Computerized decision support for beneficial home-based exercise rehabilitation in patients with cardiovascular disease

Artificial intelligence-driven virtual rehabilitation for people living in the community: A scoping review

Virtual Rehabilitation (VRehab) is a promising approach to improving the physical and mental functioning of patients living in the community. The use of VRehab technology results in the generation of multi-modal datasets collected through various devices. This presents opportunities for the development of Artificial Intelligence (AI) techniques in VRehab, namely the measurement, detection, and prediction of various patients' health outcomes. The objective of this scoping review was to explore the applications and effectiveness of incorporating AI into home-based VRehab programs. PubMed/MEDLINE, Embase, IEEE Xplore, Web of Science databases, and Google Scholar were searched from inception until June 2023 for studies that applied AI for the delivery of VRehab programs to the homes of adult patients. After screening 2172 unique titles and abstracts and 51 full-text studies, 13 studies were included in the review. A variety of AI algorithms were applied to analyze data collected from various sensors and make inferences about patients' health outcomes, most involving evaluating patients' exercise quality and providing feedback to patients. The AI algorithms used in the studies were mostly fuzzy rule-based methods, template matching, and deep neural networks. Despite the growing body of literature on the use of AI in VRehab, very few studies have examined its use in patients' homes. Current research suggests that integrating AI with home-based VRehab can lead to improved rehabilitation outcomes for patients. However, further research is required to fully assess the effectiveness of various forms of AI-driven home-based VRehab, taking into account its unique challenges and using standardized metrics.

A mobile-based airway clearance care system using deep learning-based vision technology to support personalized home-based pulmonary rehabilitation for COAD patients: Development and usability testing

Background

Excessive mucus secretion is a serious issue for patients with chronic obstructive airway disease (COAD), which can be effectively managed through postural drainage and percussion (PD + P) during pulmonary rehabilitation (PR). Home-based (H)-PR can be as effective as center-based PR but lacks professional supervision and timely feedback, leading to low motivation and adherence. Telehealth home-based pulmonary (TH-PR) has emerged to assist H-PR, but video conferencing and telephone calls remain the main approaches for COAD patients. Therefore, research on effectively assisting patients in performing PD + P during TH-PR is limited.

Objective

This study developed a mobile-based airway clearance care for chronic obstructive airway disease (COAD-MoAcCare) system to support personalized TH-PR for COAD patients and evaluated its usability through expert validation.

Methods

The COAD-MoAcCare system uses a mobile device through deep learning-based vision technology to monitor, guide, and evaluate COAD patients' PD + P operations in real time during TH-PR programs. Medical personnel can manage and monitor their personalized PD + P and operational statuses through the system to improve TH-PR performance. Respiratory therapists from different hospitals evaluated the system usability using system questionnaires based on the technology acceptance model, system usability scale (SUS), and task load index (NASA-TLX).

Results

Eleven participant therapists were highly satisfied with the COAD-MoAcCare system, rating it between 4.1 and 4.6 out of 5.0 on all scales. The system demonstrated good usability (SUS score of 74.1 out of 100) and a lower task load (NASA-TLX score of 30.0 out of 100). The overall accuracy of PD + P operations reached a high level of 97.5% by comparing evaluation results of the system by experts.

Conclusions

The COAD-MoAcCare system is the first mobile-based method to assist COAD patients in conducting PD + P in TH-PR. It was proven to be usable by respiratory therapists, so it is expected to benefit medical personnel and COAD patients. It will be further evaluated through clinical trials.

Qualitative study of the views of people living with cardiovascular disease, and healthcare professionals, towards the use of a digital platform to support cardiovascular disease self-management

OBJECTIVES

This paper focuses on formative research as part of a broader study to develop and evaluate an innovative digital health platform for the self-management of cardiovascular disease (CVD). The primary objective is to better understand the perceptions of key stakeholders towards the proposed platform (Salvio) and to identify the development considerations they may prioritise based on their own experiences of CVD management.

DESIGN

A qualitative research study using thematic analysis to explore patterns and themes within the various participant contributions.

SETTING

Triangulation of data collection methods were used to generate data, including focus group discussions, semistructured interviews and guided conversations.

PARTICIPANTS

Participants (n=26) were people with a diagnosis of CVD (n=18) and relevant healthcare professionals (n=8).

RESULTS

Findings indicate that the proposed platform would be a beneficial solution for certain groups whose health behaviour change is not currently supported by discrete solutions. Both participant groups perceive the digital health platform more trustworthy than accessing multiple interventions through unsupported digital repositories. Healthcare professionals agreed that they would endorse an evidence-based platform that had been rigorously developed and evaluated. CVD participants prioritised a decision support tool to guide them through the platform, as they perceive an unstructured approach as overly complex. Both participant groups perceived data sharing with certain self-selected individuals (eg, spouse) to be a useful method for gaining support with their health behaviour change.

CONCLUSIONS

A digital health platform offering a variety of existing, evidence-based interventions would provide users with suitable self-management solution(s) based on their own individual needs and preferences. Salvio could be enhanced by providing adequate support to platform users, guiding the diverse CVD population through a host of digital solutions, ensuring that Salvio is endorsed by trusted healthcare professionals and maintaining connections with usual care. Such a platform would augment existing self-management and secondary prevention services.

Muscle force estimation from lower limb EMG signals using novel optimised machine learning techniques

The main objective of this work is to establish a framework for processing and evaluating the lower limb electromyography (EMG) signals ready to be fed to a rehabilitation robot. We design and build a knee rehabilitation robot that works with surface EMG (sEMG) signals. In our device, the muscle forces are estimated from sEMG signals using several machine learning techniques, i.e. support vector machine (SVM), support vector regression (SVR) and random forest (RF). In order to improve the estimation accuracy, we devise genetic algorithm (GA) for parameter optimisation and feature extraction within the proposed methods. At the same time, a load cell and a wearable inertial measurement unit (IMU) are mounted on the robot to measure the muscle force and knee joint angle, respectively. Various performance measures have been employed to assess the performance of the proposed system. Our extensive experiments and comparison with related works revealed a high estimation accuracy of 98.67% for lower limb muscles. The main advantage of the proposed techniques is high estimation accuracy leading to improved performance of the therapy while muscle models become especially sensitive to the tendon stiffness and the slack length.

Toward the Value Sensitive Design of eHealth Technologies to Support Self-management of Cardiovascular Diseases: Content Analysis

BACKGROUND

eHealth can revolutionize the way self-management support is offered to chronically ill individuals such as those with a cardiovascular disease (CVD). However, patients' fluctuating motivation to actually perform self-management is an important factor for which to account. Tailoring and personalizing eHealth to fit with the values of individuals promises to be an effective motivational strategy. Nevertheless, how specific eHealth technologies and design features could potentially contribute to values of individuals with a CVD has not been explicitly studied before.

OBJECTIVE

This study sought to connect a set of empirically validated, health-related values of individuals with a CVD with existing eHealth technologies and their design features. The study searched for potential connections between design features and values with the goal to advance knowledge about how eHealth technologies can actually be more meaningful and motivating for end users.

METHODS

Undertaking a technical investigation that fits with the value sensitive design framework, a content analysis of existing eHealth technologies was conducted. We matched 11 empirically validated values of CVD patients with 70 design features from 10 eHealth technologies that were previously identified in a systematic review. The analysis consisted mainly of a deductive coding stage performed independently by 3 members of the study team. In addition, researchers and developers of 6 of the 10 reviewed technologies provided input about potential feature-value connections.

RESULTS

In total, 98 connections were made between eHealth design features and patient values. This meant that some design features could contribute to multiple values. Importantly, some values were more often addressed than others. CVD patients' values most often addressed were related to (1) having or maintaining a healthy lifestyle, (2) having an overview of personal health data, (3) having reliable information and advice, (4) having extrinsic motivators to accomplish goals or health-related activities, and (5) receiving personalized care. In contrast, values less often addressed concerned (6) perceiving low thresholds to access health care, (7) receiving social support, (8) preserving a sense of autonomy over life, and (9) not feeling fear, anxiety, or insecurity about health. Last, 2 largely unaddressed values were related to (10) having confidence and self-efficacy in the treatment or ability to achieve goals and (11) desiring to be seen as a person rather than a patient.

CONCLUSIONS

Positively, existing eHealth technologies could be connected with CVD patients' values, largely through design features that relate to educational support, self-monitoring support, behavior change support, feedback, and motivational incentives. Other design features such as reminders, prompts or cues, peer-based or expert-based human support, and general system personalization were also connected with values but in narrower ways. In future studies, the inferred feature-value connections must be validated with empirical data from individuals with a CVD or similar chronic conditions.

Toward a Digital Platform for the Self-Management of Noncommunicable Disease: Systematic Review of Platform-Like Interventions

BACKGROUND

Digital interventions are effective for health behavior change, as they enable the self-management of chronic, noncommunicable diseases (NCDs). However, they often fail to facilitate the specific or current needs and preferences of the individual. A proposed alternative is a digital platform that hosts a suite of discrete, already existing digital health interventions. A platform architecture would allow users to explore a range of evidence-based solutions over time to optimize their self-management and health behavior change.

OBJECTIVE

This review aims to identify digital platform-like interventions and examine their potential for supporting self-management of NCDs and health behavior change.

METHODS

A literature search was conducted in January 2020 using EBSCOhost, PubMed, Scopus, and EMBASE. No digital platforms were identified, so criteria were broadened to include digital platform-like interventions. Eligible platform-like interventions offered a suite of discrete, evidence-based health behavior change features to optimize self-management of NCDs in an adult population and provided digitally supported guidance for the user toward the features best suited to their needs and preferences. Data collected on interventions were guided by the CONSORT-EHEALTH (Consolidated Standards of Reporting Trials of Electronic and Mobile Health Applications and Online Telehealth) checklist, including evaluation data on effectiveness and process outcomes. The quality of the included literature was assessed using the Mixed Methods Appraisal Tool.

RESULTS

A total of 7 studies were included for review. Targeted NCDs included cardiovascular diseases (CVD; n=3), diabetes (n=3), and chronic obstructive pulmonary disease (n=1). The mean adherence (based on the number of follow-up responders) was 69% (SD 20%). Of the 7 studies, 4 with the highest adherence rates (80%) were also guided by behavior change theories and took an iterative, user-centered approach to development, optimizing intervention relevance. All 7 interventions presented algorithm-supported user guidance tools, including electronic decision support, smart features that interact with patterns of use, and behavior change stage-matching tools. Of the 7 studies, 6 assessed changes in behavior. Significant effects in moderate-to-vigorous physical activity were reported, but for no other specific health behaviors. However, positive behavior change was observed in studies that focused on comprehensive behavior change measures, such as self-care and self-management, each of which addresses several key lifestyle risk factors (eg, medication adherence). No significant difference was found for psychosocial outcomes (eg, quality of life). Significant changes in clinical outcomes were predominately related to disease-specific, multifaceted measures such as clinical disease control and cardiovascular risk score.

CONCLUSIONS

Iterative, user-centered development of digital platform structures could optimize user engagement with self-management support through existing, evidence-based digital interventions. Offering a palette of interventions with an appropriate degree of guidance has the potential to facilitate disease-specific health behavior change and effective self-management among a myriad of users, conditions, or stages of care.

Applications of Artificial Intelligence and Big Data Analytics in m-Health: A Healthcare System Perspective

Mobile health (m-health) is the term of monitoring the health using mobile phones and patient monitoring devices etc. It has been often deemed as the substantial breakthrough in technology in this modern era. Recently, artificial intelligence (AI) and big data analytics have been applied within the m-health for providing an effective healthcare system. Various types of data such as electronic health records (EHRs), medical images, and complicated text which are diversified, poorly interpreted, and extensively unorganized have been used in the modern medical research. This is an important reason for the cause of various unorganized and unstructured datasets due to emergence of mobile applications along with the healthcare systems. In this paper, a systematic review is carried out on application of AI and the big data analytics to improve the m-health system. Various AI-based algorithms and frameworks of big data with respect to the source of data, techniques used, and the area of application are also discussed. This paper explores the applications of AI and big data analytics for providing insights to the users and enabling them to plan, using the resources especially for the specific challenges in m-health, and proposes a model based on the AI and big data analytics for m-health. Findings of this paper will guide the development of techniques using the combination of AI and the big data as source for handling m-health data more effectively.

Prediction of the Adherence to a Home-Based Cardiac Rehabilitation Program

The incidence and prevalence of cardiovascular diseases (CVD) is increasing which is partly due to an increase in unhealthy lifestyles, including lack of physical activity. Therefore, following a cardiovascular event, patients are encouraged to participate in a supervised exercise-based cardiac rehabilitation (CR) program. However, uptake rates of these programs are low and compliance to adequate volumes of physical activity after the completion of such programs are even lower. An approach that has been proposed towards the increase of patient adherence to exercise, is the incorporation of technology-enabled solutions which are applied at patient's homes. However, different factors may affect patient engagement with such alternative solutions. In this work, we use diverse types of data, including baseline characteristics of the patient (i.e. physiological, behavioral, demographical data) as well as usage data of a tele-rehabilitation solution during a 4-week familiarization period, in order to predict the compliance of patients with CVD to a technology-supported physical activity intervention after completion of a supervised exercise program. Patients were clustered based on their use of a technology intervention during a previously conducted study. Following a feature selection approach, a support vector machine was trained to classify patients as adherent or non-adherent to the intervention. The performance of the classifier was assessed by means of the receiving operator curve (ROC). Bio-psycho-social baseline variables predicted adherence with a ROC of 0.86, but adding usage data of the platform during a 4-week familiarization period increased the ROC up to 0.94. Furthermore, the high sensitivity values (83.8% and 95.5% respectively) support the strength of the models to identify those patients with CVD that will be adherent to a technology-enabled, home-based CR program.

Feasibility, Acceptability, and Clinical Effectiveness of a Technology-Enabled Cardiac Rehabilitation Platform (Physical Activity Toward Health-I): Randomized Controlled Trial

Background

Cardiac rehabilitation (CR) is highly effective as secondary prevention for cardiovascular diseases (CVDs). Uptake of CR remains suboptimal (30% of eligible patients), and long-term adherence to a physically active lifestyle is even lower. Innovative strategies are needed to counteract this phenomenon.

Objective

The Physical Activity Toward Health (PATHway) system was developed to provide a comprehensive, remotely monitored, home-based CR program for CVD patients. The PATHway-I study aimed to investigate its feasibility and clinical efficacy during phase III CR.

Methods

Participants were randomized on a 1:1 basis to the PATHway (PW) intervention group or usual care (UC) control group in a single-blind, multicenter, randomized controlled pilot trial. Outcomes were assessed at completion of phase II CR and 6-month follow-up. The primary outcome was physical activity (PA; Actigraph GT9X link). Secondary outcomes included measures of physical fitness, modifiable cardiovascular risk factors, endothelial function, intima-media thickness of the common carotid artery, and quality of life. System usability and patients’ experiences were evaluated only in PW. A mixed-model analysis of variance with Bonferroni adjustment was used to analyze between-group effects over time. Missing values were handled by means of an intention-to-treat analysis. Statistical significance was set at a 2-sided alpha level of .05. Data are reported as mean (SD).

Results

A convenience sample of 120 CVD patients (mean 61.4 years, SD 13.5 years; 22 women) was included. The PATHway system was deployed in the homes of 60 participants. System use decreased over time and system usability was average with a score of 65.7 (SD 19.7; range 5-100). Moderate-to-vigorous intensity PA increased in PW (PW: 127 [SD 58] min to 141 [SD 69] min, UC: 146 [SD 66] min to 143 [SD 71] min; P_interaction=.04; effect size of 0.42), while diastolic blood pressure (PW: 79 [SD 11] mmHg to 79 [SD 10] mmHg, UC: 78 [SD 9] mmHg to 83 [SD 10] mmHg; P_interaction=.004; effect size of −0.49) and cardiovascular risk score (PW: 15.9% [SD 10.4%] to 15.5% [SD 10.5%], UC: 14.5 [SD 9.7%] to 15.7% [SD 10.9%]; P_interaction=.004; effect size of −0.36) remained constant, but deteriorated in UC.

Conclusions

This pilot study demonstrated the feasibility and acceptability of a technology-enabled, remotely monitored, home-based CR program. Although clinical effectiveness was demonstrated, several challenges were identified that could influence the adoption of PATHway.

Trial Registration

ClinicalTrials.gov NCT02717806; https://clinicaltrials.gov/ct2/show/NCT02717806

International Registered Report Identifier (IRRID)

RR2-10.1136/bmjopen-2017-016781

Features, outcomes, and challenges in mobile health interventions for patients living with chronic diseases: A review of systematic reviews

BACKGROUND

Mobile health (mHealth) technology has the potential to play a key role in improving the health of patients with chronic non-communicable diseases.

OBJECTIVES

We present a review of systematic reviews of mHealth in chronic disease management, by showing the features and outcomes of mHealth interventions, along with associated challenges in this rapidly growing field.

METHODS

We searched the bibliographic databases of PubMed, Scopus, and Cochrane to identify systematic reviews of mHealth interventions with advanced technical capabilities (e.g., Internet-linked apps, interoperation with sensors, communication with clinical platforms, etc.) utilized in randomized clinical trials. The original studies included the reviews were synthesized according to their intervention features, the targeted diseases, the primary outcome, the number of participants and their average age, as well as the total follow-up duration.

RESULTS

We identified 5 reviews respecting our inclusion and exclusion criteria, which examined 30 mHealth interventions. The highest percentage of the interventions targeted patients with diabetes (n = 19, 63%), followed by patients with psychotic disorders (n = 7, 23%), lung diseases (n = 3, 10%), and cardiovascular disease (n = 1, 3%). 14 studies showed effective results: 9 in diabetes management, 2 in lung function, and 3 in mental health. Significantly positive outcomes were reported in 8 interventions (n = 8, 47%) from 17 studies assessing glucose concentration, one intervention assessing physical activity, 2 interventions (n = 2, 67%) from 3 studies assessing lung function parameters, and 3 mental health interventions assessing N-back performance, medication adherence, and number of hospitalizations. Divergent features were adopted in 14 interventions with significantly positive outcomes, such as personalized goal setting (n = 10, 71%), motivational feedback (n = 5, 36%), and alerts for health professionals (n = 3, 21%). The most significant found challenges in the development and evaluation of mHealth interventions include the design of studies with high quality, the construction of robust interventions in combination with health professional inputs, and the identification of tools and methods to improve patient adherence.

CONCLUSIONS

This review found mixed evidence regarding the health benefits of mHealth interventions for patients living with chronic diseases. Further rigorous studies are needed to assess the outcomes of personalized mHealth interventions toward the optimal management of chronic diseases.

Applications of Machine Learning in Real-Life Digital Health Interventions: Review of the Literature

Background

Machine learning has attracted considerable research interest toward developing smart digital health interventions. These interventions have the potential to revolutionize health care and lead to substantial outcomes for patients and medical professionals.

Objective

Our objective was to review the literature on applications of machine learning in real-life digital health interventions, aiming to improve the understanding of researchers, clinicians, engineers, and policy makers in developing robust and impactful data-driven interventions in the health care domain.

Methods

We searched the PubMed and Scopus bibliographic databases with terms related to machine learning, to identify real-life studies of digital health interventions incorporating machine learning algorithms. We grouped those interventions according to their target (ie, target condition), study design, number of enrolled participants, follow-up duration, primary outcome and whether this had been statistically significant, machine learning algorithms used in the intervention, and outcome of the algorithms (eg, prediction).

Results

Our literature search identified 8 interventions incorporating machine learning in a real-life research setting, of which 3 (37%) were evaluated in a randomized controlled trial and 5 (63%) in a pilot or experimental single-group study. The interventions targeted depression prediction and management, speech recognition for people with speech disabilities, self-efficacy for weight loss, detection of changes in biopsychosocial condition of patients with multiple morbidity, stress management, treatment of phantom limb pain, smoking cessation, and personalized nutrition based on glycemic response. The average number of enrolled participants in the studies was 71 (range 8-214), and the average follow-up study duration was 69 days (range 3-180). Of the 8 interventions, 6 (75%) showed statistical significance (at the P=.05 level) in health outcomes.

Conclusions

This review found that digital health interventions incorporating machine learning algorithms in real-life studies can be useful and effective. Given the low number of studies identified in this review and that they did not follow a rigorous machine learning evaluation methodology, we urge the research community to conduct further studies in intervention settings following evaluation principles and demonstrating the potential of machine learning in clinical practice.

User Models for Personalized Physical Activity Interventions: Scoping Review

Background

Fitness devices have spurred the development of apps that aim to motivate users, through interventions, to increase their physical activity (PA). Personalization in the interventions is essential as the target users are diverse with respect to their activity levels, requirements, preferences, and behavior.

Objective

This review aimed to (1) identify different kinds of personalization in interventions for promoting PA among any type of user group, (2) identify user models used for providing personalization, and (3) identify gaps in the current literature and suggest future research directions.

Methods

A scoping review was undertaken by searching the databases PsycINFO, PubMed, Scopus, and Web of Science. The main inclusion criteria were (1) studies that aimed to promote PA; (2) studies that had personalization, with the intention of promoting PA through technology-based interventions; and (3) studies that described user models for personalization.

Results

The literature search resulted in 49 eligible studies. Of these, 67% (33/49) studies focused solely on increasing PA, whereas the remaining studies had other objectives, such as maintaining healthy lifestyle (8 studies), weight loss management (6 studies), and rehabilitation (2 studies). The reviewed studies provide personalization in 6 categories: goal recommendation, activity recommendation, fitness partner recommendation, educational content, motivational content, and intervention timing. With respect to the mode of generation, interventions were found to be semiautomated or automatic. Of these, the automatic interventions were either knowledge-based or data-driven or both. User models in the studies were constructed with parameters from 5 categories: PA profile, demographics, medical data, behavior change technique (BCT) parameters, and contextual information. Only 27 of the eligible studies evaluated the interventions for improvement in PA, and 16 of these concluded that the interventions to increase PA are more effective when they are personalized.

Conclusions

This review investigates personalization in the form of recommendations or feedback for increasing PA. On the basis of the review and gaps identified, research directions for improving the efficacy of personalized interventions are proposed. First, data-driven prediction techniques can facilitate effective personalization. Second, use of BCTs in automated interventions, and in combination with PA guidelines, are yet to be explored, and preliminary studies in this direction are promising. Third, systems with automated interventions also need to be suitably adapted to serve specific needs of patients with clinical conditions. Fourth, previous user models focus on single metric evaluations of PA instead of a potentially more effective, holistic, and multidimensional view. Fifth, with the widespread adoption of activity monitoring devices and mobile phones, personalized and dynamic user models can be created using available user data, including users’ social profile. Finally, the long-term effects of such interventions as well as the technology medium used for the interventions need to be evaluated rigorously.

Automated recognition of cardiac arrhythmias using sparse decomposition over composite dictionary

BACKGROUND AND OBJECTIVE

Cardiovascular diseases (CVDs) are the leading cause of deaths worldwide. Due to an increase in the rate of global mortalities, biopathological signal processing and evaluation are widely used in the ambulatory situations for healthcare applications. For decades, the processing of pathological electrocardiogram (ECG) signals for arrhythmia detection has been thoroughly studied for diagnosis of various cardiovascular diseases. Apart from these studies, efficient diagnosis of ECG signals remains a challenge in the clinical cardiovascular domain due to its non-stationary nature. The classical signal processing methods are widely employed to analyze the ECG signals, but they exhibit certain limitations and hence, are insufficient to achieve higher accuracy.

METHODS

This study presents a novel technique for an efficient representation of electrocardiogram (ECG) signals using sparse decomposition using composite dictionary (CD). The dictionary consists of the stockwell, sine and cosine analytical functions. The technique decomposes an input ECG signal into stationary and non-stationary components or atoms. For each of these atoms, five features i.e., permutation entropy, energy, RR-interval, standard deviation and kurtosis are extracted to determine the feature sets representing the heartbeats that are classified into different categories using the multi-class least-square twin support vector machines. The artificial bee colony (ABC) technique is used to determine the optimal classifier parameters. The proposed method is evaluated under category and personalized schemes and its validation is performed on MIT-BIH data.

RESULTS

The experimental results reported a higher overall accuracy of 99.21% and 90.08% in category and personalized schemes respectively than the existing techniques reported in the literature. Further a sensitivity, positive predictivity and F-score of 99.21% each in the category based scheme and 90.08% each in the personalized schemes respectively.

CONCLUSIONS

The proposed methodology can be utilized in computerized decision support systems to monitor different classes of cardiac arrhythmias with higher accuracy for early detection and treatment of cardiovascular diseases.