Mehari Mulki, Warrier Gayathri, Dada Abraham, Kabir Aymen, Haskell-Mendoza Aden P, Tripathy Arushi, Jha Rohan, Nieblas-Bedolla Edwin, Jackson Joshua D, Gonzalez Ariel T, Reason Ellery H, Flusche Ann Marie, Reihl Sheantel, Dalton Tara, Negussie Mikias, Gonzales Cesar Nava, Ambati Vardhaan S, Desjardins Annick, Daniel Andy G S, Krishna Saritha, Chang Susan, Porter Alyx, Fecci Peter E, Hollon Todd, Chukwueke Ugonma N, Badal Kimberly, Molinaro Annette M, Hervey-Jumper Shawn L
Department of Neurosurgery, University of California, San Francisco, San Francisco, CA 94143, USA.
Department of Neurosurgery, Duke University Medical Center, Durham, NC 27710, USA.
Sci Adv. 2025 Jun 6;11(23):eadt5708. doi: 10.1126/sciadv.adt5708. Epub 2025 Jun 4.
Therapeutic clinical trial enrollment does not match glioma incidence across demographics. Traditional statistical methods have identified independent predictors of trial enrollment; however, our understanding of the interactions between these factors remains limited. To test the interactive effects of demographic, socioeconomic, and oncologic variables on trial enrollment, we designed boosted neural networks (BNNs) for all glioma patients ( = 1042), women ( = 445, 42.7%), and minorities ( = 151, 14.5%) and externally validated these models [whole cohort, = 230; women, = 89 (38.7%); minority, = 66 (28.7%)]. For the whole-cohort BNN, the most influential variables on enrollment were oncologic variables, including KPS [total effect (TE), 0.327], chemotherapy (TE, 0.326), tumor location (TE, 0.322), and seizures (TE, 0.239). The women-only BNN exhibited a similar trend. Conversely, for the minority-only BNN, socioeconomic variables [insurance status (TE, 0.213), occupation classification (TE, 0.204), and employment status (TE, 0.150)] were most influential. These results may help prioritize patient-specific initiatives to increase accrual.
治疗性临床试验的入组情况在不同人口统计学特征中与胶质瘤发病率不匹配。传统统计方法已确定了试验入组的独立预测因素；然而，我们对这些因素之间相互作用的理解仍然有限。为了测试人口统计学、社会经济和肿瘤学变量对试验入组的交互作用，我们为所有胶质瘤患者（n = 1042）、女性患者（n = 445，42.7%）和少数族裔患者（n = 151，14.5%）设计了增强神经网络（BNN），并对这些模型进行了外部验证[全队列，n = 230；女性，n = 89（38.7%）；少数族裔，n = 66（28.7%）]。对于全队列BNN，对入组影响最大的变量是肿瘤学变量，包括 Karnofsky 功能状态评分（KPS）[总效应（TE），0.327]、化疗（TE，0.326）、肿瘤位置（TE，0.322）和癫痫发作（TE，0.239）。仅针对女性的BNN呈现出类似趋势。相反，对于仅针对少数族裔的BNN，社会经济变量[保险状况（TE，0.213）、职业分类（TE，0.204）和就业状况（TE，0.150）]影响最大。这些结果可能有助于确定针对特定患者的举措的优先级，以增加入组人数。
