The rhetoric surrounding clinical artificial intelligence (AI) often exaggerates its effect on real-world care. Limited understanding of the factors that influence its implementation can perpetuate ...this.
In this qualitative systematic review, we aimed to identify key stakeholders, consolidate their perspectives on clinical AI implementation, and characterize the evidence gaps that future qualitative research should target.
Ovid-MEDLINE, EBSCO-CINAHL, ACM Digital Library, Science Citation Index-Web of Science, and Scopus were searched for primary qualitative studies on individuals' perspectives on any application of clinical AI worldwide (January 2014-April 2021). The definition of clinical AI includes both rule-based and machine learning-enabled or non-rule-based decision support tools. The language of the reports was not an exclusion criterion. Two independent reviewers performed title, abstract, and full-text screening with a third arbiter of disagreement. Two reviewers assigned the Joanna Briggs Institute 10-point checklist for qualitative research scores for each study. A single reviewer extracted free-text data relevant to clinical AI implementation, noting the stakeholders contributing to each excerpt. The best-fit framework synthesis used the Nonadoption, Abandonment, Scale-up, Spread, and Sustainability (NASSS) framework. To validate the data and improve accessibility, coauthors representing each emergent stakeholder group codeveloped summaries of the factors most relevant to their respective groups.
The initial search yielded 4437 deduplicated articles, with 111 (2.5%) eligible for inclusion (median Joanna Briggs Institute 10-point checklist for qualitative research score, 8/10). Five distinct stakeholder groups emerged from the data: health care professionals (HCPs), patients, carers and other members of the public, developers, health care managers and leaders, and regulators or policy makers, contributing 1204 (70%), 196 (11.4%), 133 (7.7%), 129 (7.5%), and 59 (3.4%) of 1721 eligible excerpts, respectively. All stakeholder groups independently identified a breadth of implementation factors, with each producing data that were mapped between 17 and 24 of the 27 adapted Nonadoption, Abandonment, Scale-up, Spread, and Sustainability subdomains. Most of the factors that stakeholders found influential in the implementation of rule-based clinical AI also applied to non-rule-based clinical AI, with the exception of intellectual property, regulation, and sociocultural attitudes.
Clinical AI implementation is influenced by many interdependent factors, which are in turn influenced by at least 5 distinct stakeholder groups. This implies that effective research and practice of clinical AI implementation should consider multiple stakeholder perspectives. The current underrepresentation of perspectives from stakeholders other than HCPs in the literature may limit the anticipation and management of the factors that influence successful clinical AI implementation. Future research should not only widen the representation of tools and contexts in qualitative research but also specifically investigate the perspectives of all stakeholder HCPs and emerging aspects of non-rule-based clinical AI implementation.
PROSPERO (International Prospective Register of Systematic Reviews) CRD42021256005; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=256005.
RR2-10.2196/33145.
A growing number of artificial intelligence (AI)-based clinical decision support systems are showing promising performance in preclinical, in silico evaluation, but few have yet demonstrated real ...benefit to patient care. Early-stage clinical evaluation is important to assess an AI system's actual clinical performance at small scale, ensure its safety, evaluate the human factors surrounding its use and pave the way to further large-scale trials. However, the reporting of these early studies remains inadequate. The present statement provides a multi-stakeholder, consensus-based reporting guideline for the Developmental and Exploratory Clinical Investigations of DEcision support systems driven by Artificial Intelligence (DECIDE-AI). We conducted a two-round, modified Delphi process to collect and analyze expert opinion on the reporting of early clinical evaluation of AI systems. Experts were recruited from 20 pre-defined stakeholder categories. The final composition and wording of the guideline was determined at a virtual consensus meeting. The checklist and the Explanation & Elaboration (E&E) sections were refined based on feedback from a qualitative evaluation process. In total, 123 experts participated in the first round of Delphi, 138 in the second round, 16 in the consensus meeting and 16 in the qualitative evaluation. The DECIDE-AI reporting guideline comprises 17 AI-specific reporting items (made of 28 subitems) and ten generic reporting items, with an E&E paragraph provided for each. Through consultation and consensus with a range of stakeholders, we developed a guideline comprising key items that should be reported in early-stage clinical studies of AI-based decision support systems in healthcare. By providing an actionable checklist of minimal reporting items, the DECIDE-AI guideline will facilitate the appraisal of these studies and replicability of their findings.
The SPIRIT 2013 (The Standard Protocol Items: Recommendations for Interventional Trials) statement aims to improve the completeness of clinical trial protocol reporting, by providing evidence-based ...recommendations for the minimum set of items to be addressed. This guidance has been instrumental in promoting transparent evaluation of new interventions. More recently, there is a growing recognition that interventions involving artificial intelligence need to undergo rigorous, prospective evaluation to demonstrate their impact on health outcomes.The SPIRIT-AI extension is a new reporting guideline for clinical trials protocols evaluating interventions with an AI component. It was developed in parallel with its companion statement for trial reports: CONSORT-AI. Both guidelines were developed using a staged consensus process, involving a literature review and expert consultation to generate 26 candidate items, which were consulted on by an international multi-stakeholder group in a 2-stage Delphi survey (103 stakeholders), agreed on in a consensus meeting (31 stakeholders) and refined through a checklist pilot (34 participants).The SPIRIT-AI extension includes 15 new items, which were considered sufficiently important for clinical trial protocols of AI interventions. These new items should be routinely reported in addition to the core SPIRIT 2013 items. SPIRIT-AI recommends that investigators provide clear descriptions of the AI intervention, including instructions and skills required for use, the setting in which the AI intervention will be integrated, considerations around the handling of input and output data, the human-AI interaction and analysis of error cases.SPIRIT-AI will help promote transparency and completeness for clinical trial protocols for AI interventions. Its use will assist editors and peer-reviewers, as well as the general readership, to understand, interpret and critically appraise the design and risk of bias for a planned clinical trial.
To investigate the impact of diabetic macular ischemia (DMI) on visual acuity (VA), through the analysis of novel fluorescein angiography (FA) parameters.
Data were retrospectively collected over a ...6-month period. DMI severity was graded using Early Treatment Diabetic Retinopathy Study (ETDRS) protocols. Custom software was used to quantify areas of the foveal avascular zone (FAZ), and of capillary nonperfusion over the papillo-macular nerve fiber layer bundle, and temporal macula, and associations tested with VA.
A total of 488 patients with type 2 diabetes mellitus and FAs of sufficient quality to allow detailed quantitative analyses were included. ETDRS-DMI SEVerity was graded as: none, 39.7%; questionable, 18.4%; mild, 25.2%; moderate, 11.0%; and severe, 5.6%. Median FAZ areas were 0.19 mm(2) (interquartile range IQR, 0.13-0.25); 0.25 mm(2) (IQR, 0.18-0.32); 0.27 mm(2) (IQR, 0.19-0.38); 0.32 mm(2) (IQR, 0.25-0.54); and 0.78 mm(2) (IQR, 0.60-1.32), respectively, and were significantly different between all grades (P < 0.002), apart from "questionable" versus "mild" grades. Significant association of VA to FAZ area was observed only in the moderate (β = 0.406, SE = 0.101, P = 0.001) and severe (β = 0.299, SE = 0.108, P = 0.006) subgroups, but not in milder ETDRS-DMI grades. A strong association with VA was observed in cases with papillomacular ischemia (β = 1.123, SE = 0.355, P = 0.005), independent of FAZ size or the presence of macular edema.
Diabetic macular ischemia is associated with reduced VA in eyes with moderate to severe ETDRS-DMI grades of ischemia but preserved in milder grades. In addition, we describe the independent association of papillomacular nerve fiber bundle ischemia with reduced VA.
To describe an optical coherence tomography angiography (OCTA) system adapted for anterior segment imaging, compared with indocyanine green angiography (ICGA) in eyes with corneal vascularisation.
...Retrospective study of subjects with corneal vascularisation secondary to microbial keratitis who had OCTA scans performed using a commercially available split-spectrum amplitude-decorrelation algorithm angiography system (AngioVue; Optovue Inc., Fremont, California, USA) and ICGA images (Spectralis; Heidelberg Engineering, Heidelberg, Germany). The agreement between OCTA and ICGA techniques in terms of area of vascularisation measured, using Bland-Altman 95% limits of agreement (LOA).
We compared the area of corneal vascularisation in 64 scan images (eight eyes, four scans for each angiography technique). In our series, the overall mean area of vascularisation from the ICGA scans was 0.49±0.34 mm
and OCTA scans was 0.51±0.36 mm
. We obtained substantial repeatability in terms of image quality score (κ=0.80) for all OCTA scans. The agreement between OCTA and ICGA scans was good, although ICGA measured a smaller area compared with the OCTA with a mean difference of -0.03 mm
(95% CI -0.07 to 0.01). The LOA ranged from a lower limit of -0.27 (95% CI -0.34 to -0.19) to an upper limit of 0.20 (95% CI 0.13 to 0.28, p=0.127).
We found that rapid, non-contact OCTA adapted for the cornea was comparable with ICGA for measurement of the area of corneal vascularisation in this pilot clinical study. Further prospective studies are required to confirm if this relatively new imaging technique may be further developed to replace invasive angiography techniques for the anterior segment.
Birdshot chorioretinopathy (BCR) is a rare form of chronic, bilateral, posterior uveitis with a distinctive clinical phenotype, and a strong association with HLA-A29. It predominantly affects people ...in middle age. Given its rarity, patients often encounter delays in diagnosis leading to delays in adequate treatment, and thus risking significant visual loss. Recent advances have helped increase our understanding of the underlying autoimmune mechanisms involved in disease pathogenesis, and new diagnostic approaches such as multimodality imaging have improved our ability to both diagnose and monitor disease activity. Whilst traditional immunosuppressants may be effective in BCR, increased understanding of immune pathways is enabling development of newer treatment modalities, offering the potential for targeted modulation of immune mediators. In this review, we will discuss current understanding of BCR and explore recent developments in diagnosis, monitoring and treatment of this disease. Synonyms for BCR: Birdshot chorioretinopathy, Birdshot retinochoroiditis, Birdshot retino-choroidopathy, Vitiliginous choroiditis. Orphanet number: ORPHA179 OMIM: 605808.
To discuss foveal development in the context of detailed retinal vasculature imaging in foveal hypoplasia using optical coherence tomography angiography.
In this case series, the optical coherence ...tomography angiography results of four patients with idiopathic foveal hypoplasia and two patients with foveal hypoplasia secondary to oculocutaneous albinism are presented.
Cases with intact visual acuity demonstrated lower grades of foveal hypoplasia on optical coherence tomography, while those with poor vision demonstrated high grades of foveal hypoplasia. The superficial retinal capillary plexus was intact in the foveal area in all cases, with no demonstrable foveal avascular zone. The deep retinal capillary plexus was absent to variable degrees in most cases, but was most persistent in those cases with reduced vision.
The superficial retinal capillary plexus is present in cases with foveal hypoplasia, while the deep retinal capillary plexus is absent to varying degrees. Our findings support the hypothesis that an intact foveal avascular zone of the deep capillary plexus allows for outer retinal photoreceptor specialisation to occur unimpeded, resulting in preserved visual acuity, while this process may be inhibited by an absent deep capillary foveal avascular zone with resultant poor vision.
Quantitative volumetric measures of retinal disease in optical coherence tomography (OCT) scans are infeasible to perform owing to the time required for manual grading. Expert-level deep learning ...systems for automatic OCT segmentation have recently been developed. However, the potential clinical applicability of these systems is largely unknown.
To evaluate a deep learning model for whole-volume segmentation of 4 clinically important pathological features and assess clinical applicability.
This diagnostic study used OCT data from 173 patients with a total of 15 558 B-scans, treated at Moorfields Eye Hospital. The data set included 2 common OCT devices and 2 macular conditions: wet age-related macular degeneration (107 scans) and diabetic macular edema (66 scans), covering the full range of severity, and from 3 points during treatment. Two expert graders performed pixel-level segmentations of intraretinal fluid, subretinal fluid, subretinal hyperreflective material, and pigment epithelial detachment, including all B-scans in each OCT volume, taking as long as 50 hours per scan. Quantitative evaluation of whole-volume model segmentations was performed. Qualitative evaluation of clinical applicability by 3 retinal experts was also conducted. Data were collected from June 1, 2012, to January 31, 2017, for set 1 and from January 1 to December 31, 2017, for set 2; graded between November 2018 and January 2020; and analyzed from February 2020 to November 2020.
Rating and stack ranking for clinical applicability by retinal specialists, model-grader agreement for voxelwise segmentations, and total volume evaluated using Dice similarity coefficients, Bland-Altman plots, and intraclass correlation coefficients.
Among the 173 patients included in the analysis (92 53% women), qualitative assessment found that automated whole-volume segmentation ranked better than or comparable to at least 1 expert grader in 127 scans (73%; 95% CI, 66%-79%). A neutral or positive rating was given to 135 model segmentations (78%; 95% CI, 71%-84%) and 309 expert gradings (2 per scan) (89%; 95% CI, 86%-92%). The model was rated neutrally or positively in 86% to 92% of diabetic macular edema scans and 53% to 87% of age-related macular degeneration scans. Intraclass correlations ranged from 0.33 (95% CI, 0.08-0.96) to 0.96 (95% CI, 0.90-0.99). Dice similarity coefficients ranged from 0.43 (95% CI, 0.29-0.66) to 0.78 (95% CI, 0.57-0.85).
This deep learning-based segmentation tool provided clinically useful measures of retinal disease that would otherwise be infeasible to obtain. Qualitative evaluation was additionally important to reveal clinical applicability for both care management and research.