General Surgery, Cancer Center, Department of Hernia Surgery, Zhejiang Provincial People's Hospital (Affiliated People's Hospital). Hangzhou Medical College, Hangzhou, Zhejiang, China.
Cancer Center, Department of Ultrasound Medicine, Zhejiang Provincial People's Hospital, Affiliated People's Hospital, Hangzhou Medical College, Hangzhou, Zhejiang, China.
Comput Biol Med. 2024 Jun;175:108394. doi: 10.1016/j.compbiomed.2024.108394. Epub 2024 Apr 16.
Gastroesophageal reflux disease (GERD) profoundly compromises the quality of life, with prolonged untreated cases posing a heightened risk of severe complications such as esophageal injury and esophageal carcinoma. The imperative for early diagnosis is paramount in averting progressive pathological developments. This study introduces a wrapper-based feature selection model based on the enhanced Runge Kutta algorithm (SCCRUN) and fuzzy k-nearest neighbors (FKNN) for GERD prediction, named bSCCRUN-FKNN-FS. Runge Kutta algorithm (RUN) is a metaheuristic algorithm designed based on the Runge-Kutta method. However, RUN's effectiveness in local search capabilities is insufficient, and it exhibits insufficient convergence accuracy. To enhance the convergence accuracy of RUN, spiraling communication and collaboration (SCC) is introduced. By facilitating information exchange among population individuals, SCC expands the solution search space, thereby improving convergence accuracy. The optimization capabilities of SCCRUN are experimentally validated through comparisons with classical and state-of-the-art algorithms on the IEEE CEC 2017 benchmark. Subsequently, based on SCCRUN, the bSCCRUN-FKNN-FS model is proposed. During the period from 2019 to 2023, a dataset comprising 179 cases of GERD, including 110 GERD patients and 69 healthy individuals, was collected from Zhejiang Provincial People's Hospital. This dataset was utilized to compare our proposed model against similar algorithms in order to evaluate its performance. Concurrently, it was determined that features such as the internal diameter of the esophageal hiatus during distention, esophagogastric junction diameter during distention, and external diameter of the esophageal hiatus during non-distention play crucial roles in influencing GERD prediction. Experimental findings demonstrate the outstanding performance of the proposed model, with a predictive accuracy reaching as high as 93.824 %. These results underscore the significant advantage of the proposed model in both identifying and predicting GERD patients.
胃食管反流病（GERD）严重影响生活质量，未经治疗的长期病例会增加食管损伤和食管癌等严重并发症的风险。早期诊断至关重要，可以避免进行性病理发展。本研究提出了一种基于增强龙格库塔算法（SCCRUN）和模糊 K 最近邻（FKNN）的胃食管反流病预测的包装式特征选择模型，称为 bSCCRUN-FKNN-FS。龙格库塔算法（RUN）是一种基于龙格库塔法设计的元启发式算法。然而，RUN 在局部搜索能力方面的有效性不足，并且收敛精度也不够。为了提高 RUN 的收敛精度，引入了螺旋通信和协作（SCC）。通过促进种群个体之间的信息交换，SCC 扩展了解的搜索空间，从而提高了收敛精度。通过在 IEEE CEC 2017 基准测试上与经典算法和最先进算法进行比较，实验验证了 SCCRUN 的优化能力。随后，基于 SCCRUN，提出了 bSCCRUN-FKNN-FS 模型。在 2019 年至 2023 年期间，从浙江省人民医院收集了一个包含 179 例胃食管反流病病例的数据集，其中包括 110 例胃食管反流病患者和 69 例健康个体。利用该数据集将我们提出的模型与类似算法进行比较，以评估其性能。同时，确定了在扩张时食管裂孔内径、扩张时胃食管交界处直径和非扩张时食管裂孔外径等特征对胃食管反流病预测有重要影响。实验结果表明，所提出的模型具有出色的性能，预测准确率高达 93.824%。这些结果突出了所提出模型在识别和预测胃食管反流病患者方面的显著优势。
