A Prediction Model to Discriminate Small Choroidal Melanoma from Choroidal Nevus

Abstract

Objective: To develop a validated machine learning model to diagnose small choroidal melanoma. Design: Cohort study Subjects, Participants, and/or Controls: The training data included 123 patients diagnosed as small choroidal melanocytic tumor (5.0-16.0 mm in largest basal diameter and 1.0 mm to 2.5 mm in height; Collaborative Ocular Melanoma Study criteria). Those diagnosed as melanoma (n=61) had either documented growth or pathologic confirmation. 62 patients with stable lesions classified as choroidal nevus, were used as negative controls. The external validation data set included 240 patients managed at a different tertiary clinic, also with small choroidal melanocytic tumor, observed for malignant growth. Methods: In the training data, lasso logistic regression was used to select variables for inclusion in the final model for the association with melanoma versus choroidal nevus. Internal and external validation were performed to assess model performance. Main Outcome Measures: Predicted probability of small choroidal melanoma Results: Distance to optic disc ≥3mm and drusen were associated with decreased odds of melanoma whereas male versus female sex, increased height, subretinal fluid, and orange pigment were associated with increased odds of choroidal melanoma. The area under the receiver operating characteristic (AUROC) “discrimination value” for this model was 0.880. The top four variables that were most frequently selected for inclusion in the model on internal validation, implying their importance as predictors of melanoma, were subretinal fluid, height, distance to optic disc, and orange pigment. When tested against the validation data, the prediction model could distinguish between choroidal nevus and melanoma with high discrimination of 0.861. The final prediction model was converted into an online calculator to generate predicted probability of melanoma. Conclusions: To minimize diagnostic uncertainty, a machine learning based diagnostic prediction calculator can be readily applied for decision making and counselling patients with small choroidal melanoma.

Artificial intelligence for ocular oncology

“…Small choroidal melanocytic tumors are a diagnostic challenge, as they could represent either as benign nevi or malignant melanomas [ 7 ]. Zabor et al [ 8 ▪ ] developed a ML model, using lasso regression, to distinguish small choroidal melanoma (SCM) from choroidal nevus using multimodal data. A total of 123 patients with small choroidal melanocytic tumor, identified according to Collaborative Ocular Melanoma Study criteria (5.0–16.0 mm in largest basal diameter and 1.0–2.5 mm in height), were included in the training set.…”

Clinical Applications of Machine Learning in the Management of Intraocular Cancers: A Narrative Review

“… 33 The clinical utility of this work with respect to ML models could be optimized further by integrating biomarkers with clinical imaging data, as Zabor et al. 34 have shown with their model, which is able to differentiate between UM and choroidal nevus with an AUC of 0.86 using patient and tumor characteristics.…”