-
PLOS Digital Health May 2024Clinical discoveries largely depend on dedicated clinicians and scientists to identify and pursue unique and unusual clinical encounters with patients and communicate...
Clinical discoveries largely depend on dedicated clinicians and scientists to identify and pursue unique and unusual clinical encounters with patients and communicate these through case reports and case series. This process has remained essentially unchanged throughout the history of modern medicine. However, these traditional methods are inefficient, especially considering the modern-day availability of health-related data and the sophistication of computer processing. Outlier analysis has been used in various fields to uncover unique observations, including fraud detection in finance and quality control in manufacturing. We propose that clinical discovery can be formulated as an outlier problem within an augmented intelligence framework to be implemented on any health-related data. Such an augmented intelligence approach would accelerate the identification and pursuit of clinical discoveries, advancing our medical knowledge and uncovering new therapies and management approaches. We define clinical discoveries as contextual outliers measured through an information-based approach and with a novelty-based root cause. Our augmented intelligence framework has five steps: define a patient population with a desired clinical outcome, build a predictive model, identify outliers through appropriate measures, investigate outliers through domain content experts, and generate scientific hypotheses. Recognizing that the field of obstetrics can particularly benefit from this approach, as it is traditionally neglected in commercial research, we conducted a systematic review to explore how outlier analysis is implemented in obstetric research. We identified two obstetrics-related studies that assessed outliers at an aggregate level for purposes outside of clinical discovery. Our findings indicate that using outlier analysis in clinical research in obstetrics and clinical research, in general, requires further development.
PubMed: 38776276
DOI: 10.1371/journal.pdig.0000515 -
European Heart Journal. Digital Health May 2024Telehealth-delivered cardiac rehabilitation (CR) programmes can potentially increase participation rates while delivering equivalent outcomes to facility-based... (Review)
Review
Key features in telehealth-delivered cardiac rehabilitation required to optimize cardiovascular health in coronary heart disease: a systematic review and realist synthesis.
Telehealth-delivered cardiac rehabilitation (CR) programmes can potentially increase participation rates while delivering equivalent outcomes to facility-based programmes. However, key components of these interventions that reduce cardiovascular risk factors are not yet distinguished. This study aims to identify features of telehealth-delivered CR that improve secondary prevention outcomes, exercise capacity, participation, and participant satisfaction and develop recommendations for future telehealth-delivered CR. The protocol for our review was registered with the Prospective Register of Systematic Reviews (#CRD42021236471). We systematically searched four databases (PubMed, Scopus, EMBASE, and Cochrane Database) for randomized controlled trials comparing telehealth-delivered CR programmes to facility-based interventions or usual care. Two independent reviewers screened the abstracts and then full texts. Using a qualitative review methodology (realist synthesis), included articles were evaluated to determine contextual factors and potential mechanisms that impacted cardiovascular risk factors, exercise capacity, participation in the intervention, and increased satisfaction. We included 37 reports describing 26 randomized controlled trials published from 2010 to 2022. Studies were primarily conducted in Europe and Australia/Asia. Identified contextual factors and mechanisms were synthesized into four theories required to enhance participant outcomes and participation. These theories are as follows: (i) early and regular engagement; (ii) personalized interventions and shared goals; (iii) usable, accessible, and supported interventions; and (iv) exercise that is measured and monitored. Providing a personalized approach with frequent opportunities for bi-directional interaction was a critical feature for success across telehealth-delivered CR trials. Real-world effectiveness studies are now needed to complement our findings.
PubMed: 38774382
DOI: 10.1093/ehjdh/ztad080 -
Digital Health 2024Mobile health applications hold immense potential for enhancing health outcomes. Usability is one of the main factors for the adoption and use of mobile health... (Review)
Review
OBJECTIVE
Mobile health applications hold immense potential for enhancing health outcomes. Usability is one of the main factors for the adoption and use of mobile health applications. However, despite the growing importance of mHealth applications, clear standards for their evaluation remain elusive. The present study aimed to determine heuristics for the usability evaluation of health-related applications.
METHODS
We systematically searched multiple databases for relevant papers published between January 2008 and April 2021. Articles were reviewed, and data were extracted and categorized from those meeting inclusion criteria by two authors independently. Heuristics were identified based on statements, words, and concepts expressed in the studies. These heuristics were first mapped to Nielsen's heuristics based on their differences or similarities. The remaining heuristics that were very important for mobile applications were categorized into new heuristics.
RESULTS
Seventeen studies met the eligibility criteria. Seventy-nine heuristics were extracted from the papers. After combining the items with the same concepts and removing irrelevant items based on the exclusion criteria, 20 heuristics remained. Common heuristics such as "Visibility of system status" and "Flexibility and efficiency of use" were categorized into 10 previously established heuristics and new heuristics like "Navigation" and "User engagement" were recognized as new ones.
CONCLUSIONS
In our study, we have meticulously identified 20 heuristics that hold promise for evaluating and designing mHealth applications. These heuristics can be used by the researchers for the development of robust tools for heuristic evaluation. These tools, when adapted or tailored for health domain applications, have the potential to significantly enhance the quality of mHealth applications. Ultimately, this improvement in quality translates to enhanced patient safety.
PROTOCOL REGISTRATION
(10.17605/OSF.IO/PZJ7H).
PubMed: 38766365
DOI: 10.1177/20552076241253539 -
NPJ Digital Medicine May 2024Scientific research of artificial intelligence (AI) in dermatology has increased exponentially. The objective of this study was to perform a systematic review and... (Review)
Review
Scientific research of artificial intelligence (AI) in dermatology has increased exponentially. The objective of this study was to perform a systematic review and meta-analysis to evaluate the performance of AI algorithms for skin cancer classification in comparison to clinicians with different levels of expertise. Based on PRISMA guidelines, 3 electronic databases (PubMed, Embase, and Cochrane Library) were screened for relevant articles up to August 2022. The quality of the studies was assessed using QUADAS-2. A meta-analysis of sensitivity and specificity was performed for the accuracy of AI and clinicians. Fifty-three studies were included in the systematic review, and 19 met the inclusion criteria for the meta-analysis. Considering all studies and all subgroups of clinicians, we found a sensitivity (Sn) and specificity (Sp) of 87.0% and 77.1% for AI algorithms, respectively, and a Sn of 79.78% and Sp of 73.6% for all clinicians (overall); differences were statistically significant for both Sn and Sp. The difference between AI performance (Sn 92.5%, Sp 66.5%) vs. generalists (Sn 64.6%, Sp 72.8%), was greater, when compared with expert clinicians. Performance between AI algorithms (Sn 86.3%, Sp 78.4%) vs expert dermatologists (Sn 84.2%, Sp 74.4%) was clinically comparable. Limitations of AI algorithms in clinical practice should be considered, and future studies should focus on real-world settings, and towards AI-assistance.
PubMed: 38744955
DOI: 10.1038/s41746-024-01103-x -
Digital Health 2024The integration of advanced technologies, including three-dimensional (3D) imaging modalities and virtual simulations, has significantly influenced contemporary... (Review)
Review
AIM
The integration of advanced technologies, including three-dimensional (3D) imaging modalities and virtual simulations, has significantly influenced contemporary approaches to preoperative planning in implant dentistry. Through a meticulous analysis of relevant studies, this review synthesizes findings related to accuracy outcomes in implant placement facilitated by 3D imaging in virtual patients.
METHODS
A comprehensive literature search was conducted across relevant databases to identify relevant studies published to date. The inclusion criteria were studies utilizing 3D imaging techniques, virtual patients, and those focusing on the accuracy of dental implant planning and surgical placement. The selected studies were critically appraised for their methodological quality.
RESULTS
After a rigorous analysis, 21 relevant articles were included out of 3021 articles. This study demonstrates the versatility and applicability of these technologies in both and settings. Integrating Computer-Aided Design/Computer-Aided Manufacturing (CAD/CAM), cone bean computed tomography (CBCT), and advanced 3D reconstruction methodologies showcases a trend toward enhanced precision in implant planning and placement. Notably, the evaluation parameters varied, encompassing distances, discrepancies, and deviations in the implant placement. The ongoing integration of systems such as dynamic navigation systems, augmented reality, and sophisticated software platforms shows a promising trajectory for the continued refinement of virtual reality applications in dental implantology, providing valuable insights for future research and clinical implementation. Moreover, using stereolithographic surgical guides, virtual planning with CBCT data, and 3D-printed templates consistently demonstrates enhanced precision in dental implant placement compared to traditional methods.
CONCLUSION
The synthesis of the available evidence underscores the substantial positive impact of 3D imaging techniques and virtual patients on dental implant planning and surgical placement accuracy. Utilizing these technologies contributes to a more personalized and precise approach that enhances overall treatment outcomes. Future research directions and potential refinements to the application of these technologies in clinical practice should be discussed.
PubMed: 38726220
DOI: 10.1177/20552076241253550 -
NPJ Digital Medicine May 2024Posttraumatic stress disorder (PTSD) recently becomes one of the most important mental health concerns. However, no previous study has comprehensively reviewed the... (Review)
Review
Posttraumatic stress disorder (PTSD) recently becomes one of the most important mental health concerns. However, no previous study has comprehensively reviewed the application of big data and machine learning (ML) techniques in PTSD. We found 873 studies meet the inclusion criteria and a total of 31 of those in a sample of 210,001 were included in quantitative analysis. ML algorithms were able to discriminate PTSD with an overall accuracy of 0.89. Pooled estimates of classification accuracy from multi-dimensional data (0.96) are higher than single data types (0.86 to 0.90). ML techniques can effectively classify PTSD and models using multi-dimensional data perform better than those using single data types. While selecting optimal combinations of data types and ML algorithms to be clinically applied at the individual level still remains a big challenge, these findings provide insights into the classification, identification, diagnosis and treatment of PTSD.
PubMed: 38724610
DOI: 10.1038/s41746-024-01117-5 -
NPJ Digital Medicine May 2024Ensuring diagnostic performance of artificial intelligence (AI) before introduction into clinical practice is essential. Growing numbers of studies using AI for digital... (Review)
Review
Ensuring diagnostic performance of artificial intelligence (AI) before introduction into clinical practice is essential. Growing numbers of studies using AI for digital pathology have been reported over recent years. The aim of this work is to examine the diagnostic accuracy of AI in digital pathology images for any disease. This systematic review and meta-analysis included diagnostic accuracy studies using any type of AI applied to whole slide images (WSIs) for any disease. The reference standard was diagnosis by histopathological assessment and/or immunohistochemistry. Searches were conducted in PubMed, EMBASE and CENTRAL in June 2022. Risk of bias and concerns of applicability were assessed using the QUADAS-2 tool. Data extraction was conducted by two investigators and meta-analysis was performed using a bivariate random effects model, with additional subgroup analyses also performed. Of 2976 identified studies, 100 were included in the review and 48 in the meta-analysis. Studies were from a range of countries, including over 152,000 whole slide images (WSIs), representing many diseases. These studies reported a mean sensitivity of 96.3% (CI 94.1-97.7) and mean specificity of 93.3% (CI 90.5-95.4). There was heterogeneity in study design and 99% of studies identified for inclusion had at least one area at high or unclear risk of bias or applicability concerns. Details on selection of cases, division of model development and validation data and raw performance data were frequently ambiguous or missing. AI is reported as having high diagnostic accuracy in the reported areas but requires more rigorous evaluation of its performance.
PubMed: 38704465
DOI: 10.1038/s41746-024-01106-8 -
NPJ Digital Medicine Apr 2024The integration of robotics in surgery has increased over the past decade, and advances in the autonomous capabilities of surgical robots have paralleled that of... (Review)
Review
The integration of robotics in surgery has increased over the past decade, and advances in the autonomous capabilities of surgical robots have paralleled that of assistive and industrial robots. However, classification and regulatory frameworks have not kept pace with the increasing autonomy of surgical robots. There is a need to modernize our classification to understand technological trends and prepare to regulate and streamline surgical practice around these robotic systems. We present a systematic review of all surgical robots cleared by the United States Food and Drug Administration (FDA) from 2015 to 2023, utilizing a classification system that we call Levels of Autonomy in Surgical Robotics (LASR) to categorize each robot's decision-making and action-taking abilities from Level 1 (Robot Assistance) to Level 5 (Full Autonomy). We searched the 510(k), De Novo, and AccessGUDID databases in December 2023 and included all medical devices fitting our definition of a surgical robot. 37,981 records were screened to identify 49 surgical robots. Most surgical robots were at Level 1 (86%) and some reached Level 3 (Conditional Autonomy) (6%). 2 surgical robots were recognized by the FDA to have machine learning-enabled capabilities, while more were reported to have these capabilities in their marketing materials. Most surgical robots were introduced via the 510(k) pathway, but a growing number via the De Novo pathway. This review highlights trends toward greater autonomy in surgical robotics. Implementing regulatory frameworks that acknowledge varying levels of autonomy in surgical robots may help ensure their safe and effective integration into surgical practice.
PubMed: 38671232
DOI: 10.1038/s41746-024-01102-y -
Digital Health 2024Smartphone apps (apps) are widely recognised as promising tools for improving access to mental healthcare. However, a key challenge is the development of digital... (Review)
Review
OBJECTIVE
Smartphone apps (apps) are widely recognised as promising tools for improving access to mental healthcare. However, a key challenge is the development of digital interventions that are acceptable to end users. Co-production with providers and stakeholders is increasingly positioned as the gold standard for improving uptake, engagement, and healthcare outcomes. Nevertheless, clear guidance around the process of co-production is lacking. The objectives of this review were to: (i) present an overview of the methods and approaches to co-production when designing, producing, and evaluating digital mental health interventions; and (ii) explore the barriers and facilitators affecting co-production in this context.
METHODS
A pre-registered (CRD42023414007) systematic review was completed in accordance with The Preferred Reporting Items for Systematic reviews and Meta-Analyses guidelines. Five databases were searched. A co-produced bespoke quality appraisal tool was developed with an expert by experience to assess the quality of the co-production methods and approaches. A narrative synthesis was conducted.
RESULTS
Twenty-six studies across 24 digital mental health interventions met inclusion criteria. App interventions were rarely co-produced with end users throughout all stages of design, development, and evaluation. Co-producing digital mental health interventions added value by creating culturally sensitive and acceptable interventions. Reported challenges included resource issues exacerbated by the digital nature of the intervention, variability across stakeholder suggestions, and power imbalances between stakeholders and researchers.
CONCLUSIONS
Variation in approaches to co-producing digital mental health interventions is evident, with inconsistencies between stakeholder groups involved, stage of involvement, stakeholders' roles and methods employed.
PubMed: 38665886
DOI: 10.1177/20552076241239172 -
Digital Health 2024The Covid-19 pandemic has accelerated the adoption of digital technologies to address social needs, leading to increased investments in digital healthcare applications.... (Review)
Review
OBJECTIVE
The Covid-19 pandemic has accelerated the adoption of digital technologies to address social needs, leading to increased investments in digital healthcare applications. Germany implemented a special law called the "Digitales Versorgungsgesetz" (DVG-Digital Supply Act) in 2019, which enables the reimbursement of digital health applications, including digital therapeutics (DTx), through a fast-track process. The Federal Institute for Drugs and Medical Devices (BfArM), the German federal authority responsible for overseeing digital health applications, has implemented legislative adjustments since the law's introduction, which have increased requirements for these applications and potentially led to the removal of some from the directory as well as a slowdown in the addition of new ones. To counteract this trend, this work aimed to identify key success factors for digital health applications (DiGAs).
METHODS
This research identifies critical success factors through a structured literature review for developing sustainable digital health applications within the European healthcare systems, specifically DiGAs. The study aims to support the ongoing digital transformation in healthcare.
RESULTS
The identified success factors that significantly impact the sustainability of DiGAs include patient-centered design, application effectiveness, user-friendliness, and adherence to data protection and information security regulations using standardized approaches. These factors are crucial in preventing the failure of DiGA manufacturers in European countries.
CONCLUSION
By considering and implementing these critical success factors, DiGA manufacturers can enhance their chances of long-term success and contribute to the digital transformation of the healthcare system in Europe.
PubMed: 38665883
DOI: 10.1177/20552076241249604