skip to main content


Title: A Bayesian nonparametric approach for inferring drug combination effects on mental health in people with HIV
Abstract

Although combination antiretroviral therapy (ART) with three or more drugs is highly effective in suppressing viral load for people with HIV (human immunodeficiency virus), many ART agents may exacerbate mental health‐related adverse effects including depression. Therefore, understanding the effects of combination ART on mental health can help clinicians personalize medicine with less adverse effects to avoid undesirable health outcomes. The emergence of electronic health records offers researchers' unprecedented access to HIV data including individuals' mental health records, drug prescriptions, and clinical information over time. However, modeling such data is challenging due to high dimensionality of the drug combination space, the individual heterogeneity, and sparseness of the observed drug combinations. To address these challenges, we develop a Bayesian nonparametric approach to learn drug combination effect on mental health in people with HIV adjusting for sociodemographic, behavioral, and clinical factors. The proposed method is built upon the subset‐tree kernel that represents drug combinations in a way that synthesizes known regimen structure into a single mathematical representation. It also utilizes a distance‐dependent Chinese restaurant process to cluster heterogeneous populations while considering individuals' treatment histories. We evaluate the proposed approach through simulation studies, and apply the method to a dataset from the Women's Interagency HIV Study, showing the clinical utility of our model in guiding clinicians to prescribe informed and effective personalized treatment based on individuals' treatment histories and clinical characteristics.

 
more » « less
Award ID(s):
1918854
NSF-PAR ID:
10397039
Author(s) / Creator(s):
 ;  ;  ;  ;  
Publisher / Repository:
Oxford University Press
Date Published:
Journal Name:
Biometrics
Volume:
78
Issue:
3
ISSN:
0006-341X
Format(s):
Medium: X Size: p. 988-1000
Size(s):
["p. 988-1000"]
Sponsoring Org:
National Science Foundation
More Like this
  1. Summary

    Combination antiretroviral therapy (ART) with at least three different drugs has become the standard of care for people with HIV (PWH) due to its exceptional effectiveness in viral suppression. However, many ART drugs have been reported to associate with neuropsychiatric adverse effects including depression, especially when certain genetic polymorphisms exist. Pharmacogenetics is an important consideration for administering combination ART as it may influence drug efficacy and increase risk for neuropsychiatric conditions. Large-scale longitudinal HIV databases provide researchers opportunities to investigate the pharmacogenetics of combination ART in a data-driven manner. However, with more than 30 FDA-approved ART drugs, the interplay between the large number of possible ART drug combinations and genetic polymorphisms imposes statistical modeling challenges. We develop a Bayesian approach to examine the longitudinal effects of combination ART and their interactions with genetic polymorphisms on depressive symptoms in PWH. The proposed method utilizes a Gaussian process with a composite kernel function to capture the longitudinal combination ART effects by directly incorporating individuals’ treatment histories, and a Bayesian classification and regression tree to account for individual heterogeneity. Through both simulation studies and an application to a dataset from the Women’s Interagency HIV Study, we demonstrate the clinical utility of the proposed approach in investigating the pharmacogenetics of combination ART and assisting physicians to make effective individualized treatment decisions that can improve health outcomes for PWH.

     
    more » « less
  2. Abstract Objective

    Multilevel treatment barriers prevent up to 80% of individuals experiencing eating disorders (EDs) from accessing care. This treatment gap creates a critical need to identify interventions that are accessible, easily completable, and optimized for effectiveness by targeting core mechanisms linked to ED onset and maintenance. We propose single‐session interventions (SSIs) as a promising path toward catalyzing innovation in the development of accessible, effective ED interventions. SSIs are structured programs that intentionally involve one encounter with a program or provider; they may serve as stand‐alone or adjunctive clinical supports. All SSIs are built to acknowledge that any session might be someone's last—and that any single session can nonetheless yield meaningful clinical benefit.

    Method

    We define SSIs, summarize research supporting their utility for ED symptoms and other mental health problems, and recommend future directions for work in this domain.

    Results

    Single‐session interventions may hold promise to reduce some ED symptoms and risk factors, including restrictive eating and negative body image. Steps toward realizing this promise include (1) testing whether existing evidence‐based SSIs (e.g., for depression) can also reduce EDs, risk factors, and symptoms; (2) developing novel SSIs that target modifiable ED risk factors and symptoms largely unaddressed by SSIs, such as purging and binge eating; (3) studying diverse implementation pathways; (4) capitalizing on SSIs' transdiagnostic utility to broaden funding opportunities; and (5) educating ED researchers and clinicians about SSIs.

    Discussion

    Understanding the strengths and limits of mechanism‐targeted SSIs for ED‐related problems could be a low‐risk, high‐reward avenue toward reducing EDs at scale.

    Public Significance

    Most individuals experiencing EDs never access any form of treatment, creating an urgent need to identify ED interventions built to overcome barriers to engaging with care. This Forum article introduces SSIs as a promising path to rapidly developing and testing accessible, evidence‐based ED supports; supplementing existing ED treatment models; and reducing the individual, familial, and societal burdens of EDs at scale.

     
    more » « less
  3. Abstract Motivation

    The use of drug combinations, termed polypharmacy, is common to treat patients with complex diseases or co-existing conditions. However, a major consequence of polypharmacy is a much higher risk of adverse side effects for the patient. Polypharmacy side effects emerge because of drug–drug interactions, in which activity of one drug may change, favorably or unfavorably, if taken with another drug. The knowledge of drug interactions is often limited because these complex relationships are rare, and are usually not observed in relatively small clinical testing. Discovering polypharmacy side effects thus remains an important challenge with significant implications for patient mortality and morbidity.

    Results

    Here, we present Decagon, an approach for modeling polypharmacy side effects. The approach constructs a multimodal graph of protein–protein interactions, drug–protein target interactions and the polypharmacy side effects, which are represented as drug–drug interactions, where each side effect is an edge of a different type. Decagon is developed specifically to handle such multimodal graphs with a large number of edge types. Our approach develops a new graph convolutional neural network for multirelational link prediction in multimodal networks. Unlike approaches limited to predicting simple drug–drug interaction values, Decagon can predict the exact side effect, if any, through which a given drug combination manifests clinically. Decagon accurately predicts polypharmacy side effects, outperforming baselines by up to 69%. We find that it automatically learns representations of side effects indicative of co-occurrence of polypharmacy in patients. Furthermore, Decagon models particularly well polypharmacy side effects that have a strong molecular basis, while on predominantly non-molecular side effects, it achieves good performance because of effective sharing of model parameters across edge types. Decagon opens up opportunities to use large pharmacogenomic and patient population data to flag and prioritize polypharmacy side effects for follow-up analysis via formal pharmacological studies.

    Availability and implementation

    Source code and preprocessed datasets are at: http://snap.stanford.edu/decagon.

     
    more » « less
  4. Abstract Objective

    To compare individuals who have experienced binge‐eating disorder (BED) and anorexia nervosa (AN) (BED AN+) to those who have experienced BED and not AN (BED AN–).

    Method

    Participants (N = 898) met criteria for lifetime BED and reported current binge eating. Approximately 14% had a lifetime diagnosis of AN. Analyses compared BED AN+ and BED AN– on sociodemographic variables and clinical history.

    Results

    The presence of lifetimeANwas associated with more severe eating disorder symptoms, including earlier onset, more frequent, more chronic, and more types of eating disorder behaviors over the lifetime, as well as a higher lifetime prevalence of bulimia nervosa (BN). Participants with lifetimeANreported being more likely to have received treatments forBEDorBN, had significantly lower minimum, current, and maximumBMIs, had more severe general anxiety, and were significantly more likely to be younger and female. In the full sample, the lifetime prevalence of unhealthy weight control behaviors was high and treatment utilization was low, despite an average 15‐year history since symptom onset. Gastrointestinal disorders and comorbid anxiety, depression, and attention‐deficit/hyperactivity disorder symptoms were prevalent.

    Discussion

    Individuals fared poorly on a wide array of domains, yet those with lifetimeANfared considerably more poorly. All patients withBEDshould be screened for mental health and gastrointestinal comorbidities and offered referral and treatment options.

    Public Significance

    Individuals experiencing binge‐eating disorder have severe symptomology, but those who have experienced binge‐eating disorder and anorexia nervosa fare even more poorly. Our study emphasizes that patients with binge‐eating disorder would benefit from being screened for mental health and gastrointestinal comorbidities, and clinicians should consider history of unhealthy weight control behaviors to inform treatment and relapse prevention.

     
    more » « less
  5. A Mavragani (Ed.)
    Background

    Posttraumatic stress disorder (PTSD) is a serious public health concern. However, individuals with PTSD often do not have access to adequate treatment. A conversational agent (CA) can help to bridge the treatment gap by providing interactive and timely interventions at scale. Toward this goal, we have developed PTSDialogue—a CA to support the self-management of individuals living with PTSD. PTSDialogue is designed to be highly interactive (eg, brief questions, ability to specify preferences, and quick turn-taking) and supports social presence to promote user engagement and sustain adherence. It includes a range of support features, including psychoeducation, assessment tools, and several symptom management tools.

    Objective

    This paper focuses on the preliminary evaluation of PTSDialogue from clinical experts. Given that PTSDialogue focuses on a vulnerable population, it is critical to establish its usability and acceptance with clinical experts before deployment. Expert feedback is also important to ensure user safety and effective risk management in CAs aiming to support individuals living with PTSD.

    Methods

    We conducted remote, one-on-one, semistructured interviews with clinical experts (N=10) to gather insight into the use of CAs. All participants have completed their doctoral degrees and have prior experience in PTSD care. The web-based PTSDialogue prototype was then shared with the participant so that they could interact with different functionalities and features. We encouraged them to “think aloud” as they interacted with the prototype. Participants also shared their screens throughout the interaction session. A semistructured interview script was also used to gather insights and feedback from the participants. The sample size is consistent with that of prior works. We analyzed interview data using a qualitative interpretivist approach resulting in a bottom-up thematic analysis.

    Results

    Our data establish the feasibility and acceptance of PTSDialogue, a supportive tool for individuals with PTSD. Most participants agreed that PTSDialogue could be useful for supporting self-management of individuals with PTSD. We have also assessed how features, functionalities, and interactions in PTSDialogue can support different self-management needs and strategies for this population. These data were then used to identify design requirements and guidelines for a CA aiming to support individuals with PTSD. Experts specifically noted the importance of empathetic and tailored CA interactions for effective PTSD self-management. They also suggested steps to ensure safe and engaging interactions with PTSDialogue.

    Conclusions

    Based on interviews with experts, we have provided design recommendations for future CAs aiming to support vulnerable populations. The study suggests that well-designed CAs have the potential to reshape effective intervention delivery and help address the treatment gap in mental health.

     
    more » « less