More Like this

1. Uncovering the Varied Impact of Behavioral Change Messages on Population Groups

   Xu, Jiaai; Mihalcea, Rada; Frank, Elena; Sen, Srijan; Makar, Maggie (December 2023, Proceedings of Machine Learning Research)

   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
2. Conditional differential measurement error: partial identifiability and estimation

   Huang, Pengrun; Makar, Maggie (January 2022, NeurIPS workshop on causal machine learning for real world impact)

   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
3. A deep learning approach for mental health quality prediction using functional network connectivity and assessment data

   https://doi.org/10.1007/s11682-024-00857-y  

   Ajith, Meenu; Aycock, Dawn M; Tone, Erin B; Liu, Jingyu; Misiura, Maria B; Ellis, Rebecca; Plis, Sergey M; King, Tricia Z; Dotson, Vonetta M; Calhoun, Vince (February 2024, Brain Imaging and Behavior)

   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
4. Psychological impacts from COVID-19 among university students: Risk factors across seven states in the United States

   https://doi.org/10.1371/journal.pone.0245327  

   Browning, Matthew H.; Larson, Lincoln R.; Sharaievska, Iryna; Rigolon, Alessandro; McAnirlin, Olivia; Mullenbach, Lauren; Cloutier, Scott; Vu, Tue M.; Thomsen, Jennifer; Reigner, Nathan; et al (January 2021, PLOS ONE)

   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
5. Zero-shot causal learning

   Nilforoshan, Hamed; Moor, Michael; Roohani, Yusuf; Chen, Yining; Surina, Anja; Yasunaga, Michihiro; Oblak, Sara; Leskovec, Jure (December 2023, Advances in neural information processing systems)

   Predicting how different interventions will causally affect a specific individual is important in a variety of domains such as personalized medicine, public policy, and online marketing. There are a large number of methods to predict the effect of an existing intervention based on historical data from individuals who received it. However, in many settings it is important to predict the effects of novel interventions (e.g., a newly invented drug), which these methods do not address. Here, we consider zero-shot causal learning: predicting the personalized effects of a novel intervention. We propose CaML, a causal meta-learning framework which formulates the personalized prediction of each intervention’s effect as a task. CaML trains a single meta-model across thousands of tasks, each constructed by sampling an intervention, its recipients, and its nonrecipients. By leveraging both intervention information (e.g., a drug’s attributes) and individual features (e.g., a patient’s history), CaML is able to predict the personalized effects of novel interventions that do not exist at the time of training. Experimental results on real world datasets in large-scale medical claims and cell-line perturbations demonstrate the effectiveness of our approach. Most strikingly, CaML’s zero-shot predictions outperform even strong baselines trained directly on data from the test interventions. 

   more » « less