Abstract 665P
Background
Post-radiation neurocognitive decline is a debilitating late complication after (chemo-)radiotherapy for nasopharyngeal cancer (NPC). Radiation dose correlates poorly with neurocognitive outcomes. This study explored the association between retinal vessel characteristics with neurocognitive outcomes in NPC survivors using an artificial intelligence-based analytic platform.
Methods
This cross-sectional study recruited 180 NPC survivors in a tertiary oncology center. Comprehensive neurocognitive assessments were performed on 8 principal domains. Results were presented as z-scores normalized to population references. Retinal images were captured by a non-mydriatic fundus camera. Vascular characteristics were analyzed by a machine learning approach using fractal analysis, high order spectra analysis, and statistical texture analysis. Results were outputted as a continuous risk score (ARIA-WMH Score) ranging from 0 to 1, with cutoffs of >0.4 and >0.6 refer to moderate and high risk of severe white matter hyperintensities from cerebral magnetic resonance imaging, respectively.
Results
The median time from radiotherapy was 7.0 years. Significant impairments were observed in verbal memory (mean z-score -0.43), executive function (mean z-score -1.71), processing speed (mean z-score -0.73), motor dexterity (mean z-score -0.88) and language fluency (mean z-score -0.28). Upon analysis of the retinal vessels characteristics by ARIA-WMH, 11.7% (21/180) and 48.9% (88/180) of the patients scored >0.6 and >0.4, respectively. Patients with ARIA-WMH Score >0.6 had more severe verbal memory impairment than patients who scored ≤0.6 (mean z-score, -1.04 vs -0.35, p=0.0035). Similar findings were observed if lower cutoff of 0.4 was used (mean z-score, -0.60 vs -0.26, p=0.029). The severity of ARIA-WMH was associated with the level of verbal memory impairment.
Conclusions
Neurocognitive impairment is prevalent after radiotherapy for NPC. Retinal image analysis may offer a quick and non-invasive tool to identify patients with impairment in verbal memory for formal assessments or interventions. Further studies that incorporate radiation dosimetry information are warranted.
Clinical trial identification
Editorial acknowledgement
Legal entity responsible for the study
Queen Elizabeth Hospital, Department of Clinical Oncology.
Funding
The Health and Medical Research Fund, the Food and Health Bureau, The Government of the Hong Kong Special Administrative Region.
Disclosure
All authors have declared no conflicts of interest.