The publication data currently available has been vetted by Vanderbilt faculty, staff, administrators and trainees. The data itself is retrieved directly from NCBI's PubMed and is automatically updated on a weekly basis to ensure accuracy and completeness.
If you have any questions or comments, please contact us.
OBJECTIVE - Hepatorenal Syndrome (HRS) is a devastating form of acute kidney injury (AKI) in advanced liver disease patients with high morbidity and mortality, but phenotyping algorithms have not yet been developed using large electronic health record (EHR) databases. We evaluated and compared multiple phenotyping methods to achieve an accurate algorithm for HRS identification.
MATERIALS AND METHODS - A national retrospective cohort of patients with cirrhosis and AKI admitted to 124 Veterans Affairs hospitals was assembled from electronic health record data collected from 2005 to 2013. AKI was defined by the Kidney Disease: Improving Global Outcomes criteria. Five hundred and four hospitalizations were selected for manual chart review and served as the gold standard. Electronic Health Record based predictors were identified using structured and free text clinical data, subjected through NLP from the clinical Text Analysis Knowledge Extraction System. We explored several dimension reduction techniques for the NLP data, including newer high-throughput phenotyping and word embedding methods, and ascertained their effectiveness in identifying the phenotype without structured predictor variables. With the combined structured and NLP variables, we analyzed five phenotyping algorithms: penalized logistic regression, naïve Bayes, support vector machines, random forest, and gradient boosting. Calibration and discrimination metrics were calculated using 100 bootstrap iterations. In the final model, we report odds ratios and 95% confidence intervals.
RESULTS - The area under the receiver operating characteristic curve (AUC) for the different models ranged from 0.73 to 0.93; with penalized logistic regression having the best discriminatory performance. Calibration for logistic regression was modest, but gradient boosting and support vector machines were superior. NLP identified 6985 variables; a priori variable selection performed similarly to dimensionality reduction using high-throughput phenotyping and semantic similarity informed clustering (AUC of 0.81 - 0.82).
CONCLUSION - This study demonstrated improved phenotyping of a challenging AKI etiology, HRS, over ICD-9 coding. We also compared performance among multiple approaches to EHR-derived phenotyping, and found similar results between methods. Lastly, we showed that automated NLP dimension reduction is viable for acute illness.
Copyright © 2018 Elsevier Inc. All rights reserved.
BACKGROUND - Electronic health records (EHRs) are increasingly used for clinical and translational research through the creation of phenotype algorithms. Currently, phenotype algorithms are most commonly represented as noncomputable descriptive documents and knowledge artifacts that detail the protocols for querying diagnoses, symptoms, procedures, medications, and/or text-driven medical concepts, and are primarily meant for human comprehension. We present desiderata for developing a computable phenotype representation model (PheRM).
METHODS - A team of clinicians and informaticians reviewed common features for multisite phenotype algorithms published in PheKB.org and existing phenotype representation platforms. We also evaluated well-known diagnostic criteria and clinical decision-making guidelines to encompass a broader category of algorithms.
RESULTS - We propose 10 desired characteristics for a flexible, computable PheRM: (1) structure clinical data into queryable forms; (2) recommend use of a common data model, but also support customization for the variability and availability of EHR data among sites; (3) support both human-readable and computable representations of phenotype algorithms; (4) implement set operations and relational algebra for modeling phenotype algorithms; (5) represent phenotype criteria with structured rules; (6) support defining temporal relations between events; (7) use standardized terminologies and ontologies, and facilitate reuse of value sets; (8) define representations for text searching and natural language processing; (9) provide interfaces for external software algorithms; and (10) maintain backward compatibility.
CONCLUSION - A computable PheRM is needed for true phenotype portability and reliability across different EHR products and healthcare systems. These desiderata are a guide to inform the establishment and evolution of EHR phenotype algorithm authoring platforms and languages.
© The Author 2015. Published by Oxford University Press on behalf of the American Medical Informatics Association.
OBJECTIVE - The objective was to develop non-invasive predictive models for late-onset neonatal sepsis from off-the-shelf medical data and electronic medical records (EMR).
DESIGN - The data used in this study are from 299 infants admitted to the neonatal intensive care unit in the Monroe Carell Jr. Children's Hospital at Vanderbilt and evaluated for late-onset sepsis. Gold standard diagnostic labels (sepsis negative, culture positive sepsis, culture negative/clinical sepsis) were assigned based on all the laboratory, clinical and microbiology data available in EMR. Only data that were available up to 12 h after phlebotomy for blood culture testing were used to build predictive models using machine learning (ML) algorithms.
MEASUREMENT - We compared sensitivity, specificity, positive predictive value and negative predictive value of sepsis treatment of physicians with the predictions of models generated by ML algorithms.
RESULTS - The treatment sensitivity of all the nine ML algorithms and specificity of eight out of the nine ML algorithms tested exceeded that of the physician when culture-negative sepsis was included. When culture-negative sepsis was excluded both sensitivity and specificity exceeded that of the physician for all the ML algorithms. The top three predictive variables were the hematocrit or packed cell volume, chorioamnionitis and respiratory rate.
CONCLUSIONS - Predictive models developed from off-the-shelf and EMR data using ML algorithms exceeded the treatment sensitivity and treatment specificity of clinicians. A prospective study is warranted to assess the clinical utility of the ML algorithms in improving the accuracy of antibiotic use in the management of neonatal sepsis.
INTRODUCTION - Pulmonary nodules of the adenocarcinoma spectrum are characterized by distinctive morphological and radiologic features and variable prognosis. Noninvasive high-resolution computed tomography-based risk stratification tools are needed to individualize their management.
METHODS - Radiologic measurements of histopathologic tissue invasion were developed in a training set of 54 pulmonary nodules of the adenocarcinoma spectrum and validated in 86 consecutively resected nodules. Nodules were isolated and characterized by computer-aided analysis, and data were analyzed by Spearman correlation, sensitivity, and specificity and the positive and negative predictive values.
RESULTS - Computer-aided nodule assessment and risk yield (CANARY) can noninvasively characterize pulmonary nodules of the adenocarcinoma spectrum. Unsupervised clustering analysis of high-resolution computed tomography data identified nine unique exemplars representing the basic radiologic building blocks of these lesions. The exemplar distribution within each nodule correlated well with the proportion of histologic tissue invasion, Spearman R = 0.87, p < 0.0001 and 0.89 and p < 0.0001 for the training and the validation set, respectively. Clustering of the exemplars in three-dimensional space corresponding to tissue invasion and lepidic growth was used to develop a CANARY decision algorithm that successfully categorized these pulmonary nodules as "aggressive" (invasive adenocarcinoma) or "indolent" (adenocarcinoma in situ and minimally invasive adenocarcinoma). Sensitivity, specificity, positive predictive value, and negative predictive value of this approach for the detection of aggressive lesions were 95.4, 96.8, 95.4, and 96.8%, respectively, in the training set and 98.7, 63.6, 94.9, and 87.5%, respectively, in the validation set.
CONCLUSION - CANARY represents a promising tool to noninvasively risk stratify pulmonary nodules of the adenocarcinoma spectrum.
BACKGROUND - To facilitate the use of automated databases for studies of sudden cardiac death, we previously developed a computerized case definition that had a positive predictive value between 86% and 88%. However, the definition has not been specifically validated for prescription opioid users, for whom out-of-hospital overdose deaths may be difficult to distinguish from sudden cardiac death.
FINDINGS - We assembled a cohort of persons 30-74 years of age prescribed propoxyphene or hydrocodone who had no life-threatening non-cardiovascular illness, diagnosed drug abuse, residence in a nursing home in the past year, or hospital stay within the past 30 days. Medical records were sought for a sample of 140 cohort deaths within 30 days of a prescription fill meeting the computer case definition. Of the 140 sampled deaths, 81 were adjudicated; 73 (90%) were sudden cardiac deaths. Two deaths had possible opioid overdose; after removing these two the positive predictive value was 88%.
CONCLUSIONS - These findings are consistent with our previous validation studies and suggest the computer case definition of sudden cardiac death is a useful tool for pharmacoepidemiologic studies of opioid analgesics.
High resolution mapping of electrical activity is becoming an important technique for analysing normal and dysrhythmic gastrointestinal (GI) slow wave activity. Several methods are used to extract meaningful information from the large quantities of data obtained, however, at present these methods can only be used offline. Thus, all analysis currently performed is retrospective and done after the recordings have finished. Limited information about the quality or characteristics of the data is therefore known while the experiments take place. Building on these offline analysis methods, an online implementation has been developed that identifies and displays slow wave activations working alongside an existing recording system. This online system was developed by adapting existing and novel signal processing techniques and linking these to a new user interface to present the extracted information. The system was tested using high resolution porcine data, and will be applied in future high resolution mapping studies allowing researchers to respond in real time to experimental observations.
High resolution electrical mapping of slow waves on the stomach serosa has improved our understanding of gastric electrical activity in normal and diseased states. In order to assess the signals acquired from high resolution mapping, a robust framework is required. Our framework is semi-automated and allows for rapid processing, analysis and interpretation of slow waves via qualitative and quantitative measures including isochronal activation time mapping, and velocity and amplitude mapping. Noise removal techniques were validated for raw recorded signals, where three filters were evaluated for baseline drift removal and three filters for removal of high frequency interference. For baseline drift removal, the Gaussian moving median filter was most effective, while for eliminating high frequency interference the Savitzky Golay filter was the most effective. Methods for assessing slow wave velocity and amplitude were investigated. To estimate slow wave velocity, a finite difference approach with interpolation and smoothing was used. To evaluate the slow wave amplitude and width, a peak and trough method based on Savitzky Golay derivative filters was used. Together, these methods constitute a significantly improved framework for analyzing gastric high resolution mapping data.
In this article, we present the design and implementation of a regional ocular telehealth network for remote assessment and management of diabetic retinopathy (DR), including the design requirements, network topology, protocol design, system work flow, graphics user interfaces, and performance evaluation. The Telemedical Retinal Image Analysis and Diagnosis Network is a computer-aided, image analysis telehealth paradigm for the diagnosis of DR and other retinal diseases using fundus images acquired from primary care end users delivering care to underserved patient populations in the mid-South and southeastern United States.
Rheumatoid arthritis is the only secondary cause of osteoporosis that is considered independent of bone density in the FRAX(®) algorithm. Although input for rheumatoid arthritis in FRAX(®) is a dichotomous variable, intuitively, one would expect that more severe or active disease would be associated with a greater risk for fracture. We reviewed the literature to determine if specific disease parameters or medication use could be used to better characterize fracture risk in individuals with rheumatoid arthritis. Although many studies document a correlation between various parameters of disease activity or severity and decreased bone density, fewer have associated these variables with fracture risk. We reviewed these studies in detail and concluded that disability measures such as HAQ (Health Assessment Questionnaire) and functional class do correlate with clinical fractures but not morphometric vertebral fractures. One large study found a strong correlation with duration of disease and fracture risk but additional studies are needed to confirm this. There was little evidence to correlate other measures of disease such as DAS (disease activity score), VAS (visual analogue scale), acute phase reactants, use of non-glucocorticoid medications and increased fracture risk. We concluded that FRAX(®) calculations may underestimate fracture probability in patients with impaired functional status from rheumatoid arthritis but that this could not be quantified at this time. At this time, other disease measures cannot be used for fracture prediction. However only a few, mostly small studies addressed other disease parameters and further research is needed. Additional questions for future research are suggested.
Copyright © 2011 The International Society for Clinical Densitometry. Published by Elsevier Inc. All rights reserved.