ObjectiveTo explore the development and application of a novel ventilator alarm management model in critically ill patients receiving invasive mechanical ventilation (MV) in the intensive care unit (ICU) using machine learning (ML) and Internet of Medical Things (IoMT). The study aims to identify alarms’ intervention requirements. MethodsA retrospective cohort study and ML analysis were conducted, including adult patients receiving invasive MV in the ICU at West China Hospital from February 10, 2024, to July 22, 2024. A total of 76 ventilator alarm-related parameters were collected through the IoMT system. Feature selection was performed using a stratified approach, and six ML algorithms were applied: Gaussian Naive Bayes, K-Nearest Neighbors, Linear Discriminant Analysis, Support Vector Machine, Categorical Boosting (CatBoost), and Logistic Regression. Model performance was evaluated using the area under the receiver operating characteristic curve (AUC-ROC). ResultsA total of 107 patients and their associated ventilator alarm records were included. Thirteen highly relevant features were selected from the 76 parameters for model training through stratified feature selection. The CatBoost model demonstrated the best predictive performance, with an AUC-ROC of 0.984 7 and an accuracy of 0.912 3 in the training set. External validation of the CatBoost model yielded an AUC-ROC of 0.805 4. ConclusionThe CatBoost-based ML model successfully constructed in this study has high accuracy and reliability in predicting the ventilator alarms in ICU patients, providing an effective tool for ventilator alarm management. The CatBoost-based ML method exhibited remarkable efficacy in predicting the necessity of ventilator intervention in critically ill ICU patients. Further large-scale multicenter studies are recommended to validate its clinical application value and promote model optimization and implementation.
In the internet of medical things, data primarily exhibits time-series and streaming characteristics, featuring typical attributes such as large-scale volume, high transmission rates, and significant heterogeneity. Given these data properties and the application requirements of medical scenarios, the development of specialized data platforms tailored to these needs holds considerable research significance and practical value. This study innovatively proposes the internet of medical things data platform solution based on a cloud-edge-end architecture, and elaborates on its architecture, functions, and implementation effects. The edge side is responsible for streaming data access, storage, and computation; the cloud side encompasses three layers of services: resources, data, and applications, constructing a data lake to provide data analysis services. This study has been implemented in PLA General Hospital for verification. From 2021 to 2024, 263 medical devices have been connected accumulatively, with a total data volume of 24.07 TB and stable operation within 4 years. In the performance stress test, the platform achieved the data access throughput of 23.91 MB/s and the data storage efficiency of 30.98 MB/s. These results demonstrate the feasibility of the architecture platform. This study has engineered and successfully applied the cloud-edge-end architecture in complex internet of medical things scenarios, addressing challenges such as heterogeneous protocol compatibility of medical devices, real-time response to clinical operations, and large-scale storage and application of the internet of things data. The established data platform provides a solid data foundation for smart medical applications and holds significant value for the research of medical artificial intelligence and the construction of future smart hospitals.