Development of Machine Learning Models Predicting Estimated Blood Loss during Liver Transplant Surgery.

The incidence of major hemorrhage and transfusion during liver transplantation has decreased significantly over the past decade, but major bleeding remains a common expectation. Massive intraoperative hemorrhage during liver transplantation can lead to mortality or reoperation. This study aimed to develop machine learning models for the prediction of massive hemorrhage and a scoring system which is applicable to new patients. Data were retrospectively collected from patients aged >18 years who had undergone liver transplantation. These data included emergency information, donor information, demographic data, preoperative laboratory data, the etiology of hepatic failure, the Model for End-stage Liver Disease (MELD) score, surgical history, antiplatelet therapy, continuous renal replacement therapy (CRRT), the preoperative dose of vasopressor, and the estimated blood loss (EBL) during surgery. The logistic regression model was one of the best-performing machine learning models. The most important factors for the prediction of massive hemorrhage were the disease etiology, activated partial thromboplastin time (aPTT), operation duration, body temperature, MELD score, mean arterial pressure, serum creatinine, and pulse pressure. The risk-scoring system was developed using the odds ratios of these factors from the logistic model. The risk-scoring system showed good prediction performance and calibration (AUROC: 0.775, AUPR: 0.753).

Explainable machine learning model to predict refeeding hypophosphatemia.

BACKGROUND & AIMS: Refeeding syndrome (RFS) is a disease that occurs when feeding is restarted and metabolism changes from catabolic to anabolic status. RFS can manifest variously, ranging from asymptomatic to fatal, therefore it may easily be overlooked. RFS prediction using explainable machine learning can improve diagnosis and treatment. Our study aimed to propose a machine learning model for RFS prediction, specifically refeeding hypophosphatemia, to evaluate its performance compared with conventional regression models, and to explain the machine learning classification through Shapley additive explanations (SHAP) values. METHODS: A retrospective study was conducted including 806 patients, with 2 or more days of nothing-by-mouth prescription, and with phosphate (P) level measurements within 5 days of refeeding were selected. We divided the patients into hypophosphatemia (n = 367) and non-hypophosphatemia groups (n = 439) at a P level of 0.8 mmol/L. Among the features examined within 48 h after admission, we reviewed laboratory test results and electronic medical records. Logistic, Lasso, and ridge regressions were used as conventional models, and performances were compared with our extreme gradient boosting (XGBoost) machine learning model using the area under the receiver operating characteristic curve. Our model was explained using the SHAP value. RESULTS: The areas under the curve were 0.950 (95% confidence interval: 0.924-0.975) for our XGBoost machine learning model and surpassed the performance of conventional regression models; 0.760 (0.707-0.813) for logistic regression, 0.751 (0.694-0.807) for Lasso regression, and 0.758 (0.701-0.809) for ridge regression. According to the SHAP values in the order of importance, low initial P, recent weight loss, high creatinine, diabetes mellitus with insulin use, low haemoglobin A1c, furosemide use, intensive care unit admission, blood urea nitrogen level of 19-65, parenteral nutrition, magnesium below or above the normal range, low potassium, and older age were features to predict refeeding hypophosphatemia. CONCLUSIONS: The machine learning model for predicting RFS has a substantially higher effectiveness than conventional regression methods. Creating an accurate risk assessment tool based on machine learning for early identification of patients at risk for RFS can enable careful nutrition management planning and monitoring in the intensive care unit, towards reducing the incidence of RFS-related morbidity and mortality.

Ability of dynamic preload indices to predict fluid responsiveness in a high femoral-to-radial arterial pressure gradient: a retrospective study.

BACKGROUND: Dynamic preload indices may predict fluid responsiveness in end-stage liver disease. However, their usefulness in patients with altered vascular compliance is uncertain. This study is the first to evaluate whether dynamic indices can reliably predict fluid responsiveness in patients undergoing liver transplantation with a high femoral-to-radial arterial pressure gradient (PG). METHODS: Eighty liver transplant recipients were retrospectively categorized as having a normal (n = 56) or high (n = 24, difference in systolic pressure ≥ 10 mmHg and/or mean pressure ≥ 5 mmHg) femoral-to-radial arterial PG, measured immediately after radial and femoral arterial cannulation. The ability of dynamic preload indices (stroke volume variation, pulse pressure variation [PPV], pleth variability index) to predict fluid responsiveness was assessed before the surgery. Fluid replacement of 500 ml of crystalloid solution was performed over 15 min. Fluid responsiveness was defined as ≥ 15% increase in the stroke volume index. The area under the receiver-operating characteristic curve (AUC) indicated the prediction of fluid responsiveness. RESULTS: Fourteen patients in the normal, and eight in the high PG group were fluid responders. The AUCs for PPV in the normal, high PG groups and total patients were 0.702 (95% confidence interval [CI] 0.553-0.851, P = 0.008), 0.633 (95% CI 0.384-0.881, P = 0.295) and 0.667 (95% CI 0.537-0.798, P = 0.012), respectively. No other index predicted fluid responsiveness. CONCLUSIONS: PPV can be used as a dynamic index of fluid responsiveness in patients with end-stage liver disease but not in patients with altered vascular compliance.