Comparison of MOLES and Mel AI noma for Differentiating Small Choroidal Melanomas from Nevi.
AI algorithm Mel AI noma more strongly linked to melanoma diagnosis than MOLES score
Comparison of MOLES and Mel AI noma for Differentiating Small Choroidal Melanomas from Nevi.
Early identification of small choroidal melanomas is important, as metastatic risk increases with tumor size.
This study aims to compare the association between MOLES and Mel AI noma scores and to assess their relative association with expert melanoma versus nevus diagnosis.
In this retrospective cohort study, 86 patients with small pigmented choroidal lesions (29 melanomas and 57 nevi) diagnosed at a national ocular oncology referral center were included.
Mel AI noma's score predicts a melanoma diagnosis better than MOLES score does
Mel AI noma scores increased monotonically with higher MOLES categories ( p = 0.0001).
In univariable logistic regression, both MOLES and Mel AI noma scores were associated with increased odds of melanoma diagnosis.
In multivariable analysis including both scores, each remained independently associated with melanoma diagnosis.
Both MOLES and Mel AI noma are effective for differentiating small choroidal melanomas from nevi. Although the scores are statistically associated, they capture partly distinct information.
Mel AI noma demonstrates slightly stronger association with melanoma diagnosis and provides fully reproducible output, supporting its role as a complementary aid in lesion triage.