Search

This project assessed the use of multivariate auto-regressive (MAR) models to create forecasts of continuous vital signs in hospitalized patients. A total of 20 hours continuous (1/60Hz) heart rate and respiration rate from eight postoperative patients, where used to fit a centered MAR model for forecasting in windows of 15 minutes. The model was fitted using Markov Chain Monte Carlo sampling, and the model was evaluated on data from five additional patients. The results demonstrate an average RMSE in the forecast window of 11.4 (SD: 7.30) beats per minute for heart rate and 3.3 (SD:1.3) breaths per minute for respiration rate. These results indicate potential for forecasting vital signs in a clinical setting.

The period directly following surgery is critical for patients as they are at risk of infections and other types of complications, often summarized as severe adverse events (SAE). We hypothesize that impending complications might alter the circadian rhythm and, therefore, be detectable during the night before. We propose a SMOTE-enhanced XGBoost prediction model that classifies nighttime vital signs depending on whether they precede a serious adverse event or come from a patient that does not have a complication at all, based on data from 450 postoperative patients. The approach showed respectable results, producing a ROC-AUC score of 0.65 and an accuracy of 0.75. These findings demonstrate the need for further investigation.

Deep learning has gained increased impact on medical classification problems in recent years, with models being trained to high performance. However neural networks require large amounts of labeled data, which on medical data can be expensive and cumbersome to obtain. We propose a semi-supervised setup using an unsupervised variational autoencoder combined with a supervised classifier to distinguish between atrial fibrillation and non-atrial fibrillation using ECG records from the MIT-BIH Atrial Fibrillation Database. The proposed model was compared to a fully-supervised convolutional neural network at different proportions of labeled and unlabeled data (1%-50% labeled and the remaining unlabeled). The results demonstrate that the semi-supervised approach was superior to the fully-supervised, from using as little as 5% (5,594 samples) labeled data with an accuracy of 98.7%. The work provides proof of concept and demonstrates that the proposed semisupervised setup can train high accuracy models at low amounts of labeled data.

Monitoring post-operative patients is important for preventing severe adverse events (SAE), which increases morbidity and mortality. Conventional bedside monitoring system has demonstrated the difficulty in long term monitoring of those patients because majority of them are ambulatory. With development of wearable system and advanced data analytics, those patients would benefit greatly from continuous and predictive monitoring. In this study, we aim to predict SAE based on monitoring of vital signs. Heart rate, respiration rate, and blood oxygen saturation were continuously acquired by wearable devices and blood pressure was measured intermittently from 453 post-operative patients. SAEs from various complications were extracted from patients' database. The trends of vital signs were first extracted with moving average. Then four descriptive statistics were calculated from trend of each modality as features. Finally, a machine learning approach based on support vector machine was employed for prediction of SAE. It has shown the averaged accuracy of 89%, sensitivity of 80%, specificity of 93% and the area under receiver operating characteristic curve (AUROC) of 93%. These findings are promising and demonstrate the feasibility of predicting SAE from vital signs acquired with wearable devices and measured intermittently.