ABSTRACT
BACKGROUND: Cardiac arrest is a leading cause of mortality prior to discharge for children admitted to the pediatric intensive care unit. To address this problem, we used machine learning to predict cardiac arrest up to three hours in advance. METHODS: Our data consists of 240 Hz ECG waveform data, 0.5 Hz physiological time series data, medications, and demographics from 1,145 patients in the pediatric intensive care unit at the Johns Hopkins Hospital, 15 of whom experienced a cardiac arrest. The data were divided into training, validating, and testing sets, and features were generated every five minutes. 23 heart rate variability (HRV) metrics were determined from ECG waveforms. 96 summary statistics were calculated for 12 vital signs, such as respiratory rate and blood pressure. Medications were classified into 42 therapeutic drug classes. Binary features were generated to indicate the administration of these different drugs. Next, six machine learning models were evaluated: logistic regression, support vector machine, random forest, XGBoost, LightGBM, and a soft voting ensemble. RESULTS: XGBoost performed the best, with 0.971 auROC, 0.797 auPRC, 99.5% sensitivity, and 69.6% specificity on an independent test set. CONCLUSION: We have created high-performing models that identify signatures of in-hospital cardiac arrest (IHCA) that may not be evident to clinicians. These signatures include a combination of heart rate variability metrics, vital signs data, and therapeutic drug classes. These machine learning models can predict IHCA up to three hours prior to onset with high performance, allowing clinicians to intervene earlier, improving patient outcomes.
Subject(s)
Heart Arrest , Child , Humans , Pilot Projects , Intensive Care Units, Pediatric , Vital Signs , Machine Learning , Intensive Care UnitsABSTRACT
There have been over 621 million cases of COVID-19 worldwide with over 6.5 million deaths. Despite the high secondary attack rate of COVID-19 in shared households, some exposed individuals do not contract the virus. In addition, little is known about whether the occurrence of COVID-19 resistance differs among people by health characteristics as stored in the electronic health records (EHR). In this retrospective analysis, we develop a statistical model to predict COVID-19 resistance in 8,536 individuals with prior COVID-19 exposure using demographics, diagnostic codes, outpatient medication orders, and count of Elixhauser comorbidities in EHR data from the COVID-19 Precision Medicine Platform Registry. Cluster analyses identified 5 patterns of diagnostic codes that distinguished resistant from non-resistant patients in our study population. In addition, our models showed modest performance in predicting COVID-19 resistance (best performing model AUROC = 0.61). Monte Carlo simulations conducted indicated that the AUROC results are statistically significant (p < 0.001) for the testing set. We hope to validate the features found to be associated with resistance/non-resistance through more advanced association studies.
Subject(s)
COVID-19 , Humans , SARS-CoV-2 , Retrospective Studies , Machine Learning , Electronic Health RecordsABSTRACT
Purpose: The objective of the study is to develop deep learning models using synthetic fundus images to assess the direction (intorsion versus extorsion) and amount (physiologic versus pathologic) of static ocular torsion. Static ocular torsion assessment is an important clinical tool for classifying vertical ocular misalignment; however, current methods are time-intensive with steep learning curves for frontline providers. Methods: We used a dataset (n = 276) of right eye fundus images. The disc-foveal angle was calculated using ImageJ to generate synthetic images via image rotation. Using synthetic datasets (n = 12,740 images per model) and transfer learning (the reuse of a pretrained deep learning model on a new task), we developed a binary classifier (intorsion versus extorsion) and a multiclass classifier (physiologic versus pathologic intorsion and extorsion). Model performance was evaluated on unseen synthetic and nonsynthetic data. Results: On the synthetic dataset, the binary classifier had an accuracy and area under the receiver operating characteristic curve (AUROC) of 0.92 and 0.98, respectively, whereas the multiclass classifier had an accuracy and AUROC of 0.77 and 0.94, respectively. The binary classifier generalized well on the nonsynthetic data (accuracy = 0.94; AUROC = 1.00). Conclusions: The direction of static ocular torsion can be detected from synthetic fundus images using deep learning methods, which is key to differentiate between vestibular misalignment (skew deviation) and ocular muscle misalignment (superior oblique palsies). Translational Relevance: Given the robust performance of our models on real fundus images, similar strategies can be adopted for deep learning research in rare neuro-ophthalmologic diseases with limited datasets.