准确区分不确定的肺结节仍然是临床实践中的重大挑战。当处理低剂量计算机断层扫描（一种正在世界许多地区推广的肺癌筛查技术）获得的大量放射学特征时，这一挑战变得越来越艰巨。因此，本研究提出了利他海鸥优化算法（AltSOA），用于选择放射组学特征来预测肺结节的恶性风险。这种创新方法将利他主义融入到传统的海鸥优化算法中，以寻求全局最优解。设计了多目标适应度函数来训练肺结节预测模型，旨在在保证预测性能的同时使用更少的放射组学特征。在全局放射组学特征中，AltSOA 识别了 11 个感兴趣的特征，包括灰度共生矩阵。这种自动选择的放射组学特征组能够精确预测肺结节的恶性风险（曲线下面积 = 0.8383（95% 置信区间 0.7862-0.8863）），超出了放射科医生的熟练程度。此外，还深入讨论了肺结节预测模型的可解释性、临床实用性和普遍性。所有结果一致强调了 AltSOA 在预测肺结节恶性风险方面的优越性。所提出的肺结节恶性风险预测模型有望增强现有的肺癌筛查方法。这项工作的支持源代码可以在以下网址找到：https://github.com/zzl2022/PBMPN。版权所有 © 2024。由 Elsevier Ltd 出版。

Accurately differentiating indeterminate pulmonary nodules remains a significant challenge in clinical practice. This challenge becomes increasingly formidable when dealing with the vast radiomic features obtained from low-dose computed tomography, a lung cancer screening technique being rolling out in many areas of the world. Consequently, this study proposed the Altruistic Seagull Optimization Algorithm (AltSOA) for the selection of radiomic features in predicting the malignancy risk of pulmonary nodules. This innovative approach incorporated altruism into the traditional seagull optimization algorithm to seek a global optimal solution. A multi-objective fitness function was designed for training the pulmonary nodule prediction model, aiming to use fewer radiomic features while ensuring prediction performance. Among global radiomic features, the AltSOA identified 11 interested features, including the gray level co-occurrence matrix. This automatically selected panel of radiomic features enabled precise prediction (area under the curve = 0.8383 (95 % confidence interval 0.7862-0.8863)) of the malignancy risk of pulmonary nodules, surpassing the proficiency of radiologists. Furthermore, the interpretability, clinical utility, and generalizability of the pulmonary nodule prediction model were thoroughly discussed. All results consistently underscore the superiority of the AltSOA in predicting the malignancy risk of pulmonary nodules. And the proposed malignant risk prediction model for pulmonary nodules holds promise for enhancing existing lung cancer screening methods. The supporting source codes of this work can be found at: https://github.com/zzl2022/PBMPN.Copyright © 2024. Published by Elsevier Ltd.