Objective To analyze the common causes of ventilator alarms during mechanical ventilation and their management. Methods A total of 104 ventilator alarms that were not instantly solved by first-line residents but referred to pulmonary therapist and attending physicians during September 2007 and August 2008 in the MICU of our hospital were analyzed retrospectively. Results Of all the 104 ventilator alarms, 27 ( 26%) were due to problems of ventilation circuits; 18 were due to patient effortagainst ventilator secondary to anxiety, horror or pain; 15 were due to inappropriate ventilator parameters;13 were due to airway problems; 5 were due to ventilator malfunction; 4 were due to worsening clinical status; 22 were due to other causes. Conclusion During mechanical ventilation, accurate assessment andprompt management of ventilator alarms are of great importance to patient safety and ventilation efficacy.
Objective To investigate the relationship between the tibia callus diameter ratio(CDR) and prognosis during tibial distraction and the occurrenceof late deformity or fracture. Methods We measured tibiallengthening callus diameter and added up the cases of angular deformity and fracture in 68 casesfrom January 1996 to December 2001, to calculated callus diameter ratios and compare the relationship between the tibia callus diameter during tibial distraction and the occurrence of late callus angular deformity or fracture. Results In 23 cases of CDRlt;80%, 13 cases had new bone fracture, 21 cases had angular deformity gt;5 degree. In 6 cases of 81%lt;CDRlt;85%, there were 4 cases of angular deformity gt;5 degree. In the other 39 cases of CDRgt;85%, there were no fracture and angular deformity. Conclusion When the CDR was gt;85%, there wereno angular deformity and fracture, but when the CDR was lt;80%, the complications of fracture and angular deformity occur. CDR is a better alarming index for preventing the complications occurring in tibial lengthening.
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 the 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 February10, 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.