This study developed and validated a machine learning model to accurately predict acute kidney injury (AKI) after non-cardiac surgery, aiming to improve patient outcomes by assessing its clinical feasibility and generalizability. We conducted a retrospective cohort study using data from 76,032 adults who underwent non-cardiac surgery at a single tertiary medical center between March 2019 and February 2021, and used data from 5512 patients from the VitalDB open dataset for external model validation. The predictive variables for model training consisted of demographic, preoperative laboratory, and intraoperative data, including calculated statistical values such as the minimum, maximum, and mean intraoperative blood pressure. When predicting postoperative AKI, our gradient boosting machine model incorporating all the variables achieved the best results, with AUROC values of 0.868 and 0.757 for the internal and external validations using the VitalDB dataset, respectively. The model using intraoperative data performed best in internal validation, while the model with preoperative data excelled in external validation. In this study, we developed a predictive model for postoperative AKI in adult patients undergoing non-cardiac surgery using preoperative and intraoperative data, and external validation demonstrated the efficacy of open datasets for generalization in medical artificial modeling research.

Lee SW, et al. J Korean Med Sci. 2024 Jul;39:e241. https://doi.org/10.3346/jkms.2024.39.e241

Background: This retrospective study introduces an AI-driven VitalCare-Major Adverse Event Score (VC-MAES) developed to predict major in-hospital adverse events and determine optimal cutoff thresholds. VC-MAES was originally developed to predict a composite outcome including unplanned intensive care unit (ICU) transfer, in-hospital cardiac arrest, and mortality; the present study evaluates its performance for the composite of unplanned ICU transfer and in-hospital cardiac arrest. Methods: Patients aged ≥19 years in Yongin Severance Hospital between 1 March 2020, and 31 December 2022, were included. The primary outcome was clinica l deterioration, defined as unplanned ICU transfer or in-hospital cardiac arrest. Secondary outcomes included model performance metrics (area under the receiver operating characteristic (ROC) curve, sensitivity, specificity, F1 score) and optimal alarm frequency (number of alarms per 100 patient-days) across cutoff determination methods (Youden’s index, F1 score, Euclidean distance, and alarm-based approach); they were used to determine optimal cutoff values. 20 July 2026. Results: VC-MAES achieved an area under the ROC curve of 0.895(full evaluable sample) at 6-h intervals, outperforming traditional early warning systems. It exhibited improved sensitivity (0.5853) compared to NEWS (0.3775) and MEWS (0.3049) while maintaining a specificity exceeding 0.95, balancing alarm frequency and predictive accuracy (all figures based on each model’s own full evaluable sample: VC-MAES, n = 7425 events; NEWS, n = 3494; MEWS, n = 3198). On the common prediction time-point sample (n = 1678 events), the alarm-based cutoff yielded a sensitivity of 0.5244 for VC-MAES versus 0.2271 for NEWS and 0.1740 for MEWS, with alarm frequencies of 9.67, 7.07, and 5.58 per 100 patient-days, respectively. When compared on a common set of prediction time-points, VC-MAES (AUROC 0.832 on the common sample, 95% CI: 0.822–0.842) significantly outperformed NEWS (AUROC 0.743, 95% CI: 0.732–0.756; DeLong Z = −14.19, p < 0.0001) and MEWS (AUROC 0.706, 95% CI: 0.693–0.720; DeLong Z = −18.22, p < 0.0001). ROC-based methods, such as Youden’s index and Euclidean distance, were deemed unsuitable for practical clinical use. Conclusions: Conventional ROC-based cutoff selection methods may not be suitable for real-world clinical implementation due to excessive alarm burden. An alarm-based cutoff approach provides a more clinically applicable strategy by balancing predictive performance with manageable alarm frequency. These findings highlight the importance of incorporating clinical usability into cutoff determination for AI-based early warning systems.

Background: Pneumonia-associated sepsis constitutes a significant portion of all sepsis cases and is a leading cause of sepsis-related morbidity and mortality. The clinical burden is especially pronounced in general ward settings, where delayed recognition can hinder timely intervention. This underscores the necessity for advanced tools that facilitate early detection. Methods: This retrospective, single-center study assessed an AI-driven deep learning model designed to predict in-hospital sepsis up to four hours in advance. We analyzed 7715 pneumonia cases identified through chest radiography or CT. The model’s performance was evaluated using AUROC, sensitivity, specificity, and lead time to sepsis onset and was compared against established scoring systems: NEWS, MEWS, SOFA, and qSOFA. Sepsis was defined according to the CDC Adult Sepsis Event criteria in alignment with Sepsis-3 guidelines. Results: The AI model exhibited strong performance in the early detection of sepsis among pneumonia patients, achieving an AUROC of 0.870, with a sensitivity of 76.7% and specificity of 84.1%. It significantly surpassed conventional scoring systems: NEWS (0.697), MEWS (0.661), SOFA (0.649), and qSOFA (0.678). Importantly, the model identified sepsis a median of 183 min earlier than recognition based on the operational definition. This lead-time advantage was consistent in the pneumonia cohort, where 18.3% of patients developed sepsis. Conclusions: The AI model demonstrated strong predictive capabilities for pneumonia-associated sepsis, facilitating earlier clinical decision-making. Integrating this model into EMR systems could be an effective strategy to enhance sepsis outcomes in general ward settings. Further prospective studies are needed to validate its effectiveness in real-time clinical applications.