An Artificial Intelligence Algorithm to Predict Nodal Metastasis in Lung Cancer

ABSTRACT Background Endobronchial Ultrasound (EBUS) features have high accuracy for predicting lymph node (LN) malignancy. However, their clinical application remains limited due to high operator dependency. We hypothesized that an Artificial Intelligence algorithm (NeuralSeg) is capable of accurately identifying and predicting LN malignancy based on EBUS images. Methods In the derivation phase, EBUS images were segmented twice by an endosonographer and used as controls in 5-fold cross-validation training of NeuralSeg. In the validation phase, the algorithm was tested on new images it had not seen before. Logistic regression and receiver operator characteristic curves were used to determine NeuralSeg’s capability of discrimination between benign and malignant LNs, using pathologic specimens as gold standard. Results In total, 298 LNs from 140 patients were used for derivation and 108 LNs from 47 patients for validation. In the derivation cohort, NeuralSeg was able to predict malignant LNs with an accuracy of 73.8% (95% CI: 68.4% to 78.7%). In the validation cohort, NeuralSeg had an accuracy of 72.9% (95% CI: 63.5% to 81.0%), a specificity of 90.8% (95% CI: 81.9% to 96.2%) and negative predictive value (NPV) of 75.9% (95% CI: 71.5% to 79.9%). NeuralSeg showed higher diagnostic discrimination during validation compared to derivation (c-statistic= 0.75 [95% CI: 0.65-0.85] vs c-statistic=0.63 [95% CI: 0.54-0.72]). Conclusions NeuralSeg is able to accurately rule out nodal metastasis and can possibly be used as an adjunct to EBUS when nodal biopsy is not possible or inconclusive. Future work to evaluate the algorithm in a clinical trial will be required.