This paper explores the use of an ensemble of machine learning classifiers combined with active learning strategiesto predict radiologists' assessments of lung nodule characteristics in the Lung Image Database Consortium (LIDC).The study focuses on modeling and predicting agreement among radiologists’ semantic ratings across seven keynodule characteristics: spiculation, lobulation, texture, sphericity, margin, subtlety, and malignancy. Thesecharacteristics are essential in evaluating and diagnosing pulmonary nodules.The proposed approach utilizes anensemble of classifiers, functioning as a simulated "computer panel of experts," to analyze 64 image features extractedfrom the nodules. These features span four critical categories: shape, intensity, texture, and size. By leveraging activelearning, the system initiates the training phase with nodules where radiologists’ semantic ratings are consistent. Thesystem then progressively learns to classify nodules with varying degrees of disagreement among radiologists,effectively addressing uncertainty and variability in expert interpretations. The results demonstrate that the ensembleapproach outperforms individual classifiers in terms of classification accuracy, showcasing its ability to synthesizediverse perspectives and make more reliable predictions. This enhanced predictive capability underscores the potentialof machine learning to serve as a supportive tool in radiological diagnostics. By acting as a "second read" forphysicians, the proposed system can improve consistency in radiological interpretations, reduce diagnostic variability,and ultimately enhance patient care. The findings highlight the promising role of advanced computational methodsin augmenting human expertise in medical imaging analysis.Keywords: Ensemble learning; Active learning; Lung nodule classification; LIDC database; Radiological assessment;Semantic characteristics; Nodule spiculation; Nodule lobulation; Nodule texture; Nodule sphericity;