Application of artificial intelligence in the assessment of thyroid eye disease (TED) - a scoping review

Background

There is emerging evidence which suggests the utility of artificial intelligence (AI) in the diagnostic assessment and pre-treatment evaluation of thyroid eye disease (TED). This scoping review aims to (1) identify the extent of the available evidence (2) provide an in-depth analysis of AI research methodology of the studies included in the review (3) Identify knowledge gaps pertaining to research in this area.

Methods

This review was performed according to the 2020 Preferred Reporting Items for Systematic Reviews and Meta-Analyses statement (PRISMA). We quantify the diagnostic accuracy of AI models in the field of TED assessment and appraise the quality of these studies using the modified QUADAS-2 tool.

Results

A total of 13 studies were included in this review. The most common AI models used in these studies are convolutional neural networks (CNN). The majority of the studies compared algorithm performance against healthcare professionals. The overall risk of bias and applicability using the modified Quality Assessment of Diagnostic Accuracy Studies 2 (QUADAS-2) tool led to most of the studies being classified as low risk, although higher deficiency was noted in the risk of bias in flow and timing.

Conclusions

While the results of the review showed high diagnostic accuracy of the AI models in identifying features of TED relevant to disease assessment, deficiencies in study design causing study bias and compromising study applicability were noted. Moving forward, limitations and challenges inherent to machine learning should be addressed with improved standardized guidance around study design, reporting, and legislative framework.

Comparison of Unilateral Versus Bilateral Lateral Rectus Recession for Small Angle Intermittent Exotropia: Outcomes and Surgical Dose-Responses

PURPOSE

To compare the surgical outcomes of unilateral lateral rectus recession to bilateral lateral rectus recession for small angle intermittent exotropia.

METHODS

This was a retrospective cohort study of pediatric patients with an intermittent exotropia between 16 and 20 prism diopters (PD) who underwent unilateral lateral rectus recession or bilateral lateral rectus recession at a single tertiary care pediatric hospital. The primary outcome was success (exotropia < 10 PD of esotropia < 5 PD, no decrease in stereopsis > 0.6 log arcsec, and no reoperation) at 12 months postoperatively. Secondary outcomes included survival analysis of time to surgical failure, surgical dose-response, and improvement in central fusion or stereopsis.

RESULTS

At 12 months, successful outcomes were achieved in 13 of 27 patients (46%) in the bilateral lateral rectus recession group and 19 of 28 patients (70%) in the unilateral lateral rectus recession group, which was not a statistically significant difference (P = .10). Survival analysis showed a trend toward a higher rate of failure in the bilateral lateral rectus recession group compared to the unilateral lateral rectus recession group (P = .04). The mean surgical dose-response was 1.7 PD/mm at 1 week and 1.0 PD/mm at 12 months for the bilateral lateral rectus recession group, and 2.0 PD/mm at 1 week postoperatively and 1.4 PD/mm at 12 months postoperatively for the unilateral lateral rectus recession group. There were no cases of long-term postoperative lateral incomitance in either group.

CONCLUSIONS

Unilateral lateral rectus recession and bilateral lateral rectus recession have similar success rates for small angle intermittent exotropia after at least 12 months of follow-up. Randomized controlled trials in surgical management of intermittent exotropia should consider unilateral lateral rectus recession as a treatment arm. [J Pediatr Ophthalmol Strabismus. 2022;59(5):350-355.].

Eosinophilic angiocentric fibrosis and IgG4-related disease revisited

INTRODUCTION

Eosinophilic angiocentric fibrosis (EAF) has been postulated to lie on the spectrum of IgG4-related disease (IgG4-RD) in a study reported in 2011. However, the aetiology of EAF remains controversial despite increasing literature reporting IgG4-RD targeted investigations in those studies. This review aims to formally evaluate the relationship between EAF and IgG4-RD using the latest 2019 ACR/EULAR classification scheme for IgG4-RD.

METHODS

A literature search was performed on the PubMed database for all studies describing patients diagnosed with EAF. Additionally, two EAF cases were retrospectively identified from our institution and presented. The demographics, clinical presentation, histological and serological data of each patient were analysed.

RESULTS

A total of twenty cases were evaluated, including eighteen patients from fourteen articles in the English literature and two cases from our institution. Six out of twenty (30%) patients with EAF met the criteria for IgG4-RD with the 2019 ACR/EULAR classification scheme.

CONCLUSION

This represents the first attempt at formally evaluating the relationship between EAF and IgG4-RD using a validated set of classification criteria. Using the currently available data, a small proportion of patients with EAF met the criteria for IgG4-RD. However, various limitations of this study suggest that further efforts at disease characterization of EAF may be required.