A Personal Health System for Self-Management of Congestive Heart Failure (HeartMan): Development, Technical Evaluation, and Proof-of-Concept Randomized Controlled Trial

Human Factors in AI-Driven Digital Solutions for Increasing Physical Activity: Scoping Review

BACKGROUND

Artificial intelligence (AI) has the potential to enhance physical activity (PA) interventions. However, human factors (HFs) play a pivotal role in the successful integration of AI into mobile health (mHealth) solutions for promoting PA. Understanding and optimizing the interaction between individuals and AI-driven mHealth apps is essential for achieving the desired outcomes.

OBJECTIVE

This study aims to review and describe the current evidence on the HFs in AI-driven digital solutions for increasing PA.

METHODS

We conducted a scoping review by searching for publications containing terms related to PA, HFs, and AI in the titles and abstracts across 3 databases-PubMed, Embase, and IEEE Xplore-and Google Scholar. Studies were included if they were primary studies describing an AI-based solution aimed at increasing PA, and results from testing the solution were reported. Studies that did not meet these criteria were excluded. Additionally, we searched the references in the included articles for relevant research. The following data were extracted from included studies and incorporated into a qualitative synthesis: bibliographic information, study characteristics, population, intervention, comparison, outcomes, and AI-related information. The certainty of the evidence in the included studies was evaluated using GRADE (Grading of Recommendations Assessment, Development, and Evaluation).

RESULTS

A total of 15 studies published between 2015 and 2023 involving 899 participants aged approximately between 19 and 84 years, 60.7% (546/899) of whom were female participants, were included in this review. The interventions lasted between 2 and 26 weeks in the included studies. Recommender systems were the most commonly used AI technology in digital solutions for PA (10/15 studies), followed by conversational agents (4/15 studies). User acceptability and satisfaction were the HFs most frequently evaluated (5/15 studies each), followed by usability (4/15 studies). Regarding automated data collection for personalization and recommendation, most systems involved fitness trackers (5/15 studies). The certainty of the evidence analysis indicates moderate certainty of the effectiveness of AI-driven digital technologies in increasing PA (eg, number of steps, distance walked, or time spent on PA). Furthermore, AI-driven technology, particularly recommender systems, seems to positively influence changes in PA behavior, although with very low certainty evidence.

CONCLUSIONS

Current research highlights the potential of AI-driven technologies to enhance PA, though the evidence remains limited. Longer-term studies are necessary to assess the sustained impact of AI-driven technologies on behavior change and habit formation. While AI-driven digital solutions for PA hold significant promise, further exploration into optimizing AI's impact on PA and effectively integrating AI and HFs is crucial for broader benefits. Thus, the implications for innovation management involve conducting long-term studies, prioritizing diversity, ensuring research quality, focusing on user experience, and understanding the evolving role of AI in PA promotion.

The role of patient-oriented mHealth interventions in improving heart failure outcomes: A systematic review of the literature

Heart failure (HF) is a debilitating disease with 26 million patients worldwide. Consistent and complex self-care is required on the part of patients to adequately adhere to medication and to the lifestyle changes that the disease necessitates. Mobile health (mHealth) is being increasingly incorporated in patient interventions in HF, as smartphones prove to be ideal platforms for patient education and self-help assistance. This systematic review aims to summarize and report on all studies that have tested the effect of mHealth on HF patient outcomes. Our search yielded 17 studies, namely 11 randomized controlled trials and six non-randomized prospective studies. In these, patients with the assistance of an mHealth intervention regularly measured their blood pressure and/or body weight and assessed their symptoms. The outcomes were mostly related to hospitalizations, clinical biomarkers, patients' knowledge about HF, quality of life (QoL) and quality of self-care. QoL consistently increased in patients who received mHealth interventions, while study results on all other outcomes were not as ubiquitously positive. The first mHealth interventions in HF were not universally successful in improving patient outcomes but provided valuable insights for patient-oriented application development. Future trials are expected to build on these insights and deploy applications that measurably assist HF patients.

Concordance of randomised controlled trials for artificial intelligence interventions with the CONSORT-AI reporting guidelines

The Consolidated Standards of Reporting Trials extension for Artificial Intelligence interventions (CONSORT-AI) was published in September 2020. Since its publication, several randomised controlled trials (RCTs) of AI interventions have been published but their completeness and transparency of reporting is unknown. This systematic review assesses the completeness of reporting of AI RCTs following publication of CONSORT-AI and provides a comprehensive summary of RCTs published in recent years. 65 RCTs were identified, mostly conducted in China (37%) and USA (18%). Median concordance with CONSORT-AI reporting was 90% (IQR 77-94%), although only 10 RCTs explicitly reported its use. Several items were consistently under-reported, including algorithm version, accessibility of the AI intervention or code, and references to a study protocol. Only 3 of 52 included journals explicitly endorsed or mandated CONSORT-AI. Despite a generally high concordance amongst recent AI RCTs, some AI-specific considerations remain systematically poorly reported. Further encouragement of CONSORT-AI adoption by journals and funders may enable more complete adoption of the full CONSORT-AI guidelines.

Machine learning to detect, stage and classify diseases and their symptoms based on inertial sensor data: a mapping review

This article presents a systematic review aimed at mapping the literature published in the last decade on the use of machine learning (ML) for clinical decision-making through wearable inertial sensors. The review aims to analyze the trends, perspectives, strengths, and limitations of current literature in integrating ML and inertial measurements for clinical applications. The review process involved defining four research questions and applying four relevance assessment indicators to filter the search results, providing insights into the pathologies studied, technologies and setups used, data processing schemes, ML techniques applied, and their clinical impact. When combined with ML techniques, inertial measurement units (IMUs) have primarily been utilized to detect and classify diseases and their associated motor symptoms. They have also been used to monitor changes in movement patterns associated with the presence, severity, and progression of pathology across a diverse range of clinical conditions. ML models trained with IMU data have shown potential in improving patient care by objectively classifying and predicting motor symptoms, often with a minimally encumbering setup. The findings contribute to understanding the current state of ML integration with wearable inertial sensors in clinical practice and identify future research directions. Despite the widespread adoption of these technologies and techniques in clinical applications, there is still a need to translate them into routine clinical practice. This underscores the importance of fostering a closer collaboration between technological experts and professionals in the medical field.

Configurations of human-centered AI at work: seven actor-structure engagements in organizations

Purpose

The discourse on the human-centricity of AI at work needs contextualization. The aim of this study is to distinguish prevalent criteria of human-centricity for AI applications in the scientific discourse and to relate them to the work contexts for which they are specifically intended. This leads to configurations of actor-structure engagements that foster human-centricity in the workplace.

Theoretical foundation

The study applies configurational theory to sociotechnical systems' analysis of work settings. The assumption is that different approaches to promote human-centricity coexist, depending on the stakeholders responsible for their application.

Method

The exploration of criteria indicating human-centricity and their synthesis into configurations is based on a cross-disciplinary literature review following a systematic search strategy and a deductive-inductive qualitative content analysis of 101 research articles.

Results

The article outlines eight criteria of human-centricity, two of which face challenges of human-centered technology development (trustworthiness and explainability), three challenges of human-centered employee development (prevention of job loss, health, and human agency and augmentation), and three challenges of human-centered organizational development (compensation of systems' weaknesses, integration of user-domain knowledge, accountability, and safety culture). The configurational theory allows contextualization of these criteria from a higher-order perspective and leads to seven configurations of actor-structure engagements in terms of engagement for (1) data and technostructure, (2) operational process optimization, (3) operators' employment, (4) employees' wellbeing, (5) proficiency, (6) accountability, and (7) interactive cross-domain design. Each has one criterion of human-centricity in the foreground. Trustworthiness does not build its own configuration but is proposed to be a necessary condition in all seven configurations.

Discussion

The article contextualizes the overall debate on human-centricity and allows us to specify stakeholder-related engagements and how these complement each other. This is of high value for practitioners bringing human-centricity to the workplace and allows them to compare which criteria are considered in transnational declarations, international norms and standards, or company guidelines.

Use of Human-Centered Design Methodology to Develop a Digital Toolkit to Optimize Heart Failure Guideline-Directed Medical Therapy

BACKGROUND

Guideline-directed medical therapies (GDMTs) improve quality of life and health outcomes for patients with heart failure (HF). However, GDMT utilization is suboptimal among patients with HF.

OBJECTIVE

The aims of this study were to engage key stakeholders in semistructured, virtual human-centered design sessions to identify challenges in GDMT optimization posthospitalization and inform the development of a digital toolkit aimed at optimizing HF GDMTs.

METHODS

For the human-centered design sessions, we recruited (a) clinicians who care for patients with HF across 3 hospital systems, (b) patients with HF with reduced ejection fraction (ejection fraction ≤ 40%) discharged from the hospital within 30 days of enrollment, and (c) caregivers. All participants were 18 years or older, English speaking, with Internet access.

RESULTS

A total of 10 clinicians (median age, 37 years [interquartile range, 35-41], 12 years [interquartile range, 10-14] of experience caring for patients with HF, 80% women, 50% White, 50% nurse practitioners) and three patients and one caregiver (median age 57 years [IQR: 53-60], 75% men, 50% Black, 75% married) were included. Five themes emerged from the clinician sessions on challenges to GDMT optimization (eg, barriers to patient buy-in). Six themes on challenges (eg, managing medications), 4 themes on motivators (eg, regaining independence), and 3 themes on facilitators (eg, social support) to HF management arose from the patient and caregiver sessions.

CONCLUSIONS

The clinician, patient, and caregiver insights identified through human-centered design will inform a digital toolkit aimed at optimizing HF GDMTs, including a patient-facing smartphone application and clinician dashboard. This digital toolkit will be evaluated in a multicenter, clinical trial.

Estimation of Physiologic Pressures: Invasive and Non-Invasive Techniques, AI Models, and Future Perspectives

The measurement of physiologic pressure helps diagnose and prevent associated health complications. From typical conventional methods to more complicated modalities, such as the estimation of intracranial pressures, numerous invasive and noninvasive tools that provide us with insight into daily physiology and aid in understanding pathology are within our grasp. Currently, our standards for estimating vital pressures, including continuous BP measurements, pulmonary capillary wedge pressures, and hepatic portal gradients, involve the use of invasive modalities. As an emerging field in medical technology, artificial intelligence (AI) has been incorporated into analyzing and predicting patterns of physiologic pressures. AI has been used to construct models that have clinical applicability both in hospital settings and at-home settings for ease of use for patients. Studies applying AI to each of these compartmental pressures were searched and shortlisted for thorough assessment and review. There are several AI-based innovations in noninvasive blood pressure estimation based on imaging, auscultation, oscillometry and wearable technology employing biosignals. The purpose of this review is to provide an in-depth assessment of the involved physiologies, prevailing methodologies and emerging technologies incorporating AI in clinical practice for each type of compartmental pressure measurement. We also bring to the forefront AI-based noninvasive estimation techniques for physiologic pressure based on microwave systems that have promising potential for clinical practice.

A feasibility study on the efficacy of a patient-owned wound surveillance system for diabetic foot ulcer care (ePOWS study)

Objective

Wound image analysis tools hold promise in helping patients to monitor their wounds. We aim to perform a novel feasibility study on the efficacy of a patient-owned wound surveillance system for diabetic foot ulcer (DFU) care.

Methods

This two-institutional, prospective, single-arm pilot study examined patients with DFU. An artificial intelligence-enabled image analysis app calculating the wound surface area was installed and patients or caregivers were instructed to take pictures of wounds during dressing changes. Patients were followed until wound deterioration, wound healing, or wound stability at 6 months occurred and the outcomes of interest included study adherence, algorithm performance, and user experience.

Results

Between January 2021 and December 2021, 39 patients were enrolled in the study, with a mean age of 61.6 ± 8.6 years, and 69% (n = 27) of subjects were male. All patients had documented diabetes and 85% (n = 33) of them had peripheral arterial disease. A mean follow-up for those completing the study was 12.0 ± 8.5 weeks. At the conclusion of the study, 80% of patients (n = 20) had primary wound healing whilst 20% (n = 5) had wound deterioration. The study completion rate was 64% (n = 25). Usage of the app for surveillance of DFU healing, as compared to physician evaluation, yielded a sensitivity of 100%, specificity of 20%, positive predictive value of 83%, and negative predictive value of 100%. Of those who provided user experience feedback, 59% (n = 10) felt the app was easy to use, 47% (n = 8) would recommend the wound analysis app to others but only 6% would pay for the app out of pocket (n = 1).

Conclusion

Implementation of a patient-owned wound surveillance system is feasible. Most patients were able to effectively monitor wounds using a smartphone app-based solution. The image analysis algorithm demonstrates strong performance in identifying wound healing and is capable of detecting deterioration prior to interval evaluation by a physician. Patients generally found the app easy to use but were reluctant to pay for the use of the solution out of pocket.

Randomized Clinical Trials of Machine Learning Interventions in Health Care: A Systematic Review

IMPORTANCE

Despite the potential of machine learning to improve multiple aspects of patient care, barriers to clinical adoption remain. Randomized clinical trials (RCTs) are often a prerequisite to large-scale clinical adoption of an intervention, and important questions remain regarding how machine learning interventions are being incorporated into clinical trials in health care.

OBJECTIVE

To systematically examine the design, reporting standards, risk of bias, and inclusivity of RCTs for medical machine learning interventions.

EVIDENCE REVIEW

In this systematic review, the Cochrane Library, Google Scholar, Ovid Embase, Ovid MEDLINE, PubMed, Scopus, and Web of Science Core Collection online databases were searched and citation chasing was done to find relevant articles published from the inception of each database to October 15, 2021. Search terms for machine learning, clinical decision-making, and RCTs were used. Exclusion criteria included implementation of a non-RCT design, absence of original data, and evaluation of nonclinical interventions. Data were extracted from published articles. Trial characteristics, including primary intervention, demographics, adherence to the CONSORT-AI reporting guideline, and Cochrane risk of bias were analyzed.

FINDINGS

Literature search yielded 19 737 articles, of which 41 RCTs involved a median of 294 participants (range, 17-2488 participants). A total of 16 RCTS (39%) were published in 2021, 21 (51%) were conducted at single sites, and 15 (37%) involved endoscopy. No trials adhered to all CONSORT-AI standards. Common reasons for nonadherence were not assessing poor-quality or unavailable input data (38 trials [93%]), not analyzing performance errors (38 [93%]), and not including a statement regarding code or algorithm availability (37 [90%]). Overall risk of bias was high in 7 trials (17%). Of 11 trials (27%) that reported race and ethnicity data, the median proportion of participants from underrepresented minority groups was 21% (range, 0%-51%).

CONCLUSIONS AND RELEVANCE

This systematic review found that despite the large number of medical machine learning-based algorithms in development, few RCTs for these technologies have been conducted. Among published RCTs, there was high variability in adherence to reporting standards and risk of bias and a lack of participants from underrepresented minority groups. These findings merit attention and should be considered in future RCT design and reporting.

What Actually Works for Activity Recognition in Scenarios with Significant Domain Shift: Lessons Learned from the 2019 and 2020 Sussex-Huawei Challenges

From 2018 to 2021, the Sussex-Huawei Locomotion-Transportation Recognition Challenge presented different scenarios in which participants were tasked with recognizing eight different modes of locomotion and transportation using sensor data from smartphones. In 2019, the main challenge was using sensor data from one location to recognize activities with sensors in another location, while in the following year, the main challenge was using the sensor data of one person to recognize the activities of other persons. We use these two challenge scenarios as a framework in which to analyze the effectiveness of different components of a machine-learning pipeline for activity recognition. We show that: (i) selecting an appropriate (location-specific) portion of the available data for training can improve the F1 score by up to 10 percentage points (p. p.) compared to a more naive approach, (ii) separate models for human locomotion and for transportation in vehicles can yield an increase of roughly 1 p. p., (iii) using semi-supervised learning can, again, yield an increase of roughly 1 p. p., and (iv) temporal smoothing of predictions with Hidden Markov models, when applicable, can bring an improvement of almost 10 p. p. Our experiments also indicate that the usefulness of advanced feature selection techniques and clustering to create person-specific models is inconclusive and should be explored separately in each use-case.

CODESING DE APLICATIVO CUIDATIVO-EDUCACIONAL PARA PESSOAS COM INSUFICIÊNCIA CARDÍACA: IDEAÇÃO, PROTOTIPAGEM E CO-IMPLANTAÇÃO

RESUMO Objetivo descrever o processo de ideação, prototipagem e co-implantação do protótipo de aplicativo cuidativo-educacional à pessoa com insuficiência cardíaca em vulnerabilidade, seus familiares/cuidadores e equipe de saúde. Método estudo metodológico, com cinco fases: Constructo; Ideação; Prototipagem; Co-implantação e Adequação, realizadas de setembro de 2020 a julho de 2021. A equipe do Codesign envolveu 72 atores (15 pacientes com IC, 19 familiares/cuidadores, 35 profissionais da saúde, dois pesquisadores e um designer e desenvolvedor), que contribuíram com dados linguísticos e visuais. Resultados foi produzido o protótipo InCare®, representado pelo fluxograma de interação do usuário e esboços estruturais. Foram definidas cores para composição das telas e escolhidos recursos do protótipo, com delineamento da descrição, proposta e requisitos funcionais. O aplicativo envolveu temáticas relevantes (definição da doença e vulnerabilidade, etiologia, classificação, sinais e sintomas, cuidados diários e abordagens paliativistas, tratamentos, alimentação, atividade física e redes de suporte, benefícios) e aglutinou funcionalidades conforme necessidades e preferências da equipe, sendo considerado inovador e um incentivo ao autocuidado. Conclusão O Codesign permitiu a ideação de recursos, conteúdos, esboços das telas, fluxo do usuário, prototipagem e nome do protótipo, em processo criativo e participativo, para promoção da saúde da pessoa com insuficiência cardíaca em situação de vulnerabilidade em saúde.

CODESIGN OF A CARE-EDUCATIONAL APP FOR PEOPLE WITH HEART FAILURE: DESIGN, PROTOTYPING AND CO-IMPLEMENTATION

ABSTRACT Objective to describe the process corresponding to the design, prototyping and co-implementation of a care-educational app prototype for vulnerable people with heart failure, their family members/caregivers and the health team. Method a methodological study with five phases: Construct, Design, Prototyping, Co-implementation and Adaptation, all performed from September 2020 to July 2021. The Codesign team involved 72 actors (15 patients with HF, 19 family members/caregivers, 35 health professionals, two researchers and a designer and developer), who contributed with linguistic and visual data. Results the InCare® prototype was produced, represented by the flowchart corresponding to the user's interaction and structural sketches. Colors were defined to compose the screens and the prototype resources were chosen, outlining the description, proposal and functional requirements. The app involved relevant themes (definition of the disease and vulnerability, etiology, classification, signs and symptoms, daily care measures and palliative approaches, treatments, diet, physical activity and support networks, benefits) and gathered functionalities according to the team's needs and preferences, being considered innovative and encouraging for self-care. Conclusion codesign allowed designing resources, contents, screen sketches, user flow, prototyping and prototype name, in a creative and participatory process to promote the health of people with heart failure in vulnerable health situations.

Use of mobile applications for heart failure self-management: a systematic review of experimental and qualitative studies (Preprint)

Background

Heart failure self-management is essential to avoid decompensation and readmissions. Mobile apps seem promising in supporting heart failure self-management, and there has been a rapid growth in publications in this area. However, to date, systematic reviews have mostly focused on remote monitoring interventions using nonapp types of mobile technologies to transmit data to health care providers, rarely focusing on supporting patient self-management of heart failure.

Objective

This study aims to systematically review the evidence on the effect of heart failure self-management apps on health outcomes, patient-reported outcomes, and patient experience.

Methods

Four databases (PubMed, Embase, CINAHL, and PsycINFO) were searched for studies examining interventions that comprised a mobile app targeting heart failure self-management and reported any health-related outcomes or patient-reported outcomes or perspectives published from 2008 to December 2021. The studies were independently screened. The risk of bias was appraised using Cochrane tools. We performed a narrative synthesis of the results. The protocol was registered on PROSPERO (International Prospective Register of Systematic Reviews; CRD42020158041).

Results

A total of 28 articles (randomized controlled trials [RCTs]: n=10, 36%), assessing 23 apps, and a total of 1397 participants were included. The most common app features were weight monitoring (19/23, 83%), symptom monitoring (18/23, 78%), and vital sign monitoring (15/23, 65%). Only 26% (6/23) of the apps provided all guideline-defined core components of heart failure self-management programs: education, symptom monitoring, medication support, and physical activity support. RCTs were small, involving altogether 717 participants, had ≤6 months of follow-up, and outcomes were predominantly self-reported. Approximately 20% (2/10) of RCTs reported a significant improvement in their primary outcomes: heart failure knowledge (P=.002) and self-care (P=.004). One of the RCTs found a significant reduction in readmissions (P=.02), and 20% (2/10) of RCTs reported higher unplanned clinic visits. Other experimental studies also found significant improvements in knowledge, self-care, and readmissions, among others. Less than half of the studies involved patients and clinicians in the design of apps. Engagement with the intervention was poorly reported, with only 11% (3/28) of studies quantifying app engagement metrics such as frequency of use over the study duration. The most desirable app features were automated self-monitoring and feedback, personalization, communication with clinicians, and data sharing and integration.

Conclusions

Mobile apps may improve heart failure self-management; however, more robust evaluation studies are needed to analyze key end points for heart failure. On the basis of the results of this review, we provide a road map for future studies in this area.