Development and Integration of Machine Learning Algorithm to Identify Peripheral Arterial Disease: Multistakeholder Qualitative Study.

BACKGROUND: Machine learning (ML)-driven clinical decision support (CDS) continues to draw wide interest and investment as a means of improving care quality and value, despite mixed real-world implementation outcomes. OBJECTIVE: This study aimed to explore the factors that influence the integration of a peripheral arterial disease (PAD) identification algorithm to implement timely guideline-based care. METHODS: A total of 12 semistructured interviews were conducted with individuals from 3 stakeholder groups during the first 4 weeks of integration of an ML-driven CDS. The stakeholder groups included technical, administrative, and clinical members of the team interacting with the ML-driven CDS. The ML-driven CDS identified patients with a high probability of having PAD, and these patients were then reviewed by an interdisciplinary team that developed a recommended action plan and sent recommendations to the patient's primary care provider. Pseudonymized transcripts were coded, and thematic analysis was conducted by a multidisciplinary research team. RESULTS: Three themes were identified: positive factors translating in silico performance to real-world efficacy, organizational factors and data structure factors affecting clinical impact, and potential challenges to advancing equity. Our study found that the factors that led to successful translation of in silico algorithm performance to real-world impact were largely nontechnical, given adequate efficacy in retrospective validation, including strong clinical leadership, trustworthy workflows, early consideration of end-user needs, and ensuring that the CDS addresses an actionable problem. Negative factors of integration included failure to incorporate the on-the-ground context, the lack of feedback loops, and data silos limiting the ML-driven CDS. The success criteria for each stakeholder group were also characterized to better understand how teams work together to integrate ML-driven CDS and to understand the varying needs across stakeholder groups. CONCLUSIONS: Longitudinal and multidisciplinary stakeholder engagement in the development and integration of ML-driven CDS underpins its effective translation into real-world care. Although previous studies have focused on the technical elements of ML-driven CDS, our study demonstrates the importance of including administrative and operational leaders as well as an early consideration of clinicians' needs. Seeing how different stakeholder groups have this more holistic perspective also permits more effective detection of context-driven health care inequities, which are uncovered or exacerbated via ML-driven CDS integration through structural and organizational challenges. Many of the solutions to these inequities lie outside the scope of ML and require coordinated systematic solutions for mitigation to help reduce disparities in the care of patients with PAD.

Stakeholder Perspectives on Clinical Decision Support Tools to Inform Clinical Artificial Intelligence Implementation: Protocol for a Framework Synthesis for Qualitative Evidence.

BACKGROUND: Quantitative systematic reviews have identified clinical artificial intelligence (AI)-enabled tools with adequate performance for real-world implementation. To our knowledge, no published report or protocol synthesizes the full breadth of stakeholder perspectives. The absence of such a rigorous foundation perpetuates the "AI chasm," which continues to delay patient benefit. OBJECTIVE: The aim of this research is to synthesize stakeholder perspectives of computerized clinical decision support tools in any health care setting. Synthesized findings will inform future research and the implementation of AI into health care services. METHODS: The search strategy will use MEDLINE (Ovid), Scopus, CINAHL (EBSCO), ACM Digital Library, and Science Citation Index (Web of Science). Following deduplication, title, abstract, and full text screening will be performed by 2 independent reviewers with a third topic expert arbitrating. The quality of included studies will be appraised to support interpretation. Best-fit framework synthesis will be performed, with line-by-line coding completed by 2 independent reviewers. Where appropriate, these findings will be assigned to 1 of 22 a priori themes defined by the Nonadoption, Abandonment, Scale-up, Spread, and Sustainability framework. New domains will be inductively generated for outlying findings. The placement of findings within themes will be reviewed iteratively by a study advisory group including patient and lay representatives. RESULTS: Study registration was obtained from PROSPERO (CRD42021256005) in May 2021. Final searches were executed in April, and screening is ongoing at the time of writing. Full text data analysis is due to be completed in October 2021. We anticipate that the study will be submitted for open-access publication in late 2021. CONCLUSIONS: This paper describes the protocol for a qualitative evidence synthesis aiming to define barriers and facilitators to the implementation of computerized clinical decision support tools from all relevant stakeholders. The results of this study are intended to expedite the delivery of patient benefit from AI-enabled clinical tools. TRIAL REGISTRATION: PROSPERO CRD42021256005; https://tinyurl.com/r4x3thvp. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): DERR1-10.2196/33145.

Evaluation of a low-resource screening strategy for ophthalmic pathologies and associated neurological morbidity in an older Tanzanian HIV-positive population.

Globally, 43 million people are living with HIV, 90% in developing countries. Increasing life expectancy with combination antiretroviral therapy (cART) results in chronic complications, including HIV-associated neurocognitive disorders (HAND) and eye diseases. HAND screening is currently challenging. Our aim was to evaluate clinical utility of retinopathy as a screening measure of HAND in older cART-treated individuals in Tanzania and feasibility of smartphone-based retinal screening in this low-resource setting. A cross-sectional systematic sample aged ≥ 50-years attending routine HIV follow-up in Tanzania were comprehensively assessed for HAND by American Academy of Neurology criteria and received ophthalmic assessment including smartphone-based retinal imaging. HAND and ophthalmic assessments were independent and blinded. Diagnostic accuracy was evaluated by AUROC curves. Of 129 individuals assessed, 69.8% were visually impaired. Thirteen had retinopathy. HAND prevalence was 66.7%. Retinopathy was significantly associated with HAND but HIV-disease factors (CD4, viral load) were not. Diagnostic accuracy of retinopathy for HAND was poor (AUROC 0.545-0.617) but specificity and positive predictive value were high. We conclude that ocular pathology and HAND appear highly prevalent in this low-resource setting. Although retinal screening cannot be used alone identify HAND, prioritization of individuals with abnormal retinal screening is a potential strategy in low-resource settings.

An observational clinical study of the influence of phacoemulsification on choroidal neovascular membrane activity in age related macular degeneration.

BACKGROUND: Thousands of phacoemulsification surgeries are performed on eyes with age-related macular degeneration (AMD) complicated by choroidal neovascular membrane (CNV) in the United Kingdom each year. As populations age this number is expected to rise. Controversy over phacoemulsification's influence on CNV activity limits the information which clinicians and these patients use to decide on surgery. This observational study aims to resolve this controversy by reporting on intravitreal injection (IVI) frequency as a pragmatic marker of CNV activity in a large cohort. METHODS: A cohort of eyes with AMD complicated by CNV (n = 327) that underwent cataract surgery at a single tertiary centre from 2014 to 2019 were identified. These cases were matched by interval since CNV diagnosis at a specified 'time zero' within the follow-up of pseudophakic eyes with AMD (n = 327). Data concerning demographics, visual acuity (VA) and intravitreal injection frequency before and after 'time zero'/phacoemulsification were collected. RESULTS: Following 'time zero'/phacoemulsification' the mean reduction in annual IVI frequency was 0.6 injections/year (95% CI 0.4,0.9) and 0.4 injections/year (95% CI 0.1,0.7) in the comparison and phacoemulsification cohorts respectively. The mean VA gain 12 months after phacoemulsification in the intervention cohort was 11.3 (95% CI 9.2,13.4) early treatment of diabetic retinopathy study (ETDRS) letters, with 214 eyes (65.4%) having gained ≥5 ETDRS letters after surgery. CONCLUSIONS: Phacoemulsification has no clinically significant impact on the activity of pre-existent CNV secondary to AMD. Phacoemulsification should be offered to patients with AMD and cataract that limits vision, regardless of CNV activity.

Real-World Visual and Neovascularisation Outcomes from anti-VEGF in Central Retinal Vein Occlusion.

PURPOSE: Central retinal vein occlusion (CRVO) can be complicated by macular oedema, requiring intravitreal injection (IVI) of anti-vascular endothelial growth factor (VEGF). CRVO can cause neovascularisation, potentially causing persistent pain if not identified early. Whilst clinical trial data describe visual and anti-neovascular benefit from anti-VEGF there are limited real-world data. METHODS: A retrospective cohort study of a consecutive series of patients found from a review of the electronic medical record at a single UK centre. Visual acuity, macula status, number of IVIs and neovascular status were extracted at standardised timepoints. RESULTS: In total, 231 eyes from 231 patients were identified with 6-48 months of follow up. Twenty-four months after treatment initiation, 81 eyes (53.3%) had no remaining macula oedema and mean visual acuity gained was 8.9 (SD 19.0) Early Treatment of Diabetic Retinopathy Study (ETDRS) letters following a mean of 10.1 (3.9) IVIs. Of 222 eyes that had no initial neovascularisation, 11 went on to develop it, with iris involvement in 10 eyes. Median time from treatment initiation to neovascularisation was 17.2 (range 5.0-44.1) months, and the median time from latest IVI to neovascularisation was 9.6 (2.9-27.6) months after a median of 4 (3-10) IVIs. CONCLUSIONS: Visual acuity in CRVO complicated by macular oedema improves following anti-VEGF treatment but real-world gains are more modest than those from clinical trials. Neovascularisation following CRVO can be substantially delayed by anti-VEGF treatment and so if individuals who have received IVIs are to be effectively screened for neovascularisation long-term surveillance is necessary.

A non-randomised trial of video and written educational adjuncts in undergraduate ophthalmology.

BACKGROUND: Provision of relevant pre-learning materials has been shown to increase student engagement and improve outcomes in medical education. This non-randomised study attempts to quantify the educational gains, and relative efficacy of video and written pre-learning materials, in ophthalmology undergraduate teaching. METHODS: Ninety-eight final year medical students were contacted prior to their three-day ophthalmology placements at a British tertiary ophthalmology unit. All participants were sent welcome packs prior to arrival requesting they undertake 90 min of work focusing on a list of specified ophthalmic conditions. One cohort (N = 33) were sent written materials, another (N = 32) was provided with video materials and a third cohort (N = 33) were not sent any materials. On arrival participants completed a simple knowledge test, a questionnaire estimating the time they spent preparing for the placement and a self-reported knowledge score. The teaching on placement was the same for all cohorts. At the conclusion of each placement participants completed a challenging knowledge test, a clinical skills test and repeated self-reported knowledge scores. RESULTS: Eighty seven percent of students receiving specified materials claimed to complete pre-placement work compared to 70% of those receiving learning outcomes alone (p = 0.05). Students receiving learning materials scored higher in the post-placement tests of knowledge (p < 0.001), 74.8% (72.4-77.2%) vs 63.6% (95%CI 59.3-67.9%) and skills (p = 0.04), 86.9% (83.9-89.9%) vs 81.3% (77.2-85.4%). Students using video resources outperformed students using written materials in their visual acuity assessment test (p = 0.03), 90.4% (86.6-94.2%) vs 83.6% (80.1-87.1%) whilst those receiving written rather than video material performed better in the end of placement knowledge test (p = 0.03), 77.7% (74.3-81.1%) vs 72.0% (68.9-75.1%). CONCLUSION: This study showed that providing pre-placement learning materials improves undergraduates' commitment and achievement. Written materials better facilitate knowledge acquisition while video materials preferentially promote skill acquisition. This is a novel demonstration within ophthalmology and can help address the imbalance between the expectations placed on undergraduates and the resources committed to ensuring they are met.

10-year trends in English primary care glaucoma prescribing.

BACKGROUND: In 2018 NHS prescriptions in England cost £8.83 billion. Within ophthalmic prescribing, glaucoma is the most costly indication. The 2017 glaucoma NICE guideline shows there is little evidence for clinical preference of particular molecules within a therapeutic class, yet the cost of these products varies greatly. We aim to describe trends in glaucoma prescribing and its relation to recent NICE Guidance. METHODS: Prescription cost analyses for England from 2009 to 2018 were reviewed and data concerning items for the treatment of glaucoma were extracted. Costs and prescription frequencies were normalised for inflation and population. RESULTS: The 2018 cost of glaucoma prescribing was £114.2 million. This cost is 18.1% lower than in 2009 but the annual number of items prescribed per 10,000 people has increased from 1382 to 1668 (20.7%). This is despite an increased prescription of combination drops from 265 to 478 per 10,000 (80.4%). Preservative free item prescriptions rose from 1.7% of total spend in 2009, at £3.4 million in 2009, to 13.9%, in 2018, at £22.5 million. Generic items represented 11.7% of prescriptions in 2009 and 55.2% in 2018. Around half of glaucoma spending is accounted for by the use of preservative free or branded items in the place of the cheapest item in each therapeutic class. CONCLUSIONS: Glaucoma prescribing costs the NHS a great deal. There is a broad trend to generic prescribing as per recent NICE guidance, but significant further costs could be saved with no robustly evidenced clinical consequence.