Assessment of genetic and nongenetic interactions for the prediction of depressive symptomatology: an analysis of the Wisconsin Longitudinal Study using machine learning algorithms

Race-Dependent Association of Single-Nucleotide Polymorphisms in TrkB Receptor in People Living with HIV and Depression

Human immunodeficiency virus (HIV)-associated cognitive disorders (HAND) is characterized by impaired motor and intellectual functions, as well as mood disorders. Brain-derived neurotrophic factor and its receptor TrkB (or NTRK2) mediate the efficacy of antidepressant drugs. Genomic studies of BDNF/TrkB have implicated common single-nucleotide polymorphisms in the pathology of depression. In the current study, we investigated whether single-nucleotide polymorphisms (SNPs) (rs1212171, rs1439050, rs1187352, rs1778933, rs1443445, rs3780645, rs2378672, and rs11140800) in the NTRK2 has a functional impact on depression in HIV-positive subjects. We have utilized the Central Nervous System (CNS) HIV Antiretroviral Therapy Effects Research (CHARTER) cohort. Our methods explored the univariate associations of these SNPs with clinical (current and lifetime) diagnosis of depression via chi-square. The distribution of alleles was significantly different for African-Americans and Caucasians (non-Hispanic) for several SNPs, so our regression analyses included both "statistical controls" for race group and models for each group separately. Finally, we applied a method of simultaneous analysis of associations, estimating the mutually shared information across a system of variables, separately by race group. Our results indicate that there is no significant association between clinical diagnosis of major depression and these SNPs for either race group in any analysis. However, we identified that the SNP associations varied by race group and sex.

Youth Perspectives regarding the Regulating of Bathroom Use by Transgender Individuals

Regulations regarding bathroom use by transgender people affect youth across the United States. This study examines youth opinions on bathroom use regulations. Data were obtained from MyVoice, a weekly text messaging survey of youth aged 14-24 years. Youth were recruited nationally at community events and online; Southeast Michigan was overrepresented. Mixed methods analysis was performed using grounded theory methodology. The majority of respondents (n = 683) were white (71.4%) and had education beyond high school (56.5%). Most (79%) stated that bathroom use by transgender people should not be restricted, rationalizing: 1) bathroom use is private and should be a personal decision; 2) choosing bathrooms is a matter of equality, freedom, and human rights; 3) transgender people are not sexual perpetrators; and 4) forcing transgender people to use particular bathrooms puts them at risk. Contrary to the current policy in many schools, respondents do not support restrictions on bathroom use by transgender people.

A Population-Based Study of Coupling and Physical Activity by Sexual Orientation for Men

Research has suggested that men in relationships are more physically active than men who are single. This study provides a weighted analysis of physical activity by coupling status for men of different sexual orientations. Aggregated data from the United States 2013-2014 National Health Interview Survey were used to conduct multivariate logistic regression analyses. Compared to straight men (n = 29,926), gay men (n = 623) were less likely to be in a relationship (AOR 0.32, CI: 0.25-0.41). Coupled gay men did more physical activity than coupled straight men and were 1.62 (CI: 1.05-2.50) times more likely to be active, 1.67 (CI: 1.10-2.51) times more likely to be high active, 1.89 (CI: 1.24-2.89) times more likely to engage in muscle-strengthening activities, and 2.00 (CI: 1.28-3.11) times more likely to meet aerobic and muscle-strengthening recommendations. Coupling facilitates physical activity for men. However, more research is needed to help explore underlying mechanisms for differences by sexuality.

Development of Classification Models for the Prediction of Alzheimer's Disease Utilizing Circulating Sex Hormone Ratios

BACKGROUND

While sex hormones are essential for normal cognitive health, those individuals with greater endocrine dyscrasia around menopause and with andropause are more likely to develop cognitive loss and Alzheimer's disease (AD).

OBJECTIVE

To assess whether circulating sex hormones may provide an etiologically significant, surrogate biomarker, for cognitive decline.

METHODS

Plasma (n = 152) and serum (n = 107) samples from age- and gender-matched AD and control subjects from the Wisconsin Alzheimer's Disease Research Center (ADRC) were analyzed for 11 steroids and follicle-stimulating hormone. Logistic regression (LR), correlation analyses, and recursive partitioning (RP) were used to examine the interactions of hormones and hormone ratios and their association with AD. Models generated were then tested on an additional 43 ADRC samples.

RESULTS

The wide variation and substantial overlap in the concentrations of all circulating sex steroids across control and AD groups precluded their use for predicting AD. Classification tree analyses (RP) revealed interactions among single hormones and hormone ratios that associated with AD status, the most predictive including only the hormone ratios identified by LR. The strongest associations were observed between cortisol, cortisone, and androstenedione with AD, with contributions from progesterone and 17β-estradiol. Utilizing this model, we correctly predicted 81% of AD test cases and 64% of control test cases.

CONCLUSION

We have developed a diagnostic model for AD, the Wisconsin Hormone Algorithm Test for Cognition (WHAT-Cog), that utilizes classification tree analyses of hormone ratios. Further refinement of this technology could provide a quick and cheap diagnostic method for screening those with AD.

Machine learning classification of ADHD and HC by multimodal serotonergic data

Serotonin neurotransmission may impact the etiology and pathology of attention-deficit and hyperactivity disorder (ADHD), partly mediated through single nucleotide polymorphisms (SNPs). We propose a multivariate, genetic and positron emission tomography (PET) imaging classification model for ADHD and healthy controls (HC). Sixteen patients with ADHD and 22 HC were scanned by PET to measure serotonin transporter (SERT') binding potential with [¹¹C]DASB. All subjects were genotyped for thirty SNPs within the HTR1A, HTR1B, HTR2A and TPH2 genes. Cortical and subcortical regions of interest (ROI) were defined and random forest (RF) machine learning was used for feature selection and classification in a five-fold cross-validation model with ten repeats. Variable selection highlighted the ROI posterior cingulate gyrus, cuneus, precuneus, pre-, para- and postcentral gyri as well as the SNPs HTR2A rs1328684 and rs6311 and HTR1B rs130058 as most discriminative between ADHD and HC status. The mean accuracy for the validation sets across repeats was 0.82 (±0.09) with balanced sensitivity and specificity of 0.75 and 0.86, respectively. With a prediction accuracy above 0.8, the findings underlying the proposed model advocate the relevance of the SERT as well as the HTR1B and HTR2A genes in ADHD and hint towards disease-specific effects. Regarding the high rates of comorbidities and difficult differential diagnosis especially for ADHD, a reliable computer-aided diagnostic tool for disorders anchored in the serotonergic system will support clinical decisions.

Common themes and emerging trends for the use of technology to support mental health and psychosocial well-being in limited resource settings: A review of the literature

There are significant disparities in access to mental health care. With the burgeoning of technologies for health, digital tools have been leveraged within mental health and psychosocial support programming (eMental health). A review of the literature was conducted to understand and identify how eMental health has been used in resource-limited settings in general. PubMed, Ovid Medline and Web of Science were searched. Six-hundred and thirty full-text articles were identified and assessed for eligibility; of those, 67 articles met the inclusion criteria and were analyzed. The most common mental health use cases were for depression (n = 25) and general mental health and well-being (n = 21). Roughly one-third used a website or Internet-enabled intervention (n = 23) and nearly one-third used an SMS intervention (n = 22). Technology was applied to enhance service delivery (n = 32), behavior change communication (n = 26) and data collection (n = 8), and specifically dealt with adherence (n = 7), ecological momentary assessments (n = 7), well-being promotion (n = 5), education (n = 8), telemedicine (n = 28), machine learning (n = 5) and games (n = 2). Emerging trends identified wearables, predictive analytics, robots and virtual reality as promising areas. eMental health interventions that leverage low-tech tools can introduce, strengthen and expand mental health and psychosocial support services and can be a starting point for future, advanced tools.

The Enduring Effects of Mother-Child Interactions on Episodic Memory in Adulthood

OBJECTIVE

To examine the enduring effects of retrospective reports of early life mother-child interactions on psychosocial and cognitive functioning later in life.

BACKGROUND

Mother-child interactions have been linked to cognitive outcomes in childhood, however, little work has examined whether early life mother-child interactions have far-reaching effects on episodic memory in adulthood. Early life mother-child interactions may also influence cognitive functioning in adulthood indirectly through the development of academic competence (education attainment), social competence (marital satisfaction, social support, contact frequency), and/or depressive symptoms.

METHODS

Using longitudinal data from the Wisconsin Longitudinal Study sibling respondents (1993-2011; baseline: 29-79 years), we examined how retrospective positive mother-child interactions (PMCI) and negative mother-child interactions (NMCI) were independently associated with episodic memory. Structural equation modeling was used to model direct and indirect pathways from PMCI and NMCI to episodic memory and latent change in episodic memory.

RESULTS

More PMCI retrospectively reported at T1 were associated with higher T2 memory and less memory decline from T2 to T3 via higher education. Additionally, more PMCI were associated with higher T2 memory through greater marital satisfaction. Independent of these indirect effects, more PMCI and NMCI were each associated with higher T2 memory, but not memory change.

CONCLUSION

Mother-child interactions appeared to have an enduring effect on episodic memory in adulthood. These findings highlight the importance of taking a more integrative and lifespan perspective to assess how early life experiences affect socioemotional and cognitive development.

"We have this awesome organization where it was built by women for women like us": Supporting African American women through their pregnancies and beyond

Infant mortality is a problem that disproportionately affects infants of African American women, particularly residents in underserved neighborhoods. Chronic stress due to racism has been identified as an important factor in infant mortality. This study examined a novel community-based perinatal support professional (PSP) program, Birthing Beautiful Communities (BBC), in Cleveland, Ohio. BBC provides services for pregnant African American women in underserved neighborhoods with the goal of decreasing infant mortality and low birthweight rates by addressing chronic stress. Focus groups and one individual interview were conducted with the program's 14 PSPs, and 25 clients were interviewed individually. Interviews were analyzed inductively using qualitative thematic analysis to identify pervasive themes. Coders identified major themes of stress, resilience, community, cultural matching, advocacy, self-care, transformation, and self-actualization. BBC PSPs and clients alike reported the program is transforming the lives of clients by helping them address stressors. Findings suggest the community-based PSP model is an important but underused intervention in addressing infant mortality.

Self-assessment of clinical competence with LGBT patients at a pediatric hospital

Hospital social workers were asked to complete the LGBT-DOCSS, a validated self-assessment of clinical competence, attitudes, and knowledge about working with lesbian, gay, bisexual (LGB), and transgender patients. As a group, they held positive attitudes about LGBT patients (Mean 6.9/7, SD .22) but were less confident about their knowledge (Mean 5.9/7, SD 0.96) and clinical preparedness (Mean 5.0/7, SD 1.24). In addition, providers felt significantly less competent about working with transgender than LGB patients. Factors that affected domains of self-assessed competence including experience working with LGB or transgender patients and the year training was completed.

Migrant Farmworker Nutritional Strategies: Implications for Diabetes Management

OBJECTIVES

Diabetes is a chronic disease prevalent in Hispanic/Latino adults, including migrant farmworkers in the US. Its management requires that individuals follow dietary guidelines, which may be difficult for migrant farmworkers due to work and environmental constraints. This analysis is designed to explore potential barriers to and supports for migrant farmworkers' practice of effective dietary self-management.

METHODS

Interviews were conducted with 200 Latino migrant farmworkers in North Carolina, including workers with and without diabetes, recruited at housing sites throughout the 2017 agricultural season. The survey instrument included questions designed to elucidate how workers obtain food, prepare and consume food, and maintain food security.

RESULTS

Most purchased food is obtained once per week at large grocery stores, with most farmworkers depending on others for transportation. Less than 1 in 5 supplement with garden produce and food from food pantries, farmers markets, and hunting and fishing. About half of lunches and a quarter of dinners are purchased from vendors or other commercial sources. More than 2 in 5 workers report they have to compromise on or lack control of meal content. About 1 in 5 report issues with food security.

CONCLUSIONS

The food-related practices of farmworkers would require change to accommodate effective dietary self-management of diabetes. Greater use of sources of fresh produce and other nutrient-dense foods, coupled with greater control over meal content and cooking techniques would be needed. While some accommodations could be encouraged through education, others would require policy change in housing or access to community resources.

Is Smoking Queer? Implications of California Tobacco Denormalization Strategies for Queer Current and Former Smokers

This article is concerned with normative conceptions of health structuring tobacco control strategies designed to "denormalize" tobacco use. Analysis of 201 interviews with non-heterosexual and/or non-cisgender adults in California revealed that participants implicated tobacco use in exacerbating health inequities and perpetuating harmful narratives of queer suffering, but also regarded smoking as a critical tool for self-care and symbol of resistance. Participant narratives suggest that using stigma in health promotion efforts which reinforce normative conceptions of health may be harmful to queer people whose social identities exist within ongoing legacies of pathology, health stigma, and deviance from hegemonic structural norms.

Prediction of Autopsy Verified Neuropathological Change of Alzheimer's Disease Using Machine Learning and MRI

Background: Alzheimer’s disease (AD) is the most common form of dementia. While neuropathological changes pathognomonic for AD have been defined, early detection of AD prior to cognitive impairment in the clinical setting is still lacking. Pioneer studies applying machine learning to magnetic-resonance imaging (MRI) data to predict mild cognitive impairment (MCI) or AD have yielded high accuracies, however, an algorithm predicting neuropathological change is still lacking. The objective of this study was to compute a prediction model supporting a more distinct diagnostic criterium for AD compared to clinical presentation, allowing identification of hallmark changes even before symptoms occur.

Methods: Autopsy verified neuropathological changes attributed to AD, as described by a combined score for Aβ-peptides, neurofibrillary tangles and neuritic plaques issued by the National Institute on Aging – Alzheimer’s Association (NIAA), the ABC score for AD, were predicted from structural MRI data with RandomForest (RF). MRI scans were performed at least 2 years prior to death. All subjects derive from the prospective Vienna Trans-Danube Aging (VITA) study that targeted all 1750 inhabitants of the age of 75 in the starting year of 2000 in two districts of Vienna and included irregular follow-ups until death, irrespective of clinical symptoms or diagnoses. For 68 subjects MRI as well as neuropathological data were available and 49 subjects (mean age at death: 82.8 ± 2.9, 29 female) with sufficient MRI data quality were enrolled for further statistical analysis using nested cross-validation (CV). The decoding data of the inner loop was used for variable selection and parameter optimization with a fivefold CV design, the new data of the outer loop was used for model validation with optimal settings in a fivefold CV design. The whole procedure was performed ten times and average accuracies with standard deviations were reported.

Results: The most informative ROIs included caudal and rostral anterior cingulate gyrus, entorhinal, fusiform and insular cortex and the subcortical ROIs anterior corpus callosum and the left vessel, a ROI comprising lacunar alterations in inferior putamen and pallidum. The resulting prediction models achieved an average accuracy for a three leveled NIAA AD score of 0.62 within the decoding sets and of 0.61 for validation sets. Higher accuracies of 0.77 for both sets, respectively, were achieved when predicting presence or absence of neuropathological change.

Conclusion: Computer-aided prediction of neuropathological change according to the categorical NIAA score in AD, that currently can only be assessed post-mortem, may facilitate a more distinct and definite categorization of AD dementia. Reliable detection of neuropathological hallmarks of AD would enable risk stratification at an earlier level than prediction of MCI or clinical AD symptoms and advance precision medicine in neuropsychiatry.

Transgender Identities, Pressures, and Social Policy: A Study Carried Out in Spain

This article draws on a qualitative research project concerning the relationship between trans people's mental health and wellbeing, pressures, social policy, and heteronormative gender norms in Spain. Drawing on interviews carried out with trans people from all regions and generations, we use an ecological framework to illustrate how a socially entrenched heteronormativity pressures trans people to comply with gender norms that impact negatively their mental health and wellbeing. The article argues that the legal changes in Spain are not enough in themselves to bring about social change, but, rather, Spanish social policy makers also need to challenge gender categorization and work toward transforming public discourses on gender issues if trans people are to gain full social recognition and equal social rights.

A Machine Learning Approach to Identify NIH-Funded Applied Prevention Research

INTRODUCTION

To fulfill its mission, the NIH Office of Disease Prevention systematically monitors NIH investments in applied prevention research. Specifically, the Office focuses on research in humans involving primary and secondary prevention, and prevention-related methods. Currently, the NIH uses the Research, Condition, and Disease Categorization system to report agency funding in prevention research. However, this system defines prevention research broadly to include primary and secondary prevention, studies on prevention methods, and basic and preclinical studies for prevention. A new methodology was needed to quantify NIH funding in applied prevention research.

METHODS

A novel machine learning approach was developed and evaluated for its ability to characterize NIH-funded applied prevention research during fiscal years 2012-2015. The sensitivity, specificity, positive predictive value, accuracy, and F1 score of the machine learning method; the Research, Condition, and Disease Categorization system; and a combined approach were estimated. Analyses were completed during June-August 2017.

RESULTS

Because the machine learning method was trained to recognize applied prevention research, it more accurately identified applied prevention grants (F1 = 72.7%) than the Research, Condition, and Disease Categorization system (F1 = 54.4%) and a combined approach (F1 = 63.5%) with p<0.001.

CONCLUSIONS

This analysis demonstrated the use of machine learning as an efficient method to classify NIH-funded research grants in disease prevention.

Machine Learning for Social Services: A Study of Prenatal Case Management in Illinois

OBJECTIVES

To evaluate the positive predictive value of machine learning algorithms for early assessment of adverse birth risk among pregnant women as a means of improving the allocation of social services.

METHODS

We used administrative data for 6457 women collected by the Illinois Department of Human Services from July 2014 to May 2015 to develop a machine learning model for adverse birth prediction and improve upon the existing paper-based risk assessment. We compared different models and determined the strongest predictors of adverse birth outcomes using positive predictive value as the metric for selection.

RESULTS

Machine learning algorithms performed similarly, outperforming the current paper-based risk assessment by up to 36%; a refined paper-based assessment outperformed the current assessment by up to 22%. We estimate that these improvements will allow 100 to 170 additional high-risk pregnant women screened for program eligibility each year to receive services that would have otherwise been unobtainable.

CONCLUSIONS

Our analysis exhibits the potential for machine learning to move government agencies toward a more data-informed approach to evaluating risk and providing social services. Overall, such efforts will improve the efficiency of allocating resource-intensive interventions.

From genomes to societies: a holistic view of determinants of human health

Both biological and social sciences have identified contributing factors to human health. However, health outcomes are unlikely to equal a simple sum of these identified factors. This article makes an attempt to put together the information, methods, and technologies that relate to health outcomes from biological, behavioral, and social disciplines. Much of this information was obtained by controlling for the variations of the factors in 'other' disciplines. For example, genetic factors were controlled for in identifying the behavioral determinants of health. Looking forward, better understandings of health outcomes may require exploiting the interactions of health determinants that were identified from different disciplines. We propose the concept of 'systems health' studies, which take health outcomes as the outputs of a system, where the inputs and their interactions from multiple disciplines are considered.