Machine learning-based preoperative analytics for the prediction of anastomotic leakage in colorectal surgery: a swiss pilot study.

BACKGROUND: Anastomotic leakage (AL), a severe complication following colorectal surgery, arises from defects at the anastomosis site. This study evaluates the feasibility of predicting AL using machine learning (ML) algorithms based on preoperative data. METHODS: We retrospectively analyzed data including 21 predictors from patients undergoing colorectal surgery with bowel anastomosis at four Swiss hospitals. Several ML algorithms were applied for binary classification into AL or non-AL groups, utilizing a five-fold cross-validation strategy with a 90% training and 10% validation split. Additionally, a holdout test set from an external hospital was employed to assess the models' robustness in external validation. RESULTS: Among 1244 patients, 112 (9.0%) suffered from AL. The Random Forest model showed an AUC-ROC of 0.78 (SD: ± 0.01) on the internal test set, which significantly decreased to 0.60 (SD: ± 0.05) on the external holdout test set comprising 198 patients, including 7 (3.5%) with AL. Conversely, the Logistic Regression model demonstrated more consistent AUC-ROC values of 0.69 (SD: ± 0.01) on the internal set and 0.61 (SD: ± 0.05) on the external set. Accuracy measures for Random Forest were 0.82 (SD: ± 0.04) internally and 0.87 (SD: ± 0.08) externally, while Logistic Regression achieved accuracies of 0.81 (SD: ± 0.10) and 0.88 (SD: ± 0.15). F1 Scores for Random Forest moved from 0.58 (SD: ± 0.03) internally to 0.51 (SD: ± 0.03) externally, with Logistic Regression maintaining more stable scores of 0.53 (SD: ± 0.04) and 0.51 (SD: ± 0.02). CONCLUSION: In this pilot study, we evaluated ML-based prediction models for AL post-colorectal surgery and identified ten patient-related risk factors associated with AL. Highlighting the need for multicenter data, external validation, and larger sample sizes, our findings emphasize the potential of ML in enhancing surgical outcomes and inform future development of a web-based application for broader clinical use.

The Development of Electronic Health and Artificial Intelligence in Surgery after the SARS-CoV-2 Pandemic-A Scoping Review.

BACKGROUND: SARS-CoV-2 has significantly transformed the healthcare environment, and it has triggered the development of electronic health and artificial intelligence mechanisms, for instance. In this overview, we concentrated on enhancing the two concepts in surgery after the pandemic, and we examined the factors on a global scale. OBJECTIVE: The primary goal of this scoping review is to elaborate on how surgeons have used eHealth and AI before; during; and after the current global pandemic. More specifically, this review focuses on the empowerment of the concepts of electronic health and artificial intelligence after the pandemic; which mainly depend on the efforts of countries to advance the notions of surgery. DESIGN: The use of an online search engine was the most applied method. The publication years of all the studies included in the study ranged from 2013 to 2021. Out of the reviewed studies; forty-four qualified for inclusion in the review. DISCUSSION: We evaluated the prevalence of the concepts in different continents such as the United States; Europe; Asia; the Middle East; and Africa. Our research reveals that the success of eHealth and artificial intelligence adoption primarily depends on the efforts of countries to advance the notions in surgery. CONCLUSIONS: The study's primary limitation is insufficient information on eHealth and artificial intelligence concepts; particularly in developing nations. Future research should focus on establishing methods of handling eHealth and AI challenges around confidentiality and data security.