English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Background: Several studies indicate that the anterior visual pathwayprovides information about the dynamics of axonal degeneration in MultipleSclerosis (MS). Current research in the field is focused on the quest for themost discriminative features among patients and controls and the development ofmachine learning models that yield computer-aided solutions widely usable inclinical practice. However, most studies are conducted with small samples andthe models are used as black boxes. Clinicians should not trust machinelearning decisions unless they come with comprehensive and easilyunderstandable explanations. Materials and methods: A total of 216 eyes from111 healthy controls and 100 eyes from 59 patients with relapsing-remitting MSwere enrolled. The feature set was obtained from the thickness of the ganglioncell layer (GCL) and the retinal nerve fiber layer (RNFL). Measurements wereacquired by the novel Posterior Pole protocol from Spectralis Optical CoherenceTomography (OCT) device. We compared two black-box methods (gradient boostingand random forests) with a glass-box method (explainable boosting machine).Explainability was studied using SHAP for the black-box methods and the scoresof the glass-box method. Results: The best-performing models were obtained forthe GCL layer. Explainability pointed out to the temporal location of the GCLlayer that is usually broken or thinning in MS and the relationship between lowthickness values and high probability of MS, which is coherent with clinicalknowledge. Conclusions: The insights on how to use explainability shown in thiswork represent a first important step toward a trustworthy computer-aidedsolution for the diagnosis of MS with OCT.

Explainable artificial intelligence toward usable and trustworthy  computer-aided early diagnosis of multiple sclerosis from Optical Coherence  Tomography