Soo Bin Yoon

In modern anesthesia, multiple medical devices are used simultaneously to comprehensively monitor real-time vital signs to optimize patient care and improve surgical outcomes. However, interpreting the dynamic changes of time-series biosignals and their correlations is a difficult task even for experienced anesthesiologists. Recent advanced machine learning technologies have shown promising results in biosignal analysis, however, research and development in this area is relatively slow due to the lack of biosignal datasets for machine learning. The VitalDB (Vital Signs DataBase) is an open dataset created specifically to facilitate machine learning studies related to monitoring vital signs in surgical patients. This dataset contains high-resolution multi-parameter data from 6,388 cases, including 486,451 waveform and numeric data tracks of 196 intraoperative monitoring parameters, 73 perioperative clinical parameters, and 34 time-series laboratory result parameters. All data is stored in the public cloud after anonymization. The dataset can be freely accessed and analysed using application programming interfaces and Python library. The VitalDB public dataset is expected to be a valuable resource for biosignal research and development.

Acute kidney injury (AKI) after liver transplantation has been reported to be associated with increased mortality. Recently, machine learning approaches were reported to have better predictive ability than the classic statistical analysis. We compared the performance of machine learning approaches with that of logistic regression analysis to predict AKI after liver transplantation. We reviewed 1211 patients and preoperative and intraoperative anesthesia and surgery-related variables were obtained. The primary outcome was postoperative AKI defined by acute kidney injury network criteria. The following machine learning techniques were used: decision tree, random forest, gradient boosting machine, support vector machine, naïve Bayes, multilayer perceptron, and deep belief networks. These techniques were compared with logistic regression analysis regarding the area under the receiver-operating characteristic curve (AUROC). AKI developed in 365 patients (30.1%). The performance in terms of AUROC was best in gradient boosting machine among all analyses to predict AKI of all stages (0.90, 95% confidence interval [CI] 0.86⁻0.93) or stage 2 or 3 AKI. The AUROC of logistic regression analysis was 0.61 (95% CI 0.56⁻0.66). Decision tree and random forest techniques showed moderate performance (AUROC 0.86 and 0.85, respectively). The AUROC of support the vector machine, naïve Bayes, neural network, and deep belief network was smaller than that of the other models. In our comparison of seven machine learning approaches with logistic regression analysis, the gradient boosting machine showed the best performance with the highest AUROC. An internet-based risk estimator was developed based on our model of gradient boosting. However, prospective studies are required to validate our results.

Predicting in-hospital cardiac arrest in patients admitted to an intensive care unit (ICU) allows prompt interventions to improve patient outcomes. We developed and validated a machine learning-based real-time model for in-hospital cardiac arrest predictions using electrocardiogram (ECG)-based heart rate variability (HRV) measures. The HRV measures, including time/frequency domains and nonlinear measures, were calculated from 5 min epochs of ECG signals from ICU patients. A light gradient boosting machine (LGBM) algorithm was used to develop the proposed model for predicting in-hospital cardiac arrest within 0.5-24 h. The LGBM model using 33 HRV measures achieved an area under the receiver operating characteristic curve of 0.881 (95% CI: 0.875-0.887) and an area under the precision-recall curve of 0.104 (95% CI: 0.093-0.116). The most important feature was the baseline width of the triangular interpolation of the RR interval histogram. As our model uses only ECG data, it can be easily applied in clinical practice.

Bispectral index (BIS), a useful marker of anaesthetic depth, is calculated by a statistical multivariate model using nonlinear functions of electroencephalography-based subparameters. However, only a portion of the proprietary algorithm has been identified. We investigated the BIS algorithm using clinical big data and machine learning techniques. Retrospective data from 5,427 patients who underwent BIS monitoring during general anaesthesia were used, of which 80% and 20% were used as training datasets and test datasets, respectively. A histogram of data points was plotted to define five BIS ranges representing the depth of anaesthesia. Decision tree analysis was performed to determine the electroencephalography subparameters and their thresholds for classifying five BIS ranges. Random sample consensus regression analyses were performed using the subparameters to derive multiple linear regression models of BIS calculation in five BIS ranges. The performance of the decision tree and regression models was externally validated with positive predictive value and median absolute error, respectively. A four-level depth decision tree was built with four subparameters such as burst suppression ratio, power of electromyogram, 95% spectral edge frequency, and relative beta ratio. Positive predictive values were 100%, 80%, 80%, 85% and 89% in the order of increasing BIS in the five BIS ranges. The average of median absolute errors of regression models was 4.1 as BIS value. A data driven BIS calculation algorithm using multiple electroencephalography subparameters with different weights depending on BIS ranges has been proposed. The results may help the anaesthesiologists interpret the erroneous BIS values observed during clinical practice.