Development and Implementation of a Person-Centered, Technology-Enhanced Care Model For Managing Chronic Conditions: Cohort Study

Definitions of digital biomarkers: a systematic mapping of the biomedical literature

BACKGROUND

Technological devices such as smartphones, wearables and virtual assistants enable health data collection, serving as digital alternatives to conventional biomarkers. We aimed to provide a systematic overview of emerging literature on 'digital biomarkers,' covering definitions, features and citations in biomedical research.

METHODS

We analysed all articles in PubMed that used 'digital biomarker(s)' in title or abstract, considering any study involving humans and any review, editorial, perspective or opinion-based articles up to 8 March 2023. We systematically extracted characteristics of publications and research studies, and any definitions and features of 'digital biomarkers' mentioned. We described the most influential literature on digital biomarkers and their definitions using thematic categorisations of definitions considering the Food and Drug Administration Biomarkers, EndpointS and other Tools framework (ie, data type, data collection method, purpose of biomarker), analysing structural similarity of definitions by performing text and citation analyses.

RESULTS

We identified 415 articles using 'digital biomarker' between 2014 and 2023 (median 2021). The majority (283 articles; 68%) were primary research. Notably, 287 articles (69%) did not provide a definition of digital biomarkers. Among the 128 articles with definitions, there were 127 different ones. Of these, 78 considered data collection, 56 data type, 50 purpose and 23 included all three components. Those 128 articles with a definition had a median of 6 citations, with the top 10 each presenting distinct definitions.

CONCLUSIONS

The definitions of digital biomarkers vary significantly, indicating a lack of consensus in this emerging field. Our overview highlights key defining characteristics, which could guide the development of a more harmonised accepted definition.

Usability and feasibility analysis of an mHealth-tool for supporting physical activity in people with heart failure

BACKGROUND

Physical inactivity and a sedentary lifestyle are common among people with heart failure (HF), which may lead to worse prognosis. On an already existing mHealth platform, we developed a novel tool called the Activity coach, aimed at increasing physical activity. The aim of this study was to evaluate the usability of the Activity coach and assess feasibility of outcome measures for a future efficacy trial.

METHODS

A mixed-methods design was used to collect data. People with a HF diagnosis were recruited to use the Activity coach for four weeks. The Activity coach educates the user about physical activity, provides means of registering daily physical activity and helps the user to set goals for the next week. The usability was assessed by analysing system user logs for adherence, reported technical issues and by interviews about user experiences. Outcome measures assessed for feasibility were objective physical activity as measured by an accelerometer, and subjective goal attainment. Progression criteria for the usability assessment and for the proposed outcomes, were described prospectively.

RESULTS

Ten people with HF were recruited, aged 56 to 78 with median age 72. Data from nine of the ten study participants were included in the analyses. Usability: The Activity coach was used 61% of the time and during the first week two study participants called to seek technical support. The Activity coach was found to be intuitive and easy to use by all study participants. An increased motivation to be more physically active was reported by six of the nine study participants. However, in spite of feeling motivated, four reported that their habits or behaviours had not been affected by the Activity coach.

FEASIBILITY

Data was successfully stored in the deployed hardware as intended and the accelerometers were used enough, for the data to be analysable. One finding was that the subjective outcome goal attainment, was challenging to collect. A proposed mitigator for this is to use pre-defined goals in future studies, as opposed to having the study participants be completely free to formulate the goals themselves.

CONCLUSIONS

It was confirmed that the Activity coach was easy to use. Furthermore, it might stimulate increased physical activity in a population of people with HF, who are physically inactive. The outcomes investigated seem feasible to include in a future efficacy trial.

TRIAL REGISTRATION

ClinicalTrials.gov identifier: NCT05235763. Date of first registration: 11/02/2022.

Patterns and Predictors Associated With Long-Term Glycemic Control in Pediatric and Young Adult Patients with Type 1 Diabetes

BACKGROUND

The development of diabetes technology is rapid and requires education and resources to be successfully implemented in diabetes care management.

METHOD

In an observational study, we evaluated the use of advanced diabetes technology, resource utilization, and glycemic control. The study population was 725 individuals with type 1 diabetes (T1D) living in Region Halland, Sweden. The study cohort was followed for 7 years between 2013 and 2019.

RESULTS

Children aged 0 to 17 years were associated with significantly better glucose control than young adults aged 18 to 25 years. The mean HbA1c in children and young adults was 53 mmol/mol (7.0%) compared to 61 mmol/mol (7.7%) (P < .0001), respectively. Comorbidities such as attention deficit hyperactivity disorder (ADHD), autism, and coelic disease were associated with higher HbA1c. All groups, regardless of age and comorbidity, showed a positive effect on glucose control after visiting a dietitian or psychologist. Differences were found between the age groups in terms of more use of advanced diabetes technology and more frequent visits to a physician in children compared to young adults.

CONCLUSIONS

More frequent visits to physicians, and a visit to dietitians, and psychologists were associated with improved glucose control in individuals with T1D 0 to 25 years. Increased resources, including access to more advanced technologies, may be required in young adults with T1D.

Current Perspective on the Potential Benefits of Smart Insulin Pens on Glycemic Control in Patients With Diabetes: Spanish Delphi Consensus

INTRODUCTION

Diabetes mellitus (DM) is a chronic disease with high morbidity and mortality, and glycemic control is key to avoiding complications. Technological innovations have led to the development of new tools to help patients with DM manage their condition.

OBJECTIVE

This consensus assesses the current perspective of physicians on the potential benefits of using smart insulin pens in the glycemic control of patients with type 1 diabetes (DM1) in Spain.

METHODS

The Delphi technique was used by 110 physicians who were experts in managing patients with DM1. The questionnaire consisted of 94 questions.

RESULTS

The consensus obtained was 95.74%. The experts recommended using the ambulatory glucose profile report and the different time-in-range (TIR) metrics to assess poor glycemic control. Between 31% and 65% of patients had TIR values less than 70% and were diagnosed based on glycosylated hemoglobin values. They believed that less than 10% of patients needed to remember to administer the basal insulin dose and between 10% and 30% needed to remember the prandial insulin dose.

CONCLUSIONS

The perception of physicians in their usual practice leads them to recommend the use of ambulatory glucose profile and time in range for glycemic control. Forgetting to administer insulin is a very common problem and the actual occurrence rate does not correspond with clinicians' perceptions. Technological improvements and the use of smart insulin pens can increase treatment adherence, strengthen the doctor-patient relationship, and help improve patients' education and quality of life.

Connected Insulin Pens and Caps: An Expert's Recommendation from the Area of Diabetes of the Spanish Endocrinology and Nutrition Society (SEEN)

Undoubtedly, technological advances have revolutionised diabetes management in recent years. The development of advanced closed hybrid loop insulin pumps or continuous glucose monitoring (CGM) systems, among others, have increased the quality of life and improved glycaemic control of people with diabetes. However, only some patients have access to such technology, and only some want to use it. CGM has become much more widespread, but in terms of insulin delivery, most people with type 1 diabetes (T1D) and almost all people with type 2 diabetes (T2D) on insulin therapy are treated with multiple-dose insulin injections (MDI) rather than an insulin pump. For these patients, using connected insulin pens or caps has shown benefits in reducing missed insulin injections and promoting correct administration over time. In addition, using these devices improves the quality of life and user satisfaction. The integration of insulin injection and CGM data facilitates both users and the healthcare team to analyse glucose control and implement appropriate therapeutic changes, reducing therapeutic inertia. This expert's recommendation reviews the characteristics of the devices marketed or in the process of being marketed and their available scientific evidence. Finally, it suggests the profile of users and professionals who would benefit most, the barriers to its generalisation and the changes in the care model that implementing these devices can bring with it.

Better self-care through co-care? A latent profile analysis of primary care patients' experiences of e-health-supported chronic care management

Background

Efficient self-care of chronic conditions requires that an individual's resources be optimally combined with healthcare's resources, sometimes supported by e-health services (i.e., co-care). This calls for a system perspective of self-care to determine to what extent it involves demanding or unnecessary tasks and whether role clarity, needs support, and goal orientation are sufficient. This study aims to explore typical configurations of how the co-care system is experienced by individuals with chronic conditions who used an e-health service supporting self-monitoring and digital communication with primary care.

Method

We performed a latent profile analysis using questionnaire data from two waves (7 months apart) involving 180 of 308 eligible patients who pilot-tested an e-health service for co-care at a Swedish primary care center. The five subscales of the Distribution of Co-Care Activities (DoCCA) scale were used to create profiles at Time 1 (T1) and Time 2 (T2). Profiles were described based on sociodemographic variables (age, gender, education level, and health condition) and compared based on exogenous variables (self-rated health, satisfaction with healthcare, self-efficacy in self-care, and perceptions of the e-health service).

Results

We identified four typical configurations of co-care experiences at T1: strained, neutral, supportive, and optimal. Patients with optimal and supportive profiles had higher self-rated health, self-efficacy in self-care, and satisfaction with healthcare than patients with strained and neutral profiles. Slightly more than half transitioned to a similar or more positive profile at T2, for which we identified five profiles: unsupportive, strained, neutral, supportive, and optimal. Patients with optimal and supportive profiles at T2 had higher self-efficacy in self-care and satisfaction with healthcare than the other profiles. The optimal profiles also had higher self-rated health than all other profiles. Members of the optimal and supportive profiles perceived the effectiveness of the e-health service as more positive than the unsupportive and strained profile members.

Discussion

Primary care patients' co-care profiles were primarily distinguished by their experiences of needs support, goal orientation, and role clarity. Patients with more positive co-care experiences also reported higher self-rated health, self-efficacy in self-care, and satisfaction with healthcare, as well as more positive experiences of the e-health service.

Diagnostic accuracy of an artificial intelligence online engine in migraine: A multi‐center study

Objective

This study assesses the concordance in migraine diagnosis between an online, self‐administered, Computer‐based, Diagnostic Engine (CDE) and semi‐structured interview (SSI) by a headache specialist, both using International Classification of Headache Disorders, 3rd edition (ICHD‐3) criteria.

Background

Delay in accurate diagnosis is a major barrier to headache care. Accurate computer‐based algorithms may help reduce the need for SSI‐based encounters to arrive at correct ICHD‐3 diagnosis.

Methods

Between March 2018 and August 2019, adult participants were recruited from three academic headache centers and the community via advertising to our cross‐sectional study. Participants completed two evaluations: phone interview conducted by headache specialists using the SSI and a web‐based expert questionnaire and analytics, CDE. Participants were randomly assigned to either the SSI followed by the web‐based questionnaire or the web‐based questionnaire followed by the SSI. Participants completed protocols a few minutes apart. The concordance in migraine/probable migraine (M/PM) diagnosis between SSI and CDE was measured using Cohen’s kappa statistics. The diagnostic accuracy of CDE was assessed using the SSI as reference standard.

Results

Of the 276 participants consented, 212 completed both SSI and CDE (study completion rate = 77%; median age = 32 years [interquartile range: 28–40], female:male ratio = 3:1). Concordance in M/PM diagnosis between SSI and CDE was: κ = 0.83 (95% confidence interval [CI]: 0.75–0.91). CDE diagnostic accuracy: sensitivity = 90.1% (118/131), 95% CI: 83.6%–94.6%; specificity = 95.8% (68/71), 95% CI: 88.1%–99.1%. Positive and negative predictive values = 97.0% (95% CI: 91.3%–99.0%) and 86.6% (95% CI: 79.3%–91.5%), respectively, using identified migraine prevalence of 60%. Assuming a general migraine population prevalence of 10%, positive and negative predictive values were 70.3% (95% CI: 43.9%–87.8%) and 98.9% (95% CI: 98.1%–99.3%), respectively.

Conclusion

The SSI and CDE have excellent concordance in diagnosing M/PM. Positive CDE helps rule in M/PM, through high specificity and positive likelihood ratio. A negative CDE helps rule out M/PM through high sensitivity and low negative likelihood ratio. CDE that mimics SSI logic is a valid tool for migraine diagnosis.

Analysis of "Glycemic Outcomes During Real-World Hybrid Closed-Loop System Use by Individuals With Type 1 Diabetes in the United States"

In an article in the Journal of Diabetes Science and Technology, Arunachalum et al retrospectively analyzed glycemic outcomes, regarding the use of hybrid closed-loop (HCL) systems in individuals with type-1 diabetes (T1D) in the United States in a real-world evidence (RWE) setting. In clinical trials, diabetes technology has shown to improve time in range (TIR) as well as other glucose metrics. In the light of increasing the use of diabetes technology in the T1D population, why do we not see improvement in clinical outcomes? Is it cost-effective to increase the use diabetes technology? Does access to diabetes technology vary in the United States? There is a need for additional clinical studies evaluating the effectiveness of diabetes technology in T1D including health economic aspects.

Key drivers involved in the telemonitoring of covid-19 for self-health management: an exploratory factor analysis

Background

The recent COVID-19 pandemic and the shortage of general practitioners has determined a strong pressure on the Italian health system. This critical issue highlighted the fundamental support of e-health services not only to lighten the workload of doctors, but also to offer patients a health service tailored to real needs. Therefore, the digital engagement platforms represent a valid aid, as they reconcile the efficiency needs of the healthcare system with the benefits for the patients involved. In this perspective, little is known about the main factors associated with use of telemonitoring platforms and their effectiveness. This paper investigates the critical success factors of telemonitoring platforms during COVID-19 in order to understand the mechanisms underlying patient participation with the health engagement platforms.

Methods

An exploratory factor analysis was used to explain the main dimensions of patient participation in the COVID-19 telemonitoring. A sample of 119 patients with a suspected or confirmed infection was used in the investigation. Moreover, an analysis of variance was calculated to identify the differences between three types of patients (infected, uninfected, with suspected infection) and verify the effectiveness of the platform.

Main Findings

There are six main factors underlying the use of the COVID-19 telemonitoring platform. “Self-Health Engagement” emerges as a novel factor. Moreover, compared to other platforms, cognitive engagement is a crucial trigger for effective telemonitoring.

Discussion

By identifying the main triggers involved in the use of health engagement platforms, we can improve the satisfaction of telemonitoring services for appropriate health-crisis management. Furthermore, the COVID-19 telemonitoring platform appears to improve health management for both patients and health care providers as it provides the patient with the necessary tools for Self-Health Management (SHM), as well as helping to enrich the literature on health care.

Conclusion

A new construct emerges in the study of digital telemonitoring platforms: “health self-engagement”, that is, an engagement based on self-care that demonstrates the decisive role assumed by both digital technology and patient participation in self-management.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12913-022-07828-3.

Computerized migraine diagnostic tools: a systematic review

BACKGROUND

Computerized migraine diagnostic tools have been developed and validated since 1960. We conducted a systematic review to summarize and critically appraise the quality of all published studies involving computerized migraine diagnostic tools.

METHODS

We performed a systematic literature search using PubMed, Web of Science, Scopus, snowballing, and citation searching. Cutoff date for search was 1 June 2021. Published articles in English that evaluated a computerized/automated migraine diagnostic tool were included. The following summarized each study: publication year, digital tool name, development basis, sample size, sensitivity, specificity, reference diagnosis, strength, and limitations. The Quality Assessment of Diagnostic Accuracy Studies (QUADAS) tool was applied to evaluate the quality of included studies in terms of risk of bias and concern of applicability.

RESULTS

A total of 41 studies (median sample size: 288 participants, median age = 43 years; 77% women) were included. Most (60%) tools were developed based on International Classification of Headache Disorders criteria, half were self-administered, and 82% were evaluated using face-to-face interviews as reference diagnosis. Some of the automated algorithms and machine learning programs involved case-based reasoning, deep learning, classifier ensemble, ant-colony, artificial immune, random forest, white and black box combinations, and hybrid fuzzy expert systems. The median diagnostic accuracy was concordance = 89% [interquartile range (IQR) = 76-93%; range = 45-100%], sensitivity = 87% (IQR = 80-95%; range = 14-100%), and specificity = 90% (IQR = 77-96%; range = 65-100%). Lack of random patient sampling was observed in 95% of studies. Case-control designs were avoided in all studies. Most (76%) reference tests exhibited low risk of bias and low concern of applicability. Patient flow and timing showed low risk of bias in 83%.

CONCLUSION

Different computerized and automated migraine diagnostic tools are available with varying accuracies. Random patient sampling, head-to-head comparison among tools, and generalizability to other headache diagnoses may improve their utility.

Design and Development of an eHealth Service for Collaborative Self-Management among Older Adults with Chronic Diseases: A Theory-Driven User-Centered Approach

The increasing prevalence of chronic conditions and multimorbidity poses great challenges to healthcare systems. As patients' engagement in self-managing their chronic conditions becomes increasingly important, eHealth interventions are a promising resource for the provision of adequate and timely support. However, there is inconclusive evidence about how to design eHealth services to meet the complex needs of patients. This study applied an evidence-based and theory-informed user-centered design approach in three phases to identify the needs of older adults and healthcare professionals in the collaborative management of multimorbidity (phase 1), develop an eHealth service to address these needs (phase 2), and test the feasibility and acceptance of the eHealth service in a clinical setting (phase 3). Twenty-two user needs were identified and a web-based application-ePATH (electronic Patient Activation in Treatment at Home)-with separate user interfaces for patients and healthcare professionals was developed. The feasibility study with two nurses and five patients led to a redesign and highlighted the importance of adequately addressing not only varying user needs but also the complex nature of healthcare organizations when implementing new services and processes in chronic care management.

Spanish adaptation and validation of the User Version of the Mobile Application Rating Scale (uMARS)

OBJECTIVE

While the professional version of the Mobile App Rating Scale (MARS) has already been translated, and validated into the Spanish language, its user-centered counterpart has not yet been adapted. Furthermore, no other similar tools exist in the Spanish language. The aim of this paper is to adapt and validate User Version of the MARS (uMARS) into the Spanish language.

MATERIALS AND METHODS

Cross-cultural adaptation, translation, and metric evaluation. The internal consistency and test-retest reliability of the Spanish version of the uMARS were evaluated using the RadarCovid app. Two hundred and sixteen participants rated the app using the translated scale. The app was then rated again 2 weeks later by 21 of these participants to measure test-retest reliability.

RESULTS

No major differences were observed between the uMARS original and the Spanish version. Discrimination indices (item-scale correlation) obtained appropriate results for both raters. The Spanish uMARS presented with excellent internal consistency, α = .89 and .67 for objective and subjective quality, respectively, and temporal stability (r > 0.82 for all items and subscales).

DISCUSSION

The Spanish uMARS is a useful tool for health professionals to recommend high-quality mobile apps to their patients based on the user's perspective and for researchers and app developers to use end-user feedback and evaluation, to help them identify highly appraised and valued components, as well as areas for further development, to continue ensuring the increasing quality and prominence of the area of mHealth.

CONCLUSION

uMARS Spanish version is an instrument with adequate metric properties to assess the quality of health apps from the user perspective.

Challenges in Participant Engagement and Retention using Mobile Health Apps: A Literature Review (Preprint)

Background

Mobile health (mHealth) apps are revolutionizing the way clinicians and researchers monitor and manage the health of their participants. However, many studies using mHealth apps are hampered by substantial participant dropout or attrition, which may impact the representativeness of the sample and the effectiveness of the study. Therefore, it is imperative for researchers to understand what makes participants stay with mHealth apps or studies using mHealth apps.

Objective

This study aimed to review the current peer-reviewed research literature to identify the notable factors and strategies used in adult participant engagement and retention.

Methods

We conducted a systematic search of PubMed, MEDLINE, and PsycINFO databases for mHealth studies that evaluated and assessed issues or strategies to improve the engagement and retention of adults from 2015 to 2020. We followed the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines. Notable themes were identified and narratively compared among different studies. A binomial regression model was generated to examine the factors affecting retention.

Results

Of the 389 identified studies, 62 (15.9%) were included in this review. Overall, most studies were partially successful in maintaining participant engagement. Factors related to particular elements of the app (eg, feedback, appropriate reminders, and in-app support from peers or coaches) and research strategies (eg, compensation and niche samples) that promote retention were identified. Factors that obstructed retention were also identified (eg, lack of support features, technical difficulties, and usefulness of the app). The regression model results showed that a participant is more likely to drop out than to be retained.

Conclusions

Retaining participants is an omnipresent challenge in mHealth studies. The insights from this review can help inform future studies about the factors and strategies to improve participant retention.

Satisfied or Frustrated? A Qualitative Analysis of Need Satisfying and Need Frustrating Experiences of Engaging With Digital Health Technology in Chronic Care

Introduction: Digital health technologies such as self-monitoring devices and apps are becoming increasingly important as tools to promote healthy habits and support individuals in their self-care. There is still a scarcity of research that builds on motivational theory to better understand the functioning of digital health technologies. The self-determination theory (SDT) is a macro theory of motivation that delineates three basic psychological needs that are linked to different types of motivation and lead to well-being when satisfied and illbeing when frustrated.

Objective: To explore how the use of a digital tool for self-monitoring and communication with healthcare satisfies or frustrates basic psychological needs across four spheres of user experience: interface, task, behavior, and life.

Methods: The study was conducted in a Swedish primary care setting with individuals who participated in a pilot study of a digital health intervention for self-monitoring in chronic care management. Data from a follow-up survey with participants 7 months after recruitment were analyzed using a thematic approach mixing inductive and deductive analysis. The unit of analysis is based on a total of 642 individual answers to seven open-ended questions, from 121 respondents.

Results: The analysis identified positive and negative influences of self-monitoring and digital communication with healthcare on all three psychological needs. Three main findings are that: (1) data covered all four spheres of user experiences, but most user experiences concerned the behavior and task spheres; (2) satisfaction and frustration of competence needs was more prominent than influences on other needs; (3) the same experience may be perceived as both need frustrating and need satisfying, which suggests a tension that reflects individual differences.

Conclusion: Designers of digital health technologies need to take into account basic psychological needs within all spheres of user experience, from interface to life in general. Because some features may be simultaneously experienced as satisfying and frustrating by different users, these types of tools need to be flexible to accommodate for variation of user experiences. Careful design considerations that take motivational theory into account would contribute to the transformation of care for individuals with chronic conditions.

A Web-Based Application for Complex Health Care Populations: User-Centered Design Approach

BACKGROUND

Although eHealth technology makes it possible to improve the management of complex health care systems and follow up on chronic patients, it is not without challenges, thus requiring the development of efficient programs and graphic user interface (GUI) features. Similar information technology tools are crucial, as health care populations are going to have to endure social distancing measures in the forthcoming months and years.

OBJECTIVE

This study aims to provide adequate and personalized support to complex health care populations by developing a specific web-based mobile app. The app is designed around the patient and adapted to specific groups, for example, people with complex or rare diseases, autism, or disabilities (especially among children) as well as Alzheimer or senile dementia. The app's core features include the collection, labeling, analysis, and sorting of clinical data. Furthermore, it authorizes a network of people around the patient to securely access the data contained in his or her electronic health record.

METHODS

The application was designed according to the paradigms of patient-centered care and user-centered design (UCD). It considers the patient as the main empowered and motivating factor in the management of his or her well-being. Implementation was informed through a family needs and technology perception assessment. We used 3 interdisciplinary focus groups and 2 assessment surveys to study the contexts of app use, subpopulation management, and preferred functions. Finally, we developed an observational study involving 116 enrolled patients and 253 system users, followed by 2 feedback surveys to evaluate the performance and impact of the app.

RESULTS

In the validated general GUI, we developed 10 user profiles with different privacy settings. We tested 81 functions and studied a modular structure based on disease or medical area. This allowed us to identify replicable methods to be applied to module design. The observational study not only showed good family and community engagement but also revealed some limitations that need to be addressed. In total, 42 of 51 (82%) patients described themselves as satisfied or very satisfied. Health care providers reported facilitated communication with colleagues and the need to support data quality.

CONCLUSIONS

The experimented solution addressed some of the health system challenges mentioned by the World Health Organization: usability appears to be significantly improved when the GUI is designed according to patients' UCD mental models and when new media and medical literacy are promoted. This makes it possible to maximize the impact of eHealth products, thereby overcoming some crucial gaps reported in the literature. Two main features seemed to have potential benefit compared with other eHealth products: the modeling, within the app, of both the formal and informal health care support networks and the modular structure allowing for comorbidity management, both of which require further implementation.

Smart Insulin Pens are Associated with Improved Clinical Outcomes at Lower Cost Versus Standard-of-Care Treatment of Type 1 Diabetes in Sweden: A Cost-Effectiveness Analysis

INTRODUCTION

Real-world evidence has demonstrated improved glycemic control and insulin management following introduction of smart insulin pens in a Swedish type 1 diabetes (T1D) population. To understand the implications for healthcare costs and expected health outcomes, this analysis evaluated the long-term cost-effectiveness of introducing smart insulin pens to standard-of-care T1D treatment (standard care) from a Swedish societal perspective.

METHODS

Clinical outcomes and healthcare costs (in 2018 Swedish krona, SEK) were projected over patients' lifetimes using the IQVIA CORE Diabetes Model to estimate cost-effectiveness. Clinical data and baseline characteristics for the simulated cohort were informed by population data and a prospective, noninterventional study of a smart insulin pen in a Swedish T1D population. This analysis captured direct and indirect costs, mortality, and the impact of diabetes-related complications on quality of life.

RESULTS

Over patients' lifetimes, smart insulin pen use was associated with per-patient improvements in mean discounted life expectancy (+ 0.90 years) and quality-adjusted life expectancy (+ 1.15 quality-adjusted life-years), in addition to mean cost savings (direct, SEK 124,270; indirect, SEK 373,725), versus standard care. A lower frequency and delayed onset of complications drove projected improvements in quality-adjusted life expectancy and lower costs with smart insulin pens versus standard care. Overall, smart insulin pens were a dominant treatment option relative to standard care across all base-case and sensitivity analyses.

CONCLUSIONS

Use of smart insulin pens was projected to improve clinical outcomes at lower costs relative to standard care in a Swedish T1D population and represents a good use of healthcare resources in Sweden.

Digital tools as promoters for person-centered care practices in chronic care? Healthcare professionals' experiences from rheumatology care

Background

Person-centered care (PCC) emphasize the importance of supporting individuals’ involvement in care provided and self-care. PCC has become more important in chronic care as the number of people living with chronic conditions is increasing due to the demographic changes. Digital tools have potential to support interaction between patients and healthcare providers, but empirical examples of how to achieve PCC in chronic care and the role of digital tools in this process is limited. The aim of this study was to investigate strategies to achieve PCC used by the healthcare professionals at an outpatient Rheumatology clinic (RC), the strategies’ relation to digital tools, and the perceived impact of the strategies on healthcare professionals and patients.

Methods

A single case study design was used. The qualitative data consisted of 14 semi-structured interviews and staff meeting minutes, covering the time period 2017–2019. The data were analyzed using conventional content analysis, complemented with document analyses.

Results

Ten strategies on two levels to operationalize PCC, and three categories of perceived impact were identified. On the individual patient level strategies involved several digital tools focusing on flexible access to care, mutual information sharing and the distribution of initiatives, tasks, and responsibilities from provider to patients. On the unit level, strategies concerned involving patient representatives and individual patients in development of digital services and work practices. The roles of both professionals and patients were affected and the importance of behavioral and cultural change became clear.

Conclusions

By providing an empirical example from chronic care the study contributes to the knowledge on strategies for achieving PCC, how digital tools and work practices interact, and how they can affect healthcare staff, patients and the unit. A conclusion is that the use of the digital tools, spanning over different dimensions of engagement, facilitated the healthcare professionals’ interaction with patients and the patients’ involvement in their own care. Digital tools complemented, rather than replaced, care practices.

Using Natural Language Processing and Sentiment Analysis to Augment Traditional User-Centered Design: Development and Usability Study

Background

Sarcopenia, defined as the age-associated loss of muscle mass and strength, can be effectively mitigated through resistance-based physical activity. With compliance at approximately 40% for home-based exercise prescriptions, implementing a remote sensing system would help patients and clinicians to better understand treatment progress and increase compliance. The inclusion of end users in the development of mobile apps for remote-sensing systems can ensure that they are both user friendly and facilitate compliance. With advancements in natural language processing (NLP), there is potential for these methods to be used with data collected through the user-centered design process.

Objective

This study aims to develop a mobile app for a novel device through a user-centered design process with both older adults and clinicians while exploring whether data collected through this process can be used in NLP and sentiment analysis

Methods

Through a user-centered design process, we conducted semistructured interviews during the development of a geriatric-friendly Bluetooth-connected resistance exercise band app. We interviewed patients and clinicians at weeks 0, 5, and 10 of the app development. Each semistructured interview consisted of heuristic evaluations, cognitive walkthroughs, and observations. We used the Bing sentiment library for a sentiment analysis of interview transcripts and then applied NLP-based latent Dirichlet allocation (LDA) topic modeling to identify differences and similarities in patient and clinician participant interviews. Sentiment was defined as the sum of positive and negative words (each word with a +1 or −1 value). To assess utility, we used quantitative assessment questionnaires—System Usability Scale (SUS) and Usefulness, Satisfaction, and Ease of use (USE). Finally, we used multivariate linear models—adjusting for age, sex, subject group (clinician vs patient), and development—to explore the association between sentiment analysis and SUS and USE outcomes.

Results

The mean age of the 22 participants was 68 (SD 14) years, and 17 (77%) were female. The overall mean SUS and USE scores were 66.4 (SD 13.6) and 41.3 (SD 15.2), respectively. Both patients and clinicians provided valuable insights into the needs of older adults when designing and building an app. The mean positive-negative sentiment per sentence was 0.19 (SD 0.21) and 0.47 (SD 0.21) for patient and clinician interviews, respectively. We found a positive association with positive sentiment in an interview and SUS score (ß=1.38; 95% CI 0.37 to 2.39; P=.01). There was no significant association between sentiment and the USE score. The LDA analysis found no overlap between patients and clinicians in the 8 identified topics.

Conclusions

Involving patients and clinicians allowed us to design and build an app that is user friendly for older adults while supporting compliance. This is the first analysis using NLP and usability questionnaires in the quantification of user-centered design of technology for older adults.

Artificial Intelligence in Health Care: Bibliometric Analysis

Background

As a critical driving power to promote health care, the health care–related artificial intelligence (AI) literature is growing rapidly.

Objective

The purpose of this analysis is to provide a dynamic and longitudinal bibliometric analysis of health care–related AI publications.

Methods

The Web of Science (Clarivate PLC) was searched to retrieve all existing and highly cited AI-related health care research papers published in English up to December 2019. Based on bibliometric indicators, a search strategy was developed to screen the title for eligibility, using the abstract and full text where needed. The growth rate of publications, characteristics of research activities, publication patterns, and research hotspot tendencies were computed using the HistCite software.

Results

The search identified 5235 hits, of which 1473 publications were included in the analyses. Publication output increased an average of 17.02% per year since 1995, but the growth rate of research papers significantly increased to 45.15% from 2014 to 2019. The major health problems studied in AI research are cancer, depression, Alzheimer disease, heart failure, and diabetes. Artificial neural networks, support vector machines, and convolutional neural networks have the highest impact on health care. Nucleosides, convolutional neural networks, and tumor markers have remained research hotspots through 2019.

Conclusions

This analysis provides a comprehensive overview of the AI-related research conducted in the field of health care, which helps researchers, policy makers, and practitioners better understand the development of health care–related AI research and possible practice implications. Future AI research should be dedicated to filling in the gaps between AI health care research and clinical applications.