Real-Time Monitoring in Home-Based Cardiac Rehabilitation Using Wrist-Worn Heart Rate Devices

Abstract

Cardiac rehabilitation is a key program which significantly reduces the mortality in at-risk patients with ischemic heart disease; however, there is a lack of accessibility to these programs in health centers. To resolve this issue, home-based programs for cardiac rehabilitation have arisen as a potential solution. In this work, we present an approach based on a new generation of wrist-worn devices which have improved the quality of heart rate sensors and applications. Real-time monitoring of rehabilitation sessions based on high-quality clinical guidelines is embedded in a wearable application. For this, a fuzzy temporal linguistic approach models the clinical protocol. An evaluation based on cases is developed by a cardiac rehabilitation team.

Keywords: cardiac rehabilitation; fuzzy linguistic approach; fuzzy logic; m-health; real-time wearable monitoring; wrist-worn heart rate devices.

Figure 1

Example of membership functions for the terms low, normal, and high. In the example, the optimal heart rate training zones (OHRTZs) of the sessions are for trained patients, which are closer to $V{T}_2$ than to $V{T}_1$. In the example of modifiers, the impacts of the weak modifier in short-dashed lines and the strong modifier in long-dashed lines are shown.

Figure 2

Evolution of the values of parameters from progressive to maintenance stages for a rehabilitation session: duration range (30 min), duration of progressive stage (10 m) , OHRTZ $r_{+,-}^{\ast }=$ [130 bpm, 110 bpm], $H{R}_{max}=170$ bpm, and $V{T}_{1,2}=$ [100 bpm, 150 bpm]. This includes the basal ranges $[r_{+}^0,r_{-}^0]=$ [65 bpm, 75 bpm], and the lower and upper basal threshold $V{T}_{1,2}^0=$ [60 bpm, 85 bpm] for the patient. HR: heart rate; bpm: number of contractions of the heart per minute.

Figure 3

Architecture of components: (1) wearable device with real-time monitoring; (2) mobile application for evaluating the sessions; and (3) a web platform for evaluating the sessions by the cardiac rehabilitation team. The data from the patient and the team are synchronized (A) from wearable to mobile by Bluetooth; and (B) from mobile to cloud services by 4G/WiFi.

Figure 4

Pictures of the wearable, mobile, and web applications. In the wearable application in Polar M600, we show (1) a gradual color change in the evaluation of the HR; (2) progression and total time; and (3) the current and reference HR. In the mobile application, the $V{T}_1$, $V{T}_2$, $r_{+}^{\ast }$ and $r_{-}^{\ast }$ thresholds and the 4-star evaluations are described. In the web application, the cardiac rehabilitation team has access to heart streams and $V{T}_1$, $V{T}_2$, $r_{+}^{\ast }$ and $r_{-}^{\ast }$ thresholds of patients with zoom and scale options.

Figure 5

Impact of the fuzzy modifiers on heart rate streams. Heart rate is plotted using gradually changing colors blue, green, red based on the degree of the terms $\{low,adequate,high\}$, respectively. Green dotted lines determine the OHRTZs of patient. Blue and red dotted lines determine aerobic thresholds $V{T}_1,V{T}_2$ of the patient, respectively. The impact of the models A, B and C for a case of high–adequate HRs (right); and the impact of the models A, B, and C for a case of low–adequate HRs (left).

Figure 6

Impact of temporal windows on a case of prompt heart rate streams within the zones described by the linguistic terms $\{low,adequate,high\}$. Based on expert evaluation: Model A (short-term temporal window) suits in high zones detecting immediately critical HRs; Model B (middle-term temporal window) suits in adequate zone requiring a minimal permanence within; and Model B suits in the low zone without critical differences with regard to other models.