Factors Associated with Machine Learning-Based Predictions of Retinal Aging Using Teleretinal Screening Images from Patients with Diabetes.

Ophthalmol Sci · 2026 · PMC12992952 · PMID 41853569

Europe PMC DOI

hedged sentences

0.0770

closest p · 1.5× alpha

0.0790

boldest claim

The sentences

did not reach statistical significanceP = 0.077so close (0.05 < p ≤ 0.1)

Retinal aging also appeared to show a trend toward higher 10-year risk for coronary artery disease, but did not reach statistical significance ( P = 0.077).

also in 75,281 other papers

a possible trendP = 0.079so close (0.05 < p ≤ 0.1)

Among other comorbidities, diabetic neuropathy was strongly associated with accelerated retinal age (+1.80 years, P < 0.001), whereas patients with CKD ( P = 0.119) or reduced eGFR <90 ( P = 0.573) had little impact, except patients with eGFR <60 corresponding to stage III CKD who showed a possible trend for faster retinal aging (+0.85 years, P = 0.079).

also in 939 other papers

an interesting trendno p-value reported

57 , 58 Our model predictions also showed an interesting trend where older patients were predicted to show less retinal aging, suggesting that retinal aging may follow a nonlinear trajectory, characterized by more rapid changes during early life and a gradual slowing during middle and advanced age.

also in 1,024 other papers

showed a trendno p-value reported

Neither current nor past alcohol use impacted retinal aging ( P > 0.05 for both), although current alcohol use showed a trend toward a lower retinal age gap, indicating a possible protective effect ( Fig 4 ).

also in 33,237 other papers

Quoted from the open-access full text in Europe PMC under the licence the publisher applied. The sentence is reproduced exactly as published; the emphasis is ours.