Neuromuscular electrical stimulation for the treatment of diabetic sensorimotor polyneuropathy: A prospective, cohort, proof-of-concept study.

OBJECTIVE: To assess a potential efficacy signal, safety and feasibility of neuromuscular electrical stimulation (NMES) therapy as an adjunct to standard care in patients with diabetic sensorimotor polyneuropathy (DSPN). METHODS: In this single-centre, prospective, cohort, proof-of-concept study, 25 patients with DSPN consented to at least one daily 30-minute NMES therapy session (Revitive® IX) for 10 weeks, with 20 patients completing the study. The primary outcome measure was nerve conductivity assessed using a nerve conduction study of the sural, superficial peroneal, common peroneal and tibial nerves at 10 weeks compared to baseline. Secondary outcomes included superficial femoral artery (SFA) haemodynamics during NMES therapy compared to rest and quality-of-life at 10 weeks compared to baseline. RESULTS: At 10 weeks, there were significant increases in sural sensory nerve action potential amplitude and conduction velocity (p < 0.001), superficial peroneal sensory nerve action potential amplitude (p = 0.001) and conduction velocity (p = 0.002), common peroneal nerve conduction velocity (p = 0.004) and tibial nerve compound muscle action potential amplitude (p = 0.002) compared to baseline. SFA volume flow and time-averaged mean velocity significantly increased (p ≤ 0.003) during NMES compared to rest. Patient-reported Michigan Neuropathy Screening Instrument scores significantly decreased (p = 0.028) at 10 weeks compared to baseline. Three unrelated adverse events occurred, and 15 participants adhered to treatment. CONCLUSIONS: NMES therapy as an adjunct to standard care for 10 weeks significantly increased lower limb nerve conductivity in patients with DSPN and may be beneficial in the treatment of DSPN.

Tensor decomposition and machine learning for the detection of arteriovenous fistula stenosis: An initial evaluation.

Duplex ultrasound (DUS) is the most widely used method for surveillance of arteriovenous fistulae (AVF) created for dialysis. However, DUS is poor at predicting AVF outcomes and there is a need for novel methods that can more accurately evaluate multidirectional AVF flow. In this study we aimed to evaluate the feasibility of detecting AVF stenosis using a novel method combining tensor-decomposition of B-mode ultrasound cine loops (videos) of blood flow and machine learning classification. Classification of stenosis was based on the DUS assessment of blood flow volume, vessel diameter size, flow velocity, and spectral waveform features. Real-time B-mode cine loops of the arterial inflow, anastomosis, and venous outflow of the AVFs were analysed. Tensor decompositions were computed from both the 'full-frame' (whole-image) videos and 'cropped' videos (to include areas of blood flow only). The resulting output were labelled for the presence of stenosis, as per the DUS findings, and used as a set of features for classification using a Long Short-Term Memory (LSTM) neural network. A total of 61 out of 66 available videos were used for analysis. The whole-image classifier failed to beat random guessing, achieving a mean area under the receiver operating characteristics (AUROC) value of 0.49 (CI 0.48 to 0.50). In contrast, the 'cropped' video classifier performed better with a mean AUROC of 0.82 (CI 0.66 to 0.96), showing promising predictive power despite the small size of the dataset. The combined application of tensor decomposition and machine learning are promising for the detection of AVF stenosis and warrant further investigation.

Evaluating the prognostic performance of bedside tests used for peripheral arterial disease diagnosis in the prediction of diabetic foot ulcer healing.

INTRODUCTION: Diabetic foot ulceration (DFU) is a common and challenging complication of diabetes. Risk stratification can guide further management. We aim to evaluate the prognostic performance of bedside tests used for peripheral arterial disease (PAD) diagnosis to predict DFU healing. RESEARCH DESIGN AND METHODS: Testing for Arterial Disease in Diabetes (TrEAD) was a prospective observational study comparing the diagnostic performance of commonly used tests for PAD diagnosis. We performed a secondary analysis assessing whether these could predict DFU healing. Follow-up was performed prospectively for 12 months. The primary outcome was sensitivity for predicting ulcer healing. Secondary endpoints were specificity, predictive values, and likelihood ratios for ulcer healing. RESULTS: 123 of TrEAD participants with DFU were included. In 12 months, 52.8% of ulcers healed. The best negative diagnostic likelihood ratio (NDLR) was observed for the podiatry ankle duplex scan (PAD-scan) monophasic or biphasic with adverse features(NDLR 0.35, 95% CI 0.14-0.90). The highest positive likelihood ratios were observed for toe brachial pressure index of ≤0.2 (positive diagnostic likelihood ratio (PDLR) 7.67, 95% CI 0.91-64.84) and transcutaneous pressure of oxygen of ≤20 mm Hg (PDLR 2.68, 95% CI 0.54-13.25). Cox proportional hazards modeling demonstrated significantly greater probabilities of healing with triphasic waveforms (HR=2.54, 95% CI 1.23-5.3, p=0.012) and biphasic waveforms with non-adverse features (HR=13.67, 95% CI 4.78-39.1, p<0.001) on PAD-scan. CONCLUSIONS: No single test performed well enough to be used in isolation as a prognostic marker for the prediction of DFU healing. TRIAL REGISTRATION NUMBER: NCT04058626.

Quantifying the burden of survivorship associated with infrarenal abdominal aortic aneurysms.

OBJECTIVES: Survivorship encompasses the physical, psychological, social, functional, and economic experience of a living with a chronic condition for both the patient and their caregiver. It is made up of nine distinct domains and remains understudied in nononcological pathologies, including infrarenal abdominal aortic aneurysmal disease (AAA). This review aims to quantify the extent to which existing AAA literature addresses the burden of survivorship. METHODS: The MEDLINE, EMBASE, and PsychINFO databases were searched from 1989 through September 2022. Randomized controlled trials, observational studies, and case series were included. Eligible studies had to detail outcomes related to survivorship in patients with AAA. Owing to the heterogeneity between studies and outcomes, no meta-analysis was conducted. Study quality was assessed with specific risk of bias tools. RESULTS: A total of 158 studies were included. Of these, only five (treatment complications, physical functioning, comorbidities, caregivers, and mental health) of the nine domains of survivorship have been studied previously. The available evidence is of variable quality; most studies display a moderate to high risk of bias, are of an observational study design, are based within a limited number of countries, and consist of an insufficient follow-up period. The most frequent complication after EVAR was endoleak. EVAR is associated with poorer long-term outcomes compared with open surgical repair in most studies retrieved. EVAR showed better outcomes in regard to physical functioning in the short term, but this advantage was lost in the long term. The most common comorbidity studied was obesity. No significant differences were found between open surgical repair and EVAR in terms of impact on caregivers. Depression is associated with various comorbidities and increased the risk of a nonhospital discharge. CONCLUSIONS: This review highlights the absence of robust evidence regarding survivorship in AAA. As a result, contemporary treatment guidelines rely on historic quality-of-life data that are narrow in scope and nonrepresentative of contemporary clinical practice. As such, there is an urgent need to reevaluate the aims and methodology associated with traditional quality-of-life research moving forward.

Cost-effectiveness of Diagnostic Tools to Establish the Presence of Peripheral Arterial Disease in People With Diabetes.

OBJECTIVE: To evaluate the cost-effectiveness of point-of-care duplex ultrasound (PAD-scan) and other bedside tests for the diagnosis of peripheral arterial disease (PAD) in people with diabetes. BACKGROUND: PAD is a risk factor for cardiovascular disease, diabetic foot ulceration (DFU), and amputation in diabetic patients. Diagnosis enables optimization of therapies to manage these risks. PAD-scan can be performed by frontline staff and has been shown to be the most accurate bedside test. However, its cost-effectiveness has not been investigated. METHODS: A Markov model was constructed to estimate the health outcomes and costs over 5 years of different testing strategies applied to a cohort of diabetic patients. Bedside tests investigated were PAD-scan, ankle-brachial pressure index, toe-brachial pressure index, audible and visual Doppler, transcutaneous pressure of oxygen, and pulse palpation. Health outcomes were incidence of new DFU, major cardiovascular events, amputation, death, and DFU healing rates. Sensitivity analyses were performed. RESULTS: PAD-scan was the most cost-effective bedside test with an incremental cost-effectiveness ratio of £11,391/quality-adjusted life years. PADscan had the highest probability (78.7%) of having the greatest net benefit at a willingness to pay threshold of £20,000 per quality-adjusted life years. It reduced the number of amputations by 24% and the number of cardiovascular deaths by 10% over 5 years, compared to toe-brachial pressure index (next best alternative). PAD-scans superiority in incremental cost-effectiveness ratio occurred at a PAD prevalence threshold of 0.24. DISCUSSION: PAD-scan is a cost-effective test for the detection of PAD in patients with diabetes.

Study protocol for a multicentre comparative diagnostic accuracy study of tools to establish the presence and severity of peripheral arterial disease in people with diabetes mellitus: the DM PAD study.

INTRODUCTION: Peripheral arterial disease (PAD) is a key risk factor for cardiovascular disease, foot ulceration and lower limb amputation in people with diabetes. Early diagnosis of PAD can enable optimisation of therapies to manage these risks. Its diagnosis is fundamental, though challenging in the context of diabetes. Although a variety of diagnostic bedside tests are available, there is no agreement as to which is the most accurate in routine clinical practice.The aim of this study is to determine the diagnostic performance of a variety of tests (audible waveform assessment, visual waveform assessment, ankle brachial pressure index (ABPI), exercise ABPI and toe brachial pressure index (TBPI)) for the diagnosis of PAD in people with diabetes as determined by a reference test (CT angiography (CTA) or magnetic resonance angiography (MRA)). In selected centres, we also aim to evaluate the performance of a new point-of-care duplex ultrasound scan (PAD-scan). METHODS AND ANALYSIS: A prospective multicentre diagnostic accuracy study (ClinicalTrials.gov Identifier NCT05009602). We aim to recruit 730 people with diabetes from 18 centres across the UK, covering primary and secondary healthcare. Consenting participants will undergo the tests under investigation. Reference tests (CTA or MRA) will be performed within 6 weeks of the index tests. Imaging will be reported by blinded consultant radiologists at a core imaging lab, using a validated scoring system, which will also be used to categorise PAD severity. The presence of one or more arterial lesions of ≥50% stenosis, or tandem lesions with a combined value of ≥50%, will be used as the threshold for the diagnosis of PAD. The primary outcome measure of diagnostic performance will be test sensitivity. ETHICS AND DISSEMINATION: The study has received approval from the National Research Ethics Service (NRES) (REC reference 21/PR/1221). Results will be disseminated through research presentations and papers. TRIAL REGISTRATION NUMBER: NCT05009602.

A Pilot Study of Heart Rate Variability Synchrony as a Marker of Intraoperative Surgical Teamwork and Its Correlation to the Length of Procedure.

Objective: Quality of intraoperative teamwork may have a direct impact on patient outcomes. Heart rate variability (HRV) synchrony may be useful for objective assessment of team cohesion and good teamwork. The primary aim of this study was to investigate the feasibility of using HRV synchrony in surgical teams. Secondary aims were to investigate the association of HRV synchrony with length of procedure (LOP), complications, number of intraoperative glitches and length of stay (LOS). We also investigated the correlation between HRV synchrony and team familiarity, pre- and intraoperative stress levels (STAI questionnaire), NOTECHS score and experience of team members. Methods: Ear, nose and throat (ENT) and vascular surgeons (consultant and registrar team members) were recruited into the study. Baseline demographics including level of team members' experience were gathered before each procedure. For each procedure, continuous electrocardiogram (ECG) recording was performed and questionnaires regarding pre- and intraoperative stress levels and non-technical skills (NOTECHS) scores were collected for each team member. An independent observer documented the time of each intraoperative glitch. Statistical analysis was conducted using stepwise multiple linear regression. Results: Four HRV synchrony metrics which may be markers of efficient surgical collaboration were identified from the data: 1. number of HRV synchronies per hour of procedure, 2. number of HRV synchrony trends per hour of procedure, 3. length of HRV synchrony trends per hour of procedure, 4. area under the HRV synchrony trend curve per hour of procedure. LOP was inversely correlated with number of HRV synchrony trends per hour of procedure (p < 0.0001), area under HRV synchrony trend curve per hour of procedure (p = 0.001), length of HRV synchrony trends per hour of procedure (p = 0.002) and number of HRV synchronies per hour of procedure (p < 0.0001). LOP was positively correlated with: FS (p = 0.043; R = 0.358) and intraoperative STAI score of the whole team (p = 0.007; R = 0.493). Conclusions: HRV synchrony metrics within operating teams may be used as an objective marker to quantify surgical teamwork. We have shown that LOP is shorter when the intraoperative surgical teams' HRV is more synchronised.

Prevention and Management Strategies for Diabetic Neuropathy.

Diabetic neuropathy (DN) is a common complication of diabetes that is becoming an increasing concern as the prevalence of diabetes rapidly rises. There are several types of DN, but the most prevalent and studied type is distal symmetrical polyneuropathy, which is the focus of this review and is simply referred to as DN. It can lead to a wide range of sensorimotor and psychosocial symptoms and is a major risk factor for diabetic foot ulceration and Charcot neuropathic osteoarthropathy, which are associated with high rates of lower limb amputation and mortality. The prevention and management of DN are thus critical, and clinical guidelines recommend several strategies for these based on the best available evidence. This article aims to provide a narrative review of DN prevention and management strategies by discussing these guidelines and the evidence that supports them. First, the epidemiology and diverse clinical manifestations of DN are summarized. Then, prevention strategies such as glycemic control, lifestyle modifications and footcare are discussed, as well as the importance of early diagnosis. Finally, neuropathic pain management strategies and promising novel therapies under investigation such as neuromodulation devices and nutraceuticals are reviewed.

The diagnostic and triage accuracy of digital and online symptom checker tools: a systematic review.

Digital and online symptom checkers are an increasingly adopted class of health technologies that enable patients to input their symptoms and biodata to produce a set of likely diagnoses and associated triage advice. However, concerns regarding the accuracy and safety of these symptom checkers have been raised. This systematic review evaluates the accuracy of symptom checkers in providing diagnoses and appropriate triage advice. MEDLINE and Web of Science were searched for studies that used either real or simulated patients to evaluate online or digital symptom checkers. The primary outcomes were the diagnostic and triage accuracy of the symptom checkers. The QUADAS-2 tool was used to assess study quality. Of the 177 studies retrieved, 10 studies met the inclusion criteria. Researchers evaluated the accuracy of symptom checkers using a variety of medical conditions, including ophthalmological conditions, inflammatory arthritides and HIV. A total of 50% of the studies recruited real patients, while the remainder used simulated cases. The diagnostic accuracy of the primary diagnosis was low across included studies (range: 19-37.9%) and varied between individual symptom checkers, despite consistent symptom data input. Triage accuracy (range: 48.8-90.1%) was typically higher than diagnostic accuracy. Overall, the diagnostic and triage accuracy of symptom checkers are variable and of low accuracy. Given the increasing push towards adopting this class of technologies across numerous health systems, this study demonstrates that reliance upon symptom checkers could pose significant patient safety hazards. Large-scale primary studies, based upon real-world data, are warranted to demonstrate the adequate performance of these technologies in a manner that is non-inferior to current best practices. Moreover, an urgent assessment of how these systems are regulated and implemented is required.

Pathogenesis of Distal Symmetrical Polyneuropathy in Diabetes.

Distal symmetrical polyneuropathy (DSPN) is a serious complication of diabetes associated with significant disability and mortality. Although more than 50% of people with diabetes develop DSPN, its pathogenesis is still relatively unknown. This lack of understanding has limited the development of novel disease-modifying therapies and left the reasons for failed therapies uncertain, which is critical given that current management strategies often fail to achieve long-term efficacy. In this article, the pathogenesis of DSPN is reviewed, covering pathogenic changes in the peripheral nervous system, microvasculature and central nervous system (CNS). Furthermore, the successes and limitations of current therapies are discussed, and potential therapeutic targets are proposed. Recent findings on its pathogenesis have called the definition of DSPN into question and transformed the disease model, paving the way for new research prospects.

Machine learning-based classification of arterial spectral waveforms for the diagnosis of peripheral artery disease in the context of diabetes: A proof-of-concept study.

BACKGROUND: Point-of-care duplex ultrasound has emerged as a promising test for the diagnosis of peripheral artery disease (PAD). However, the interpretation of morphologically diverse Doppler arterial spectral waveforms is challenging and associated with wide inter-observer variation. The aim of this study is to evaluate the utility of machine learning techniques for the diagnosis of PAD from Doppler arterial spectral waveforms sampled at the level of the ankle in patients with diabetes. METHODS: In two centres, 590 Doppler arterial spectral waveform images (PAD 369, no-PAD 221) from 305 patients were prospectively collected. Doppler arterial spectral waveform signals were reconstructed. Blinded full lower-limb reference duplex ultrasound results were used to label waveform according to PAD status (i.e., PAD, no-PAD). Statistical metrics and multiscale wavelet variance were extracted as discriminatory features. A long short-term memory (LSTM) network was used for the classification of raw signals, and logistic regression (LR) and support vector machines (SVM) were used for classification of extracted features. Signals and feature vectors were randomly divided into training (80%) and testing (20%) sets. RESULTS: The highest overall accuracy was achieved using a logistic regression model with a combination of statistical and multiscale wavelet variance features, with 88% accuracy, 92% sensitivity, and 82% specificity. The area under the receiver operating characteristics curve (AUC) was 0.93. CONCLUSION: We have constructed a machine learning algorithm with high discriminatory ability for the diagnosis of PAD using Doppler arterial spectral waveforms sampled at the ankle vessels.

Peripheral blood mononuclear cell gene expression and cytokine profiling in patients with intermittent claudication who exhibit exercise induced acute renal injury.

BACKGROUND: Intermittent claudication (IC) is a common manifestation of peripheral arterial disease. Some patients with IC experience a rise in Urinary N-acetyl-ß-D-Glucosaminidase (NAG)/ Creatinine (Cr) ratio, a marker of renal injury, following exercise. In this study, we aim to investigate whether peripheral blood mononuclear cells (PBMC) from patients with IC who exhibit a rise in urinary NAG/ Cr ratio following exercise exhibit differential IL-10/ IL-12 ratio and gene expression compared to those who do not have a rise in NAG/ Cr ratio. METHODS: We conducted a single center observational cohort study of patients diagnosed with IC. Blood and urine samples were collected at rest and following a standardised treadmill exercise protocol. For comparative analysis patients were separated into those with any rise in NAG/Cr ratio (Group 1) and those with no rise in NAG/Cr ratio (Group 2) post exercise. Isolated PBMC from pre- and post-exercise blood samples were analysed using flow cytometry. PBMC were also cultured for 20 hours to perform further analysis of IL-10 and IL-12 cytokine levels. RNA-sequencing analysis was performed to identify differentially expressed genes between the groups. RESULTS: 20 patients were recruited (Group 1, n = 8; Group 2, n = 12). We observed a significantly higher IL-10/IL-12 ratio in cell supernatant from participants in Group 1, as compared to Group 2, on exercise at 20 hours incubation; 47.24 (IQR 9.70-65.83) vs 6.13 (4.88-12.24), p = 0.04. 328 genes were significantly differentially expressed between Group 1 and 2. The modulated genes had signatures encompassing hypoxia, metabolic adaptation to starvation, inflammatory activation, renal protection, and oxidative stress. DISCUSSION: Our results suggest that some patients with IC have an altered immune status making them 'vulnerable' to systemic inflammation and renal injury following exercise. We have identified a panel of genes which are differentially expressed in this group of patients.

Quality assessment standards in artificial intelligence diagnostic accuracy systematic reviews: a meta-research study.

Artificial intelligence (AI) centred diagnostic systems are increasingly recognised as robust solutions in healthcare delivery pathways. In turn, there has been a concurrent rise in secondary research studies regarding these technologies in order to influence key clinical and policymaking decisions. It is therefore essential that these studies accurately appraise methodological quality and risk of bias within shortlisted trials and reports. In order to assess whether this critical step is performed, we undertook a meta-research study evaluating adherence to the Quality Assessment of Diagnostic Accuracy Studies 2 (QUADAS-2) tool within AI diagnostic accuracy systematic reviews. A literature search was conducted on all studies published from 2000 to December 2020. Of 50 included reviews, 36 performed the quality assessment, of which 27 utilised the QUADAS-2 tool. Bias was reported across all four domains of QUADAS-2. Two hundred forty-three of 423 studies (57.5%) across all systematic reviews utilising QUADAS-2 reported a high or unclear risk of bias in the patient selection domain, 110 (26%) reported a high or unclear risk of bias in the index test domain, 121 (28.6%) in the reference standard domain and 157 (37.1%) in the flow and timing domain. This study demonstrates the incomplete uptake of quality assessment tools in reviews of AI-based diagnostic accuracy studies and highlights inconsistent reporting across all domains of quality assessment. Poor standards of reporting act as barriers to clinical implementation. The creation of an AI-specific extension for quality assessment tools of diagnostic accuracy AI studies may facilitate the safe translation of AI tools into clinical practice.

Diagnostic Accuracy of Point-of-care Tests Used to Detect Arterial Disease in Diabetes: TEsting for Arterial Disease in Diabetes (TrEAD) Study.

OBJECTIVE: We compared the diagnostic performance of a novel point-of-care duplex ultrasound test (podiatry ankle duplex scan; PAD-scan) against commonly used bedside tests for the detection of PAD in diabetes. BACKGROUND: PAD is a major risk factor for diabetic foot ulceration and amputation. Its diagnosis is fundamental though challenging. Although a variety of bedside tests are available, there is no agreement as to which is the most useful. PAD-scan may be advantageous over current tests as it allows for vessel visualization and more accurate arterial waveform assessment. However, its accuracy has not been previously evaluated. METHODS: From March to October 2019, we recruited 305 patients from 2 diabetic foot clinics. The diagnostic performance of ankle-brachial pressure index, toe-brachial pressure index, transcutaneous pressure of oxygen, pulse palpation, and ankle waveform assessment using PAD-scan and Doppler devices (audible and visual waveform assessment) were assessed. The reference test was a full lower limb duplex ultrasound. RESULTS: Based on the reference test, 202 (66.2%) patients had evidence of PAD. PAD-scan had a significantly higher sensitivity [95%, confidence interval (CI) 90%-97%) as compared to all other tests. Particularly low sensitivities were seen with pulse palpation (43%, CI 36%-50%) and transcutaneous pressure of oxygen (31%, CI 24%-38%). PAD-scan had a lower specificity (77%, CI 67%-84%) compared to toe-brachial pressure index (86%, CI 78%-93%; P < 0.001), but not statistically different when compared to all other tests. CONCLUSIONS: PAD-scan has superior diagnostic utility and is a valid first line investigation.

Factors associated with infrainguinal bypass graft patency at 1-year; a retrospective analysis of a single centre experience.

INTRODUCTION: The aim of this study was to identify factors associated with primary graft patency 1 year following open lower limb revascularisation (LLR) at a tertiary referral vascular service. METHODS: A retrospective analysis of patients undergoing infra-inguinal bypass surgery between January 2016 and May 2017 at a tertiary vascular centre (St Mary's Hospital, London) was performed. Data regarding patient demographics, comorbidities, type of operation and post-operative anti-thrombotic strategy were collected. Quality of run-off score was assessed from pre-operative imaging. RESULTS: Seventy-seven cases were included in the analysis. Overall, the primary patency rate at 1-year was 63.6% (n = 49/77) and the secondary patency rate was 67.5% (n = 52/77). Independent variables with statistically significant inferior patency rates at 1-year were (1) bypasses with below knee targets (p = 0.0096), (2) chronic limb threatening ischaemia indication (p = 0.038), (3) previous ipsilateral revascularisation (p < 0.001) and (4) absence of hypertension history (p = 0.041). There was also a trend towards significance for American Society of Anesthesiologists (ASA) grade (p = 0.06). Independent variables with log-rank test p values of <0.1 were included in a Cox proportional hazards model. The only variable with a statistically significant impact on primary patency rates was previous open or endovascular ipsilateral revascularisation (HR 2.44 (1.04-5.7), p = 0.04). CONCLUSION: At 1-year follow-up, previous ipsilateral revascularisation was the most significant factor in affecting patency rates. Patients in this subgroup should therefore be deemed high-risk, which should be reflected in the informed consent and peri-operative management.

Harnessing Machine Learning to Personalize Web-Based Health Care Content.

Web-based health care content has emerged as a primary source for patients to access health information without direct guidance from health care providers. The benefit of this approach is dependent on the ability of patients to access engaging high-quality information, but significant variability in the quality of web-based information often forces patients to navigate large quantities of inaccurate, incomplete, irrelevant, or inaccessible content. Personalization positions the patient at the center of health care models by considering their needs, preferences, goals, and values. However, the traditional methods used thus far in health care to determine the factors of high-quality content for a particular user are insufficient. Machine learning (ML) uses algorithms to process and uncover patterns within large volumes of data to develop predictive models that automatically improve over time. The health care sector has lagged behind other industries in implementing ML to analyze user and content features, which can automate personalized content recommendations on a mass scale. With the advent of big data in health care, which builds comprehensive patient profiles drawn from several disparate sources, ML can be used to integrate structured and unstructured data from users and content to deliver content that is predicted to be effective and engaging for patients. This enables patients to engage in their health and support education, self-management, and positive behavior change as well as to enhance clinical outcomes.

Factors Affecting Engagement in Web-Based Health Care Patient Information: Narrative Review of the Literature.

BACKGROUND: Web-based content is rapidly becoming the primary source of health care information. There is a pressing need for web-based health care content to not only be accurate but also be engaging. Improved engagement of people with web-based health care content has the potential to inform as well as influence behavioral change to enable people to make better health care choices. The factors associated with better engagement with web-based health care content have previously not been considered. OBJECTIVE: The aims of this study are to identify the factors that affect engagement with web-based health care content and develop a framework to be considered when creating such content. METHODS: A comprehensive search of the PubMed and MEDLINE database was performed from January 1, 1946, to January 5, 2020. The reference lists of all included studies were also searched. The Medical Subject Headings database was used to derive the following keywords: "patient information," "online," "internet," "web," and "content." All studies in English pertaining to the factors affecting engagement in web-based health care patient information were included. No restrictions were set on the study type. Analysis of the themes arising from the results was performed using inductive content analysis. RESULTS: The search yielded 814 articles, of which 56 (6.9%) met our inclusion criteria. The studies ranged from observational and noncontrolled studies to quasi-experimental studies. Overall, there was significant heterogeneity in the types of interventions and outcome assessments, which made quantitative assessment difficult. Consensus among all authors of this study resulted in six categories that formed the basis of a framework to assess the factors affecting engagement in web-based health care content: easy to understand, support, adaptability, accessibility, visuals and content, and credibility and completeness. CONCLUSIONS: There is a paucity of high-quality data relating to the factors that improve the quality of engagement with web-based health care content. Our framework summarizes the reported studies, which may be useful to health care content creators. An evaluation of the utility of web-based content to engage users is of significant importance and may be accessible through tools such as the Net Promoter score. Web 3.0 technology and development of the field of psychographics for health care offer further potential for development. Future work may also involve improvement of the framework through a co-design process.

Developing a reporting guideline for artificial intelligence-centred diagnostic test accuracy studies: the STARD-AI protocol.

INTRODUCTION: Standards for Reporting of Diagnostic Accuracy Study (STARD) was developed to improve the completeness and transparency of reporting in studies investigating diagnostic test accuracy. However, its current form, STARD 2015 does not address the issues and challenges raised by artificial intelligence (AI)-centred interventions. As such, we propose an AI-specific version of the STARD checklist (STARD-AI), which focuses on the reporting of AI diagnostic test accuracy studies. This paper describes the methods that will be used to develop STARD-AI. METHODS AND ANALYSIS: The development of the STARD-AI checklist can be distilled into six stages. (1) A project organisation phase has been undertaken, during which a Project Team and a Steering Committee were established; (2) An item generation process has been completed following a literature review, a patient and public involvement and engagement exercise and an online scoping survey of international experts; (3) A three-round modified Delphi consensus methodology is underway, which will culminate in a teleconference consensus meeting of experts; (4) Thereafter, the Project Team will draft the initial STARD-AI checklist and the accompanying documents; (5) A piloting phase among expert users will be undertaken to identify items which are either unclear or missing. This process, consisting of surveys and semistructured interviews, will contribute towards the explanation and elaboration document and (6) On finalisation of the manuscripts, the group's efforts turn towards an organised dissemination and implementation strategy to maximise end-user adoption. ETHICS AND DISSEMINATION: Ethical approval has been granted by the Joint Research Compliance Office at Imperial College London (reference number: 19IC5679). A dissemination strategy will be aimed towards five groups of stakeholders: (1) academia, (2) policy, (3) guidelines and regulation, (4) industry and (5) public and non-specific stakeholders. We anticipate that dissemination will take place in Q3 of 2021.