Methods for the Clinical Validation of Digital Endpoints: Protocol for a Scoping Review Abstract.

BACKGROUND: Clinical trials often use digital technologies to collect data continuously outside the clinic and use the derived digital endpoints as trial endpoints. Digital endpoints are also being developed to support diagnosis, monitoring, or therapeutic interventions in clinical care. However, clinical validation stands as a significant challenge, as there are no specific guidelines orienting the validation of digital endpoints. OBJECTIVE: This paper presents the protocol for a scoping review that aims to map the existing methods for the clinical validation of digital endpoints. METHODS: The scoping review will comprise searches from the electronic literature databases MEDLINE (PubMed), Scopus (including conference proceedings), Embase, IEEE (Institute of Electrical and Electronics Engineers) Xplore, ACM (Association for Computing Machinery) Digital Library, CENTRAL (Cochrane Central Register of Controlled Trials), Web of Science Core Collection (including conference proceedings), and Joanna Briggs Institute Database of Systematic Reviews and Implementation Reports. We will also include various sources of gray literature with search terms related to digital endpoints. The methodology will adhere to the Joanna Briggs Institute Scoping Review and the Guidance for Conducting Systematic Scoping Reviews. RESULTS: A search for reviews on the existing evidence related to this topic was conducted and has shown that no such review was previously undertaken. This review will provide a systematic assessment of the literature on methods for the clinical validation of digital endpoints and highlight any potential need for harmonization or reporting of methods. The results will include the methods for the clinical validation of digital endpoints according to device, digital endpoint, and clinical application goal of digital endpoints. The study started in January 2023 and is expected to end by December 2023, with results to be published in a peer-reviewed journal. CONCLUSIONS: A scoping review of methodologies that validate digital endpoints is necessary. This review will be unique in its breadth since it will comprise digital endpoints collected from several devices and not focus on a specific disease area. The results of our work should help guide researchers in choosing validation methods, identify potential gaps in the literature, or inform the development of novel methods to optimize the clinical validation of digital endpoints. Resolving these gaps is the key to presenting evidence in a consistent way to regulators and other parties and obtaining regulatory acceptance of digital endpoints for patient benefit. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): PRR1-10.2196/47119.

A Technological-Based Platform for Risk Assessment, Detection, and Prevention of Falls Among Home-Dwelling Older Adults: Protocol for a Quasi-Experimental Study.

BACKGROUND: According to the United Nations, it is estimated that by 2050, the number of people aged 80 years and older will have increased by 3 times. Increased longevity is often accompanied by structural and functional changes that occur throughout an individual's lifespan. These changes are often aggravated by chronic comorbidities, adopted behaviors or lifestyles, and environmental exposure, among other factors. Some of the related outcomes are loss of muscle strength, decreased balance control, and mobility impairments, which are strongly associated with the occurrence of falls in the elderly. Despite the continued undervaluation of the importance of knowledge on fall prevention among the elderly population by primary care health professionals, several evidence-based (single or multifaceted) fall prevention programs such as the Otago Exercise Program (OEP) have demonstrated a significant reduction in the risk of falls and fall-related injuries in the elderly within community settings. Recent studies have strived to integrate technology into physical exercise programs, which is effective for adherence and overcoming barriers to exercise, as well as improving physical functioning. OBJECTIVE: This study aims to assess the impact of the OEP on the functionality of home-dwelling elderly using a common technological platform. Particularly, the impact on muscle strength, balance, mobility, risk of falling, the perception of fear of falling, and the perception of the elderly regarding the ease of use of technology are being examined in this study. METHODS: A quasi-experimental study (before and after; single group) will be conducted with male and female participants aged 65 years or older living at home in the district of Porto. Participants will be recruited through the network COLABORAR, with a minimum of 30 participants meeting the study inclusion and exclusion criteria. All participants will sign informed consent forms. The data collection instrument consists of sociodemographic and clinical variables (self-reported), functional evaluation variables, and environmental risk variables. The data collection tool integrates primary and secondary outcome variables. The primary outcome is gait (timed-up and go test; normal step). The secondary outcome variables are lower limb strength and muscle resistance (30-second chair stand test), balance (4-stage balance test), frequency of falls, functional capacity (Lawton and Brody - Portuguese version), fear of falling (Falls Efficacy Scale International - Portuguese version), usability of the technology (System Usability Scale - Portuguese version), and environmental risk variables (home fall prevention checklist for older adults). Technological solutions, such as the FallSensing Home application and Kallisto wearable device, will be used, which will allow the detection and prevention of falls. The intervention is characterized by conducting the OEP through a common technological platform 3 times a week for 8 weeks. Throughout these weeks, the participants will be followed up in person or by telephone contact by the rehabilitation nurse. Considering the COVID-19 outbreak, all guidelines from the National Health Service will be followed. The project was funded by InnoStars, in collaboration with the Local EIT Health Regional Innovation Scheme Hub of the University of Porto. RESULTS: This study was approved on October 9, 2020 by the Ethics Committee of Escola Superior de Enfermagem do Porto (ESEP). The recruitment process was meant to start in October, but due to the COVID-19 pandemic, it was suspended. We expect to restart the study by the beginning of the third quarter of 2021. CONCLUSIONS: The findings of this study protocol will contribute to the design and development of future robust studies for technological tests in a clinical context. TRIAL REGISTRATION: ISRCTN 15895163; https://www.isrctn.com/ISRCTN15895163. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): PRR1-10.2196/25781.

Screening for Diabetic Retinopathy Using an Automated Diagnostic System Based on Deep Learning: Diagnostic Accuracy Assessment.

PURPOSE: To evaluate the diagnostic accuracy of a diagnostic system software for the automated screening of diabetic retinopathy (DR) on digital colour fundus photographs, the 2019 Convolutional Neural Network (CNN) model with Inception-V3. METHODS: In this cross-sectional study, 295 fundus images were analysed by the CNN model and compared to a panel of ophthalmologists. Images were obtained from a dataset acquired within a screening programme. Diagnostic accuracy measures and respective 95% CI were calculated. RESULTS: The sensitivity and specificity of the CNN model in diagnosing referable DR was 81% (95% CI 66-90%) and 97% (95% CI 95-99%), respectively. Positive predictive value was 86% (95% CI 72-94%) and negative predictive value 96% (95% CI 93-98%). The positive likelihood ratio was 33 (95% CI 15-75) and the negative was 0.20 (95% CI 0.11-0.35). Its clinical impact is demonstrated by the change observed in the pre-test probability of referable DR (assuming a prevalence of 16%) to a post-test probability for a positive test result of 86% and for a negative test result of 4%. CONCLUSION: A CNN model negative test result safely excludes DR, and its use may significantly reduce the burden of ophthalmologists at reading centres.

Postablation-acquired short atrioventricular Mahaim-type fibers: observations on their clinical, electrocardiographic, and electrophysiologic profile.

BACKGROUND: The electrophysiologic characteristics of decrementally conducting accessory pathways (APs) are well described; however, little is known about decrementally conducting APs caused by the radiofrequency ablation of a rapidly conducting AP. OBJECTIVE: To report the clinical, electrocardiographic, and electrophysiologic characteristics of 6 patients who developed a decremental AP after an attempt at ablation. METHODS: We compared the clinical and electrophysiologic characteristics of 295 consecutive patients with the Wolff-Parkinson-White syndrome who underwent radiofrequency ablation of 311 manifest APs (group A) with those of 6 patients with the Wolff-Parkinson-White syndrome in whom a decrementally conducting AP was detected after an attempt at ablation. RESULTS: The AP ablation site in group B patients was at the coronary sinus ostium region in 3 patients, middle cardiac vein in 2 patients, and left posteroseptal region in 1 patient. Sixty-two bypass tracts in group A patients and all 6 in group B patients were ablated at these locations, while 249 bypass tracts in group A patients and none in group B patients were ablated elsewhere (P = .0001). Five of the 6 patients (83%) with acquired Mahaim physiology had an AP located in the venous system. The odds for developing an acquired decremental antegrade atrioventricular AP when it was located inside the venous system were 1 in 6. All group B decremental APs were sensitive to adenosine, but none in 85 group A patients (P <.0001). CONCLUSIONS: The risk for developing decremental conduction after the ablation of a rapidly conducting AP is greater for APs inside the coronary venous system. Acquired decremental antegrade atrioventricular APs are electrophysiologically similar to de novo ones. They are capable of being part of an arrhythmia circuit and, therefore, should be targeted for ablation.

Clinical, electrocardiographic, and electrophysiologic characteristics of patients with a fasciculoventricular pathway: the role of PRKAG2 mutation.

BACKGROUND: The ECG, clinical, and electrophysiologic profiles of patients with a fasciculoventricular pathway are well described. Fasciculoventricular pathways occurring in the setting of glycogen storage cardiomyopathy possess unique features. OBJECTIVE: The purpose of this study was to compare the clinical, ECG, and electrophysiologic characteristics of patients with a fasciculoventricular pathway, with or without glycogen storage cardiomyopathy. METHODS: Two groups of patients with a fasciculoventricular pathway were compared: group A consisted of 10 patients with the PRKAG2 mutation (Arg302gln), and group B consisted of 9 patients without the mutation. RESULTS: Thirty percent of group A patients had left ventricular hypertrophy, and none had an additional accessory pathway. Group B patients had no structural heart disease, and 33% had an additional accessory pathway. Group A patients had a slower resting heart rate (56 ± 7 vs 75 ± 10 bpm, P <0.0001), a wider QRS complex (0.15 ± 0.01 vs 0.11 ± 0.02 ms, P = .0004), and a longer HV interval (34 ± 1 vs 25 ± 3 ms, P = .0003). During long-term follow-up, 50% of group A patients developed complete AV block versus none in group B. Eighty percent of group A patients developed atrial flutter and/or atrial fibrillation. No Group B patient had any arrhythmia during follow-up after successful ablation of additional arrhythmia circuits. No sustained ventricular arrhythmia was induced in any patient from either group. CONCLUSION: Patients with a fasciculoventricular pathway associated with the PRKAG2 mutation have distinct clinical, ECG, and electrophysiologic profiles and should be correctly identified because of their ominous long-term prognosis. Patients without the mutation have an excellent arrhythmia-free prognosis after treatment of additional circuits.