+1 Recommend
0 collections
      • Record: found
      • Abstract: found
      • Article: found
      Is Open Access

      mHealth Intervention Applications for Adults Living With the Effects of Stroke: A Scoping Review


      Read this article at

          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.



          To conduct a scoping review of mobile health (mHealth) application (app) interventions to support needs of adults living with the effects of stroke reported in the literature.

          Data Sources

          PubMed, Cumulative Index to Nursing and Allied Health Literature (CINAHL), and Scopus were systematically searched for peer-reviewed publications. Articles were published between January 2007 and September 2020 and met predefined inclusion and exclusion criteria.

          Study Selection

          Articles included were written in English language, involved adults older than 18 years, and described an mHealth app specifically tested and/or developed as an intervention for someone with stroke to be used remotely and/or independently without constant provider supervision or assistance. Articles were excluded if they focused on acute management of stroke only, focused on primary prevention, were animal studies, were not an app for smartphone or tablet, and did not describe an empirical study.

          Data Extraction

          Two researchers independently screened titles and abstracts for inclusion. The full-text articles were then reviewed for eligibility by the research team. Data were extracted and verified by a third reviewer.

          Data Synthesis

          The search yielded 2123 studies and 49 were included for data extraction. The findings reveal that a global surge of studies on mHealth apps for people with stroke have emerged within the past 2 years. Most studies were developed for persons with stroke in the United States and the primary content foci included upper extremity function (31.5%); lower extremity function (5.3%); general exercise, physical activity, and/or functional mobility (23.7%); trunk control (5.3%); medical management and secondary prevention (26.3%); language and speech skills (20.5%); cognitive skills (7.9%); general disability and activities of daily living (5.3%); and home safety (2.6%). Of the included studies, a majority were preliminary in nature, with 36.7% being categorized as pilot or feasibility trials and 24.4% discussing initial design, development, and/or refinement.


          Results from this study reveal that the number of apps specifically developed for people with stroke and described in the scientific literature are growing exponentially. The apps have widely varied content to meet the needs of persons with stroke; however, the studies are generally preliminary in nature, focusing on development, usability, and initial pilot testing. This review highlights the need for additional research and development of mHealth apps targeted for adults with stroke. Development should consider the various and complex needs of people living with the effects of chronic stroke, while large-scale trials are needed to build on the existing evidence.

          Related collections

          Most cited references55

          • Record: found
          • Abstract: found
          • Article: not found

          PRISMA Extension for Scoping Reviews (PRISMA-ScR): Checklist and Explanation

          Scoping reviews, a type of knowledge synthesis, follow a systematic approach to map evidence on a topic and identify main concepts, theories, sources, and knowledge gaps. Although more scoping reviews are being done, their methodological and reporting quality need improvement. This document presents the PRISMA-ScR (Preferred Reporting Items for Systematic reviews and Meta-Analyses extension for Scoping Reviews) checklist and explanation. The checklist was developed by a 24-member expert panel and 2 research leads following published guidance from the EQUATOR (Enhancing the QUAlity and Transparency Of health Research) Network. The final checklist contains 20 essential reporting items and 2 optional items. The authors provide a rationale and an example of good reporting for each item. The intent of the PRISMA-ScR is to help readers (including researchers, publishers, commissioners, policymakers, health care providers, guideline developers, and patients or consumers) develop a greater understanding of relevant terminology, core concepts, and key items to report for scoping reviews.
            • Record: found
            • Abstract: found
            • Article: found
            Is Open Access

            A clinical text classification paradigm using weak supervision and deep representation

            Background Automatic clinical text classification is a natural language processing (NLP) technology that unlocks information embedded in clinical narratives. Machine learning approaches have been shown to be effective for clinical text classification tasks. However, a successful machine learning model usually requires extensive human efforts to create labeled training data and conduct feature engineering. In this study, we propose a clinical text classification paradigm using weak supervision and deep representation to reduce these human efforts. Methods We develop a rule-based NLP algorithm to automatically generate labels for the training data, and then use the pre-trained word embeddings as deep representation features for training machine learning models. Since machine learning is trained on labels generated by the automatic NLP algorithm, this training process is called weak supervision. We evaluat the paradigm effectiveness on two institutional case studies at Mayo Clinic: smoking status classification and proximal femur (hip) fracture classification, and one case study using a public dataset: the i2b2 2006 smoking status classification shared task. We test four widely used machine learning models, namely, Support Vector Machine (SVM), Random Forest (RF), Multilayer Perceptron Neural Networks (MLPNN), and Convolutional Neural Networks (CNN), using this paradigm. Precision, recall, and F1 score are used as metrics to evaluate performance. Results CNN achieves the best performance in both institutional tasks (F1 score: 0.92 for Mayo Clinic smoking status classification and 0.97 for fracture classification). We show that word embeddings significantly outperform tf-idf and topic modeling features in the paradigm, and that CNN captures additional patterns from the weak supervision compared to the rule-based NLP algorithms. We also observe two drawbacks of the proposed paradigm that CNN is more sensitive to the size of training data, and that the proposed paradigm might not be effective for complex multiclass classification tasks. Conclusion The proposed clinical text classification paradigm could reduce human efforts of labeled training data creation and feature engineering for applying machine learning to clinical text classification by leveraging weak supervision and deep representation. The experimental experiments have validated the effectiveness of paradigm by two institutional and one shared clinical text classification tasks.
              • Record: found
              • Abstract: found
              • Article: found
              Is Open Access

              Designing, Implementing, and Evaluating Mobile Health Technologies for Managing Chronic Conditions in Older Adults: A Scoping Review

              Background The current landscape of a rapidly aging population accompanied by multiple chronic conditions presents numerous challenges to optimally support the complex needs of this group. Mobile health (mHealth) technologies have shown promise in supporting older persons to manage chronic conditions; however, there remains a dearth of evidence-informed guidance to develop such innovations. Objectives The purpose of this study was to conduct a scoping review of current practices and recommendations for designing, implementing, and evaluating mHealth technologies to support the management of chronic conditions in community-dwelling older adults. Methods A 5-stage scoping review methodology was used to map the relevant literature published between January 2005 and March 2015 as follows: (1) identified the research question, (2) identified relevant studies, (3) selected relevant studies for review, (4) charted data from selected literature, and (5) summarized and reported results. Electronic searches were conducted in 5 databases. In addition, hand searches of reference lists and a key journal were completed. Inclusion criteria were research and nonresearch papers focused on mHealth technologies designed for use by community-living older adults with at least one chronic condition, or health care providers or informal caregivers providing care in the home and community setting. Two reviewers independently identified articles for review and extracted data. Results We identified 42 articles that met the inclusion criteria. Of these, described innovations focused on older adults with specific chronic conditions (n=17), chronic conditions in general (n=6), or older adults in general or those receiving homecare services (n=18). Most of the mHealth solutions described were designed for use by both patients and health care providers or health care providers only. Thematic categories identified included the following: (1) practices and considerations when designing mHealth technologies; (2) factors that support/hinder feasibility, acceptability, and usability of mHealth technologies; and (3) approaches or methods for evaluating mHealth technologies. Conclusions There is limited yet increasing use of mHealth technologies in home health care for older adults. A user-centered, collaborative, interdisciplinary approach to enhance feasibility, acceptability, and usability of mHealth innovations is imperative. Creating teams with the required pools of expertise and insight regarding needs is critical. The cyclical, iterative process of developing mHealth innovations needs to be viewed as a whole with supportive theoretical frameworks. Many barriers to implementation and sustainability have limited the number of successful, evidence-based mHealth solutions beyond the pilot or feasibility stage. The science of implementation of mHealth technologies in home-based care for older adults and self-management of chronic conditions are important areas for further research. Additionally, changing needs as cohorts and technologies advance are important considerations. Lessons learned from the data and important implications for practice, policy, and research are discussed to inform the future development of innovations.

                Author and article information

                Arch Rehabil Res Clin Transl
                Arch Rehabil Res Clin Transl
                Archives of Rehabilitation Research and Clinical Translation
                16 December 2020
                March 2021
                16 December 2020
                : 3
                : 1
                [a ]School of Occupational Therapy, Texas Woman's University, Denton, Texas
                [b ]Pate Rehabilitation, Fort Worth, Texas
                [c ]ABC Therapy LTD, Copley, Ohio
                [d ]Texas Woman's University Libraries, Texas Woman's University, Denton, Texas
                Author notes
                []Corresponding author Suzanne P. Burns, PhD, OTR, School of Occupational Therapy, Texas Woman’s University, 304 Administration Dr, Denton, TX 76204. sburns3@ 123456twu.edu
                S2590-1095(20)30088-4 100095
                © 2020 The Authors

                This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).

                Systematic Review

                delivery of health care,rehabilitation,smartphone,stroke,stroke rehabilitation,telemedicine,telerehabilitation,adl, activities of daily living,app, application,mhealth, mobile health


                Comment on this article