A machine learning‐derived neuroanatomical pattern predicts delayed reward discounting in the Human Connectome Project Young Adult sample

Abstract

Delayed reward discounting (DRD) is defined as the extent to which person favors smaller rewards that are immediately available over larger rewards available in the future. Higher levels of DRD have been identified in individuals with a wide range of clinical disorders. Although there have been studies adopting larger samples and using only gray matter volume to characterize the neuroanatomical correlates of DRD, it is still unclear whether previously identified relationships are generalizable (out‐of‐sample) and how cortical thickness and cortical surface area contribute to DRD. In this study, using the Human Connectome Project Young Adult dataset (N = 1038), a machine learning cross‐validated elastic net regression approach was used to characterize the neuroanatomical pattern of structural magnetic resonance imaging variables associated with DRD. The results revealed a multi‐region neuroanatomical pattern predicted DRD and this was robust in a held‐out test set (morphometry‐only R2 = 3.34%, morphometry + demographics R2 = 6.96%). The neuroanatomical pattern included regions implicated in the default mode network, executive control network, and salience network. The relationship of these regions with DRD was further supported by univariate linear mixed effects modeling results, in which many of the regions identified as part of this pattern showed significant univariate associations with DRD. Taken together, these findings provide evidence that a machine learning‐derived neuroanatomical pattern encompassing various theoretically relevant brain networks produces robustly predicts DRD in a large sample of healthy young adults.

Two sides of the same coin: distinct neuroanatomical patterns predict crystallized and fluid intelligence in adults

“…Data were drawn from the HCP, which remains one of the largest studies to date with contemporaneously collected Gc, Gf, and sMRI data. This study conducted ENR models with the CV approach, which is well suited to assess the overfitting and generalization of findings ( Xu et al, 2023a ). This approach simultaneously investigates all brain morphological variables as predictors of a target.…”

Neuroanatomical profile of BMI implicates impulsive delay discounting and general cognitive ability

“…Lower AUC represents less steep DRD, which conceptually reflects superior ability to delay gratification. For more details about DRD, see previous research [16].…”

“…Impulsive DRD was obtained from two tasks asking participants to select between smaller amounts of money available immediately or a larger amount after a delay in HCP [16]. Two different dollar amounts were used as the larger delayed reward: $200 or $40,000, which were held constant as the smaller immediate reward and delay period varied.…”

“…Moreover, obesity was significantly associated with cortical and subcortical abnormalities in major depressive disorder ( N = 6420) [15]. However, these studies have been largely conducted using mass univariate approaches without tests of statistical robustness, such as cross‐validation (CV), which has been shown to increase risks of overfitting [16]. In contrast, it has been shown that machine learning approaches with CV can assess and prevent overfitting more effectively than univariate approaches and ultimately lead to more generalizable findings [17].…”