Explore the vast range of titles available.

Sudden death related to hypoglycemia is thought to be due to cardiac arrhythmias. A clearer understanding of the cardiac changes associated with hypoglycemia is needed to reduce mortality. The objective of this work was to identify distinct patterns of electrocardiogram heartbeat changes that correlated with glycemic level, diabetes status, and mortality using a rodent model. Electrocardiogram and glucose measurements were collected from 54 diabetic and 37 non-diabetic rats undergoing insulin-induced hypoglycemic clamps. Shape-based unsupervised clustering was performed to identify distinct clusters of electrocardiogram heartbeats, and clustering performance was assessed using internal evaluation metrics. Clusters were evaluated by experimental conditions of diabetes status, glycemic level, and death status. Overall, shape-based unsupervised clustering identified 10 clusters of ECG heartbeats across multiple internal evaluation metrics. Several clusters demonstrating normal ECG morphology were specific to hypoglycemia conditions (Clusters 3, 5, and 8), non-diabetic rats (Cluster 4), or were generalized among all experimental conditions (Cluster 1). In contrast, clusters demonstrating QT prolongation alone or a combination of QT, PR, and QRS prolongation were specific to severe hypoglycemia experimental conditions and were stratified heartbeats by non-diabetic (Clusters 2 and 6) or diabetic status (Clusters 9 and 10). One cluster demonstrated an arrthymogenic waveform with premature ventricular contractions and was specific to heartbeats from severe hypoglycemia conditions (Cluster 7). Overall, this study provides the first data-driven characterization of ECG heartbeats in a rodent model of diabetes during hypoglycemia.

Background Social risk factors are important dimensions of health and are linked to access to care, quality of life, health outcomes and life expectancy. However, in the Electronic Health Record, data related to many social risk factors are primarily recorded in free-text clinical notes, rather than as more readily computable structured data, and hence cannot currently be easily incorporated into automated assessments of health. In this paper, we present Moonstone , a new, highly configurable rule-based clinical natural language processing system designed to automatically extract information that requires inferencing from clinical notes. Our initial use case for the tool is focused on the automatic extraction of social risk factor information — in this case, housing situation , living alone , and social support — from clinical notes. Nursing notes, social work notes, emergency room physician notes, primary care notes, hospital admission notes, and discharge summaries, all derived from the Veterans Health Administration, were used for algorithm development and evaluation. Results An evaluation of Moonstone demonstrated that the system is highly accurate in extracting and classifying the three variables of interest ( housing situation , living alone , and social support ). The system achieved positive predictive value (i.e. precision) scores ranging from 0.66 ( homeless/marginally housed ) to 0.98 ( lives at home/not homeless ), accuracy scores ranging from 0.63 ( lives in facility ) to 0.95 ( lives alone ), and sensitivity (i.e. recall) scores ranging from 0.75 ( lives in facility ) to 0.97 ( lives alone ). Conclusions The Moonstone system is — to the best of our knowledge — the first freely available, open source natural language processing system designed to extract social risk factors from clinical text with good ( lives in facility ) to excellent ( lives alone ) performance. Although developed with the social risk factor identification task in mind, Moonstone provides a powerful tool to address a range of clinical natural language processing tasks, especially those tasks that require nuanced linguistic processing in conjunction with inference capabilities.

Introduction Clinical notes, biomarkers, and neuroimaging have proven valuable in dementia prediction models. Whether commonly available structured clinical data can predict dementia is an emerging area of research. We aimed to predict gold-standard, research-based diagnoses of dementia including Alzheimer’s disease (AD) and/or Alzheimer’s disease related dementias (ADRD), in addition to ICD-based AD and/or ADRD diagnoses, in a well-phenotyped, population-based cohort using a machine learning approach. Methods Administrative healthcare data (k = 163 diagnostic features), in addition to census/vital record sociodemographic data (k = 6 features), were linked to the Cache County Study (CCS, 1995–2008). Results Among successfully linked UPDB-CCS participants ( n  = 4206), 522 (12.4%) had incident dementia (AD alone, AD comorbid with ADRD, or ADRD alone) as per the CCS “gold standard” assessments. Random Forest models, with a 1-year prediction window, achieved the best performance with an Area Under the Curve (AUC) of 0.67. Accuracy declined for dementia subtypes: AD/ADRD (AUC = 0.65); ADRD (AUC = 0.49). Accuracy improved when using ICD-based dementia diagnoses (AUC = 0.77). Discussion Commonly available structured clinical data (without labs, notes, or prescription information) demonstrate modest ability to predict “gold-standard” research-based AD/ADRD diagnoses, corroborated by prior research. Using ICD diagnostic codes to identify dementia as done in the majority of machine learning dementia prediction models, as compared to “gold-standard” dementia diagnoses, can result in higher accuracy, but whether these models are predicting true dementia warrants further research.

Introduction Women with hypertensive disorders of pregnancy (HDP) have an increased risk of cardiovascular disease. Whether HDP is also associated with later‐life dementia has not been fully explored. Methods Using the Utah Population Database, we performed an 80‐year retrospective cohort study of 59,668 parous women. Results Women with, versus without, HDP, had a 1.37 higher risk of all‐cause dementia (95% confidence interval [CI]: 1.26, 1.50) after adjustment for maternal age at index birth, birth year, and parity. HDP was associated with a 1.64 higher risk of vascular dementia (95% CI: 1.19, 2.26) and 1.49 higher risk of other dementia (95% CI: 1.34, 1.65) but not Alzheimer's disease dementia (adjusted hazard ratio = 1.04; 95% CI: 0.87, 1.24). Gestational hypertension and preeclampsia/eclampsia showed similar increased dementia risk. Nine mid‐life cardiometabolic and mental health conditions explained 61% of HDP's effect on subsequent dementia risk. Discussion Improved HDP and mid‐life care could reduce the risk of dementia.

Objective: Sepsis is a life-threatening response to infection and a major cause of hospital mortality. Machine learning (ML) models have demonstrated better sepsis prediction performance than integer risk scores but are less widely used in clinical settings, in part due to lower interpretability. This study aimed to improve the interpretability of an ML-based model without reducing its performance in non-ICU sepsis prediction. Methods: A logistic regression model was trained to predict sepsis onset and then converted into a more interpretable integer point system, STEWS, using its regression coefficients. We compared STEWS with the logistic regression model using PPV at 90% sensitivity. Results: STEWS was significantly equivalent to logistic regression using the two one-sided tests procedure (0.051 vs. 0.051; p = 0.004). Conclusions: STEWS demonstrated equivalent performance to a comparable logistic regression model for non-ICU sepsis prediction, suggesting that converting ML models into more interpretable forms does not necessarily reduce predictive power.

Background The aim of this study was to propose an analytical approach to develop high-performing predictive models for congestive heart failure (CHF) readmission using an operational dataset with incomplete records and changing data over time. Methods Our analytical approach involves three steps: pre-processing, systematic model development, and risk factor analysis. For pre-processing, variables that were absent in >50% of records were removed. Moreover, the dataset was divided into a validation dataset and derivation datasets which were separated into three temporal subsets based on changes to the data over time. For systematic model development, using the different temporal datasets and the remaining explanatory variables, the models were developed by combining the use of various (i) statistical analyses to explore the relationships between the validation and the derivation datasets; (ii) adjustment methods for handling missing values; (iii) classifiers; (iv) feature selection methods; and (iv) discretization methods. We then selected the best derivation dataset and the models with the highest predictive performance. For risk factor analysis, factors in the highest-performing predictive models were analyzed and ranked using (i) statistical analyses of the best derivation dataset, (ii) feature rankers, and (iii) a newly developed algorithm to categorize risk factors as being strong, regular, or weak. Results The analysis dataset consisted of 2,787 CHF hospitalizations at University of Utah Health Care from January 2003 to June 2013. In this study, we used the complete-case analysis and mean-based imputation adjustment methods; the wrapper subset feature selection method; and four ranking strategies based on information gain, gain ratio, symmetrical uncertainty, and wrapper subset feature evaluators. The best-performing models resulted from the use of a complete-case analysis derivation dataset combined with the Class-Attribute Contingency Coefficient discretization method and a voting classifier which averaged the results of multi-nominal logistic regression and voting feature intervals classifiers. Of 42 final model risk factors, discharge disposition, discretized age, and indicators of anemia were the most significant. This model achieved a c-statistic of 86.8%. Conclusion The proposed three-step analytical approach enhanced predictive model performance for CHF readmissions. It could potentially be leveraged to improve predictive model performance in other areas of clinical medicine.

Lack of participation in clinical trials (CTs) is a major barrier for the evaluation of new pharmaceuticals and devices. Here we report the results of the analysis of a dataset from ResearchMatch, an online clinical registry, using supervised machine learning approaches and a deep learning approach to discover characteristics of individuals more likely to show an interest in participating in CTs. We trained six supervised machine learning classifiers (Logistic Regression (LR), Decision Tree (DT), Gaussian Naïve Bayes (GNB), K-Nearest Neighbor Classifier (KNC), Adaboost Classifier (ABC) and a Random Forest Classifier (RFC)), as well as a deep learning method, Convolutional Neural Network (CNN), using a dataset of 841,377 instances and 20 features, including demographic data, geographic constraints, medical conditions and ResearchMatch visit history. Our outcome variable consisted of responses showing specific participant interest when presented with specific clinical trial opportunity invitations ('yes' or 'no'). Furthermore, we created four subsets from this dataset based on top self-reported medical conditions and gender, which were separately analysed. The deep learning model outperformed the machine learning classifiers, achieving an area under the curve (AUC) of 0.8105. The results show sufficient evidence that there are meaningful correlations amongst predictor variables and outcome variable in the datasets analysed using the supervised machine learning classifiers. These approaches show promise in identifying individuals who may be more likely to participate when offered an opportunity for a clinical trial.

Tasks such as clustering and classification assume the existence of a similarity measure to assess the similarity (or dissimilarity) of a pair of observations or clusters. The key difference between most clustering methods is in their similarity measures. This article proposes a new similarity measure function called PWO “Probability of the Weights between Overlapped items ”which could be used in clustering categorical dataset; proves that PWO is a metric; presents a framework implementation to detect the best similarity value for different datasets; and improves the F-tree clustering algorithm with Semi-supervised method to refine the results. The experimental evaluation on real categorical datasets, such as “Mushrooms, KrVskp, Congressional Voting, Soybean-Large, Soybean-Small, Hepatitis, Zoo, Lenses, and Adult-Stretch” shows that PWO is more effective in measuring the similarity between categorical data than state-of-the-art algorithms; clustering based on PWO with pre-defined number of clusters results a good separation of classes with a high purity of average 80% coverage of real classes; and the overlap estimator perfectly estimates the value of the overlap threshold using a small sample of dataset of around 5% of data size.

Background The anti-diabetic drug, empagliflozin (EMPA), has many pleiotropic actions and is challenged recently to possess renoprotective properties. This renoprotective potential is proposed to be mediated via the activation of AMP-activated protein kinase (AMPK)/nuclear factor erythroid 2-related factor 2 (Nrf2) signaling pathways. This research investigated the renoprotective potential and the mechanistic pathway of EMPA against methotrexate (MTX)-induced nephrotoxicity and evaluated the role of AMPK by utilizing an AMPK inhibitor, dorsomorphin (Dorso). Methods Thirty male Wistar rats, weighing 180–200 g, were divided equally into five groups. Group I represented the control group. Nephrotoxicity was induced in the remaining rats through the administration of a single intraperitoneal injection of MTX (20 mg/kg). Rats were then randomly assigned to: Group 2 (received MTX injection only); Group 3 (received MTX and EMPA 30 mg/kg/day); Group 4 (received MTX and Dorso 0.2 mg/kg/day), Group 5 (received MTX, Dorso, EMPA). After one week, blood samples were collected, the rats were euthanized, and renal tissues were harvested for biochemical and histomorphometric assessments. Results MTX produced a significant rise in serum creatinine and tissue MDA levels; an increase in BAX, p53, cytochrome-c expression; a reduction in Bcl2 level; and disruption of renal microarchitecture. In contrast, EMPA therapy in group 3, resulted in a significant improvement of all these parameters, correlated with significant increase in AMPK phosphorylation and Nrf2 expression. Importantly, the co-administration of Dorso, in group 5, prevented EMPA’s beneficial effects. Conclusion EMPA has a potential protective effect against MTX-induced toxicity through the activation of the AMPK/Nrf2 signaling pathway.

OBJECTIVES/SPECIFIC AIMS: Translational researchers often require the use of informatics methods in their work. Lack of an understanding of key informatics principles and methods limits the abilities of translational researchers to successfully implement Findable, Accessible, Interoperable, Reusable (FAIR) principles in grant proposal submissions and performed studies. In this study we describe our work in addressing this limitation in the workforce by developing a competency-based, modular course in informatics to meet the needs of diverse translational researchers. METHODS/STUDY POPULATION: We established a Translational Research Informatics Education Collaborative (TRIEC) consisting of faculty at the University of Utah (UU) with different primary expertise in informatics methods, and working in different tiers of the translational spectrum. The TRIEC, in collaboration with the Foundation of Workforce Development of the Utah Center for Clinical and Translational Science (CCTS), gathered informatics needs of early investigators by consolidating requests for informatics services, assistance provided in grant writing, and consultations. We then reviewed existing courses and literature for informatics courses that focused on clinical and translational researchers [3–9]. Using the structure and content of the identified courses, we developed an initial draft of a syllabus for a Translational Research Informatics (TRI) course which included key informatics topics to be covered and learning activities, and iteratively refined it through discussions. The course was approved by the UU Department of Biomedical Informatics, UU Graduate School and the CCTS. RESULTS/ANTICIPATED RESULTS: The TRI course introduces informatics PhD students, clinicians, and public health practitioners who have a demonstrated interest in research, to fundamental principles and tools of informatics. At the completion of the course, students will be able to describe and identify informatics tools and methods relevant to translational research and demonstrate inter-professional collaboration in the development of a research proposal addressing a relevant translational science question that utilizes the state-of-the-art in informatics. TRI covers a diverse set of informatics content presented as modules: genomics and bioinformatics, electronic health records, exposomics, microbiomics, molecular methods, data integration and fusion, metadata management, semantics, software architectures, mobile computing, sensors, recruitment, community engagement, secure computing environments, data mining, machine learning, deep learning, artificial intelligence and data science, open source informatics tools and platforms, research reproducibility, and uncertainty quantification. The teaching methods for TRI include (1) modular didactic learning consisting of presentations and readings and face-to-face discussions of the content, (2) student presentations of informatics literature relevant to their final project, and (3) a final project consisting of the development, critique and chalk talk and formal presentations of informatics methods and/or aims of an National Institutes of Health style K or R grant proposal. For (3), the student presents their translational research proposal concept at the beginning of the course, and works with members of the TRIEC with corresponding expertise. The final course grade is a combination of the final project, paper presentations and class participation. We offered TRI to a first cohort of students in the Fall semester of 2018. DISCUSSION/SIGNIFICANCE OF IMPACT: Translational research informatics is a sub-domain of biomedical informatics that applies and develops informatics theory and methods for translational research. TRI covers a diverse set of informatics topics that are applicable across the translational spectrum. It covers both didactic material and hands-on experience in using the material in grant proposals and research studies. TRI’s course content, teaching methodology and learning activities enable students to initially learn factual informatics knowledge and skills for translational research correspond to the ‘Remember, Understand, and Apply’ levels of the Bloom’s taxonomy [10]. The final project provides opportunity for applying these informatics concepts corresponding to the ‘Analyze, Evaluate, and Create’ levels of the Bloom’s taxonomy [10]. This inter-professional, competency-based, modular course will develop an informatics-enabled workforce trained in using state-of-the-art informatics solutions, increasing the effectiveness of translational science and precision medicine, and promoting FAIR principles in research data management and processes. Future work includes opening the course to all Clinical and Translational Science Award hubs and publishing the course material as a reference book. While student evaluations for the first cohort will be available end of the semester, true evaluation of TRI will be the number of trainees taking the course and successful grant proposal submissions. References: 1. Wilkinson MD, Dumontier M, et al. The FAIR Guiding Principles for scientific data management and stewardship. Sci Data. 2016 Mar 15. 2. National Center for Advancing Translational Sciences. Translational Science Spectrum. National Center for Advancing Translational Sciences. 2015 [cited 2018 Nov 15]. Available from: https://ncats.nih.gov/translation/spectrum 3. Hu H, Mural RJ, Liebman MN. Biomedical Informatics in Translational Research. 1 edition. Boston: Artech House; 2008. 264 p. 4. Payne PRO, Embi PJ, Niland J. Foundational biomedical informatics research in the clinical and translational science era: a call to action. J Am Med Inform Assoc JAMIA. 2010;17(6):615–6. 5. Payne PRO, Embi PJ, editors. Translational Informatics: Realizing the Promise of Knowledge-Driven Healthcare. Softcover reprint of the original 1 st ed. 2015 edition. Springer; 2016. 196 p. 6. Richesson R, Andrews J, editors. Clinical Research Informatics. 2 nd ed. Springer International Publishing; 2019. (Health Informatics). 7. Robertson D, MD GHW, editors. Clinical and Translational Science: Principles of Human Research. 2 edition. Amsterdam: Academic Press; 2017. 808 p. 8. Shen B, Tang H, Jiang X, editors. Translational Biomedical Informatics: A Precision Medicine Perspective. Softcover reprint of the original 1 st ed. 2016 edition. S.l.: Springer; 2018. 340 p. 9. Valenta AL, Meagher EA, Tachinardi U, Starren J. Core informatics competencies for clinical and translational scientists: what do our customers and collaborators need to know? J Am Med Inform Assoc. 2016 Jul 1;23(4):835–9. 10. Anderson LW, Krathwohl DR, Airasian PW, Cruikshank KA, Mayer RE, Pintrich PR, Raths J, Wittrock MC. A Taxonomy for Learning, Teaching, and Assessing: A Revision of Bloom’s Taxonomy of Educational Objectives, Abridged Edition. 1 edition. New York: Pearson; 2000.