Performance and usability testing of an automated tool for detection of peripheral artery disease using electronic health records.

Peripheral artery disease (PAD) is a common cardiovascular disorder that is frequently underdiagnosed, which can lead to poorer outcomes due to lower rates of medical optimization. We aimed to develop an automated tool to identify undiagnosed PAD and evaluate physician acceptance of a dashboard representation of risk assessment. Data were derived from electronic health records (EHR). We developed and compared traditional risk score models to novel machine learning models. For usability testing, primary and specialty care physicians were recruited and interviewed until thematic saturation. Data from 3168 patients with PAD and 16,863 controls were utilized. Results showed a deep learning model that utilized time engineered features outperformed random forest and traditional logistic regression models (average AUCs 0.96, 0.91 and 0.81, respectively), P < 0.0001. Of interviewed physicians, 75% were receptive to an EHR-based automated PAD model. Feedback emphasized workflow optimization, including integrating risk assessments directly into the EHR, using dashboard designs that minimize clicks, and providing risk assessments for clinically complex patients. In conclusion, we demonstrate that EHR-based machine learning models can accurately detect risk of PAD and that physicians are receptive to automated risk detection for PAD. Future research aims to prospectively validate model performance and impact on patient outcomes.

Comparing methods for estimation of heterogeneous treatment effects using observational data from health care databases.

There is growing interest in using routinely collected data from health care databases to study the safety and effectiveness of therapies in "real-world" conditions, as it can provide complementary evidence to that of randomized controlled trials. Causal inference from health care databases is challenging because the data are typically noisy, high dimensional, and most importantly, observational. It requires methods that can estimate heterogeneous treatment effects while controlling for confounding in high dimensions. Bayesian additive regression trees, causal forests, causal boosting, and causal multivariate adaptive regression splines are off-the-shelf methods that have shown good performance for estimation of heterogeneous treatment effects in observational studies of continuous outcomes. However, it is not clear how these methods would perform in health care database studies where outcomes are often binary and rare and data structures are complex. In this study, we evaluate these methods in simulation studies that recapitulate key characteristics of comparative effectiveness studies. We focus on the conditional average effect of a binary treatment on a binary outcome using the conditional risk difference as an estimand. To emulate health care database studies, we propose a simulation design where real covariate and treatment assignment data are used and only outcomes are simulated based on nonparametric models of the real outcomes. We apply this design to 4 published observational studies that used records from 2 major health care databases in the United States. Our results suggest that Bayesian additive regression trees and causal boosting consistently provide low bias in conditional risk difference estimates in the context of health care database studies.

Big Data and Adverse Drug Reaction Detection.

Big Data holds the promise of fundamentally transforming the manner in which adverse drug reactions can be identified and evaluated. This commentary discusses new data sources that are envisioned to form a Big Data-enabled pharmacovigilance system and the role of these data in powering the future of adverse drug reactions detection.

Toward enhanced pharmacovigilance using patient-generated data on the internet.

The promise of augmenting pharmacovigilance with patient-generated data drawn from the Internet was called out by a scientific committee charged with conducting a review of the current and planned pharmacovigilance practices of the US Food and Drug Administration (FDA). To this end, we present a study on harnessing behavioral data drawn from Internet search logs to detect adverse drug reactions (ADRs). By analyzing search queries collected from 80 million consenting users and by using a widely recognized benchmark of ADRs, we found that the performance of ADR detection via search logs is comparable and complementary to detection based on the FDA's adverse event reporting system (AERS). We show that by jointly leveraging data from the AERS and search logs, the accuracy of ADR detection can be improved by 19% relative to the use of each data source independently. The results suggest that leveraging nontraditional sources such as online search logs could supplement existing pharmacovigilance approaches.

Performance of pharmacovigilance signal-detection algorithms for the FDA adverse event reporting system.

Signal-detection algorithms (SDAs) are recognized as vital tools in pharmacovigilance. However, their performance characteristics are generally unknown. By leveraging a unique gold standard recently made public by the Observational Medical Outcomes Partnership (OMOP) and by conducting a unique systematic evaluation, we provide new insights into the diagnostic potential and characteristics of SDAs that are routinely applied to the US Food and Drug Administration (FDA) Adverse Event Reporting System (AERS). We find that SDAs can attain reasonable predictive accuracy in signaling adverse events. Two performance classes emerge, indicating that the class of approaches that address confounding and masking effects benefits safety surveillance. Our study shows that not all events are equally detectable, suggesting that specific events might be monitored more effectively using other data sources. We provide performance guidelines for several operating scenarios to inform the trade-off between sensitivity and specificity for specific use cases. We also propose an approach and demonstrate its application in identifying optimal signaling thresholds, given specific misclassification tolerances.

Pharmacovigilance using clinical notes.

With increasing adoption of electronic health records (EHRs), there is an opportunity to use the free-text portion of EHRs for pharmacovigilance. We present novel methods that annotate the unstructured clinical notes and transform them into a deidentified patient-feature matrix encoded using medical terminologies. We demonstrate the use of the resulting high-throughput data for detecting drug-adverse event associations and adverse events associated with drug-drug interactions. We show that these methods flag adverse events early (in most cases before an official alert), allow filtering of spurious signals by adjusting for potential confounding, and compile prevalence information. We argue that analyzing large volumes of free-text clinical notes enables drug safety surveillance using a yet untapped data source. Such data mining can be used for hypothesis generation and for rapid analysis of suspected adverse event risk.

Tramadol inhibits the contractility of isolated human myometrium.

This study was conducted to determine whether the atypical opioid analgesic tramadol inhibits the contractility of isolated non-pregnant human myometrium. Ten strips of non-pregnant human myometrium stimulated with 55 mm potassium chloride (KCl) were treated with three concentrations (30, 100 and 300 µm) of tramadol to test for any inhibitory effect of tramadol. The effects of concurrent administration of the ß adrenoceptor antagonist propranolol (1 µm), the guanylyl cyclase and nitric oxide synthase inhibitor methylene blue (20 µm) and the opioid receptor antagonist naloxone (100 µm) with tramadol were also studied. Tramadol caused a concentration-dependent inhibition of KCl-induced myometrial contractility, which was statistically significant at all three concentrations of tramadol used. Propranolol significantly reversed the inhibitory effect of 100 µm tramadol on KCl-induced myometrial contractility but not that of 300 µm tramadol. Neither methylene blue nor naloxone reversed the inhibitory effect of tramadol on KCl-induced myometrial contractility. These results suggest that tramadol inhibits KCl-induced contractility of isolated human myometrium. They also suggest that tramadol relaxes the myometrium due to stimulation of ß1 adrenoceptors. However, the concentrations of tramadol required to relax the myometrium were high and likely to be attained at toxic doses, rather than therapeutic doses, of tramadol.

Translational bioinformatics embraces big data.

We review the latest trends and major developments in translational bioinformatics in the year 2011-2012. Our emphasis is on highlighting the key events in the field and pointing at promising research areas for the future. The key take-home points are: • Translational informatics is ready to revolutionize human health and healthcare using large-scale measurements on individuals. • Data-centric approaches that compute on massive amounts of data (often called "Big Data") to discover patterns and to make clinically relevant predictions will gain adoption. • Research that bridges the latest multimodal measurement technologies with large amounts of electronic healthcare data is increasing; and is where new breakthroughs will occur.

Novel data-mining methodologies for adverse drug event discovery and analysis.

An important goal of the health system is to identify new adverse drug events (ADEs) in the postapproval period. Datamining methods that can transform data into meaningful knowledge to inform patient safety have proven essential for this purpose. New opportunities have emerged to harness data sources that have not been used within the traditional framework. This article provides an overview of recent methodological innovations and data sources used to support ADE discovery and analysis.

Five-year functional outcome analysis of ankle fracture fixation.

This study examines retrospectively the functional outcome of patients at 5 years following their ankle fracture surgery using the Olerud-Molander Ankle Score (OMAS) and SF-12 questionnaire. Of 69 patients, 43 were females and 26 males. The mean age was 50.7 years. There were 74 and 26% of Weber 'B' and 'C' fractures, respectively. The mean OMAS was 75.2. About 63% of the patients were still complaining of stiffness, around 45% patients were still complaining of ankle swelling, 50% of patients still had some sort of pain, 39% still thought that they had not fully recovered and 38% did not return to their pre-injury sporting activity. Apart from the age, no significant difference was seen in the OMAS due to gender, fracture type or timing of surgery. Our findings show that many patients who have had surgery for ankle fractures will still have some functional limitations even 5 years after the injury.

UK acquired hepatitis E--An emerging problem?

Eight cases of hepatitis E acquired in the UK are reported. These cases presented to an inner city hospital in Birmingham, UK, over a 5-month period in 2005. HEV is considered unusual in the UK and generally occurs after travel to endemic regions. Only five cases of hepatitis E acquired in the UK have been reported in the literature. This series represents an increase in the local incidence of hepatitis E, particularly that of UK-acquired infection. HEV should be considered in all patients with acute hepatitis, irrespective of travel history.

Screening time for extra-capsular proximal femoral fracture fixation; the difference between extra-medullary and intra-medullary implant usage.

The aim of this study was to compare the fluoroscopic screening time used for treatment of fractures of the trochanteric region of the femur using two different implant systems. Data were collected from 277 proximal femoral fracture fixations. A dynamic hip screw (DHS) was used in 145, and an intra-medullary hip screw (IMHS) was used in 132. There was no difference between the two groups with respect to age, gender or side. Altogether, there were 42% two parts, 35% were three parts and 23% were four parts extra-capsular neck fractures. There was no statistical difference in ionising radiation exposure in closed reduction of these fractures regardless of the fracture configuration or surgical experience of the surgeon. The mean screening time to implant a DHS in two part fractures was 0.48 min, for three part fractures it was 0.45 min and for four part fractures it was 0.46 min. The mean screening time to implant IMHS was 1.02 min for two part fractures, 0.96 min for three part fractures and 1.03 min for four part fractures. These differences were statistically significant (P < or = 0.05).

HyBrow: a prototype system for computer-aided hypothesis evaluation.

MOTIVATION: Experimental design, hypothesis-testing and model-building in the current data-rich environment require the biologists' to collect, evaluate and integrate large amounts of information of many disparate kinds. Developing a unified framework for the representation and conceptual integration of biological data and processes is a major challenge in bioinformatics because of the variety of available data and the different levels of detail at which biological processes can be considered. RESULTS: We have developed the HyBrow (Hypothesis Browser) system as a prototype bioinformatics tool for designing hypotheses and evaluating them for consistency with existing knowledge. HyBrow consists of a modeling framework with the ability to accommodate diverse biological information sources, an event-based ontology for representing biological processes at different levels of detail, a database to query information in the ontology and programs to perform hypothesis design and evaluation. We demonstrate the HyBrow prototype using the galactose gene network in Saccharomyces cerevisiae as our test system, and evaluate alternative hypotheses for consistency with stored information. AVAILABILITY: www.hybrow.org

CLENCH: a program for calculating Cluster ENriCHment using the Gene Ontology.

SUMMARY: Analysis of microarray data most often produces lists of genes with similar expression patterns, which are then subdivided into functional categories for biological interpretation. Such functional categorization is most commonly accomplished using Gene Ontology (GO) categories. Although there are several programs that identify and analyze functional categories for human, mouse and yeast genes, none of them accept Arabidopsis thaliana data. In order to address this need for A.thaliana community, we have developed a program that retrieves GO annotations for A.thaliana genes and performs functional category analysis for lists of genes selected by the user. AVAILABILITY: http://www.personal.psu.edu/nhs109/Clench

A tool-kit for cDNA microarray and promoter analysis.

We describe two sets of programs for expediting routine tasks in analysis of cDNA microarray data and promoter sequences. The first set permits bad data points to be flagged with respect to a number of parameters and performs normalization in three different ways. It allows combining of result files into comprehensive data sets, evaluation of the quality of both technical and biological replicates and row and/or column standardization of data matrices. The second set supports mapping ESTs in the genome, identifying the corresponding genes and recovering their promoters, analyzing promoters for transcription factor binding sites, and visual representation of the results. The programs are designed primarily for Arabidopsis thaliana researchers, but can be adapted readily for other model systems. Availability and Supplementary information: http://www.personal.psu.edu/nhs109/Programs/

Critical processing factors affecting rheological behavior of a wax based formulation.

The use of a wax-based vehicle is one approach to stabilize a drug which is susceptible to hydrolysis and/or oxidation. The drug used in the study, as a microfine powder, is dispersed in the wax mixture and encapsulated in a soft gelatin capsule. To ensure reproducibility of drug content uniformity and encapsulability of the soft gelatin capsule dosage form, optimal viscosity and lot to lot uniformity of the viscosity of the suspension are required. The objective of the study was to identify the critical processing factors which could affect the rheological behavior of the wax based vehicle. Rheological behavior of the vehicle at temperatures ranging from 15 to 90 degrees C was evaluated using a CSL Rheometer equipped with parallel plates and a shear rate sweep mode, unless otherwise specified. Viscosity vs. temperature profiles of the vehicle were determined using the same conditions at different cooling rates ranging from 1.3 to 20 degrees C per min. Three distinct regions of phase transition of the wax mixture can be seen in the Arrhenius plot: (i) a sol region at temperatures above 50 degrees C, (ii) a transition of gel to sol at temperatures ranging from 30 to 45 degrees C, and (iii) a gel region at temperatures below 30 degrees C. The vehicle in a sol region behaved as a Newtonian fluid, indicating minimal interactions between the hydrocarbon chains of the vehicle. The vehicle in a gel region behaved thixotropic in nature, as indicated by a hysteresis loop. The shear rate had a more pronounced effect on the area of thixotropy than the shear time. The cooling rate had a pronounced effect on the resultant viscosity. At the same applied shear rate, the vehicle which was cooled at a faster rate, may cause a recrystallization of the wax mixture in different crystalline forms, resulting in a higher viscosity than the vehicle cooled at a slower rate. This effect was more pronounced when the shear was applied at a lower rate. The results of this study indicate that shear rate and cooling rate are the critical processing factors in controlling the viscosity of the final product and must be well controlled in the manufacturing procedure.

Safety and efficacy of an oil-adjuvant vaccine against haemorrhagic septicaemia in buffalo calves: cross-protection between the serotypes B:2,5 and E:2,5.

The safety, efficacy and duration of immunity of an improved oil-adjuvant vaccine against haemorrhagic septicaemia, containing inactivated cells of Pasteurella multocida serotype B:2,5, were tested in young buffalo calves in Pakistan. For safety testing, five buffalo calves were vaccinated intramuscularly with twice the normal dose, and six weeks later with a normal dose. Except for a transient rise in rectal temperature at six hours after the vaccinations, no systemic reactions were observed. The buffaloes remained in good condition and had a normal appetite. No local reactions were observed at the injection site. For efficacy testing two trials were carried out. In the first, buffalo calves were vaccinated intramuscularly either with two doses two-and-a-half months apart, or with a single dose, or left unvaccinated. They were challenged subcutaneously with virulent P multocida after eight, 13 or 15 months. After challenge at eight months the four buffaloes given two doses and the buffalo given one dose were protected, whereas the control animal developed the typical signs of the disease. After the challenges at 13 and 15 months, the vaccinated animals were still protected whereas the control animals died. In the second trial, buffalo calves were vaccinated intramuscularly either with two doses two months apart, or with a single dose at two months or left unvaccinated. The buffaloes were challenged after eight or 14 months. After challenge at eight months the four control animals died, whereas three of the four buffaloes given a single dose were protected. After challenge at 14 months, the three control animals died, whereas four of the five buffaloes given two doses and both the buffaloes given a single dose were protected. To test for cross-protection against the heterologous serotypes E:2,5 and B:3,4, groups of mice were vaccinated once or left unvaccinated. Four weeks later, the vaccinated and control groups were challenged with a dilution series of the different challenge cultures. The vaccine appeared to induce protection against challenge with different strains of serotypes B:2,5 and E:2,5 but not against strains of serotype B:3,4.