Background: Recent studies have linked low heart rate variability (HRV) with COVID-19, indicating that this parameter can be a marker of the onset of the disease and its severity and a predictor of mortality in infected people. Given the large number of wearable devices that capture physiological signals of the human body easily and noninvasively, several studies have used this equipment to measure the HRV of individuals and related these measures to COVID-19. Objective: The objective of this study was to assess the utility of HRV measurements obtained from wearable devices as predictive indicators of COVID-19, as well as the onset and worsening of symptoms in affected individuals. Methods: A systematic review was conducted searching the following databases up to the end of January 2023: Embase, PubMed, Web of Science, Scopus, and IEEE Xplore. Studies had to include (1) measures of HRV in patients with COVID-19 and (2) measurements involving the use of wearable devices. We also conducted a meta-analysis of these measures to reduce possible biases and increase the statistical power of the primary research. Results: The main finding was the association between low HRV and the onset and worsening of COVID-19 symptoms. In some cases, it was possible to predict the onset of COVID-19 before a positive clinical test. The meta-analysis of studies reported that a reduction in HRV parameters is associated with COVID-19. Individuals with COVID-19 presented a reduction in the SD of the normal-to-normal interbeat intervals and root mean square of the successive differences compared with healthy individuals. The decrease in the SD of the normal-to-normal interbeat intervals was 3.25 ms (95% CI −5.34 to −1.16 ms), and the decrease in the root mean square of the successive differences was 1.24 ms (95% CI −3.71 to 1.23 ms). Conclusions: Wearable devices that measure changes in HRV, such as smartwatches, rings, and bracelets, provide information that allows for the identification of COVID-19 during the presymptomatic period as well as its worsening through an indirect and noninvasive self-diagnosis.

Heart rate variability (HRV) is a validated biomarker of autonomic and inflammatory regulation, and has been associated with both acute COVID-19 and long COVID. Although RT-PCR remains the diagnostic gold standard for acute infection, there is a lack of accessible, noninvasive physiological tools to support ongoing monitoring and stage differentiation of COVID-19 and its sequelae. The growing availability of wearable devices capable of real-time HRV data collection opens opportunities for early detection and health status classification using machine learning. This study aimed to identify HRV patterns capable of distinguishing individuals with active COVID-19, long COVID, and healthy controls, using data collected from wearable devices and processed with machine learning models. A secondary objective was to assess the feasibility of a near-real-time health monitoring system based on these patterns using wearable-derived HRV data. HRV indices (SDNN, RMSSD, LF%, HF%) were collected from 61 participants (21 with active COVID-19, 20 with long COVID, and 20 healthy controls) using two standardized datasets. Classification models were developed using supervised machine learning algorithms (Decision Tree, SVM, k-NN, Neural Networks) and evaluated through cross-validation. A contextual clinical variable indicating recent SARS-CoV-2 infection was incorporated into one model configuration to assess its impact on classification performance. In addition, a prototype system for near-real-time monitoring was implemented and tested in a separate group of 4 participants. Participants with active COVID-19 showed significantly lower HRV indices (SDNN, RMSSD, LF%, HF%) compared to both long COVID and healthy controls (P ≤ .0007), while differences between the long COVID and healthy groups were not statistically significant. Decision tree models trained solely on HRV features achieved 76.4% accuracy, with high discriminative performance for active COVID-19 (F1 = 88%, AUC = 0.85), but limited detection of long COVID (F1 = 56%). When a contextual clinical variable indicating recent SARS-CoV-2 infection was included, overall accuracy increased to 87%, and the F1-score for long COVID rose to 92%, with improved AUC metrics across classes. A prototype system tested on four independent participants correctly classified their status, demonstrating feasibility for near-real-time application. HRV patterns collected from wearable devices and analyzed via machine learning successfully distinguished active COVID-19 from healthy individuals with high accuracy using physiological data alone. When a clinical contextual variable indicating recent infection was added, the model also achieved strong performance in identifying long COVID cases. A prototype system demonstrated feasibility for near-real-time application, reinforcing the potential of HRV for individualized health monitoring in line with emerging trends in digital and predictive healthcare.

BACKGROUND Recent studies have linked low heart rate variability (HRV) with COVID-19, indicating that this parameter can be a marker of the onset of the disease and its severity and a predictor of mortality in infected people. Given the large number of wearable devices that capture physiological signals of the human body easily and noninvasively, several studies have used this equipment to measure the HRV of individuals and related these measures to COVID-19. OBJECTIVE The objective of this study was to assess the utility of HRV measurements obtained from wearable devices as predictive indicators of COVID-19, as well as the onset and worsening of symptoms in affected individuals. METHODS A systematic review was conducted searching the following databases up to the end of January 2023: Embase, PubMed, Web of Science, Scopus, and IEEE Xplore. Studies had to include (1) measures of HRV in patients with COVID-19 and (2) measurements involving the use of wearable devices. We also conducted a meta-analysis of these measures to reduce possible biases and increase the statistical power of the primary research. RESULTS The main finding was the association between low HRV and the onset and worsening of COVID-19 symptoms. In some cases, it was possible to predict the onset of COVID-19 before a positive clinical test. The meta-analysis of studies reported that a reduction in HRV parameters is associated with COVID-19. Individuals with COVID-19 presented a reduction in the SD of the normal-to-normal interbeat intervals and root mean square of the successive differences compared with healthy individuals. The decrease in the SD of the normal-to-normal interbeat intervals was 3.25 ms (95% CI −5.34 to −1.16 ms), and the decrease in the root mean square of the successive differences was 1.24 ms (95% CI −3.71 to 1.23 ms). CONCLUSIONS Wearable devices that measure changes in HRV, such as smartwatches, rings, and bracelets, provide information that allows for the identification of COVID-19 during the presymptomatic period as well as its worsening through an indirect and noninvasive self-diagnosis.

Current train signaling systems are being replaced by advanced systems like Communications‐Based Train Control, European Rail Traffic Management System, and Positive Train Control, which rely on radio networks. However, railways operating in dense forest environments face unique challenges for wireless systems due to high levels of signal attenuation, reflection, and diffraction caused by dense vegetation. The lack of comprehensive real‐world data makes it difficult to design systems in such areas. This study presents measurements performed at 460 MHz in a dense forest environment and compares the results with predictions from two models, irregular terrain model and ITU‐R (International Telecommunication Union) P.1812, with and without adjustments for vegetation attenuation using ITU‐R P.833. Measurements were conducted in Brazil, using a transmitter antenna in a railway corridor and a mobile antenna on a moving locomotive. Our findings indicate that while predicting wireless performance in dense forests is feasible, the best model still had a mean absolute error of 7.43 dB, underscoring the challenges of accurate signal prediction in such environments.