TY - JOUR
T1 - Predicting therapeutic clinical trial enrollment for adult patients with low- and high-grade glioma using supervised machine learning
AU - Mehari, Mulki
AU - Warrier, Gayathri
AU - Dada, Abraham
AU - Kabir, Aymen
AU - Haskell-Mendoza, Aden P.
AU - Tripathy, Arushi
AU - Jha, Rohan
AU - Nieblas-Bedolla, Edwin
AU - Jackson, Joshua D.
AU - Gonzalez, Ariel T.
AU - Reason, Ellery H.
AU - Flusche, Ann Marie
AU - Reihl, Sheantel
AU - Dalton, Tara
AU - Negussie, Mikias
AU - Gonzales, Cesar Nava
AU - Ambati, Vardhaan S.
AU - Desjardins, Annick
AU - Daniel, Andy G.S.
AU - Krishna, Saritha
AU - Chang, Susan
AU - Porter, Alyx
AU - Fecci, Peter E.
AU - Hollon, Todd
AU - Chukwueke, Ugonma N.
AU - Badal, Kimberly
AU - Molinaro, Annette M.
AU - Hervey-Jumper, Shawn L.
N1 - Publisher Copyright:
Copyright © 2025 The Authors, some rights reserved.
PY - 2025/6/6
Y1 - 2025/6/6
N2 - 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 (n = 1042), women (n = 445, 42.7%), and minorities (n = 151, 14.5%) and externally validated these models [whole cohort, n = 230; women, n = 89 (38.7%); minority, n = 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.
AB - 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 (n = 1042), women (n = 445, 42.7%), and minorities (n = 151, 14.5%) and externally validated these models [whole cohort, n = 230; women, n = 89 (38.7%); minority, n = 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.
UR - https://www.scopus.com/pages/publications/105007983126
UR - https://www.scopus.com/pages/publications/105007983126#tab=citedBy
U2 - 10.1126/sciadv.adt5708
DO - 10.1126/sciadv.adt5708
M3 - Article
C2 - 40465719
AN - SCOPUS:105007983126
SN - 2375-2548
VL - 11
JO - Science Advances
JF - Science Advances
IS - 23
M1 - eadt5708
ER -