Augmenting K-Means Clustering With Qualitative Data to Discover the Engagement Patterns of Older Adults With Multimorbidity When Using Digital Health Technologies: Proof-of-Concept Trial.

BACKGROUND: Multiple chronic conditions (multimorbidity) are becoming more prevalent among aging populations. Digital health technologies have the potential to assist in the self-management of multimorbidity, improving the awareness and monitoring of health and well-being, supporting a better understanding of the disease, and encouraging behavior change. OBJECTIVE: The aim of this study was to analyze how 60 older adults (mean age 74, SD 6.4; range 65-92 years) with multimorbidity engaged with digital symptom and well-being monitoring when using a digital health platform over a period of approximately 12 months. METHODS: Principal component analysis and clustering analysis were used to group participants based on their levels of engagement, and the data analysis focused on characteristics (eg, age, sex, and chronic health conditions), engagement outcomes, and symptom outcomes of the different clusters that were discovered. RESULTS: Three clusters were identified: the typical user group, the least engaged user group, and the highly engaged user group. Our findings show that age, sex, and the types of chronic health conditions do not influence engagement. The 3 primary factors influencing engagement were whether the same device was used to submit different health and well-being parameters, the number of manual operations required to take a reading, and the daily routine of the participants. The findings also indicate that higher levels of engagement may improve the participants' outcomes (eg, reduce symptom exacerbation and increase physical activity). CONCLUSIONS: The findings indicate potential factors that influence older adult engagement with digital health technologies for home-based multimorbidity self-management. The least engaged user groups showed decreased health and well-being outcomes related to multimorbidity self-management. Addressing the factors highlighted in this study in the design and implementation of home-based digital health technologies may improve symptom management and physical activity outcomes for older adults self-managing multimorbidity.

Don't judge a book or health app by its cover: User ratings and downloads are not linked to quality.

OBJECTIVE: To analyse the relationship between health app quality with user ratings and the number of downloads of corresponding health apps. MATERIALS AND METHODS: Utilising a dataset of 881 Android-based health apps, assessed via the 300-point objective Organisation for the Review of Care and Health Applications (ORCHA) assessment tool, we explored whether subjective user-level indicators of quality (user ratings and downloads) correlate with objective quality scores in the domains of user experience, data privacy and professional/clinical assurance. For this purpose, we applied spearman correlation and multiple linear regression models. RESULTS: For user experience, professional/clinical assurance and data privacy scores, all models had very low adjusted R squared values (< .02). Suggesting that there is no meaningful link between subjective user ratings or the number of health app downloads and objective quality measures. Spearman correlations suggested that prior downloads only had a very weak positive correlation with user experience scores (Spearman = .084, p = .012) and data privacy scores (Spearman = .088, p = .009). There was a very weak negative correlation between downloads and professional/clinical assurance score (Spearman = -.081, p = .016). Additionally, user ratings demonstrated a very weak correlation with no statistically significant correlations observed between user ratings and the scores (all p > 0.05). For ORCHA scores multiple linear regression had adjusted R-squared = -.002. CONCLUSION: This study highlights that widely available proxies which users may perceive to signify the quality of health apps, namely user ratings and downloads, are inaccurate predictors for estimating quality. This indicates the need for wider use of quality assurance methodologies which can accurately determine the quality, safety, and compliance of health apps. Findings suggest more should be done to enable users to recognise high-quality health apps, including digital health literacy training and the provision of nationally endorsed "libraries".

Quality of Digital Health Interventions Across Different Health Care Domains: Secondary Data Analysis Study.

BACKGROUND: There are more than 350,000 digital health interventions (DHIs) in the app stores. To ensure that they are effective and safe to use, they should be assessed for compliance with best practice standards. OBJECTIVE: The objective of this paper was to examine and compare the compliance of DHIs with best practice standards and adherence to user experience (UX), professional and clinical assurance (PCA), and data privacy (DP). METHODS: We collected assessment data from 1574 DHIs using the Organisation for the Review of Care and Health Apps Baseline Review (OBR) assessment tool. As part of the assessment, each DHI received a score out of 100 for each of the abovementioned areas (ie, UX, PCA, and DP). These 3 OBR scores are combined to make up the overall ORCHA score (a proxy for quality). Inferential statistics, probability distributions, Kruskal-Wallis, Wilcoxon rank sum test, Cliff delta, and Dunn tests were used to conduct the data analysis. RESULTS: We found that 57.3% (902/1574) of the DHIs had an Organisation for the Review of Care and Health Apps (ORCHA) score below the threshold of 65. The overall median OBR score (ORCHA score) for all DHIs was 61.5 (IQR 51.0-73.0) out of 100. A total of 46.2% (12/26) of DHI's health care domains had a median equal to or above the ORCHA threshold score of 65. For the 3 assessment areas (UX, DP, and PCA), DHIs scored the highest for the UX assessment 75.2 (IQR 70.0-79.6), followed by DP 65.1 (IQR 55.0-73.4) and PCA 49.6 (IQR 31.9-76.1). UX scores had the least variance (SD 13.9), while PCA scores had the most (SD 24.8). Respiratory and urology DHIs were consistently highly ranked in the National Institute for Health and Care Excellence Evidence Standards Framework tiers B and C based on their ORCHA score. CONCLUSIONS: There is a high level of variability in the ORCHA scores of DHIs across different health care domains. This suggests that there is an urgent need to improve compliance with best practices in some health care areas. Possible explanations for the observed differences might include varied market maturity and commercial interests within the different health care domains. More investment to support the development of higher-quality DHIs in areas such as ophthalmology, allergy, women's health, sexual health, and dental care may be needed.

An experimental machine learning study investigating the decision-making process of students and qualified radiographers when interpreting radiographic images.

AI is becoming more prevalent in healthcare and is predicted to be further integrated into workflows to ease the pressure on an already stretched service. The National Health Service in the UK has prioritised AI and Digital health as part of its Long-Term Plan. Few studies have examined the human interaction with such systems in healthcare, despite reports of biases being present with the use of AI in other technologically advanced fields, such as finance and aviation. Understanding is needed of how certain user characteristics may impact how radiographers engage with AI systems in use in the clinical setting to mitigate against problems before they arise. The aim of this study is to determine correlations of skills, confidence in AI and perceived knowledge amongst student and qualified radiographers in the UK healthcare system. A machine learning based AI model was built to predict if the interpreter was either a student (n = 67) or a qualified radiographer (n = 39) in advance, using important variables from a feature selection technique named Boruta. A survey, which required the participant to interpret a series of plain radiographic examinations with and without AI assistance, was created on the Qualtrics survey platform and promoted via social media (Twitter/LinkedIn), therefore adopting convenience, snowball sampling This survey was open to all UK radiographers, including students and retired radiographers. Pearson's correlation analysis revealed that males who were proficient in their profession were more likely than females to trust AI. Trust in AI was negatively correlated with age and with level of experience. A machine learning model was built, the best model predicted the image interpreter to be qualified radiographers with 0.93 area under curve and a prediction accuracy of 93%. Further testing in prospective validation cohorts using a larger sample size is required to determine the clinical utility of the proposed machine learning model.

Ventricular fibrillation waveform properties influenced by thoracic impedance guided chest compressions in a porcine model.

BACKGROUND AND OBJECTIVE: Quantitative measures extracted from ventricular fibrillation (VF) waveform reflect the metabolic state of the myocardium and are associated with survival outcome. The quality of delivered chest compressions during cardiopulmonary resuscitation are also linked with survival. The aim of this research is to explore the viability and effectiveness of a thoracic impedance (TI) based chest compression (CC) guidance system to control CC depth within individual subjects and influence VF waveform properties. METHODS: This porcine investigation includes an analysis of two protocols. CC were delivered in 2 min episodes at a constant rate of 110 CC min-1. Subject-specific CC depth was controlled using a TI-thresholding system where CC were performed according to the amplitude (ZRMS, 0.125 to 1.250 Ω) of a band-passed TI signal (ZCC). Protocol A was a retrospective analysis of a 12-porcine study to characterise the response of two VF waveform metrics: amplitude spectrum area (AMSA) and mean slope (MS), to varying CC quality. Protocol B was a prospective 12-porcine study to determine if changes in VF waveform metrics, due to CC quality, were associated with defibrillation outcome. RESULTS: Protocol A: A directly proportional relationship was observed between ZRMS and CC depth applied within each subject (r = 0.90; p <0.001). A positive relationship was observed between ZRMS and both AMSA (p <0.001) and MS (p <0.001), where greater TI thresholds were associated with greater waveform metrics. PROTOCOL B: MS was associated with return of circulation following defibrillation (odds ratio = 2.657; p = 0.043). CONCLUSION: TI-thresholding was an effective way to control CC depth within-subjects. Compressions applied according to higher TI thresholds evoked an increase in AMSA and MS. The response in MS due to deeper CC resulted in a greater incidence of ROSC compared to shallow chest compressions.

A Multilingual Digital Mental Health and Well-Being Chatbot (ChatPal): Pre-Post Multicenter Intervention Study.

BACKGROUND: In recent years, advances in technology have led to an influx of mental health apps, in particular the development of mental health and well-being chatbots, which have already shown promise in terms of their efficacy, availability, and accessibility. The ChatPal chatbot was developed to promote positive mental well-being among citizens living in rural areas. ChatPal is a multilingual chatbot, available in English, Scottish Gaelic, Swedish, and Finnish, containing psychoeducational content and exercises such as mindfulness and breathing, mood logging, gratitude, and thought diaries. OBJECTIVE: The primary objective of this study is to evaluate a multilingual mental health and well-being chatbot (ChatPal) to establish if it has an effect on mental well-being. Secondary objectives include investigating the characteristics of individuals that showed improvements in well-being along with those with worsening well-being and applying thematic analysis to user feedback. METHODS: A pre-post intervention study was conducted where participants were recruited to use the intervention (ChatPal) for a 12-week period. Recruitment took place across 5 regions: Northern Ireland, Scotland, the Republic of Ireland, Sweden, and Finland. Outcome measures included the Short Warwick-Edinburgh Mental Well-Being Scale, the World Health Organization-Five Well-Being Index, and the Satisfaction with Life Scale, which were evaluated at baseline, midpoint, and end point. Written feedback was collected from participants and subjected to qualitative analysis to identify themes. RESULTS: A total of 348 people were recruited to the study (n=254, 73% female; n=94, 27% male) aged between 18 and 73 (mean 30) years. The well-being scores of participants improved from baseline to midpoint and from baseline to end point; however, improvement in scores was not statistically significant on the Short Warwick-Edinburgh Mental Well-Being Scale (P=.42), the World Health Organization-Five Well-Being Index (P=.52), or the Satisfaction With Life Scale (P=.81). Individuals that had improved well-being scores (n=16) interacted more with the chatbot and were significantly younger compared to those whose well-being declined over the study (P=.03). Three themes were identified from user feedback, including "positive experiences," "mixed or neutral experiences," and "negative experiences." Positive experiences included enjoying exercises provided by the chatbot, while most of the mixed, neutral, or negative experiences mentioned liking the chatbot overall, but there were some barriers, such as technical or performance errors, that needed to be overcome. CONCLUSIONS: Marginal improvements in mental well-being were seen in those who used ChatPal, albeit nonsignificant. We propose that the chatbot could be used along with other service offerings to complement different digital or face-to-face services, although further research should be carried out to confirm the effectiveness of this approach. Nonetheless, this paper highlights the need for blended service offerings in mental health care.

A Mental Health and Well-Being Chatbot: User Event Log Analysis.

BACKGROUND: Conversational user interfaces, or chatbots, are becoming more popular in the realm of digital health and well-being. While many studies focus on measuring the cause or effect of a digital intervention on people's health and well-being (outcomes), there is a need to understand how users really engage and use a digital intervention in the real world. OBJECTIVE: In this study, we examine the user logs of a mental well-being chatbot called ChatPal, which is based on the concept of positive psychology. The aim of this research is to analyze the log data from the chatbot to provide insight into usage patterns, the different types of users using clustering, and associations between the usage of the app's features. METHODS: Log data from ChatPal was analyzed to explore usage. A number of user characteristics including user tenure, unique days, mood logs recorded, conversations accessed, and total number of interactions were used with k-means clustering to identify user archetypes. Association rule mining was used to explore links between conversations. RESULTS: ChatPal log data revealed 579 individuals older than 18 years used the app with most users being female (n=387, 67%). User interactions peaked around breakfast, lunchtime, and early evening. Clustering revealed 3 groups including "abandoning users" (n=473), "sporadic users" (n=93), and "frequent transient users" (n=13). Each cluster had distinct usage characteristics, and the features were significantly different (P<.001) across each group. While all conversations within the chatbot were accessed at least once by users, the "treat yourself like a friend" conversation was the most popular, which was accessed by 29% (n=168) of users. However, only 11.7% (n=68) of users repeated this exercise more than once. Analysis of transitions between conversations revealed strong links between "treat yourself like a friend," "soothing touch," and "thoughts diary" among others. Association rule mining confirmed these 3 conversations as having the strongest linkages and suggested other associations between the co-use of chatbot features. CONCLUSIONS: This study has provided insight into the types of people using the ChatPal chatbot, patterns of use, and associations between the usage of the app's features, which can be used to further develop the app by considering the features most accessed by users.

What do we mean by complex percutaneous coronary intervention? An assessment of agreement amongst interventional cardiologists for defining complexity.

BACKGROUND: In the last decade, percutaneous coronary intervention (PCI) has evolved toward the treatment of complex disease in patients with multiple comorbidities. Whilst there are several definitions of complexity, it is unclear whether there is agreement between cardiologists in classifying complexity of cases. Inconsistent identification of complex PCI can lead to significant variation in clinical decision-making. AIM: This study aimed to determine the inter-rater agreement in rating the complexity and risk of PCI procedures. METHOD: An online survey was designed and disseminated amongst interventional cardiologists by the European Association of Percutaneous Cardiovascular Intervention (EAPCI) board. The survey presented four patient vignettes, with study participants assessing these cases to classify their complexity. RESULTS: From 215 respondents, there was poor inter-rater agreement in classifying the complexity level (k = 0.1) and a fair agreement (k = 0.31) in classifying the risk level. The experience level of participants did not show any significant impact on the inter-rater agreement of rating the complexity level and the risk level. There was good level of agreement between participants in terms of rating 26 factors for classifying complex PCI. The top five factors were (1) impaired left ventricular function, (2) concomitant severe aortic stenosis, (3) last remaining vessel PCI, (4) requirement fort calcium modification and (5) significant renal impairment. CONCLUSION: Agreement among cardiologists in classifying complexity of PCI is poor, which may lead to suboptimal clinical decision-making, procedural planning as well as long-term management. Consensus is needed to define complex PCI, and this requires clear criteria incorporating both lesion and patient characteristics.

A two-staged classifier to reduce false positives: On device detection of atrial fibrillation using phase-based distribution of poincaré plots and deep learning.

BACKGROUND: Mobile Cardiac Outpatient Telemetry (MCOT) can be used to screen high risk patients for atrial fibrillation (AF). These devices rely primarily on algorithmic detection of AF events, which are then stored and transmitted to a clinician for review. It is critical the positive predictive value (PPV) of MCOT detected AF is high, and this often leads to reduced sensitivity, as device manufacturers try to limit false positives. OBJECTIVE: The purpose of this study was to design a two stage classifier using artificial intelligence (AI) to improve the PPV of MCOT detected atrial fibrillation episodes whilst maintaining high levels of detection sensitivity. METHODS: A low complexity, RR-interval based, AF classifier was paired with a deep convolutional neural network (DCNN) to create a two-stage classifier. The DCNN was limited in size to allow it to be embedded on MCOT devices. The DCNN was trained on 491,727 ECGs from a proprietary database and contained 128,612 parameters requiring only 158 KB of storage. The performance of the two-stage classifier was then assessed using publicly available datasets. RESULTS: The sensitivity of AF detected by the low complexity classifier was high across all datasets (>93%) however the PPV was poor (<76%). Subsequent analysis by the DCNN increased episode PPV across all datasets substantially (>11%), with only a minor loss in sensitivity (<5%). This increase in PPV was due to a decrease in the number of false positive detections. Further analysis showed that DCNN processing was only required on around half of analysis windows, offering a significant computational saving against using the DCNN as a one-stage classifier. CONCLUSION: DCNNs can be combined with existing MCOT classifiers to increase the PPV of detected AF episodes. This reduces the review burden for physicians and can be achieved with only a modest decrease in sensitivity.

Digital transformation of mental health services.

This paper makes a case for digital mental health and provides insights into how digital technologies can enhance (but not replace) existing mental health services. We describe digital mental health by presenting a suite of digital technologies (from digital interventions to the application of artificial intelligence). We discuss the benefits of digital mental health, for example, a digital intervention can be an accessible stepping-stone to receiving support. The paper does, however, present less-discussed benefits with new concepts such as 'poly-digital', where many different apps/features (e.g. a sleep app, mood logging app and a mindfulness app, etc.) can each address different factors of wellbeing, perhaps resulting in an aggregation of marginal gains. Another benefit is that digital mental health offers the ability to collect high-resolution real-world client data and provide client monitoring outside of therapy sessions. These data can be collected using digital phenotyping and ecological momentary assessment techniques (i.e. repeated mood or scale measures via an app). This allows digital mental health tools and real-world data to inform therapists and enrich face-to-face sessions. This can be referred to as blended care/adjunctive therapy where service users can engage in 'channel switching' between digital and non-digital (face-to-face) interventions providing a more integrated service. This digital integration can be referred to as a kind of 'digital glue' that helps join up the in-person sessions with the real world. The paper presents the challenges, for example, the majority of mental health apps are maybe of inadequate quality and there is a lack of user retention. There are also ethical challenges, for example, with the perceived 'over-promotion' of screen-time and the perceived reduction in care when replacing humans with 'computers', and the trap of 'technological solutionism' whereby technology can be naively presumed to solve all problems. Finally, we argue for the need to take an evidence-based, systems thinking and co-production approach in the form of stakeholder-centred design when developing digital mental health services based on technologies. The main contribution of this paper is the integration of ideas from many different disciplines as well as the framework for blended care using 'channel switching' to showcase how digital data and technology can enrich physical services. Another contribution is the emergence of 'poly-digital' and a discussion on the challenges of digital mental health, specifically 'digital ethics'.

Machine learning and the electrocardiogram over two decades: Time series and meta-analysis of the algorithms, evaluation metrics and applications.

BACKGROUND: The application of artificial intelligence to interpret the electrocardiogram (ECG) has predominantly included the use of knowledge engineered rule-based algorithms which have become widely used today in clinical practice. However, over recent decades, there has been a steady increase in the number of research studies that are using machine learning (ML) to read or interrogate ECG data. OBJECTIVE: The aim of this study is to review the use of ML with ECG data using a time series approach. METHODS: Papers that address the subject of ML and the ECG were identified by systematically searching databases that archive papers from January 1995 to October 2019. Time series analysis was used to study the changing popularity of the different types of ML algorithms that have been used with ECG data over the past two decades. Finally, a meta-analysis of how various ML techniques performed for various diagnostic classifications was also undertaken. RESULTS: A total of 757 papers was identified. Based on results, the use of ML with ECG data started to increase sharply (p < 0.001) from 2012. Healthcare applications, especially in heart abnormality classification, were the most common application of ML when using ECG data (p < 0.001). However, many new emerging applications include using ML and the ECG for biometrics and driver drowsiness. The support vector machine was the technique of choice for a decade. However, since 2018, deep learning has been trending upwards and is likely to be the leading technique in the coming few years. Despite the accuracy paradox, accuracy was the most frequently used metric in the studies reviewed, followed by sensitivity, specificity, F1 score and then AUC. CONCLUSION: Applying ML using ECG data has shown promise. Data scientists and physicians should collaborate to ensure that clinical knowledge is being applied appropriately and is informing the design of ML algorithms. Data scientists also need to consider knowledge guided feature engineering and the explicability of the ML algorithm as well as being transparent in the algorithm's performance to appropriately calibrate human-AI trust. Future work is required to enhance ML performance in ECG classification.

Device agnostic AI-based analysis of ambulatory ECG recordings.

Deep Convolutional Neural Networks (DCNNs) have been shown to provide improved performance over traditional heuristic algorithms for the detection of arrhythmias from ambulatory ECG recordings. However, these DCNNs have primarily been trained and tested on device-specific databases with standardized electrode positions and uniform sampling frequencies. This work explores the possibility of training a DCNN for Atrial Fibrillation (AF) detection on a database of single­lead ECG rhythm strips extracted from resting 12­lead ECGs. We then test the performance of the DCNN on recordings from ambulatory ECG devices with different recording leads and sampling frequencies. We developed an extensive proprietary resting 12­lead ECG dataset of 549,211 patients. This dataset was randomly split into a training set of 494,289 patients and a testing set of the remaining 54,922 patients. We trained a 34-layer convolutional DCNN to detect AF and other arrhythmias on this dataset. The DCNN was then validated on two Physionet databases commonly used to benchmark automated ECG algorithms (1) MIT-BIH Arrhythmia Database and (2) MIT-BIH Atrial Fibrillation Database. Validation was performed following the EC57 guidelines, with performance assessed by gross episode and duration sensitivity and positive predictive value (PPV). Finally, validation was also performed on a selection of rhythm strips from an ambulatory ECG patch that a committee of board-certified cardiologists annotated. On MIT-BIH, The DCNN achieved a sensitivity of 100% and 84% PPV in detecting episodes of AF. and 100% sensitivity and 94% PPV in quantifying AF episode duration. On AFDB, The DCNN achieved a sensitivity of 94% and PPV of 98% in detecting episodes of AF, and 98% sensitivity and 100% PPV in quantifying AF episode duration. On the patch database, the DCNN demonstrated performance that was closely comparable to that of a cardiologist. The results indicate that DCNN models can learn features that generalize between resting 12­lead and ambulatory ECG recordings, allowing DCNNs to be device agnostic for detecting arrhythmias from single­lead ECG recordings and enabling a range of clinical applications.

Home-based digital health technologies for older adults to self-manage multiple chronic conditions: A data-informed analysis of user engagement from a longitudinal trial.

Background: Ageing populations are resulting in higher prevalence of people with multiple chronic conditions (multimorbidity). Digital health platforms have great potential to support self-management of multimorbidity, increasing a person's awareness of their health and well-being, supporting a better understanding of diseases and encouraging behaviour change. However, little research has explored the long-term engagement of older adults with such digital interventions. Methods: The aim of this study is to analyse how 60 older adults with multimorbidity engaged with digital symptom and well-being monitoring through a digital health platform over a period of approximately 12 months. Data analysis focused on user retention, frequency of monitoring, intervals in monitoring and patterns of daily engagement. Results: Our findings show that the overall engagement with the digital health platform was high, with more than 80% of participants using the technology devices for over 200 days. The submission frequency for symptom parameters (e.g. blood glucose (BG), blood pressure (BP), etc.) was between three and four times per week which was higher than that of self-report (2.24) and weight (2.84). Submissions of exercise (6.12) and sleep (5.67) were more frequent. The majority of interactions happened in the morning time. The most common time of submission for symptom parameters was 10 am, whereas 8 am was the most common time for weight measurements. Conclusions: The findings indicate the patterns of engagement of older adults with complex chronic diseases with digital home-based self-management systems.

Remote synchronous usability testing of public access defibrillators during social distancing in a pandemic.

Public access automated external defibrillators (AEDs) represent emergency medical devices that may be used by untrained lay-persons in a life-critical event. As such their usability must be confirmed through simulation testing. In 2020 the novel coronavirus caused a global pandemic. In order to reduce the spread of the virus, many restrictions such as social distancing and travel bans were enforced. Usability testing of AEDs is typically conducted in-person, but due to these restrictions, other usability solutions must be investigated. Two studies were conducted, each with 18 participants: (1) an in-person usability study of an AED conducted in an office space, and (2) a synchronous remote usability study of the same AED conducted using video conferencing software. Key metrics associated with AED use, such as time to turn on, time to place pads and time to deliver a shock, were assessed in both studies. There was no difference in time taken to turn the AED on in the in-person study compared to the remote study, but the time to place electrode pads and to deliver a shock were significantly lower in the in-person study than in the remote study. Overall, the results of this study indicate that remote user testing of public access defibrillators may be appropriate in formative usability studies for determining understanding of the user interface.

System Usability Scale Benchmarking for Digital Health Apps: Meta-analysis.

BACKGROUND: The System Usability Scale (SUS) is a widely used scale that has been used to quantify the usability of many software and hardware products. However, the SUS was not specifically designed to evaluate mobile apps, or in particular digital health apps (DHAs). OBJECTIVE: The aim of this study was to examine whether the widely used SUS distribution for benchmarking (mean 68, SD 12.5) can be used to reliably assess the usability of DHAs. METHODS: A search of the literature was performed using the ACM Digital Library, IEEE Xplore, CORE, PubMed, and Google Scholar databases to identify SUS scores related to the usability of DHAs for meta-analysis. This study included papers that published the SUS scores of the evaluated DHAs from 2011 to 2021 to get a 10-year representation. In total, 117 SUS scores for 114 DHAs were identified. R Studio and the R programming language were used to model the DHA SUS distribution, with a 1-sample, 2-tailed t test used to compare this distribution with the standard SUS distribution. RESULTS: The mean SUS score when all the collected apps were included was 76.64 (SD 15.12); however, this distribution exhibited asymmetrical skewness (-0.52) and was not normally distributed according to Shapiro-Wilk test (P=.002). The mean SUS score for "physical activity" apps was 83.28 (SD 12.39) and drove the skewness. Hence, the mean SUS score for all collected apps excluding "physical activity" apps was 68.05 (SD 14.05). A 1-sample, 2-tailed t test indicated that this health app SUS distribution was not statistically significantly different from the standard SUS distribution (P=.98). CONCLUSIONS: This study concludes that the SUS and the widely accepted benchmark of a mean SUS score of 68 (SD 12.5) are suitable for evaluating the usability of DHAs. We speculate as to why physical activity apps received higher SUS scores than expected. A template for reporting mean SUS scores to facilitate meta-analysis is proposed, together with future work that could be done to further examine the SUS benchmark scores for DHAs.

Exploring decision making 'noise' when interpreting the electrocardiogram in the context of cardiac cath lab activation.

In this commentary paper, we discuss the use of the electrocardiogram to help clinicians make diagnostic and patient referral decisions in acute care settings. The paper discusses the factors that are likely to contribute to the variability and noise in the clinical decision making process for catheterization lab activation. These factors include the variable competence in reading ECGs, the intra/inter rater reliability, the lack of standard ECG training, the various ECG machine and filter settings, cognitive biases (such as automation bias which is the tendency to agree with the computer-aided diagnosis or AI diagnosis), the order of the information being received, tiredness or decision fatigue as well as ECG artefacts such as the signal noise or lead misplacement. We also discuss potential research questions and tools that could be used to mitigate this 'noise' and improve the quality of ECG based decision making.

An insight into the current perceptions of UK radiographers on the future impact of AI on the profession: A cross-sectional survey.

INTRODUCTION: As a profession, radiographers have always been keen on adapting and integrating new technologies. The increasing integration of artificial intelligence (AI) into clinical practice in the last five years has been met with scepticism by some, who predict the demise of the profession, whilst others suggest a bright future with AI, full of opportunities and synergies. Post COVID-19 pandemic need for economic recovery and a backlog of medical imaging and reporting may accelerate the adoption of AI. It is therefore timely to appreciate practitioners' perceptions of AI used in clinical practice and their perception of the short-term impact on the profession. AIM: This study aims to explore the perceptions of AI in the UK radiography workforce and to investigate its current AI applications and future technological expectations of radiographers. METHODS: An online survey (QualtricsⓇ) was created by a team of radiography AI experts. The survey was disseminated via social media and professional networks in the UK. Demographic information and perceptions of the impact of AI on several aspects of the radiography profession were gathered, including the current use of AI in practice, future expectations and the perceived impact of AI on the profession. RESULTS: 411 responses were collected (80% diagnostic radiographers (DR); 20% therapeutic radiographers (TR)). Awareness of AI used in clinical practice is low, with DR respondents suggesting AI will have the most value/potential in cross sectional imaging and image reporting. TR responses linked AI as having most value in treatment planning, contouring, and image acquisition/matching. Respondents felt that AI will impact radiographers' daily work (DR, 79.6%; TR, 88.9%) by standardising some aspects of patient care and technical factors of radiography practice. A mixed response about impact on careers was reported. CONCLUSIONS: Respondents were unsure about the ways in which AI is currently used in practice and how AI will impact on careers in the future. It was felt that AI integration will lead to increased job opportunities to contribute to decision making as an end user. Job security was not identified as a cause for concern.

WaSP-ECG: A Wave Segmentation Pretraining Toolkit for Electrocardiogram Analysis.

Introduction: Representation learning allows artificial intelligence (AI) models to learn useful features from large, unlabelled datasets. This can reduce the need for labelled data across a range of downstream tasks. It was hypothesised that wave segmentation would be a useful form of electrocardiogram (ECG) representation learning. In addition to reducing labelled data requirements, segmentation masks may provide a mechanism for explainable AI. This study details the development and evaluation of a Wave Segmentation Pretraining (WaSP) application. Materials and Methods: Pretraining: A non-AI-based ECG signal and image simulator was developed to generate ECGs and wave segmentation masks. U-Net models were trained to segment waves from synthetic ECGs. Dataset: The raw sample files from the PTB-XL dataset were downloaded. Each ECG was also plotted into an image. Fine-tuning and evaluation: A hold-out approach was used with a 60:20:20 training/validation/test set split. The encoder portions of the U-Net models were fine-tuned to classify PTB-XL ECGs for two tasks: sinus rhythm (SR) vs atrial fibrillation (AF), and myocardial infarction (MI) vs normal ECGs. The fine-tuning was repeated without pretraining. Results were compared. Explainable AI: an example pipeline combining AI-derived segmentation masks and a rule-based AF detector was developed and evaluated. Results: WaSP consistently improved model performance on downstream tasks for both ECG signals and images. The difference between non-pretrained models and models pretrained for wave segmentation was particularly marked for ECG image analysis. A selection of segmentation masks are shown. An AF detection algorithm comprising both AI and rule-based components performed less well than end-to-end AI models but its outputs are proposed to be highly explainable. An example output is shown. Conclusion: WaSP using synthetic data and labels allows AI models to learn useful features for downstream ECG analysis with real-world data. Segmentation masks provide an intermediate output that may facilitate confidence calibration in the context of end-to-end AI. It is possible to combine AI-derived segmentation masks and rule-based diagnostic classifiers for explainable ECG analysis.

Remote and wearable ECG devices with diagnostic abilities in adults: A state-of-the-science scoping review.

The electrocardiogram (ECG) records the electrical activity in the heart in real time, providing an important opportunity to detecting various cardiac pathologies. The 12-lead ECG currently serves as the "standard" ECG acquisition technique for diagnostic purposes for many cardiac pathologies other than arrhythmias. However, the technical aspects of acquiring a 12-lead ECG are not easy. and its usage currently is restricted to trained medical personnel, which limits the scope of its usefulness. Remote and wearable ECG devices have attempted to bridge this gap by enabling patients to take their own ECG using a simplified method at the expense of a reduced number of leads, usually a single-lead ECG. In this review, we summarize the studies that investigated the use of remote ECG devices and their clinical utility in diagnosing cardiac pathologies. Eligible studies discussed Food and Drug Administration-cleared, commercially available devices that were validated in an adult population. We summarize technical logistics of signal quality and device reliability, dimensional and functional features, and diagnostic value. Our synthesis shows that reduced-set ECG wearables have huge potential for long-term monitoring, particularly if paired with real-time notification techniques. Such capabilities make them primarily useful for abnormal rhythm detection, and there is sufficient evidence that a remote ECG device can be superior to the traditional 12-lead ECG in diagnosing specific arrhythmias such as atrial fibrillation. However, this review identifies important challenges faced by this technology and highlights the limited availability of clinical research examining their usefulness.