Zabor Emily C, Raval Vishal, Luo Shiming, Pelayes David E, Singh Arun D
Taussig Cancer Institute, Department of Quantitative Health Sciences, Cleveland Clinic, Cleveland, Ohio, USA.
Cole Eye Institute, Ophthalmic Oncology, Cleveland Clinic, Cleveland, Ohio, USA.
Ocul Oncol Pathol. 2022 Feb;8(1):71-78. doi: 10.1159/000521541. Epub 2021 Dec 22.
This study aimed to develop a validated machine learning model to diagnose small choroidal melanoma.
This is a 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-2.5 mm in height; Collaborative Ocular Melanoma Study criteria). Those diagnosed as melanoma ( = 61) had either documented growth or pathologic confirmation. Sixty-two patients with stable lesions classified as choroidal nevus were used as negative controls. The external validation dataset included 240 patients managed at a different tertiary clinic, also with small choroidal melanocytic tumor, observed for malignant growth.
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 was performed to assess model performance.
The main outcome measure is the predicted probability of small choroidal melanoma.
Distance to optic disc ≥3 mm 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 "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 a high discrimination of 0.861. The final prediction model was converted into an online calculator to generate predicted probability of melanoma.
To minimize diagnostic uncertainty, a machine learning-based diagnostic prediction calculator can be readily applied for decision-making and counseling patients with small choroidal melanoma.
本研究旨在开发一种经过验证的机器学习模型，用于诊断小脉络膜黑色素瘤。
这是一项队列研究。
受试者、参与者和/或对照：训练数据包括123例被诊断为小脉络膜黑素细胞肿瘤的患者（最大基底直径5.0 - 16.0毫米，高度1.0毫米 - 2.5毫米；协作性眼黑色素瘤研究标准）。那些被诊断为黑色素瘤（n = 61）的患者有记录的生长情况或病理证实。62例病变稳定且分类为脉络膜痣的患者用作阴性对照。外部验证数据集包括在另一家三级诊所接受治疗的240例患者，他们也患有小脉络膜黑素细胞肿瘤，并观察其是否有恶性生长。
在训练数据中，使用套索逻辑回归来选择纳入最终模型的变量，以分析与黑色素瘤和脉络膜痣的相关性。进行内部和外部验证以评估模型性能。
主要观察指标是小脉络膜黑色素瘤的预测概率。
距视盘≥3毫米和玻璃膜疣与黑色素瘤的发生几率降低相关，而男性与女性、高度增加、视网膜下液和橙色色素与脉络膜黑色素瘤的发生几率增加相关。该模型的受试者操作特征曲线下面积（“辨别值”）为0.880。在内部验证中最常被选入模型的前四个变量，暗示它们作为黑色素瘤预测指标的重要性，分别是视网膜下液、高度、距视盘距离和橙色色素。在针对验证数据进行测试时，预测模型能够以0.861的高辨别力区分脉络膜痣和黑色素瘤。最终的预测模型被转换为一个在线计算器，以生成黑色素瘤的预测概率。
为了尽量减少诊断不确定性，基于机器学习的诊断预测计算器可轻松应用于小脉络膜黑色素瘤患者的决策制定和咨询。
