VarStack: a web tool for data retrieval to interpret somatic variants in cancer.

Advances in tumor genome sequencing created an urgent need for bioinformatics tools to support the interpretation of the clinical significance of the variants detected. VarStack is a web tool which is a base to retrieve somatic variant data relating to cancer from existing databases. VarStack incorporates data from several publicly available databases and presents them with an easy-to-navigate user interface. It currently supports data from the Catalogue of Somatic Mutations in Cancer, gnomAD, cBioPortal, ClinVar, OncoKB, CiViC and UCSC Genome Browser. It retrieves the data from these databases and returns them back to the user in a fraction of the time it would take to manually navigate each site independently. Users submit a variant with a gene symbol, peptide change and coding sequence change. They may select a variety of tumor-specific studies in cBioPortal to search through in addition to their original query. The results from the databases are presented in tabs. Users can export the results as an Excel file. VarStack also has the batch search feature in which the user can submit a list of variants and download an Excel file with the data from the databases. With the batch search and data download options, users can easily incorporate VarStack into their workflow or tools. VarStack saves time by providing somatic variant information to the user from multiple databases in an easy-to-export and interpretable format. VarStack is freely available under https://varstack.brown.edu.

Machine learning approach to literature mining for the genetics of complex diseases.

To generate a parsimonious gene set for understanding the mechanisms underlying complex diseases, we reasoned it was necessary to combine the curation of public literature, review of experimental databases and interpolation of pathway-associated genes. Using this strategy, we previously built the following two databases for reproductive disorders: The Database for Preterm Birth (dbPTB) and The Database for Preeclampsia (dbPEC). The completeness and accuracy of these databases is essential for supporting our understanding of these complex conditions. Given the exponential increase in biomedical literature, it is becoming increasingly difficult to manually maintain these databases. Using our curated databases as reference data sets, we implemented a machine learning-based approach to optimize article selection for manual curation. We used logistic regression, random forests and neural networks as our machine learning algorithms to classify articles. We examined features derived from abstract text, annotations and metadata that we hypothesized would best classify articles with genetically relevant content associated to the disorder of interest. Combinations of these features were used build the classifiers and the performance of these feature sets were compared to a standard 'Bag-of-Words'. Several combinations of these genetic based feature sets outperformed 'Bag-of-Words' at a threshold such that 95% of the curated gene set obtained from the original manual curation of all articles were extracted from the articles classified by machine learning as 'considered'. The performance was superior in terms of the reduction of required manual curation and two measures of the harmonic mean of precision and recall. The reduction in workload ranged from 0.814 to 0.846 for the dbPTB and 0.301 to 0.371 for the dbPEC. Additionally, a database of metadata and annotations is generated which allows for rapid query of individual features. Our results demonstrate that machine learning algorithms can identify articles with relevant data for databases of genes associated with complex diseases.

Trend Analysis of Aggregate Outcomes in Complex Health Survey Data.

Public health and clinical practice pattern trends are often analyzed using complex survey data. Use of statistical approaches that do not account for survey design predisposes to error, potentially leading to resource misdirection and inefficiency. This study examined two techniques for analyzing trends in complex survey data: (1) design-corrected logistic regression and (2) jackknife re-weighted linear regression. These approaches were compared toweighted least squares regression, as well as non-design corrected techniques. Data were obtained from NEISS, a complex survey of emergency departments that can be weighted to produce national estimates of injury occurrence. Trends were analyzed in rug-related injuries among male versus female patients ≥65 years of age. All design-corrected techniques performed comparably in assessment of trend within sex-based subgroups. In almost all cases, design-corrected approaches contrasted profoundly with standard statistical techniques. Future analyses may employ these design-corrected approaches to appropriately account for estimate variance in complex survey data.

Using Demographic Factors and Comorbidities to Develop a Predictive Model for ICU Mortality in Patients with Acute Exacerbation COPD.

Recognizing factors associated with mortality in patients admitted to the ICU with acute exacerbation of chronic obstructive pulmonary disease could reduce healthcare costs and improve end-of-life care. Previous studies have identified possible predictive variables, but analysis is lacking on the combined effect of demographic factors and comorbidities. Using the MIMIC-III database, this study examined factors associated with mortality in a model incorporating comorbidities, comorbidity indices, and demographic factors. After determining associations between predictive variables and mortality through univariate and multivariate binomial logistic regression, three predictive models were developed: (1) univariate GLM-derived logistic, (2) Mean Gini-derived logistic (MGDL), and (3) random forest. The MGDL model best predicted mortality with an AUROC of 0.778. Variables with the greatest relative importance in determining mortality included the Charlson Comorbidity Index, Elixhauser Index, male, and arrhythmia. The results support the potential of using the MGDL model and need for further work in exploring demographic factors.

Predicting Mortality in Diabetic ICU Patients Using Machine Learning and Severity Indices.

Diabetes constitutes a significant health problem that leads to many long term health issues including renal, cardiovascular, and neuropathic complications. Many of these problems can result in increased health care costs, as well risk of ICU stay and mortality. To date, no published study has used predictive modeling to examine the relative influence of diabetes, diabetic health maintenance, and comorbidities on outcomes in ICU patients. Using the MIMIC-III database, machine learning and binomial logistic regression modeling were applied to predict risk of mortality. The final models achieved good fit with AUC values of 0.787 and 0.785 respectively. Additionally, this study demonstrated that robust classification can be done as a combination of five variables (HbA1c, mean glucose during stay, diagnoses upon admission, age, and type of admission) to predict risk as compared with other machine learning models that require nearly 35 variables for similar risk assessment and prediction.

Development and validation of a multi-dimensional measure of intellectual humility.

This paper presents five studies on the development and validation of a scale of intellectual humility. This scale captures cognitive, affective, behavioral, and motivational components of the construct that have been identified by various philosophers in their conceptual analyses of intellectual humility. We find that intellectual humility has four core dimensions: Open-mindedness (versus Arrogance), Intellectual Modesty (versus Vanity), Corrigibility (versus Fragility), and Engagement (versus Boredom). These dimensions display adequate self-informant agreement, and adequate convergent, divergent, and discriminant validity. In particular, Open-mindedness adds predictive power beyond the Big Six for an objective behavioral measure of intellectual humility, and Intellectual Modesty is uniquely related to Narcissism. We find that a similar factor structure emerges in Germanophone participants, giving initial evidence for the model's cross-cultural generalizability.

An Automated System for Categorizing Transthoracic Echocardiography Indications According to the Echocardiography Appropriate Use Criteria.

The Echocardiography Appropriate Use Criteria (EAUC) are a set of indications for transthoracic echocardiography (TTE) developed to guide physician decision making around ordering of TTE. In this study, an automated rule-based method for processing "indications" listed within TTE reports and classification into one of the major EAUC categories was developed and validated against a clinician-annotated reference standard. The system performed at a comparable level to trained physicians allowing for the automated classification of more than 30,000 TTE indications from a public database in less than ten minutes. The most common indication for TTE was Valvular assessment closely followed by General. Hypertension/Heart Failure/Cardiomyopathy, Acute, and Cardiac Structure assessment each contributed more than ten percent within this patient population. These results suggest potential for automated approaches for tracking appropriate use of TTE, as well as guide the development of systems for prospectively identifying when TTE use is recommended.

Factor structure and psychometric properties of a brief measure of dysfunctional individuation.

Individuation is widely considered a fundamental developmental task of adolescence. It is a process through which the adolescent seeks to define new boundaries between his or her self and others, and the failure to do so has been shown to have serious consequences. Given its importance for understanding developmental transitions, it is surprising that there are few assessments of dysfunctional individuation. Over three studies, we provide evidence of a promising new measure of this important construct: the 10-item Dysfunctional Individuation Scale (DIS). Using confirmatory factor analysis and item response theory, we demonstrate that the DIS possesses a strong one-factor structure and excellent psychometric properties. Furthermore, we document the convergent, discriminant, and concurrent validity of the DIS through its relationships with indices of individuation, adjustment, and clinically relevant symptoms. Finally, we examine the incremental validity of the DIS over neuroticism as a predictor of depression (Beck Depression Inventory-II).

Autobiographical memory specificity among preschool-aged children.

Overgeneral memory refers to difficulty retrieving specific autobiographical memories and is consistently associated with depression and/or trauma. The present study developed a downward extension of the Autobiographical Memory Test (AMT; Williams & Broadbent, 1986) given the need to document normative developmental changes in ability to retrieve specific memories among preschoolers. Confirmatory factor analysis and item response theory demonstrated that the AMT-Preschool Version maintained the same underlying 1-factor structure as the original. Additionally, the present study determined that child age was associated with increased specificity. Inhibitory control was evaluated as a potential mediator. Although age was related to inhibition, inhibition was unrelated to memory specificity. This finding adds to research suggesting that behavioral inhibition is unrelated to overgeneral memory among youth.

Knowing where to draw the line: perceptual differences between risk-takers and non-risk-takers.

There are a variety of reasons someone might engage in risky behaviors, such as perceived invulnerability to harm or a belief that negative outcomes are more likely for others than for oneself. However, these risk-taking biases are often measured at a decision-making level or from the developmental perspective. Here we assessed whether or not risk-taking influenced perceptual judgments associated with risk. Participants were provided an objective task to measure individual differences in the perception of physical dimensions (i.e., actual size of a balloon) versus the perception of risk (i.e., size at which the balloon would explode). Our results show that specific differences in risk-taking personalities produce specific differences in perceptual judgments about risk, but do not affect perception of the actual dimensions. Thus, risk-takers differ from non-risk-takers in the perceptual estimations they make about risks, and therefore may be more likely to engage in dangerous or uncertain behaviors because they perceive risks differently.