications, however, have a multifactorial and interrelated etiology. The application of artificial intelligence might be more accurate to predict postoperative outcomes. The objective of this study was to determine the current quality of studies describing the use of artificial intelligence in predicting complications in patients undergoing major abdominal surgery. METHODS: A literature search was performed in PubMed, Embase, and Web of Science. Inclusion criteria were (1) empirical studies including patients undergoing (2) any type of gastrointestinal surgery, including hepatopancreaticobiliary surgery, whose (3) complications or mortality were predicted with the use of (4) any artificial intelligence system. Studies were screened for description of method of validation and testing in methodology. Outcome measurements were sensitivity, specificity, accuracy, and area under the receiver operating characteristic curve. RESULTS: From a total of 1,537 identified articles, 15 were included for the review. Among a large variety of algorithms used by the included studies, sensitivity was between 0.06 and 0.96, specificity was between 0.61 and 0.98, accuracy was between 0.78 and 0.95, and area under the receiver operating characteristic curve varied between 0.50 and 0.96. CONCLUSION: Artificial intelligence algorithms have the ability to accurately predict postoperative complications. Nevertheless, algorithms should be properly tested and validated, both internally and externally. Furthermore, a complete database and the absence of unsampled imbalanced data are absolute prerequisites for algorithms to predict accurately.

The Predictive Value of the Load Sharing Classification Concerning Sagittal Collapse and Posterior Instrumentation Failure: A Systematic Literature Review.

STUDY DESIGN: Systematic review. OBJECTIVE: In 1994, the Load Sharing Classification (LSC) was introduced to aid the choice of surgical treatment of thoracolumbar spine fractures. Since that time this classification system has been commonly used in the field of spine surgery. However, current literature varies regarding its use and predictive value in relation to implant failure and sagittal collapse. The objective of this study is to assess the predictive value of the LSC concerning the need for anterior stabilization to prevent sagittal collapse and posterior instrumentation failure. METHODS: An electronic search of PubMed, Medline, Embase, and the Cochrane Library was performed. Inclusion criteria were (1) cohort or clinical trial (2) including patients with thoracolumbar burst fractures (3) whose severity of the fractured vertebrae was assessed by the LSC. RESULTS: Five thousand eighty-two articles have been identified, of which 21 articles were included for this review. Twelve studies reported no correlation between the LSC and sagittal collapse or instrumentation failure in patients treated with short-segment posterior instrumentation (SSPI). Seven articles found no significant relation; 5 articles found no instrumentation failure at all. The remaining 9 articles experienced failure in patients with a high LSC or recommended a different surgical technique. CONCLUSIONS: Although the LSC was originally developed to predict the need for anterior stabilization in addition to SSPI, many studies show that SSPI only can be sufficient in treating thoracolumbar fractures regardless of the LSC. The LSC might have lost its value in predicting sagittal collapse and posterior instrumentation failure.

Implementation of robot-assisted Ivor Lewis procedure: Robotic hand-sewn, linear or circular technique?

BACKGROUND: Robot-assisted surgery for esophageal cancer is increasingly applied. Despite this upsurge, the preferential technique to create a robot-assisted intrathoracic anastomosis has not been established. DATA SOURCES: Bibliographic databases were searched to identify studies that performed a robot-assisted Ivor Lewis esophagectomy and described the technical details of the anastomotic technique. Out of 1701 articles, 16 studies were included for systematic review. CONCLUSIONS: This review shows that all technique used to create a thoracoscopic anastomosis can be adopted to robotic surgery. Techniques can be divided into three categories: robotic hand-sewn, circular stapling or linear stapling and robotic hand-sewn closure of the stapler defect. With limited robotic experience, circular stapling might be the preferred technique, however requires a well-trained bedside assistant. The linear stapling technique or hand-sewn technique are more challenging but enable experienced robotic surgeons to perform a controlled anastomosis without bedside support.