Key result
Single-lead ECG machine learning model predicts next-day wellness in older adults with ~80% accuracy.
Why the study?
Continuous health monitoring with portable ECGs is promising, but dynamic and heterogeneous signal patterns make feature construction and predictive modeling for elderly wellness challenging.
Does an integrated machine learning approach using extracted features from single-lead short ECG signals improve one-day-forward wellness prediction accuracy in community-dwelling elderly compared to using raw ECG signals?
Does an integrated machine learning approach using extracted features from single-lead short ECG signals improve one-day-forward wellness prediction accuracy in community-dwelling elderly compared to using raw ECG signals?
An integrated machine learning strategy using multiple features extracted from single-lead ECGs significantly improves the automated prediction of short-term wellness changes in the elderly, offering a potential tool for proactive monitoring.
May enable daily wellness monitoring via portable ECG in older adults; hypothesis-generating and requires prospective validation before adoption.
The accelerated growth of elderly populations in many countries and regions worldwide is creating a major burden to the healthcare system. Intelligent approaches for continuous health monitoring have the potential to promote the transition to more proactive and affordable healthcare. Electrocardiograms (ECGs), collected from portable devices, with noninvasive and cost-effective merits, have been widely used to monitor various health conditions. However, the dynamic and heterogeneous pattern of ECG signals makes relevant feature construction and predictive model development a challenging task. In this study, we aim to develop an integrated approach for one-day-forward wellness prediction in the community-dwelling elderly using single-lead short ECG signal data via multiple-features construction and predictive model implementation. Vital signs data from the elderly were collected via station-based equipment on a daily basis. After data preprocessing, a set of features were constructed from ECG signals based on the integration of various models, including time and frequency domain analysis, a wavelet transform-based model, ensemble empirical mode decomposition (EEMD), and the refined composite multiscale sample entropy (RCMSE) model. Then, a machine learning based predictive model was established to map the l-day lagged features to wellness condition. The results showed that the approach developed in this study achieved the best performance for wellness prediction in the community-dwelling elderly. In practice, the proposed approach could be useful in the timely identification of elderly people who might have health risks, and could facilitating decision-making to take appropriate interventions.
No takes yet. Share an insight, caveat, or question.
Zhao et al. (2022) studied Community-dwelling elderly (n=11). Random forest predictive model with multiple-feature construction (from one-day lagged single-lead short ECG signals) vs. Predictive models without feature construction (raw ECG signals) was evaluated on One-day-forward wellness condition prediction accuracy. A random forest model utilizing 184 features extracted from single-lead short ECG signals achieved an accuracy of 80.4% for one-day-forward wellness prediction in older adults.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: