Search

Background: This study aimed to examine the performance of machine learning algorithms for the prediction of discharge within 12 and 24 h to produce a measure of readiness for discharge after general surgery. Methods: Consecutive general surgery patients at two tertiary hospitals, over a 2‐year period, were included. Observation and laboratory parameter data were stratified into training, testing and validation datasets. Random forest, XGBoost and logistic regression models were evaluated. Each ward round note time was taken as a different event. Primary outcome was classification accuracy of the algorithmic model able to predict discharge within the next 12 h on the validation data set. Results: 42 572 ward round note timings were included from 8826 general surgery patients. Discharge occurred within 12 h for 8800 times (20.7%), and within 24 h for 9885 (23.2%). For predicting discharge within 12 h, model classification accuracies for derivation and validation data sets were: 0.84 and 0.85 random forest, 0.84 and 0.83 XGBoost, 0.80 and 0.81 logistic regression. For predicting discharge within 24 h, model classification accuracies for derivation and validation data sets were: 0.83 and 0.84 random forest, 0.82 and 0.81 XGBoost, 0.78 and 0.79 logistic regression. Algorithms generated a continuous number between 0 and 1 (or 0 and 100), representing readiness for discharge after general surgery. Conclusions: A derived artificial intelligence measure (the Adelaide Score) successfully predicts discharge within the next 12 and 24 h in general surgery patients. This may be useful for both treating teams and allied health staff within surgical systems. [ABSTRACT FROM AUTHOR]

Objective: Liver resections for non‐colorectal non‐neuroendocrine liver metastases (NCNELM) are gaining popularity. This study examines the outcomes of liver resections in patients with NCNELM in an Australian hospital. Method: A database search identified 21 attempted liver resections on 20 patients (12 men, eight women, mean age: 63.1) from 1998 to 2013. A retrospective analysis considered patient demographics and primary malignancy details. Complication rates were compared to those for colorectal metastases at the same institution. Kaplan–Meier curves were used to plot overall survival. Results: Complete resection was achieved in 16 of the 21 operations with 13 cases having proven metastases (three cases were benign lesions on final histology). Primary cancers were gastric (n = 4), gall bladder/bile duct (n = 3), renal (n = 3), soft tissue sarcoma (n = 3), melanoma (n = 2), pancreatic (n = 2), anal (n = 2), breast (n = 1) and unknown (n = 1). Primary histology types were adenocarcinoma (n = 10), sarcoma (n = 3), renal cell (n = 3), squamous cell (n = 2), melanoma (n = 2) and gastrointestinal stromal tumour (n = 1). There was no peri‐operative mortality. Significant post‐operative complications (Clavien–Dindo Grade III or more) occurred in six patients (28.5%). Overall survival at 2 and 5 years was 46.2% and 30.8%, respectively, for all 21 cases of attempted resection, and 51.9% and 34.6%, respectively, for the 13 cases of complete resection of malignant metastases. Conclusions: This study produced comparable 5‐year survival rates to those reported after liver resection for colorectal metastases and in other studies on NCNELM. Complication rates were comparable to those for colorectal liver metastasis resection at the same institution. [ABSTRACT FROM AUTHOR]