Background
Mechanical ventilation is a life-saving treatment in the Intensive Care Unit (ICU), but often causes patients to be at risk of further respiratory complication. We created a statistical model utilizing electronic health record and physiologic vitals data to predict the Center for Disease Control and Prevention (CDC) defined Ventilator Associated Complications (VACs).
Methods
We constructed a random forest model to predict occurrence of VACs using health records and chart events from adult patients in the Medical Information Mart for Intensive Care III (MIMIC-III) database. We trained the machine learning models on two patient populations of 1921 and 464 based on low and high frequency data availability. Model features were generated using both basic statistical summaries and tsfresh, an automated python feature generation library. Classification to determine whether a patient will experience VAC one hour after 36 hours of ventilation was performed using a random forest classifier. Two different sample spaces conditioned on five varying feature extraction techniques were evaluated to identify the most optimal selection of features resulting in the best VAC discrimination. Each dataset was assessed using K-folds cross-validation (k = 10), giving average area under the receiver operating curves (AUROC) s and accuracies.
Findings
After feature selection, hyperparameter tuning, and feature extraction, the best performing model used automatically generated features on high frequency data and achieved an average Area Under Receiver Operating Characteristic Curve (AUC) of 0.83 +/- 0.11 and an average accuracy of 0.69 +/- 0.10.
Interpretation
We constructed a promising model to predict VACs 1 hour prior to occurrence with 36 hours of ICU patient data. The model provides early warnings of VACs, which may allow actionable therapies to prevent or mitigate ventilator associated complications.
Schistosomiasis is still a public health burden in the Philippines. Chronic infection with Schistosoma japonicum, the only species endemic in the Philippines, clinically manifests itself in a wide variety of pathologies usually correlated with the anatomical site of adult worm activity and deposition of eggs. One of the documented ectopic sites for Schistosoma ova is the appendix. A rare sequela of this is acute appendicitis and an even rarer consequence is progression to appendiceal rupture leading to acute peritonitis. We present a case of a 27-year-old Filipino residing in Davao City but born in Agusan Province who initially complained of right lower quadrant abdominal pain but presented at the emergency room with generalized abdominal tenderness with signs of peritoneal irritation. Exploratory laparotomy with an infraumbilical incision revealed ruptured appendicitis with periappendiceal abscess formation and appendectomy was subsequently done. Schistosoma infection of the appendix was subsequently established by histopathological analysis. Furthermore, features observed suggest an atypical pathogenetic process contrary to the putative pathogenesis of most cases of acute appendicitis.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.