Predictive modeling of suicidal ideation in patients with epilepsy.

OBJECTIVE: The prevalence of suicide in the United States has seen an increasing trend and is responsible for 1.6% of all mortality nationwide. Although suicide has the potential to broadly impact the entire population, it has a substantially increased prevalence in persons with epilepsy (PWE), despite many of these individuals consistently seeing a health care provider. The goal of this work is to predict the development of suicidal ideation (SI) in PWE using machine learning methodology such that providers can be better prepared to address suicidality at visits where it is likely to be prominent. METHODS: The current study leverages data collected at an epilepsy clinic during patient visits to predict whether an individual will exhibit SI at their next visit. The data used for prediction consisted of patient responses to questions about the severity of their epilepsy, issues with memory/concentration, somatic problems, markers for mental health, and demographic information. A machine learning approach was then applied to predict whether an individual would display SI at their following visit using only data collected at the prior visit. RESULTS: The modeling approach allowed for the successful prediction of an individual's passive and active SI severity at the following visit (r = .42, r = .39) as well as the presence of SI regardless of severity (area under the curve [AUC] = .82, AUC = .8). This shows that the model was successfully able to synthesize the unique combination of an individual's responses to important questions during a clinical visit and utilize that information to indicate whether that individual will exhibit SI at their next visit. SIGNIFICANCE: The results of this modeling approach allow the health care team to be prepared, in advance of a clinical visit, for the potential reporting of SI. By allowing the necessary support to be prepared ahead of time, it can be better integrated at the point of care, where patients are most likely to follow up on potential referrals or treatment.

Phospho-valproic acid (MDC-1112) suppresses glioblastoma growth in preclinical models through the inhibition of STAT3 phosphorylation.

New therapeutic strategies against glioblastoma multiforme (GBM) are urgently needed. Signal transducer and activator of transcription 3 (STAT3), constitutively active in many GBM tumors, plays a major role in GBM tumor growth and represents a potential therapeutic target. We have documented previously that phospho-valproic acid (MDC-1112), which inhibits STAT3 activation, possesses strong anticancer properties in multiple cancer types. In this study, we explored the anticancer efficacy of MDC-1112 in preclinical models of GBM, and evaluated its mode of action. MDC-1112 inhibited the growth of multiple human GBM cell lines in a concentration- and time-dependent manner. Normal human astrocytes were resistant to MDC-1112, indicating selectivity. In vivo, MDC-1112 reduced the growth of subcutaneous GBM xenografts in mice by up to 78.2% (P < 0.01), compared with the controls. Moreover, MDC-1112 extended survival in an intracranial xenograft model. Although all vehicle-treated mice died by 19 days of treatment, 7 of 11 MDC-1112-treated mice were alive and healthy by the end of 5 weeks, with many showing tumor regression. Mechanistically, MDC-1112 inhibited STAT3 phosphorylation at the serine 727 residue, but not at tyrosine 705, in vitro and in vivo. STAT3 overexpression rescued GBM cells from the cell growth inhibition by MDC-1112. In addition, MDC-1112 reduced STAT3 levels in the mitochondria and enhanced mitochondrial levels of reactive oxygen species, which triggered apoptosis. In conclusion, MDC-1112 displays strong efficacy in preclinical models of GBM, with the serine 727 residue of STAT3 being its key molecular target. MDC-1112 merits further evaluation as a drug candidate for GBM. New therapeutic options are needed for glioblastoma. The novel agent MDC-1112 is an effective anticancer agent in multiple animal models of glioblastoma, and its mechanism of action involves the inhibition of STAT3 phosphorylation, primarily at its Serine 727 residue.

Development and evaluation of a multimodal marker of major depressive disorder.

This study aimed to identify biomarkers of major depressive disorder (MDD), by relating neuroimage-derived measures to binary (MDD/control), ordinal (severe MDD/mild MDD/control), or continuous (depression severity) outcomes. To address MDD heterogeneity, factors (severity of psychic depression, motivation, anxiety, psychosis, and sleep disturbance) were also used as outcomes. A multisite, multimodal imaging (diffusion MRI [dMRI] and structural MRI [sMRI]) cohort (52 controls and 147 MDD patients) and several modeling techniques-penalized logistic regression, random forest, and support vector machine (SVM)-were used. An additional cohort (25 controls and 83 MDD patients) was used for validation. The optimally performing classifier (SVM) had a 26.0% misclassification rate (binary), 52.2 ± 1.69% accuracy (ordinal) and r = .36 correlation coefficient (p < .001, continuous). Using SVM, R2 values for prediction of any MDD factors were <10%. Binary classification in the external data set resulted in 87.95% sensitivity and 32.00% specificity. Though observed classification rates are too low for clinical utility, four image-based features contributed to accuracy across all models and analyses-two dMRI-based measures (average fractional anisotropy in the right cuneus and left insula) and two sMRI-based measures (asymmetry in the volume of the pars triangularis and the cerebellum) and may serve as a priori regions for future analyses. The poor accuracy of classification and predictive results found here reflects current equivocal findings and sheds light on challenges of using these modalities for MDD biomarker identification. Further, this study suggests a paradigm (e.g., multiple classifier evaluation with external validation) for future studies to avoid nongeneralizable results.

A novel tricarbonylmethane agent (CMC2.24) reduces human pancreatic tumor growth in mice by targeting Ras.

Pancreatic Cancer (PC) is a deadly disease in need of new therapeutic options. We recently developed a novel tricarbonylmethane agent (CMC2.24) as a therapeutic agent for PC, and evaluated its efficacy in preclinical models of PC. CMC2.24 inhibited the growth of various human PC cell lines in a concentration and time-dependent manner. Normal human pancreatic epithelial cells were resistant to CMC2.24, indicating selectivity. CMC2.24 reduced the growth of subcutaneous and orthotopic PC xenografts in mice by up to 65% (P < 0.02), and the growth of a human patient-derived tumor xenograft by 47.5% (P < 0.03 vs vehicle control). Mechanistically, CMC2.24 inhibited the Ras-RAF-MEK-ERK pathway. Based on Ras Pull-Down Assays, CMC2.24 inhibited Ras-GTP, the active form of Ras, in MIA PaCa-2 cells and in pancreatic acinar explants isolated from Kras mutant mice, by 90.3% and 89.1%, respectively (P < 0.01, for both). The inhibition of active Ras led to an inhibition of c-RAF, MEK, and ERK phosphorylation by 93%, 91%, and 87%, respectively (P < 0.02, for all) in PC xenografts. Furthermore, c-RAF overexpression partially rescued MIA PaCa-2 cells from the cell growth inhibition by CMC2.24. In addition, downstream of ERK, CMC2.24 inhibited STAT3 phosphorylation levels at the serine 727 residue, enhanced the levels of superoxide anion in mitochondria, and induced intrinsic apoptosis as shown by the release of cytochrome c from the mitochondria to the cytosol and the further cleavage of caspase 9 in PC cells. In conclusion, CMC2.24, a potential Ras inhibitor, is an efficacious agent for PC treatment in preclinical models, deserving further evaluation.

The role of borderline personality disorder traits in predicting longitudinal variability of major depressive symptoms among a sample of depressed adults.

BACKGROUND: Major depressive disorder (MDD) and borderline personality disorder (BPD) often co-occur, with 20 % of adults with MDD meeting criteria for BPD. While MDD is typically diagnosed by symptoms persisting for several weeks, research suggests a dynamic pattern of symptom changes occurring over shorter durations. Given the diagnostic focus on affective states in MDD and BPD, with BPD characterized by instability, we expected heightened instability of MDD symptoms among depressed adults with BPD traits. The current study examined whether BPD symptoms predicted instability in depression symptoms, measured by ecological momentary assessments (EMAs). METHODS: The sample included 207 adults with MDD (76 % White, 82 % women) recruited from across the United States. At the start of the study, participants completed a battery of mental health screens including BPD severity and neuroticism. Participants completed EMAs tracking their depression symptoms three times a day over a 90-day period. RESULTS: Using self-report scores assessing borderline personality disorder (BPD) traits along with neuroticism scores and sociodemographic data, Bayesian and frequentist linear regression models consistently indicated that BPD severity was not associated with depression symptom change through time. LIMITATIONS: Diagnostic sensitivity and specificity may be restricted by use of a self-report screening tool for capturing BPD severity. Additionally, this clinical sample of depressed adults lacks a comparison group to determine whether subclinical depressive symptoms present differently among individuals with BPD only. CONCLUSIONS: The unexpected findings shed light on the interplay between these disorders, emphasizing the need for further research to understand their association.

Depressive symptoms as a heterogeneous and constantly evolving dynamical system: Idiographic depressive symptom networks of rapid symptom changes among persons with major depressive disorder.

Major depressive disorder (MDD) is conceptualized by individual symptoms occurring most of the day for at least two weeks. Despite this operationalization, MDD is highly variable with persons showing greater variation within and across days. Moreover, MDD is highly heterogeneous, varying considerably across people in both function and form. Recent efforts have examined MDD heterogeneity byinvestigating how symptoms influence one another over time across individuals in a system; however, these efforts have assumed that symptom dynamics are static and do not dynamically change over time. Nevertheless, it is possible that individual MDD system dynamics change continuously across time. Participants (N = 105) completed ratings of MDD symptoms three times a day for 90 days, and we conducted time varying vector autoregressive models to investigate the idiographic symptom networks. We then illustrated this finding with a case series of five persons with MDD. Supporting prior research, results indicate there is high heterogeneity across persons as individual network composition is unique from person to person. In addition, for most persons, individual symptom networks change dramatically across the 90 days, as evidenced by 86% of individuals experiencing at least one change in their most influential symptom and the median number of shifts being 3 over the 90 days. Additionally, most individuals had at least one symptom that acted as both the most and least influential symptom at any given point over the 90-day period. Our findings offer further insight into short-term symptom dynamics, suggesting that MDD is heterogeneous both across and within persons over time. (PsycInfo Database Record (c) 2024 APA, all rights reserved).

MoodCapture: Depression Detection Using In-the-Wild Smartphone Images.

MoodCapture presents a novel approach that assesses depression based on images automatically captured from the front-facing camera of smartphones as people go about their daily lives. We collect over 125,000 photos in the wild from N=177 participants diagnosed with major depressive disorder for 90 days. Images are captured naturalistically while participants respond to the PHQ-8 depression survey question: "I have felt down, depressed, or hopeless". Our analysis explores important image attributes, such as angle, dominant colors, location, objects, and lighting. We show that a random forest trained with face landmarks can classify samples as depressed or non-depressed and predict raw PHQ-8 scores effectively. Our post-hoc analysis provides several insights through an ablation study, feature importance analysis, and bias assessment. Importantly, we evaluate user concerns about using MoodCapture to detect depression based on sharing photos, providing critical insights into privacy concerns that inform the future design of in-the-wild image-based mental health assessment tools.

From mood to use: Using ecological momentary assessments to examine how anhedonia and depressed mood impact cannabis use in a depressed sample.

Anhedonia and depressed mood are two cardinal symptoms of major depressive disorder (MDD). Prior work has demonstrated that cannabis consumers often endorse anhedonia and depressed mood, which may contribute to greater cannabis use (CU) over time. However, it is unclear (1) how the unique influence of anhedonia and depressed mood affect CU and (2) how these symptoms predict CU over more proximal periods of time, including the next day or week (rather than proceeding weeks or months). The current study used data collected from ecological momentary assessment (EMA) in a sample with MDD (N = 55) and employed mixed effects models to detect and predict weekly and daily CU from anhedonia and depressed mood over 90 days. Results indicated that anhedonia and depressed mood were significantly associated with CU, yet varied at daily and weekly scales. Moreover, these associations varied in both strength and directionality. In weekly models, less anhedonia and greater depressed mood were associated with greater CU, and directionality of associations were reversed in the models looking at any CU (compared to none). Findings provide evidence that anhedonia and depressed mood demonstrate complex associations with CU and emphasize leveraging EMA-based studies to understand these associations with more fine-grained detail.

Applying ensemble machine learning models to predict individual response to a digitally delivered worry postponement intervention.

OBJECTIVE: Generalized anxiety disorder (GAD) is a prevalent mental health disorder that often goes untreated. A core aspect of GAD is worry, which is associated with negative health outcomes, accentuating a need for simple treatments for worry. The present study leveraged pretreatment individual differences to predict personalized treatment response to a digital intervention. METHODS: Linear mixed-effect models were used to model changes in daytime and nighttime worry duration and frequency for 163 participants who completed a six-day worry postponement intervention. Ensemble-based machine learning regression and classification models were implemented to predict changes in worry across the intervention. Model feature importance was derived using SHapley Additive exPlanation (SHAP). RESULTS: Moderate predictive performance was obtained for predicting changes in daytime worry duration (test r2 = 0.221, AUC = 0.77) and nighttime worry frequency (test r2 = 0.164, AUC = 0.72), while poor predictive performance was obtained for nighttime worry duration and daytime worry frequency. Baseline levels of worry and subjective health complaints were most important in driving model predictions. LIMITATIONS: A complete-case analysis was leveraged to analyze the present data, which was collected from participants that were Dutch and majority female. CONCLUSIONS: This study suggests that treatment response to a digital intervention for GAD can be accurately predicted using baseline characteristics. Particularly, this worry postponement intervention may be most beneficial for individuals with high baseline worry but fewer subjective health complaints. The present findings highlight the complexities of and need for further research into daily worry dynamics and the personalizable utility of digital interventions.

Leveraging deep learning models to understand the daily experience of anxiety in teenagers over the course of a year.

INTRODUCTION: Anxiety disorders are a prevalent and severe problem that are often developed early in life and can disrupt the daily lives of affected individuals for many years into adulthood. Given the persistent negative aspects of anxiety, accurate and early assessment is critical for long term outcomes. Currently, the most common method for anxiety assessment is through point-in-time measures like the GAD-7. Unfortunately, this survey and others like it can be subject to recall bias and do not fully capture the variability in an individual's day-to-day symptom experience. The current work aims to evaluate how point-in-time assessments like the GAD-7 relate to daily measurements of anxiety in a teenage population. METHODS: To evaluate this relationship, we leveraged data collected at four separate three week intervals from 30 teenagers (age 15-17) over the course of a year. The specific items of interest were a single item anxiety severity measure collected three times per day and end-of-month GAD-7 assessments. Within this sample, 40 % of individuals reported clinical levels of generalized anxiety disorder symptoms at some point during the study. The first component of analysis was a visual inspection assessing how daily anxiety severity fluctuated around end-of-month reporting via the GAD-7. The second component was a between-subjects comparison assessing whether individuals with similar GAD-7 scores experienced similar symptom dynamics across the month as represented by latent features derived from a deep learning model. With this approach, similarity was operationalized by hierarchical clustering of the latent features. RESULTS: The aim clearly indicated that an individual's daily experience of anxiety varied widely around what was captured by the GAD-7. Additionally, when hierarchical clustering was applied to the three latent features derived from the (LSTM) encoder (r = 0.624 for feature reconstruction), it was clear that individuals with similar GAD-7 outcomes were experiencing different symptom dynamics. Upon further inspection of the latent features, the LSTM model appeared to rely as much on anxiety variability over the course of the month as it did on anxiety severity (p < 0.05 for both mean and RMSSD) to represent an individual's experience. DISCUSSION: This work serves as further evidence for the heterogeneity within the experience of anxiety and that more than just point-in-time assessments are necessary to fully capture an individual's experience.

Using digital phenotyping to capture depression symptom variability: detecting naturalistic variability in depression symptoms across one year using passively collected wearable movement and sleep data.

Major Depressive Disorder (MDD) presents considerable challenges to diagnosis and management due to symptom variability across time. Only recent work has highlighted the clinical implications for interrogating depression symptom variability. Thus, the present work investigates how sociodemographic, comorbidity, movement, and sleep data is associated with long-term depression symptom variability. Participant information included (N = 939) baseline sociodemographic and comorbidity data, longitudinal, passively collected wearable data, and Patient Health Questionnaire-9 (PHQ-9) scores collected over 12 months. An ensemble machine learning approach was used to detect long-term depression symptom variability via: (i) a domain-driven feature selection approach and (ii) an exhaustive feature-inclusion approach. SHapley Additive exPlanations (SHAP) were used to interrogate variable importance and directionality. The composite domain-driven and exhaustive inclusion models were both capable of moderately detecting long-term depression symptom variability (r = 0.33 and r = 0.39, respectively). Our results indicate the incremental predictive validity of sociodemographic, comorbidity, and passively collected wearable movement and sleep data in detecting long-term depression symptom variability.

Evaluating change in body image concerns following a single session digital intervention.

Many young individuals at risk for eating disorders spend time on social media and frequently search for information related to their body image concerns. In a large randomized study, we demonstrated that a guided chat-based intervention could reduce weight and shape concerns and eating disorder pathology. The goal of the current study was to determine if a modified single session mini-course, derived from the aforementioned chat-based intervention, could reduce body image concerns among individuals using eating disorder related search terms on a social media platform. Over a two-month period of prompting individuals, 525 people followed the link to the web-based application where the intervention was hosted and subsequently completed the mini-course. This resulted in a significant improvement on the one-time body image satisfaction question pre-to post intervention (p < .001) with a moderate effect size (Cohen's d = 0.54). Additionally, individuals completing the program showed significant improvement on motivation to change their body image (p < .001) with a small effect size (Cohen's d = 0.28). Additionally, users reported that the program was enjoyable and easy to use. These results suggest that a single session micro-intervention, offered to individuals on social media, can help improve body image.

An unsupervised machine learning approach using passive movement data to understand depression and schizophrenia.

INTRODUCTION: Schizophrenia and Major Depressive Disorder (MDD) are highly burdensome mental disorders, with significant cost to both individuals and society. Despite these disorders representing distinct clinical categories, they are each heterogenous in their symptom profiles, with considerable transdiagnostic features. Although movement and sleep abnormalities exist in both disorders, little is known of the precise nature of these changes longitudinally. Passively-collected longitudinal data from wearable sensors is well suited to characterize naturalistic features which may cross traditional diagnostic categories (e.g., highlighting behavioral markers not captured by self-report information). METHODS: The present analyses utilized raw minute-level actigraphy data from three diagnostic groups: individuals with schizophrenia (N = 23), individuals with depression (N = 22), and controls (N = 32), respectively, to interrogate naturalistic behavioral differences between groups. Subjects' week-long actigraphy data was processed without diagnostic labels via unsupervised machine learning clustering methods, in order to investigate the natural bounds of psychopathology. Further, actigraphic data was analyzed across time to determine timepoints influential in model outcomes. RESULTS: We find distinct actigraphic phenotypes, which differ between diagnostic groups, suggesting that unsupervised clustering of naturalistic data aligns with existing diagnostic constructs. Further, we found statistically significant inter-group differences, with depressed persons showing the highest behavioral variability. LIMITATIONS: However, diagnostic group differences only consider biobehavioral trends captured by raw actigraphy information. CONCLUSIONS: Passively-collected movement information combined with unsupervised deep learning algorithms shows promise in identifying naturalistic phenotypes in individuals with mental health disorders, specifically in discriminating between MDD and schizophrenia.

Predicting symptom response and engagement in a digital intervention among individuals with schizophrenia and related psychoses.

Introduction: Despite existing work examining the effectiveness of smartphone digital interventions for schizophrenia at the group level, response to digital treatments is highly variable and requires more research to determine which persons are most likely to benefit from a digital intervention. Materials and methods: The current work utilized data from an open trial of patients with psychosis (N = 38), primarily schizophrenia spectrum disorders, who were treated with a psychosocial intervention using a smartphone app over a one-month period. Using an ensemble of machine learning models, pre-intervention data, app use data, and semi-structured interview data were utilized to predict response to change in symptom scores, engagement patterns, and qualitative impressions of the app. Results: Machine learning models were capable of moderately (r = 0.32-0.39, R2 = 0.10-0.16, MAE norm = 0.13-0.29) predicting interaction and experience with the app, as well as changes in psychosis-related psychopathology. Conclusion: The results suggest that individual smartphone digital intervention engagement is heterogeneous, and symptom-specific baseline data may be predictive of increased engagement and positive qualitative impressions of digital intervention in patients with psychosis. Taken together, interrogating individual response to and engagement with digital-based intervention with machine learning provides increased insight to otherwise ignored nuances of treatment response.

Association of Selective Serotonin Reuptake Inhibitor Use With Abnormal Physical Movement Patterns as Detected Using a Piezoelectric Accelerometer and Deep Learning in a Nationally Representative Sample of Noninstitutionalized Persons in the US.

Importance: Selective serotonin reuptake inhibitors (SSRIs) are a common first-line treatment for some psychiatric disorders, including depression and anxiety; although they are generally well tolerated, SSRIs have known adverse effects, including movement problems, sleep disruption, and gastrointestinal problems (eg, nausea and upset stomach). No large-scale studies using naturalistic, longitudinal, objective data have validated physical activity findings, and actigraphy data are well suited to address this task. Objectives: To evaluate whether differences in physical movement exist among individuals treated with SSRIs compared with control participants and to identify the unique features of the movement of patients treated with SSRIs. Design, Setting, and Participants: This cross-sectional study examines longitudinally collected wearable movement data within a cross-sectional sample of 7162 participants from the 2005-2006 National Health and Nutrition Examination Survey (NHANES), a nationally representative population-based sample of noninstitutionalized persons in the US having both medication information and passive movement data. Statistical analysis was performed from April 1, 2021, to February 1, 2022. Exposures: The use of SSRIs (sertraline hydrochloride, escitalopram oxalate, fluoxetine hydrochloride, paroxetine hydrochloride, and citalopram hydrobromide), as reported by participants interviewed by NNHANES personnel, was the primary exposure, measured as a binary variable (taking an SSRI vs not taking an SSRI). Main Outcomes and Measures: The primary outcome was the intensity of body movement as recorded by a piezoelectric accelerometer worn on the right hip for more than 1 week. Results: Of the 7162 participants included in the study, the mean (SD) age was 33.7 (22.6) years, 266 (3.7%) were taking an SSRI, 3706 (51.7%) were female, 1934 (27.0%) were Black, 1823 (25.5%) were Mexican American, 210 (2.9%) were other Hispanic, 336 (4.7%) were other or multiracial, and 2859 (39.9%) were White (per the NHANES data collection protocol). A cross-validated, deep learning classifier was constructed that achieved fair performance predicting SSRI use (area under the curve, 0.67 [95% CI, 0.64-0.71] for the validation set and 0.66 [95% CI, 0.64-0.68] for the test set). To account for possible confounding by indication, we constructed a parallel model incorporating depression severity, finding only marginal performance improvement. When averaged across individuals and across 7 days, the results show less overall movement in the SSRI group (mean, 120.1 vertical acceleration counts/min [95% CI, 115.7-124.6 vertical acceleration counts/min]) compared with the non-SSRI control group (mean, 168.8 vertical acceleration counts/min [95% CI, 162.8-174.9 vertical acceleration counts/min]). Conclusions and Relevance: This cross-sectional study found a moderate association between passive movement and SSRI use, as well as SSRI detection capacity of passive movement using time series deep learning models. The results support the use of passive sensors for exploration and characterization of psychotropic medication adverse effects.

Using Artificial Intelligence to Predict Change in Depression and Anxiety Symptoms in a Digital Intervention: Evidence from a Transdiagnostic Randomized Controlled Trial.

While digital psychiatric interventions reduce treatment barriers, not all persons benefit from this type of treatment. Research is needed to preemptively identify who is likely to benefit from these digital treatments in order to redirect those people to a higher level of care. The current manuscript used an ensemble of machine learning methods to predict changes in major depressive and generalized anxiety disorder symptoms from pre to 9-month follow-up in a randomized controlled trial of a transdiagnostic digital intervention based on participants' (N=632) pre-treatment data. The results suggested that baseline characteristics could accurately predict changes in depressive symptoms in both treatment groups (r=0.482, 95% CI[0.394, 0.561]; r=0.477, 95% CI[0.385, 0.560]) and anxiety symptoms in both treatment groups (r=0.569, 95% CI[0.491, 0.638]; r=0.548, 95% CI[0.464, 0.622]). These results suggest that machine learning models are capable of preemptively predicting a person's responsiveness to digital treatments, which would enable personalized decision-making about which persons should be directed towards standalone digital interventions or towards blended stepped-care.

Predictive modeling of depression and anxiety using electronic health records and a novel machine learning approach with artificial intelligence.

Generalized anxiety disorder (GAD) and major depressive disorder (MDD) are highly prevalent and impairing problems, but frequently go undetected, leading to substantial treatment delays. Electronic health records (EHRs) collect a great deal of biometric markers and patient characteristics that could foster the detection of GAD and MDD in primary care settings. We approached the problem of predicting MDD and GAD using a novel machine learning pipeline to re-analyze data from an observational study. The pipeline constitutes an ensemble of algorithmically distinct machine learning methods, including deep learning. A sample of 4,184 undergraduate students completed the study, undergoing a general health screening and completing a psychiatric assessment for MDD and GAD. After explicitly excluding all psychiatric information, 59 biomedical and demographic features from the general health survey in addition to a set of engineered features were used for model training. We assessed the model's performance on a held-out test set and found an AUC of 0.73 (sensitivity: 0.66, specificity: 0.7) and 0.67 (sensitivity: 0.55, specificity: 0.7) for GAD, and MDD, respectively. Additionally, we used advanced techniques (SHAP values) to illuminate which features had the greatest impact on prediction for each disease. The top predictive features for MDD were being satisfied with living conditions and having public health insurance. The top predictive features for GAD were vaccinations being up to date and marijuana use. Our results indicate moderate predictive performance for the application of machine learning methods in detection of GAD and MDD based on EHR data. By identifying important predictors of GAD and MDD, these results may be used in future research to aid in the early detection of MDD and GAD.

A measure of local uniqueness to identify linchpins in a social network with node attributes.

Network centrality measures assign importance to influential or key nodes in a network based on the topological structure of the underlying adjacency matrix. In this work, we define the importance of a node in a network as being dependent on whether it is the only one of its kind among its neighbors' ties. We introduce linchpin score, a measure of local uniqueness used to identify important nodes by assessing both network structure and a node attribute. We explore linchpin score by attribute type and examine relationships between linchpin score and other established network centrality measures (degree, betweenness, closeness, and eigenvector centrality). To assess the utility of this measure in a real-world application, we measured the linchpin score of physicians in patient-sharing networks to identify and characterize important physicians based on being locally unique for their specialty. We hypothesized that linchpin score would identify indispensable physicians who would not be easily replaced by another physician of their specialty type if they were to be removed from the network. We explored differences in rural and urban physicians by linchpin score compared with other network centrality measures in patient-sharing networks representing the 306 hospital referral regions in the United States. We show that linchpin score is uniquely able to make the distinction that rural specialists, but not rural general practitioners, are indispensable for rural patient care. Linchpin score reveals a novel aspect of network importance that can provide important insight into the vulnerability of health care provider networks. More broadly, applications of linchpin score may be relevant for the analysis of social networks where interdisciplinary collaboration is important.

Assessment of Imputation Methods for Missing Gene Expression Data in Meta-Analysis of Distinct Cohorts of Tuberculosis Patients.

The growth of publicly available repositories, such as the Gene Expression Omnibus, has allowed researchers to conduct meta-analysis of gene expression data across distinct cohorts. In this work, we assess eight imputation methods for their ability to impute gene expression data when values are missing across an entire cohort of Tuberculosis (TB) patients. We investigate how varying proportions of missing data (across 10%, 20%, and 30% of patient samples) influence the imputation results, and test for significantly differentially expressed genes and enriched pathways in patients with active TB. Our results indicate that truncating to common genes observed across cohorts, which is the current method used by researchers, results in the exclusion of important biology and suggest that LASSO and LLS imputation methodologies can reasonably impute genes across cohorts when total missingness rates are below 20%.