Hou Ling, Fu Junfen, Wei Haiyan, Liang Liyang, Du Hongwei, Zhang Jianping, Zhong Yan, Chen Ruimin, Cheng Xinran, Pan Jiayan, Shan Xiaoou, Zeng Ting, Gong Chunxiu, Liao Wei, Liu Deyun, Zhu Shunye, Lan Dan, Dong Zhiya, Ma Huamei, Yang Yu, Zhu Min, Sun Wen, Luo Xiaoping
Department of Pediatrics, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, 430030, China.
Department of Endocrinology, National Clinical Research Center for Child Health, Children's Hospital of Zhejiang University School of Medicine, Zhejiang University School of Medicine, Hangzhou, 310052, China.
J Endocrinol Invest. 2025 Feb 19. doi: 10.1007/s40618-025-02546-z.
Curve matching can predict the height trajectories of children by analyzing longitudinal growth data. We extended the method to improve the prediction of response to long-acting growth hormone treatment in children with growth hormone deficiency (GHD).
We analyzed data from a previous real-world study with a 36-month treatment of PEGylated recombinant human growth hormone (PEG-rhGH). The matching database comprises height measures imputed using the broken stick method. For curve matching, we proposed a flexible hyperparameter selection approach to determining the number of similar patients.
The matching database included 681 patients, with an average of 12.20 ± 2.09 height measurements per patient. Our approach demonstrated significantly improved prediction accuracy compared with the previous approach using a fixed number of similar patients (mean squared errors of 0.0412 ± 0.1156 vs. 0.564 ± 0.1639, 0.851 ± 0.2627, and 0.1077 ± 0.2960 for 5, 10, and 15 similar patients, respectively, all P < 0.05). The optimal prediction scenario was having four height measurements within the first six months and predicting height trajectories from there on.
By extending curve matching with flexible hyperparameter selection, we accurately predicted the response to long-acting PEG-rhGH in the GHD children included in this study.
曲线匹配可通过分析纵向生长数据来预测儿童的身高轨迹。我们扩展了该方法，以改善对生长激素缺乏症（GHD）儿童长效生长激素治疗反应的预测。
我们分析了一项先前真实世界研究的数据，该研究对聚乙二醇化重组人生长激素（PEG-rhGH）进行了为期36个月的治疗。匹配数据库包括使用折断棍法估算的身高测量值。对于曲线匹配，我们提出了一种灵活的超参数选择方法来确定相似患者的数量。
匹配数据库包括681名患者，每位患者平均有12.20±2.09次身高测量。与先前使用固定数量相似患者的方法相比，我们的方法显示出显著提高的预测准确性（对于5、10和15名相似患者，均方误差分别为0.0412±0.1156、0.564±0.1639、0.851±0.2627和0.1077±0.2960，均P<0.05）。最佳预测方案是在前六个月内进行四次身高测量，并从那时起预测身高轨迹。
通过扩展具有灵活超参数选择的曲线匹配，我们准确预测了本研究中纳入的GHD儿童对长效PEG-rhGH的反应。
