TOP-Net Prediction Model Using Bidirectional Long Short-term Memory and Medical-Grade Wearable Multisensor System for Tachycardia Onset: Algorithm Development Study

Abstract

Background: Without timely diagnosis and treatment, tachycardia, also called tachyarrhythmia, can cause serious complications such as heart failure, cardiac arrest, and even death. The predictive performance of conventional clinical diagnostic procedures needs improvement in order to assist physicians in detecting risk early on.

Objective: We aimed to develop a deep tachycardia onset prediction (TOP-Net) model based on deep learning (ie, bidirectional long short-term memory) for early tachycardia diagnosis with easily accessible data.

Methods: TOP-Net leverages 2 easily accessible data sources: vital signs, including heart rate, respiratory rate, and blood oxygen saturation (SpO₂) acquired continuously by wearable embedded systems, and electronic health records, containing age, gender, admission type, first care unit, and cardiovascular disease history. The model was trained with a large data set from an intensive care unit and then transferred to a real-world scenario in the general ward. In this study, 3 experiments incorporated merging patients' personal information, temporal memory, and different feature combinations. Six metrics (area under the receiver operating characteristic curve [AUROC], sensitivity, specificity, accuracy, F1 score, and precision) were used to evaluate predictive performance.

Results: TOP-Net outperformed the baseline models on the large critical care data set (AUROC 0.796, 95% CI 0.768-0.824; sensitivity 0.753, 95% CI 0.663-0.793; specificity 0.720, 95% CI 0.645-0.758; accuracy 0.721; F1 score 0.718; precision 0.686) when predicting tachycardia onset 6 hours in advance. When predicting tachycardia onset 2 hours in advance with data acquired from our hospital using the transferred TOP-Net, the 6 metrics were 0.965, 0.955, 0.881, 0.937, 0.793, and 0.680, respectively. The best performance was achieved using comprehensive vital signs (heart rate, respiratory rate, and SpO₂) statistical information.

Conclusions: TOP-Net is an early tachycardia prediction model that uses 8 types of data from wearable sensors and electronic health records. When validated in clinical scenarios, the model achieved a prediction performance that outperformed baseline models 0 to 6 hours before tachycardia onset in the intensive care unit and 2 hours before tachycardia onset in the general ward. Because of the model's implementation and use of easily accessible data from wearable sensors, the model can assist physicians with early discovery of patients at risk in general wards and houses.

Keywords: deep neural network; early prediction; electronic health record; tachycardia onset; wearable monitoring system.

Figure 1

The process of developing and transferring the early tachycardia onset model, TOP-Net. GW: general ward; ICU: intensive care unit.

Figure 2

An overview of TOP-Net using the cohort admission and personal measurement data in hospital. BiLSTM: bidirectional long short-term memory; EHR: electronic health record; HR: heart rate; RR: respiratory rate; SpO₂: blood oxygen saturation.

Figure 3

The connection between clinical and waveform information in the MIMIC-III database.

Figure 4

Overview of the SensEcho system.

Figure 5

The connection between clinical and waveform information monitored by SensEcho.

Figure 6

Continuous monitoring using (a) SensEcho system with (b) example of a patient with sensors attached, and (c) sample data. HR: heart rate; RR: respiratory rate; SpO₂: blood oxygen saturation.

Figure 7

TOP-Net performance: (a) AUROC and (b) F1 score. AUROC: area under the receiver operating characteristic curve; CNN: convolutional neural network; LSTM: long short-term memory; XGBoost: extreme gradient boosting; MLP: multilayer perceptron; RF: random forest; TO: tachycardia onset.

Figure 8

Statistical feature rankings.

Figure 9

Example of a tachycardia event and our risk score of predicting tachycardia onset. HR: heart rate.