Validation of a deep-learning-based retinal biomarker (Reti-CVD) in the prediction of cardiovascular disease: data from UK Biobank

Abstract

Background: Currently in the United Kingdom, cardiovascular disease (CVD) risk assessment is based on the QRISK3 score, in which 10% 10-year CVD risk indicates clinical intervention. However, this benchmark has limited efficacy in clinical practice and the need for a more simple, non-invasive risk stratification tool is necessary. Retinal photography is becoming increasingly acceptable as a non-invasive imaging tool for CVD. Previously, we developed a novel CVD risk stratification system based on retinal photographs predicting future CVD risk. This study aims to further validate our biomarker, Reti-CVD, (1) to detect risk group of ≥ 10% in 10-year CVD risk and (2) enhance risk assessment in individuals with QRISK3 of 7.5-10% (termed as borderline-QRISK3 group) using the UK Biobank.

Methods: Reti-CVD scores were calculated and stratified into three risk groups based on optimized cut-off values from the UK Biobank. We used Cox proportional-hazards models to evaluate the ability of Reti-CVD to predict CVD events in the general population. C-statistics was used to assess the prognostic value of adding Reti-CVD to QRISK3 in borderline-QRISK3 group and three vulnerable subgroups.

Results: Among 48,260 participants with no history of CVD, 6.3% had CVD events during the 11-year follow-up. Reti-CVD was associated with an increased risk of CVD (adjusted hazard ratio [HR] 1.41; 95% confidence interval [CI], 1.30-1.52) with a 13.1% (95% CI, 11.7-14.6%) 10-year CVD risk in Reti-CVD-high-risk group. The 10-year CVD risk of the borderline-QRISK3 group was greater than 10% in Reti-CVD-high-risk group (11.5% in non-statin cohort [n = 45,473], 11.5% in stage 1 hypertension cohort [n = 11,966], and 14.2% in middle-aged cohort [n = 38,941]). C statistics increased by 0.014 (0.010-0.017) in non-statin cohort, 0.013 (0.007-0.019) in stage 1 hypertension cohort, and 0.023 (0.018-0.029) in middle-aged cohort for CVD event prediction after adding Reti-CVD to QRISK3.

Conclusions: Reti-CVD has the potential to identify individuals with ≥ 10% 10-year CVD risk who are likely to benefit from earlier preventative CVD interventions. For borderline-QRISK3 individuals with 10-year CVD risk between 7.5 and 10%, Reti-CVD could be used as a risk enhancer tool to help improve discernment accuracy, especially in adult groups that may be pre-disposed to CVD.

Keywords: Artificial intelligence; Cardiovascular disease; Deep learning; Retinal imaging; Retinal photograph; Risk stratification; Risk stratification system; UK Biobank.

Fig. 1

Kaplan-Meier curves according to Reti-CVD and QRISK3. Cardiovascular disease (CVD) event rate according to QRISK3-five groups (A), and Reti-CVD-three groups (B) in all participants (n = 48,260) were presented. In the general population, the high-risk group of Reti-CVD (B) shows a similar incident CVD rate to that of the QRISK 10–15% group (A), indicating that if a participant is identified as Reti-CVD-high risk by retinal photography, participants may be advised to undergo a full CVD risk assessment via the NHS primary care service

Fig. 2

Kaplan-Meier curves according to Reti-CVD in borderline-QRISK3 group. Cardiovascular disease (CVD) event rate according to Reti-CVD-three groups in borderline-QRISK3 group who had QRISK3 score between 7.5 and 10% were presented in non-statin cohort (A), stage 1 hypertension cohort (B), and middle-aged (40–64 years) cohorts (C). Considering that statin and antihypertensive pharmacotherapy initiation is recommended at QRISK of ≥ 10%, Reti-CVD can be used as a risk enhancer in borderline-QRISK3 groups of 7.5–10% to reach consensus on statin initiation. In addition, although most of risk assessment systems were derived from cohorts of primarily middle-aged people and typically well-functioning individuals, Reti-CVD can still be a risk enhancer in in borderline-QRISK3 groups of 7.5–10% middle-aged people