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.

Development and validation of a predictive model of the hospital cost associated with bariatric surgery.

Hospitals are facing difficulties in predicting, evaluating, and managing cost-affecting parameters in patient treatments. Inaccurate cost prediction leads to a deficit in operational revenue. This study aims to determine the ability of Machine Learning (ML) algorithms to predict the cost of care in bariatric and metabolic surgery and develop a predictive tool for improved cost analysis. 602 patients who underwent bariatric and metabolic surgery at Wetzikon hospital from 2013 to 2019 were included in the study. Multiple variables including patient factors, surgical factors, and post-operative complications were tested using a number of predictive modeling strategies. The study was registered under Req 2022-00659 and approved by an institutional review board. The cost was defined as the sum of all costs incurred during the hospital stay, expressed in CHF (Swiss Francs). The data was preprocessed and split into a training set (80%) and a test set (20%) to build and validate models. The final model was selected based on the mean absolute percentage error (MAPE). The Random Forest model was found to be the most accurate in predicting the overall cost of bariatric surgery with a mean absolute percentage error of 12.7. The study provides evidence that the Random Forest model could be used by hospitals to help with financial calculations and cost-efficient operation. However, further research is needed to improve its accuracy. This study serves as a proof of principle for an efficient ML-based prediction tool to be tested on multi-center data in future phases of the study.

Improved distinct bone segmentation in upper-body CT through multi-resolution networks.

PURPOSE: Automated distinct bone segmentation from CT scans is widely used in planning and navigation workflows. U-Net variants are known to provide excellent results in supervised semantic segmentation. However, in distinct bone segmentation from upper-body CTs a large field of view and a computationally taxing 3D architecture are required. This leads to low-resolution results lacking detail or localisation errors due to missing spatial context when using high-resolution inputs. METHODS: We propose to solve this problem by using end-to-end trainable segmentation networks that combine several 3D U-Nets working at different resolutions. Our approach, which extends and generalizes HookNet and MRN, captures spatial information at a lower resolution and skips the encoded information to the target network, which operates on smaller high-resolution inputs. We evaluated our proposed architecture against single-resolution networks and performed an ablation study on information concatenation and the number of context networks. RESULTS: Our proposed best network achieves a median DSC of 0.86 taken over all 125 segmented bone classes and reduces the confusion among similar-looking bones in different locations. These results outperform our previously published 3D U-Net baseline results on the task and distinct bone segmentation results reported by other groups. CONCLUSION: The presented multi-resolution 3D U-Nets address current shortcomings in bone segmentation from upper-body CT scans by allowing for capturing a larger field of view while avoiding the cubic growth of the input pixels and intermediate computations that quickly outgrow the computational capacities in 3D. The approach thus improves the accuracy and efficiency of distinct bone segmentation from upper-body CT.