Search

Healthcare datasets obtained from Electronic Health Records have proven to be extremely useful for assessing associations between patients’ predictors and outcomes of interest. However, these datasets often suffer from missing values in a high proportion of cases, whose removal may introduce severe bias. Several multiple imputation algorithms have been proposed to attempt to recover the missing information under an assumed missingness mechanism. Each algorithm presents strengths and weaknesses, and there is currently no consensus on which multiple imputation algorithm works best in a given scenario. Furthermore, the selection of each algorithm's parameters and data-related modeling choices are also both crucial and challenging. In this paper we propose a novel framework to numerically evaluate strategies for handling missing data in the context of statistical analysis, with a particular focus on multiple imputation techniques. We demonstrate the feasibility of our approach on a large cohort of type-2 diabetes patients provided by the National COVID Cohort Collaborative (N3C) Enclave, where we explored the influence of various patient characteristics on outcomes related to COVID-19. Our analysis included classic multiple imputation techniques as well as simple complete-case Inverse Probability Weighted models. Extensive experiments show that our approach can effectively highlight the most promising and performant missing-data handling strategy for our case study. Moreover, our methodology allowed a better understanding of the behavior of the different models and of how it changed as we modified their parameters. Our method is general and can be applied to different research fields and on datasets containing heterogeneous types.

Graph representation learning is a family of related approaches that learn low-dimensional vector representations of nodes and other graph elements called embeddings. Embeddings approximate characteristics of the graph and can be used for a variety of machine-learning tasks such as novel edge prediction. For many biomedical applications, partial knowledge exists about positive edges that represent relationships between pairs of entities, but little to no knowledge is available about negative edges that represent the explicit lack of a relationship between two nodes. For this reason, classification procedures are forced to assume that the vast majority of unlabeled edges are negative. Existing approaches to sampling negative edges for training and evaluating classifiers do so by uniformly sampling pairs of nodes. We show here that this sampling strategy typically leads to sets of positive and negative edges with imbalanced edge degree distributions. Using representative homogeneous and heterogeneous biomedical knowledge graphs, we show that this strategy artificially inflates measured classification performance. We present a degree-aware node sampling approach for sampling negative edge examples that mitigates this effect and is simple to implement.

BackgroundWith the continuing COVID-19 pandemic, identifying medications that improve COVID-19 outcomes is crucial. Studies suggest that use of metformin, an oral antihyperglycemic, is associated with reduced COVID-19 severity in individuals with diabetes compared to other antihyperglycemic medications. Some patients without diabetes, including those with polycystic ovary syndrome (PCOS) and prediabetes, are prescribed metformin for off-label use, which provides an opportunity to further investigate the effect of metformin on COVID-19.ParticipantsIn this observational, retrospective analysis, we leveraged the harmonized electronic health record data from 53 hospitals to construct cohorts of COVID-19 positive, metformin users without diabetes and propensity-weighted control users of levothyroxine (a medication for hypothyroidism that is not known to affect COVID-19 outcome) who had either PCOS (n = 282) or prediabetes (n = 3136). The primary outcome of interest was COVID-19 severity, which was classified as: mild, mild ED (emergency department), moderate, severe, or mortality/hospice.ResultsIn the prediabetes cohort, metformin use was associated with a lower rate of COVID-19 with severity of mild ED or worse (OR: 0.630, 95% CI 0.450 - 0.882, p < 0.05) and a lower rate of COVID-19 with severity of moderate or worse (OR: 0.490, 95% CI 0.336 - 0.715, p < 0.001). In patients with PCOS, we found no significant association between metformin use and COVID-19 severity, although the number of patients was relatively small.ConclusionsMetformin was associated with less severe COVID-19 in patients with prediabetes, as seen in previous studies of patients with diabetes. This is an important finding, since prediabetes affects between 19 and 38% of the US population, and COVID-19 is an ongoing public health emergency. Further observational and prospective studies will clarify the relationship between metformin and COVID-19 severity in patients with prediabetes, and whether metformin usage may reduce COVID-19 severity.

Stratification of patients with post-acute sequelae of SARS-CoV-2 infection (PASC, or long COVID) would allow precision clinical management strategies. However, long COVID is incompletely understood and characterised by a wide range of manifestations that are difficult to analyse computationally. Additionally, the generalisability of machine learning classification of COVID-19 clinical outcomes has rarely been tested.We present a method for computationally modelling PASC phenotype data based on electronic healthcare records (EHRs) and for assessing pairwise phenotypic similarity between patients using semantic similarity. Our approach defines a nonlinear similarity function that maps from a feature space of phenotypic abnormalities to a matrix of pairwise patient similarity that can be clustered using unsupervised machine learning.We found six clusters of PASC patients, each with distinct profiles of phenotypic abnormalities, including clusters with distinct pulmonary, neuropsychiatric, and cardiovascular abnormalities, and a cluster associated with broad, severe manifestations and increased mortality. There was significant association of cluster membership with a range of pre-existing conditions and measures of severity during acute COVID-19. We assigned new patients from other healthcare centres to clusters by maximum semantic similarity to the original patients, and showed that the clusters were generalisable across different hospital systems. The increased mortality rate originally identified in one cluster was consistently observed in patients assigned to that cluster in other hospital systems.Semantic phenotypic clustering provides a foundation for assigning patients to stratified subgroups for natural history or therapy studies on PASC.NIH (TR002306/OT2HL161847-01/OD011883/HG010860), U.S.D.O.E. (DE-AC02-05CH11231), Donald A. Roux Family Fund at Jackson Laboratory, Marsico Family at CU Anschutz.

Accurate stratification of patients with post-acute sequelae of SARS-CoV-2 infection (PASC, or long COVID) would allow precision clinical management strategies. However, the natural history of long COVID is incompletely understood and characterized by an extremely wide range of manifestations that are difficult to analyze computationally. In addition, the generalizability of machine learning classification of COVID-19 clinical outcomes has rarely been tested. We present a method for computationally modeling PASC phenotype data based on electronic healthcare records (EHRs) and for assessing pairwise phenotypic similarity between patients using semantic similarity. Our approach defines a nonlinear similarity function that maps from a feature space of phenotypic abnormalities to a matrix of pairwise patient similarity that can be clustered using unsupervised machine learning procedures. Using k-means clustering of this similarity matrix, we found six distinct clusters of PASC patients, each with distinct profiles of phenotypic abnormalities. There was a significant association of cluster membership with a range of pre-existing conditions and with measures of severity during acute COVID-19. Two of the clusters were associated with severe manifestations and displayed increased mortality. We assigned new patients from other healthcare centers to one of the six clusters on the basis of maximum semantic similarity to the original patients. We show that the identified clusters were generalizable across different hospital systems and that the increased mortality rate was consistently observed in two of the clusters. Semantic phenotypic clustering can provide a foundation for assigning patients to stratified subgroups for natural history or therapy studies on PASC.

Background Non-steroidal anti-inflammatory drugs (NSAIDs) are commonly used to reduce pain, fever, and inflammation but have been associated with complications in community-acquired pneumonia. Observations shortly after the start of the COVID-19 pandemic in 2020 suggested that ibuprofen was associated with an increased risk of adverse events in COVID-19 patients, but subsequent observational studies failed to demonstrate increased risk and in one case showed reduced risk associated with NSAID use. Methods A 38-center retrospective cohort study was performed that leveraged the harmonized, high-granularity electronic health record data of the National COVID Cohort Collaborative. A propensity-matched cohort of 19,746 COVID-19 inpatients was constructed by matching cases (treated with NSAIDs at the time of admission) and 19,746 controls (not treated) from 857,061 patients with COVID-19 available for analysis. The primary outcome of interest was COVID-19 severity in hospitalized patients, which was classified as: moderate, severe, or mortality/hospice. Secondary outcomes were acute kidney injury (AKI), extracorporeal membrane oxygenation (ECMO), invasive ventilation, and all-cause mortality at any time following COVID-19 diagnosis. Results Logistic regression showed that NSAID use was not associated with increased COVID-19 severity (OR: 0.57 95% CI: 0.53–0.61). Analysis of secondary outcomes using logistic regression showed that NSAID use was not associated with increased risk of all-cause mortality (OR 0.51 95% CI: 0.47–0.56), invasive ventilation (OR: 0.59 95% CI: 0.55–0.64), AKI (OR: 0.67 95% CI: 0.63–0.72), or ECMO (OR: 0.51 95% CI: 0.36–0.7). In contrast, the odds ratios indicate reduced risk of these outcomes, but our quantitative bias analysis showed E-values of between 1.9 and 3.3 for these associations, indicating that comparatively weak or moderate confounder associations could explain away the observed associations. Conclusions Study interpretation is limited by the observational design. Recording of NSAID use may have been incomplete. Our study demonstrates that NSAID use is not associated with increased COVID-19 severity, all-cause mortality, invasive ventilation, AKI, or ECMO in COVID-19 inpatients. A conservative interpretation in light of the quantitative bias analysis is that there is no evidence that NSAID use is associated with risk of increased severity or the other measured outcomes. Our results confirm and extend analogous findings in previous observational studies using a large cohort of patients drawn from 38 centers in a nationally representative multicenter database.

Background Numerous publications describe the clinical manifestations of post-acute sequelae of SARS-CoV-2 (PASC or "long COVID"), but they are difficult to integrate because of heterogeneous methods and the lack of a standard for denoting the many phenotypic manifestations. Patient-led studies are of particular importance for understanding the natural history of COVID-19, but integration is hampered because they often use different terms to describe the same symptom or condition. This significant disparity in patient versus clinical characterization motivated the proposed ontological approach to specifying manifestations, which will improve capture and integration of future long COVID studies. Methods The Human Phenotype Ontology (HPO) is a widely used standard for exchange and analysis of phenotypic abnormalities in human disease but has not yet been applied to the analysis of COVID-19. Findings We identified 303 articles published before April 29, 2021, curated 59 relevant manuscripts that described clinical manifestations in 81 cohorts three weeks or more following acute COVID-19, and mapped 287 unique clinical findings to HPO terms. We present layperson synonyms and definitions that can be used to link patient self-report questionnaires to standard medical terminology. Long COVID clinical manifestations are not assessed consistently across studies, and most manifestations have been reported with a wide range of synonyms by different authors. Across at least 10 cohorts, authors reported 31 unique clinical features corresponding to HPO terms; the most commonly reported feature was Fatigue (median 45.1%) and the least commonly reported was Nausea (median 3.9%), but the reported percentages varied widely between studies. Interpretation Translating long COVID manifestations into computable HPO terms will improve analysis, data capture, and classification of long COVID patients. If researchers, clinicians, and patients share a common language, then studies can be compared/pooled more effectively. Furthermore, mapping lay terminology to HPO will help patients assist clinicians and researchers in creating phenotypic characterizations that are computationally accessible, thereby improving the stratification, diagnosis, and treatment of long COVID. Funding U24TR002306; UL1TR001439; P30AG024832; GBMF4552; R01HG010067; UL1TR002535; K23HL128909; UL1TR002389; K99GM145411 .

SummaryBackgroundCOVID-19 has been shown to increase the risk of adverse mental health consequences. A recent electronic health record (EHR)-based observational study showed an almost two-fold increased risk of new-onset mental illness in the first 90 days following a diagnosis of acute COVID-19.MethodsWe used the National COVID Cohort Collaborative, a harmonized EHR repository with 2,965,506 COVID-19 positive patients, and compared cohorts of COVID-19 patients with comparable controls. Patients were propensity score-matched to control for confounding factors. We estimated the hazard ratio (COVID-19:control) for new-onset of mental illness for the first year following diagnosis. We additionally estimated the change in risk for new-onset mental illness between the periods of 21-120 and 121-365 days following infection.FindingsWe find a significant increase in incidence of new-onset mental disorders in the period of 21-120 days following COVID-19 (3.8%, 3.6-4.0) compared to patients with respiratory tract infections (3%, 2.8-3.2). We further show that the risk for new-onset mental illness decreases over the first year following COVID-19 diagnosis compared to other respiratory tract infections and demonstrate a reduced (non-significant) hazard ratio over the period of 121-365 days following diagnosis. Similar findings are seen for new-onset anxiety disorders but not for mood disorders.InterpretationPatients who have recovered from COVID-19 are at an increased risk for developing new-onset mental illness, especially anxiety disorders. This risk is most prominent in the first 120 days following infection.FundingNational Center for Advancing Translational Sciences (NCATS).

Inhibiting protein kinases (PKs) that cause cancers has been an important topic in cancer therapy for years. So far, almost 8% of >530 PKs have been targeted by FDA-approved medications, and around 150 protein kinase inhibitors (PKIs) have been tested in clinical trials. We present an approach based on natural language processing and machine learning to investigate the relations between PKs and cancers, predicting PKs whose inhibition would be efficacious to treat a certain cancer. Our approach represents PKs and cancers as semantically meaningful 100-dimensional vectors based on word and concept neighborhoods in PubMed abstracts. We use information about phase I-IV trials in ClinicalTrials.gov to construct a training set for random forest classification. Our results with historical data show that associations between PKs and specific cancers can be predicted years in advance with good accuracy. Our tool can be used to predict the relevance of inhibiting PKs for specific cancers and to support the design of well-focused clinical trials to discover novel PKIs for cancer therapy.

Inhibiting protein kinases (PKs) that cause cancers has been an important topic in cancer therapy for years. So far, almost 8% of more than 530 PKs have been targeted by FDA-approved medications and around 150 protein kinase inhibitors (PKIs) have been tested in clinical trials. We present an approach based on natural language processing and machine learning to the relations between PKs and cancers, predicting PKs whose inhibition would be efficacious to treat a certain cancer. Our approach represents PKs and cancers as semantically meaningful 100-dimensional vectors based on co-occurrence patterns in PubMed abstracts. We use information about phase I-IV trials inClinicalTrials.govto construct a training set for random forest classification. In historical data, associations between PKs and specific cancers could be predicted years in advance with good accuracy. Our model may be a tool to predict the relevance of inhibiting PKs with specific cancers.

The relations among dimensions of subjective well-being (i.e., happiness and life satisfaction), spirituality and religiousness were assessed in children (aged 7–12, n = 391) and adolescents (aged 13–19, n = 902) in Zambia. These participants were sampled from schools in both urban and rural regions that represented a relatively wide range of affluence. Participants self-reported their happiness using the Faces Scale and the Subjective Happiness Scale, and their life satisfaction using the Student Life Satisfaction Scale. The surveys were available in English as well as two local languages, and were delivered in classroom settings. To assess religiosity, participants were asked about the frequency that they attended church and about the importance of religion in their life. To assess spirituality, participants were asked about whether they considered themselves to be a spiritual person and about the nature domain of spirituality (e.g., “I feel connected to nature”). Results indicated that age, gender, grade and religiosity were not strong predictors of children’s well-being. However, spirituality accounted for 21 % of the variance in life satisfaction beyond these demographic variables and religiosity, but did not account for additional variance in happiness. The results were similar for adolescents except that the demographic variables were weakly predictive of their life satisfaction, and religiosity was a modest predictor of their happiness. Spirituality predicted variance in happiness and life satisfaction more so among adolescents than among children. These results confirm earlier work showing that spirituality, but not necessarily religiosity, is associated with children’s and adolescents’ well-being.

The relation between temperament and happiness was assessed in a sample of 441 children aged 7–14 years drawn from a population in Northern India. Parents assessed their children’s happiness and rated their children’s temperament using the Emotionality, Activity, and Sociability Temperament Survey (EAS). Children self-reported their own happiness using a single-item measure, the Oxford Happiness Scale Short Form, and the Subjective Happiness Scale. Parents’ temperament ratings conformed to the four factor structure proposed by Buss and Plomin (Temperament: early developing personality traits. Lawrence Erlbaum Associates, Hillsdale, 1984): Emotionality, Activity, Sociability, and Shyness. Temperament accounted for between 4 and 11% of the variance in children’s happiness depending on the measures. Children who were more social and active, and less shy, were happier. This result parallels the well-established relation between happiness and personality in adults and is similar to recent research on happiness and temperament in children; temperament traits akin to extraversion were positively associated with happiness. However, despite that neuroticism and its temperament counterpart are strongly and consistently linked to happiness in adults, the relation between happiness and the temperament trait associated with neuroticism (i.e., Emotionality) was weak. This suggests that the relations between temperament and happiness in children may not completely generalize across cultures.

Over the past 4 years, the Every Disabled Child Matters campaign has secured almost £780 million in new funding for disabled children's services and has laid the foundation for addressing structural disadvantages for disabled children. Critical success factors for the campaign have included clear aims, a tight core strategy group, a leading political champion, widespread parliamentary support and effective mobilisation of disabled children and their families as campaigners. The campaign caught policymakers' attention at the right point to leverage significant support for a previously marginalised social group. Copyright © 2009 John Wiley & Sons, Ltd.

The relation between spirituality and happiness was assessed in 320 children aged 8–12 from public and private (i.e., faith-based) schools. Children rated their own spirituality using the Spiritual Well-Being Questionnaire and 11 items selected and modified from the Brief Multidimensional Measurement of Religiousness/Spirituality which reflected the children’s practices and beliefs. Children’s happiness was assessed using self-reports based on the Oxford Happiness Scale short form, the Subjective Happiness Scale, and a single-item measure. Parents also rated their children’s happiness. Children and parents rated the children’s temperament using the emotionality, activity, and sociability temperament survey. Children’s spirituality, but not their religious practices (e.g., attending church, praying, and meditating), was strongly linked to their happiness. Children who were more spiritual were happier. Spirituality accounted for between 3 and 26% of the unique variance in children’s happiness depending on the measures. Temperament was also a predictor of happiness, but spirituality remained a significant predictor of happiness even after removing the variance associated with temperament. The personal (i.e., meaning and value in one’s own life) and communal (quality and depth of inter-personal relationships) domains of spirituality were particularly good predictors of children’s happiness. These results parallel studies of adult happiness and suggest strategies to enhance happiness in children.

The association between happiness and social relationships was examined in 9- to 12-year-old children. Participants included 432 children and their parents. Children’s happiness was assessed using self-rating scales, parent’s ratings, and the Happiness and Satisfaction Subscale from the Piers-Harris Children’s Self-Concept Scale, Second Edition (Piers and Herzberg 2002). Children’s social relations were assessed with items from the Piers-Harris scale and questionnaires given to the children and their parents. These items were grouped into two positive (i.e., family and friends) and two negative categories (i.e., negative relations with peers and behaving badly toward others). Variance in children’s happiness was partially accounted for by positive social interactions involving the family (e.g., children agreeing that they are important members of their family) and friends (e.g., parents reporting that their children visit with friends more frequently). Negative social interactions also explained variance in children’s happiness including negative relations with peers (e.g., children agreeing that they feel left out of things) and behaving badly toward others (e.g., children agreeing that they are often mean to other people, and they cause trouble for their family). Demographic variables related to the family (i.e., number of siblings, age of parents, and marital status of parents) were only weakly, or not at all, associated with children’s happiness. The results parallel findings from the literature involving adults and adolescents; social relationships are significant correlates and predictors of happiness.

The relation between the happiness of 9–12 year old children and their temperament, popularity, and physical appearance was examined. Participants included 432 children and their parents and teachers. Happiness in children was assessed using a self-rating scale, parents’ ratings, teachers’ ratings, and the Happiness and Satisfaction Subscale of the Piers-Harris Children’s Self-Concept Scale 2 (Piers-Harris 2) [Piers, E. V., & Herzberg, D. S. (2002). Manual for the Piers-Harris Children’s Self-Concept Scale, 2nd ed. Los Angeles: Western Psychological Services]. Estimates of children’s temperament, popularity, and physical appearance included parents’ ratings, individual items on the Piers-Harris 2, and three domain scales from the Piers-Harris 2: the Freedom From Anxiety Subscale, Popularity Subscale, and Physical Appearance and Attributes Subscale. Children’s happiness was correlated with and predicted by ratings of their temperament, popularity, and appearance. Demographic variables did not account for appreciable variance in children’s happiness. The results parallel the common finding that internal factors (e.g., personality), but not external factors (e.g., demographics), predict adults’ happiness.

Can students contribute to HFOSS projects as part of their computing curriculum? How and at what level can HFOSS be integrated? What are the success stories and challenges? This BOF will be led by a diverse group of faculty who have incorporated HFOSS into their classes. They will lead a discussion on the various approaches, successes and challenges they have encountered. Their experiences will provide a backdrop for this BOF session, which should lead to a lively discussion of how and why to use HFOSS in computing courses. Faculty who are interested in HFOSS, but who are novices, will learn about potential projects and classroom materials as well as make connections with more experienced faculty in this area.

Alumni make contributions to a Computer Science program in three interconnected ways, all of which relate to the interplay between the academic environment and the "real world." For students who aim to enter the job market upon graduation, alumni provide a friendly way to receive mentoring and advice and develop a professional network. When faculty are looking for real-world projects and experiences for students, alumni provide an avenue for entrance into industry. Finally, alumni can provide assessment data about the performance of students in the workplace after graduation.In this BoF session, we will consider how individual faculty members or a department can engage alumni in meaningful ways. Small groups will consider each of the three ways to partner with alumni, with particular emphasis on sharing past experiences. Participants will be encouraged to consider ways to collaborate with their alumni office, development office, career center and student groups to leverage the potential of their alumni.

Children’s friendships are closely associated with children’s positive well-being. Children who enjoy close friendships are more likely to experience higher levels of happiness, life satisfaction and self-esteem and less likely to be lonely, depressed or victimized. Friendships during childhood are predictive of greater self worth and coping skills later in life but the direction of the relationship between children’s well-being and their friendships (i.e., whether well-being is a cause or consequence of friendships) is not firmly established. Though the study of the links between children’s happiness and friendships is relatively sparse, recent developments in measures of children’s well-being are encouraging. This is important because the relationship between friendships and well-being may be different for children compared to adults and adolescents for reasons such as children do not typically have mature romantic relationships but they do experience friendships with imaginary companions. Given the unique importance of children’s friendships in understanding and promoting children’s happiness, we outline several considerations for future studies in this promising area of research.

Improving communication and collaborative skills of computer science students has been a priority in the community for some time. We present our philosophy, collaboration across the curriculum, which moves beyond existing individual courses or course units to teach collaboration skills in a pervasive manner. In our approach, concepts are introduced and skills are developed throughout the computer science curriculum---from CS1 to a capstone experience. Students are provided with opportunities to exercise skills in reflective environments that eventually mirror real-world experiences, and technical course content is not compromised.We argue for this system and provide details about how collaboration across the curriculum is accomplished at a small liberal arts college.