- Award ID(s):
- 2153083
- PAR ID:
- 10492033
- Publisher / Repository:
- PMLR
- Date Published:
- Journal Name:
- Proceedings of Machine Learning Research
- ISSN:
- 2640-3498
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
Individuals such as medical interns who work in high-stress environments often face mental health challenges including depression and anxiety. These challenges are exacerbated by the limited access to traditional mental health services due to demanding work schedules. In this context, mobile health interventions such as push notifications targeting behavioral modification to improve mental health outcomes could deliver much needed support. In this work, we study the effectiveness of these interventions on subgroups, by studying the conditional average causal effect of these interventions. We design a two step approach for estimating the conditional average causal effect of interventions and identifying specific subgroups of the population who respond positively or negatively to the interventions. The first step of our approach follows existing causal effect estimation approaches, while the second step involves a novel tree-based approach to identify subgroups who respond to the treatment. The novelty in the second step stems from a pruning approach that deploys hypothesis testing to identify subgroups experiencing a statistically significant positive or negative causal effect. Using a semi-simulated dataset, we show that our approach retrieves affected subpopulations with a higher precision than alternatives while maintaining the same recall and accuracy. Using a real dataset with randomized push interventions among the medical intern population at a large hospital, we show how our approach can be used to identify subgroups who might benefit the most from interventions.more » « less
-
Differential measurement error, which occurs when the error in the measured outcome is correlated with the treatment renders the causal effect unidentifiable from observational data. In this work, we study conditional differential measurement error, where a subgroup of the population is known to be prone to differential measurement error. Under an assumption about the direction (but not magnitude) of the measurement error, we derive sharp bounds on the conditional average treatment effect, and present an approach to estimate them. We empirically validate our approach on semi-synthetic da, showing that it gives more credible and informative bound than other approaches. In addition, we implement our approach on real data, showing its utility in guiding decisions about dietary modification intervals to improve nutritional intake.more » « less
-
While one can characterize mental health using questionnaires, such tools do not provide direct insight into the underlying biology. By linking approaches that visualize brain activity to questionnaires in the context of individualized prediction, we can gain new insights into the biology and behavioral aspects of brain health. Resting-state fMRI (rs-fMRI) can be used to identify biomarkers of these conditions and study patterns of abnormal connectivity. In this work, we estimate mental health quality for individual participants using static functional network connectivity (sFNC) data from rs-fMRI. The deep learning model uses the sFNC data as input to predict four categories of mental health quality and visualize the neural patterns indicative of each group. We used guided gradient class activation maps (guided Grad-CAM) to identify the most discriminative sFNC patterns. The effectiveness of this model was validated using the UK Biobank dataset, in which we showed that our approach outperformed four alternative models by 4-18% accuracy. The proposed model’s performance evaluation yielded a classification accuracy of 76%, 78%, 88%, and 98% for the excellent, good, fair, and poor mental health categories, with poor mental health accuracy being the highest. The findings show distinct sFNC patterns across each group. The patterns associated with excellent mental health consist of the cerebellar-subcortical regions, whereas the most prominent areas in the poor mental health category are in the sensorimotor and visual domains. Thus the combination of rs-fMRI and deep learning opens a promising path for developing a comprehensive framework to evaluate and measure mental health. Moreover, this approach had the potential to guide the development of personalized interventions and enable the monitoring of treatment response. Overall this highlights the crucial role of advanced imaging modalities and deep learning algorithms in advancing our understanding and management of mental health.more » « less
-
Abstract Study Objectives Previous research examining toddler sleep problems has relied almost exclusively on variable-centered statistical approaches to analyze these data, which provide helpful information about the development of the average child. The current study examined whether person-centered trajectory analysis, a statistical technique that can identify subgroups of children who differ in their initial level and/or trajectory of sleep problems, has the potential to inform our understanding of toddler sleep problems and their development.
Methods Families (N = 185) were assessed at 12, 24, 30, and 36 months of child age. Latent class growth analysis was used to test for subgroups that differed in their 24–36 month sleep problems. Subgroups were compared on child 36-month externalizing, internalizing, and total problem behaviors, and on 12 month maternal mental health, inter-parental conflict, and maternal parenting behaviors.
Results Results support a four-class solution, with “low, stable,” “low, increasing,” “high, increasing,” and “high decreasing” classes. The classes whose sleep problems persisted or worsened over time had worse behavioral problems than those whose symptoms improved or remained stably low. Additionally, 12 month maternal depression and global symptom severity, intimate partner violence, and maternal harsh-intrusive parenting behaviors discriminated between the classes that had similar levels of 24 month sleep disturbance but who had diverging trajectories over time.
Conclusions This statistical approach appears to have the potential to increase understanding of sleep problem trajectories in the early years of life. Maternal mental health, intimate partner violence, and parenting behaviors may be clinically useful markers of risk for the persistence or development of toddler sleep problems.
-
Lin, Chung-Ying (Ed.)Background University students are increasingly recognized as a vulnerable population, suffering from higher levels of anxiety, depression, substance abuse, and disordered eating compared to the general population. Therefore, when the nature of their educational experience radically changes—such as sheltering in place during the COVID-19 pandemic—the burden on the mental health of this vulnerable population is amplified. The objectives of this study are to 1) identify the array of psychological impacts COVID-19 has on students, 2) develop profiles to characterize students' anticipated levels of psychological impact during the pandemic, and 3) evaluate potential sociodemographic, lifestyle-related, and awareness of people infected with COVID-19 risk factors that could make students more likely to experience these impacts. Methods Cross-sectional data were collected through web-based questionnaires from seven U.S. universities. Representative and convenience sampling was used to invite students to complete the questionnaires in mid-March to early-May 2020, when most coronavirus-related sheltering in place orders were in effect. We received 2,534 completed responses, of which 61% were from women, 79% from non-Hispanic Whites, and 20% from graduate students. Results Exploratory factor analysis on close-ended responses resulted in two latent constructs, which we used to identify profiles of students with latent profile analysis, including high (45% of sample), moderate (40%), and low (14%) levels of psychological impact. Bivariate associations showed students who were women, were non-Hispanic Asian, in fair/poor health, of below-average relative family income, or who knew someone infected with COVID-19 experienced higher levels of psychological impact. Students who were non-Hispanic White, above-average social class, spent at least two hours outside, or less than eight hours on electronic screens were likely to experience lower levels of psychological impact. Multivariate modeling (mixed-effects logistic regression) showed that being a woman, having fair/poor general health status, being 18 to 24 years old, spending 8 or more hours on screens daily, and knowing someone infected predicted higher levels of psychological impact when risk factors were considered simultaneously. Conclusion Inadequate efforts to recognize and address college students’ mental health challenges, especially during a pandemic, could have long-term consequences on their health and education.more » « less