Prediction of methylphenidate treatment response for ADHD using conventional and radiomics T1 and DTI features: Secondary analysis of a randomized clinical trial

IF 3.4 2区医学 Q2 NEUROIMAGING

Neuroimage-Clinical Pub Date : 2024-11-21 DOI:10.1016/j.nicl.2024.103707

Mingshi Chen , Zarah van der Pal , Maarten G. Poirot , Anouk Schrantee , Marco Bottelier , Sandra J.J. Kooij , Henk A. Marquering , Liesbeth Reneman , Matthan W.A. Caan

{"title":"Prediction of methylphenidate treatment response for ADHD using conventional and radiomics T1 and DTI features: Secondary analysis of a randomized clinical trial","authors":"Mingshi Chen , Zarah van der Pal , Maarten G. Poirot , Anouk Schrantee , Marco Bottelier , Sandra J.J. Kooij , Henk A. Marquering , Liesbeth Reneman , Matthan W.A. Caan","doi":"10.1016/j.nicl.2024.103707","DOIUrl":null,"url":null,"abstract":"<div><h3>Background</h3><div>Attention-Deficit/Hyperactivity Disorder (ADHD) is commonly treated with methylphenidate (MPH). Although highly effective, MPH treatment still has a relatively high non-response rate of around 30%, highlighting the need for a better understanding of treatment response. Radiomics of T1-weighted images and Diffusion Tensor Imaging (DTI) combined with machine learning approaches could offer a novel method for assessing MPH treatment response.</div></div><div><h3>Purpose</h3><div>To evaluate the accuracy of both conventional and radiomics approaches in predicting treatment response based on baseline T1 and DTI data in stimulant-naive ADHD participants.</div></div><div><h3>Methods</h3><div>We performed a secondary analysis of a randomized clinical trial (ePOD-MPH), involving 47 stimulant-naive ADHD participants (23 boys aged 11.4 ± 0.4 years, 24 men aged 28.1 ± 4.3 years) who underwent 16 weeks of treatment with MPH. Baseline T1-weighted and DTI MRI scans were acquired. Treatment response was assessed at 8 weeks (during treatment) and one week after cessation of 16-week treatment (post-treatment) using the Clinical Global Impressions − Improvement scale as our primary outcome. We compared prediction accuracy using a conventional model and a radiomics model. The conventional approach included the volume of bilateral caudate, putamen, pallidum, accumbens, and hippocampus, and for DTI the mean fractional anisotropy (FA) of the entire brain white matter, bilateral Anterior Thalamic Radiation (ATR), and the splenium of the corpus callosum, totaling 14 regional features. For the radiomics approach, 380 features (shape-based and first-order statistics) were extracted from these 14 regions. XGBoost models with nested cross-validation were used and constructed for the total cohort (n = 47), as well as children (n = 23) and adults (n = 24) separately. Exact binomial tests were employed to compare model performance.</div></div><div><h3>Results</h3><div>For the conventional model, balanced accuracy (bAcc) in predicting treatment response during treatment was 63 % for the total cohort, 32 % for children, and 36 % for adults (Area Under the Receiver Operating Characteristic Curve (AUC-ROC): 0.69, 0.33, 0.41 respectively). Radiomics models demonstrated bAcc’s of 68 %, 64 %, and 64 % during treatment (AUC-ROCs of 0.73, 0.62, 0.69 respectively). These predictions were better than chance for both conventional and radiomics models in the total cohort (<em>p</em> = 0.04, <em>p</em> = 0.003 respectively). The radiomics models outperformed the conventional models during treatment in children only (<em>p</em> = 0.02). At post-treatment, performance was markedly reduced.</div></div><div><h3>Conclusion</h3><div>While conventional and radiomics models performed equally well in predicting clinical improvement across children and adults during treatment, radiomics features offered enhanced structural information beyond conventional region-based volume and FA averages in children. Prediction of symptom improvement one week after treatment cessation was poor, potentially due to the transient effects of stimulant treatment on symptom improvement.</div></div>","PeriodicalId":54359,"journal":{"name":"Neuroimage-Clinical","volume":"45 ","pages":"Article 103707"},"PeriodicalIF":3.4000,"publicationDate":"2024-11-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Neuroimage-Clinical","FirstCategoryId":"3","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2213158224001487","RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"NEUROIMAGING","Score":null,"Total":0}

引用次数: 0

Abstract

Background

Attention-Deficit/Hyperactivity Disorder (ADHD) is commonly treated with methylphenidate (MPH). Although highly effective, MPH treatment still has a relatively high non-response rate of around 30%, highlighting the need for a better understanding of treatment response. Radiomics of T1-weighted images and Diffusion Tensor Imaging (DTI) combined with machine learning approaches could offer a novel method for assessing MPH treatment response.

Purpose

To evaluate the accuracy of both conventional and radiomics approaches in predicting treatment response based on baseline T1 and DTI data in stimulant-naive ADHD participants.

Methods

We performed a secondary analysis of a randomized clinical trial (ePOD-MPH), involving 47 stimulant-naive ADHD participants (23 boys aged 11.4 ± 0.4 years, 24 men aged 28.1 ± 4.3 years) who underwent 16 weeks of treatment with MPH. Baseline T1-weighted and DTI MRI scans were acquired. Treatment response was assessed at 8 weeks (during treatment) and one week after cessation of 16-week treatment (post-treatment) using the Clinical Global Impressions − Improvement scale as our primary outcome. We compared prediction accuracy using a conventional model and a radiomics model. The conventional approach included the volume of bilateral caudate, putamen, pallidum, accumbens, and hippocampus, and for DTI the mean fractional anisotropy (FA) of the entire brain white matter, bilateral Anterior Thalamic Radiation (ATR), and the splenium of the corpus callosum, totaling 14 regional features. For the radiomics approach, 380 features (shape-based and first-order statistics) were extracted from these 14 regions. XGBoost models with nested cross-validation were used and constructed for the total cohort (n = 47), as well as children (n = 23) and adults (n = 24) separately. Exact binomial tests were employed to compare model performance.

Results

For the conventional model, balanced accuracy (bAcc) in predicting treatment response during treatment was 63 % for the total cohort, 32 % for children, and 36 % for adults (Area Under the Receiver Operating Characteristic Curve (AUC-ROC): 0.69, 0.33, 0.41 respectively). Radiomics models demonstrated bAcc’s of 68 %, 64 %, and 64 % during treatment (AUC-ROCs of 0.73, 0.62, 0.69 respectively). These predictions were better than chance for both conventional and radiomics models in the total cohort (p = 0.04, p = 0.003 respectively). The radiomics models outperformed the conventional models during treatment in children only (p = 0.02). At post-treatment, performance was markedly reduced.

Conclusion

While conventional and radiomics models performed equally well in predicting clinical improvement across children and adults during treatment, radiomics features offered enhanced structural information beyond conventional region-based volume and FA averages in children. Prediction of symptom improvement one week after treatment cessation was poor, potentially due to the transient effects of stimulant treatment on symptom improvement.

查看原文本刊更多论文

利用传统和放射组学 T1 和 DTI 特征预测哌醋甲酯治疗多动症的反应：随机临床试验的二次分析

背景注意缺陷/多动障碍（ADHD）通常采用哌醋甲酯（MPH）治疗。虽然哌醋甲酯治疗效果显著，但其无应答率仍相对较高，约为 30%，这凸显了更好地了解治疗反应的必要性。T1加权图像和弥散张量成像（DTI）的放射组学与机器学习方法相结合，可为评估MPH治疗反应提供一种新方法。目的评估传统方法和放射组学方法在根据对刺激无反应的ADHD患者的基线T1和DTI数据预测治疗反应方面的准确性。方法我们对一项随机临床试验（ePOD-MPH）进行了二次分析，该试验涉及 47 名接受了 16 周 MPH 治疗的未受刺激的 ADHD 患者（23 名男孩，年龄为 11.4 ± 0.4 岁；24 名男性，年龄为 28.1 ± 4.3 岁）。获得了基线 T1 加权和 DTI MRI 扫描。在 8 周（治疗期间）和 16 周治疗结束后一周（治疗后），我们使用临床总体印象--改善量表评估治疗反应，并将其作为主要结果。我们比较了传统模型和放射组学模型的预测准确性。传统方法包括双侧尾状核、普特门、苍白球、延脑和海马的体积，DTI 包括整个大脑白质、双侧丘脑前部放射（ATR）和胼胝体脾的平均分数各向异性（FA），共 14 个区域特征。在放射组学方法中，从这 14 个区域中提取了 380 个特征（基于形状和一阶统计）。使用了嵌套交叉验证的 XGBoost 模型，并分别为整个队列（n = 47）、儿童（n = 23）和成人（n = 24）构建了模型。结果对于传统模型，在治疗期间预测治疗反应的平衡准确率（bAcc）为：队列总数 63%，儿童 32%，成人 36%（接收者工作特征曲线下面积 (AUC-ROC)：0.69, 0.33, 0.69, 0.69, 0.33, 0.33）：分别为 0.69、0.33 和 0.41）。放射组学模型显示，治疗期间的 bAcc 分别为 68%、64% 和 64%（AUC-ROC 分别为 0.73、0.62 和 0.69）。在整个队列中，传统模型和放射组学模型的预测结果均优于偶然结果（p = 0.04，p = 0.003）。仅在儿童治疗期间，放射组学模型的表现优于传统模型（p = 0.02）。结论虽然传统模型和放射组学模型在预测儿童和成人治疗期间的临床改善方面表现相当，但放射组学特征在儿童中提供的结构信息比传统的基于区域的容积和 FA 平均值更强。对停止治疗一周后症状改善的预测较差，这可能是由于兴奋剂治疗对症状改善的短暂影响。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Neuroimage-Clinical NEUROIMAGING-

CiteScore

7.50

自引率

4.80%

发文量

368

审稿时长

52 days

期刊介绍： NeuroImage: Clinical, a journal of diseases, disorders and syndromes involving the Nervous System, provides a vehicle for communicating important advances in the study of abnormal structure-function relationships of the human nervous system based on imaging. The focus of NeuroImage: Clinical is on defining changes to the brain associated with primary neurologic and psychiatric diseases and disorders of the nervous system as well as behavioral syndromes and developmental conditions. The main criterion for judging papers is the extent of scientific advancement in the understanding of the pathophysiologic mechanisms of diseases and disorders, in identification of functional models that link clinical signs and symptoms with brain function and in the creation of image based tools applicable to a broad range of clinical needs including diagnosis, monitoring and tracking of illness, predicting therapeutic response and development of new treatments. Papers dealing with structure and function in animal models will also be considered if they reveal mechanisms that can be readily translated to human conditions.