Future and Development Direction of Digital Healthcare

The Application of Robotics in Cardiac Rehabilitation: A Systematic Review

Background and Objectives: Robotics is commonly used in the rehabilitation of neuro-musculoskeletal injuries and diseases. While in these conditions, robotics has clear benefits, it is unknown whether robotics will also enhance the outcome of cardiac rehabilitation. This systematic review evaluates the use of robotics in cardiac rehabilitation. Methods: A systematic literature search was conducted using PubMed (MEDLINE), CINAHL, AMED, SPORTDiscus, and the Physiotherapy Evidence Database. Longitudinal interventional studies were included if they met specified criteria. Two reviewers independently conducted title, abstract, and full-text screening and data extraction. The quality assessment and risk of bias were conducted according to the PEDRO scale and Cochrane Risk of Bias tool 2, respectively. Results: Four trials were included in this review out of 60 screened studies. The quality of the included studies was good with a low risk of bias. The trials used different robotic systems: Lokomat® system, Motomed Letto/Thera Trainer tigo, BEAR, and Myosuit. It was found that interventions that included the use of robotic assistance technologies improved the exercise capacity, VO2 max/peak, left ventricular ejection fraction, QOL, and physical functioning in people with cardiac diseases. Conclusions: Robotic assistance technologies can be used in cardiac rehabilitation programs. Further studies are needed to confirm the results and determine whether the use of robotics enhances intervention outcomes above standard interventions.

Construction and validation of a machine learning model for the diagnosis of juvenile idiopathic arthritis based on fecal microbiota

Purpose

Human gut microbiota has been shown to be significantly associated with various inflammatory diseases. Therefore, this study aimed to develop an excellent auxiliary tool for the diagnosis of juvenile idiopathic arthritis (JIA) based on fecal microbial biomarkers.

Method

The fecal metagenomic sequencing data associated with JIA were extracted from NCBI, and the sequencing data were transformed into the relative abundance of microorganisms by professional data cleaning (KneadData, Trimmomatic and Bowtie2) and comparison software (Kraken2 and Bracken). After that, the fecal microbes with high abundance were extracted for subsequent analysis. The extracted fecal microbes were further screened by least absolute shrinkage and selection operator (LASSO) regression, and the selected fecal microbe biomarkers were used for model training. In this study, we constructed six different machine learning (ML) models, and then selected the best model for constructing a JIA diagnostic tool by comparing the performance of the models based on a combined consideration of area under receiver operating characteristic curve (AUC), accuracy, specificity, F1 score, calibration curves and clinical decision curves. In addition, to further explain the model, Permutation Importance analysis and Shapley Additive Explanations (SHAP) were performed to understand the contribution of each biomarker in the prediction process.

Result

A total of 231 individuals were included in this study, including 203 JIA patients and Non-JIA individuals. In the analysis of diversity at the genus level, the alpha diversity represented by Shannon value was not significantly different between the two groups, while the belt diversity was slightly different. After selection by LASSO regression, 10 fecal microbe biomarkers were selected for model training. By comparing six different models, the XGB model showed the best performance, which average AUC, accuracy and F1 score were 0.976, 0.914 and 0.952, respectively, thus being used to construct the final JIA diagnosis model.

Conclusion

A JIA diagnosis model based on XGB algorithm was constructed with excellent performance, which may assist physicians in early detection of JIA patients and improve the prognosis of JIA patients.

Smart hospital definition: Academic and industrial perspective

BACKGROUNDS

Healthcare is a social and economic challenge in many countries, exacerbated by today's increasing demand. Many studies demonstrate that hospitals that move towards smartness, and some of their processes are smart, can provide more appropriate treatments and deal with problems more flexibly. It is axiomatic that implementing smart hospitals and healthcare tools requires a clear objective. However, the concept of a smart hospital lacks a comprehensive and broadly accepted definition, leading to varied interpretations and misconceptions. Many developments touted as 'smart' merely digitize existing hospital environments without truly embracing the full potential of smart technology. Furthermore, research studies have neglected to consider industrial perspectives, which will soon cause a gap between industry and academics in this concept.

OBJECTIVES

This research aims to explore the attributes of a smart hospital and use them to propose a definition for it, considering both scholarly and industrial viewpoints.

METHOD AND RESULTS

The PRISMA method is employed to select academic and practical papers providing definitions and insights into smart hospitals or healthcare. 17 studies are analyzed, and a total, 83 characteristics are identified to describe the smart hospital. These features are categorized into three primary categories: "technologies", "services", and "goals". The most important features are determined by analyzing the frequencies of these characteristics across all the studies. In the results section, these data are presented in graphical form, highlighting both academic and industrial perspectives separately, as well as a combined analysis. Furthermore, an attempt is made to uncover trends in smart hospitals from 2015 to 2023.

CONCLUSION

A comprehensive definition of the smart hospital, encompassing both academic and industrial perspectives, is proposed using the investigated characteristics. This study also presents research opportunities and discusses the existing gap between academia and industry concerning smart hospitals.

The Constrained-Disorder Principle Assists in Overcoming Significant Challenges in Digital Health: Moving from "Nice to Have" to Mandatory Systems

The success of artificial intelligence depends on whether it can penetrate the boundaries of evidence-based medicine, the lack of policies, and the resistance of medical professionals to its use. The failure of digital health to meet expectations requires rethinking some of the challenges faced. We discuss some of the most significant challenges faced by patients, physicians, payers, pharmaceutical companies, and health systems in the digital world. The goal of healthcare systems is to improve outcomes. Assisting in diagnosing, collecting data, and simplifying processes is a "nice to have" tool, but it is not essential. Many of these systems have yet to be shown to improve outcomes. Current outcome-based expectations and economic constraints make "nice to have," "assists," and "ease processes" insufficient. Complex biological systems are defined by their inherent disorder, bounded by dynamic boundaries, as described by the constrained disorder principle (CDP). It provides a platform for correcting systems' malfunctions by regulating their degree of variability. A CDP-based second-generation artificial intelligence system provides solutions to some challenges digital health faces. Therapeutic interventions are held to improve outcomes with these systems. In addition to improving clinically meaningful endpoints, CDP-based second-generation algorithms ensure patient and physician engagement and reduce the health system's costs.

Desperately Seeking Intersectionality in Digital Health Disparity Research: Narrative Review to Inform a Richer Theorization of Multiple Disadvantage

BACKGROUND

Digital consultations between patients and clinicians increased markedly during the COVID-19 pandemic, raising questions about equity.

OBJECTIVE

This study aimed to review the literature on how multiple disadvantage-specifically, older age, lower socioeconomic status, and limited English proficiency-has been conceptualized, theorized, and studied empirically in relation to digital consultations. We focused mainly on video consultations as they have wider disparities than telephone consultations and relevant data on e-consultations are sparse.

METHODS

Using keyword and snowball searching, we identified relevant papers published between 2012 and 2022 using Ovid MEDLINE, Web of Science, Google Scholar, and PubMed. The first search was completed in July 2022. Papers meeting the inclusion criteria were analyzed thematically and summarized, and their key findings were tabulated using the Grading of Recommendations Assessment, Development, and Evaluation Confidence in the Evidence from Reviews of Qualitative Research criteria. Explanations for digital disparities were critically examined, and a search was undertaken in October 2022 to identify theoretical lenses on multiple disadvantage.

RESULTS

Of 663 articles from the initial search, 27 (4.1%) met our inclusion criteria. In total, 37% (10/27) were commentaries, and 63% (17/27) were peer-reviewed empirical studies (11/27, 41% quantitative; 5/27, 19% qualitative; 1/27, 4% mixed methods; 1/27, 4% systematic reviews; and 1/27, 4% narrative reviews). Empirical studies were mostly small, rapidly conducted, and briefly reported. Most studies (25/27, 93%) identified marked digital disparities but lacked a strong theoretical lens. Proposed solutions focused on identifying and removing barriers, but the authors generally overlooked the pervasive impact of multiple layers of disadvantage. The data set included no theoretically informed studies that examined how different dimensions of disadvantage combined to affect digital health disparities. In our subsequent search, we identified 3 theoretical approaches that might help account for these digital disparities. Fundamental cause theory by Link and Phelan addresses why the association between socioeconomic status and health is pervasive and persists over time. Digital capital theory by Ragnedda and Ruiu explains how people mobilize resources to participate in digitally mediated activities and services. Intersectionality theory by Crenshaw states that systems of oppression are inherently bound together, creating singular social experiences for people who bear the force of multiple adverse social structures.

CONCLUSIONS

A limitation of our initial sample was the sparse and undertheorized nature of the primary literature. The lack of attention to how digital health disparities emerge and play out both within and across categories of disadvantage means that solutions proposed to date may be oversimplistic and insufficient. Theories of multiple disadvantage have bearing on digital health, and there may be others of relevance besides those discussed in this paper. We call for greater interdisciplinary dialogue between theoretical research on multiple disadvantage and empirical studies on digital health disparities.

Health-Related Indicators Measured Using Earable Devices: Systematic Review

BACKGROUND

Earable devices are novel, wearable Internet of Things devices that are user-friendly and have potential applications in mobile health care. The position of the ear is advantageous for assessing vital status and detecting diseases through reliable and comfortable sensing devices.

OBJECTIVE

Our study aimed to review the utility of health-related indicators derived from earable devices and propose an improved definition of disease prevention. We also proposed future directions for research on the health care applications of earable devices.

METHODS

A systematic review was conducted of the PubMed, Embase, and Web of Science databases. Keywords were used to identify studies on earable devices published between 2015 and 2020. The earable devices were described in terms of target health outcomes, biomarkers, sensor types and positions, and their utility for disease prevention.

RESULTS

A total of 51 articles met the inclusion criteria and were reviewed, and the frequency of 5 health-related characteristics of earable devices was described. The most frequent target health outcomes were diet-related outcomes (9/51, 18%), brain status (7/51, 14%), and cardiovascular disease (CVD) and central nervous system disease (5/51, 10% each). The most frequent biomarkers were electroencephalography (11/51, 22%), body movements (6/51, 12%), and body temperature (5/51, 10%). As for sensor types and sensor positions, electrical sensors (19/51, 37%) and the ear canal (26/51, 51%) were the most common, respectively. Moreover, the most frequent prevention stages were secondary prevention (35/51, 69%), primary prevention (12/51, 24%), and tertiary prevention (4/51, 8%). Combinations of ≥2 target health outcomes were the most frequent in secondary prevention (8/35, 23%) followed by brain status and CVD (5/35, 14% each) and by central nervous system disease and head injury (4/35, 11% each).

CONCLUSIONS

Earable devices can provide biomarkers for various health outcomes. Brain status, healthy diet status, and CVDs were the most frequently targeted outcomes among the studies. Earable devices were mostly used for secondary prevention via monitoring of health or disease status. The potential utility of earable devices for primary and tertiary prevention needs to be investigated further. Earable devices connected to smartphones or tablets through cloud servers will guarantee user access to personal health information and facilitate comfortable wearing.

Future Scenarios of the Data-Driven Healthcare Economy in South Korea

Although data-based healthcare innovation has been spotlighted in South Korea in recent years, previous studies have made little effort to systematically predict various possible future outcomes in the data-driven healthcare economy. This study investigated possible future such scenarios in South Korea by conducting a general morphological analysis (GMA). Seven key factors were identified that will drive the data-driven healthcare economy: the acceptability of data utilization, the level of data literacy, the status of healthcare data regulation, the healthcare data system, medical costs, the convergence of ICT and biotechnology, and the utilization of data in medical services. The main findings are as follows: Four possible scenarios for the data-driven healthcare economy in South Korea were identified. The first scenario suggested mostly optimistic prospects and close associations between factorial values on the various spectra. The second scenario was similar to the first one, except for medical costs. However, the third scenario contrasted with the first, as it entailed relatively pessimistic factorial values. Finally, most of the elements of the current healthcare status quo were maintained in the fourth scenario. This study makes not only an academic contribution, but also has policy implications based on the four scenarios.

A Digital Health Service for Elderly People with Balance Disorders and Risk of Falling: A Design Science Approach

In this study, a design science research methodology was used aiming at designing, implementing and evaluating a digital health service to complement the provision of healthcare for elderly people with balance disorders and risk of falling. An explanatory sequential mixed methods study allowed to identify and explore the dissatisfaction with electronic medical records and the opportunity for using digital health solutions. The suggested recommendations helped to elaborate and develop “BALANCE”, a digital service implemented on the METHIS platform, which was recently validated for remote monitoring of chronic patients in primary healthcare. “BALANCE” provides clinical and interactive data, questionnaire pre and post-balance rehabilitation, tutorial videos with balance exercises and patient-recorded videos of the exercises. This digital service was demonstrated, including five elderly patients with clinical recommendations for balance rehabilitation at home. Finally, the authors conducted two focus groups with the participants and their caregivers as well as with physicians. The focus groups aimed at exploring their satisfaction level, needs of adjustment in the “BALANCE” service and strategies for applicability. The digital healthcare service evaluation revealed a significant potential for clinical applicability of this digital solution for elderly people with balance disorders and risk of falling.

The predicting value of resting heart rate to identify undiagnosed diabetes in Korean adult: Korea National Health and Nutrition Examination Survey

OBJECTIVES

The purpose of this study was (1) to examine whether the addition of resting heart rate (RHR) to the existing undiagnosed diabetes mellitus (UnDM) prediction model would improve predictability, and (2) to develop and validate UnDM prediction models by using only easily assessable variables such as gender, RHR, age, and waist circumference (WC).

METHODS

Korea National Health and Nutrition Examination Survey (KNHANES) 2010, 2012, 2014, 2016 data were used to develop the model (model building set, n=19,675), while the data from 2011, 2013, 2015, 2017 were used to validate the model (validation set, n=19,917). UnDM was defined as a fasting glucose level ≥126 mg/dL or glycated hemoglobin ≥6.5%; however, doctors have not diagnosed it. Statistical package for the social sciences logistic regression analysis was used to determine the predictors of UnDM.

RESULTS

RHR, age, and WC were associated with UnDM. When RHR was added to the existing model, sensitivity was reduced (86 vs. 73%), specificity was increased (49 vs. 65%), and a higher Youden index (35 vs. 38) was expressed. When only gender, RHR, age, and WC were used in the model, a sensitivity, specificity, and Youden index of 70%, 67%, and 37, respectively, were observed.

CONCLUSIONS

Adding RHR to the existing UnDM prediction model improved specificity and the Youden index. Furthermore, when the prediction model only used gender, RHR, age, and WC, the outcomes were not inferior to those of the existing prediction model.

Preparing for a New World: Making Friends with Digital Health

While digital health solutions have shown good outcomes in numerous studies, the adoption of digital health solutions in clinical practice faces numerous challenges. To prepare for widespread adoption of digital health, stakeholders in digital health will need to establish an objective evaluation process, consider uncertainty through critical evaluation, be aware of inequity, and consider patient engagement. By "making friends" with digital health, health care can be improved for patients.