Quality Assessment of Radiomics Studies on Functional Outcomes Following Acute Ischemic Stroke - A Systematic Review.

OBJECTIVE: Radiomics is a machine-learning method which extracts features from medical images. The objective of the present systematic review was to assess the quality of existing studies which use radiomics methods to predict functional outcomes in patients following AIS.

METHODS: Studies using radiomics-extracted features to predict functional outcomes amongst AIS patients using the modified Rankin Score (mRS) were included. PubMed, Scopus, Web of Science, and Embase were screened using the terms "radiomics" and "texture" in combination with "stroke". Quality scores were calculated based on Radiomics Quality Score (RQS), the Image Biomarkers Standardization Initiative (IBSI), and the Quality Assessment of Diagnostic Accuracy Studies (QUADAS-2).

RESULTS: 14 studies were included. Median (IQR) total RQS score was 14.5 (13,16) out of 36. Domains 1, 5, and 6 on protocol quality and stability of imaging and segmentation, level of evidence, and use of open science and data respectively were poor. Median (IQR) IBSI score was 2.5 (1,5) out of 6. Few studies included bias-field correction algorithm, isovoxel resampling, skull stripping, or grey-level discretization. 0/14 studies received +6 points, 1/14 studies received +5 points, 5/14 received +4 points, 1/14 studies received +3 points, 5/14 studies received +2 points, 2/14 received +1 points, and 0/14 received 0 points. As per the QUADAS-2, 6/14 (42.9%) studies had risk of bias concern and 0/14 (0%) had applicability concern.

CONCLUSION: Quality of included studies was low-to-moderate. With increasing use of radiomics, future studies should attempt to adhere to and report established radiomics quality guidelines.