Ramkiran Gouripeddi

Effectiveness of Fundoplication or Gastrojejunal Feeding in Children With Neurologic Impairment

BACKGROUND AND OBJECTIVES Gastroesophageal reflux (GER), aspiration, and secondary complications lead to morbidity and mortality in children with neurologic impairment (NI), dysphagia, and gastrostomy feeding. Fundoplication and gastrojejunal (GJ) feeding can reduce risk. We compared GJ to fundoplication using first-year postprocedure reflux-related hospitalization (RRH) rates. METHODS We identified children with NI, dysphagia requiring gastrostomy tube feeding and GER undergoing initial GJ placement or fundoplication from January 1, 2007 to December 31, 2012. Data came from the Pediatric Health Information Systems augmented by laboratory, microbiology, and radiology results. GJ placement was ascertained using radiology results and fundoplication by International Classification of Diseases, Ninth Revision, Clinical Modification codes. Subjects were matched within hospital using propensity scores. The primary outcome was first-year postprocedure RRH rate (hospitalization for GER disease, other esophagitis, aspiration pneumonia, other pneumonia, asthma, or mechanical ventilation). Secondary outcomes included failure to thrive, death, repeated initial intervention, crossover intervention, and procedural complications. RESULTS We identified 1178 children with fundoplication and 163 with GJ placement, matching 114 per group. Matched sample RRH incident rate per child-year (95% confidence interval) for GJ was 2.07 (1.62-2.64) and for fundoplication 1.67 (1.28-2.18), P = .19. Odds of death were similar between groups. Failure to thrive, repeat of initial intervention, and crossover intervention were more common in the GJ group. CONCLUSIONS In children with NI, GER, and dysphagia: fundoplication and GJ feeding have similar RRH outcomes. Either intervention can reduce future aspiration risk; the choice can reflect non-RRH-related complication risks, caregiver preference, and clinician recommendation.

Predicting risk of complications following a drug eluting stent procedure: A SVM approach for imbalanced data

Drug Eluting Stents (DES) have distinct advantages over other Percutaneous Coronary Intervention procedures, but have recently been associated with the development of serious complications after the procedure. There is a growing need for understanding the risk of these complications, which has led to the development of simple statistical models. In this work, we have developed a predictive model based on Support Vector Machines on a real world live dataset consisting of clinical variables of patients being treated at a cardiac care facility to predict the risk of complications at 12 months following a DES procedure. A significant challenge in this work, common to most clinical machine learning datasets, was imbalanced data, and our results showed the effectiveness of the Synthetic Minority Over-sampling Technique (SMOTE) to address this issue. The developed predictive model provided an accuracy of 94% with a 0.97 AUC (Area under ROC curve), indicating high potential to be used as a decision support for management of patients following a DES procedure in real-world cardiac care facilities

A survey of practices for the use of electronic health records to support research recruitment

Electronic health records (EHRs) provide great promise for identifying cohorts and enhancing research recruitment. Such approaches are sorely needed, but there are few descriptions in the literature of prevailing practices to guide their use. A multidisciplinary workgroup was formed to examine current practices in the use of EHRs in recruitment and to propose future directions. The group surveyed consortium members regarding current practices. Over 98% of the Clinical and Translational Science Award Consortium responded to the survey. Brokered and self-service data warehouse access are in early or full operation at 94% and 92% of institutions, respectively, whereas, EHR alerts to providers and to research teams are at 45% and 48%, respectively, and use of patient portals for research is at 20%. However, these percentages increase significantly to 88% and above if planning and exploratory work were considered cumulatively. For most approaches, implementation reflected perceived demand. Regulatory and workflow processes were similarly varied, and many respondents described substantive restrictions arising from logistical constraints and limitations on collaboration and data sharing. Survey results reflect wide variation in implementation and approach, and point to strong need for comparative research and development of best practices to protect patients and facilitate interinstitutional collaboration and multisite research.

Enhancing Comparative Effectiveness Research With Automated Pediatric Pneumonia Detection in a Multi-Institutional Clinical Repository: A PHIS+ Pilot Study

Background Community-acquired pneumonia is a leading cause of pediatric morbidity. Administrative data are often used to conduct comparative effectiveness research (CER) with sufficient sample sizes to enhance detection of important outcomes. However, such studies are prone to misclassification errors because of the variable accuracy of discharge diagnosis codes. Objective The aim of this study was to develop an automated, scalable, and accurate method to determine the presence or absence of pneumonia in children using chest imaging reports. Methods The multi-institutional PHIS+ clinical repository was developed to support pediatric CER by expanding an administrative database of children’s hospitals with detailed clinical data. To develop a scalable approach to find patients with bacterial pneumonia more accurately, we developed a Natural Language Processing (NLP) application to extract relevant information from chest diagnostic imaging reports. Domain experts established a reference standard by manually annotating 282 reports to train and then test the NLP application. Findings of pleural effusion, pulmonary infiltrate, and pneumonia were automatically extracted from the reports and then used to automatically classify whether a report was consistent with bacterial pneumonia. Results Compared with the annotated diagnostic imaging reports reference standard, the most accurate implementation of machine learning algorithms in our NLP application allowed extracting relevant findings with a sensitivity of .939 and a positive predictive value of .925. It allowed classifying reports with a sensitivity of .71, a positive predictive value of .86, and a specificity of .962. When compared with each of the domain experts manually annotating these reports, the NLP application allowed for significantly higher sensitivity (.71 vs .527) and similar positive predictive value and specificity . Conclusions NLP-based pneumonia information extraction of pediatric diagnostic imaging reports performed better than domain experts in this pilot study. NLP is an efficient method to extract information from a large collection of imaging reports to facilitate CER.

Metadata Discovery of Heterogeneous Biomedical Datasets Using Token-Based Features

Metadata discovery is the process of recognizing semantics and descriptors of data elements and datasets. This study uses a machine-learning approach to classify biomedical dataset characteristics for metadata discovery. Four common types of biomedical data sources were included in this study - genetic variant, protein structure, scientific publications, and general English corpus. Decision tree classification models were built using token-based features derived from these data files. These decision tree classification models are able to identify the four data sources with average F1 scores ranging from 0.935 to 1.000. This study demonstrates that biomedical data of different types have different distributions of token-based document structural features and that such structural features can be leveraged for metadata discovery.

Methods for examining data quality in healthcare integrated data repositories

This paper summarizes content of the workshop focused on data quality. The first speaker (VH) described data quality infrastructure and data quality evaluation methods currently in place within the Observational Data Science and Informatics (OHDSI) consortium. The speaker described in detail a data quality tool called Achilles Heel and latest development for extending this tool. Interim results of an ongoing Data Quality study within the OHDSI consortium were also presented. The second speaker (MK) described lessons learned and new data quality checks developed by the PEDsNet pediatric research network. The last two speakers (JB, RG) described tools developed by the Sentinel Initiative and University of Utahs service oriented framework. The workshop discussed at the end and throughout how data quality assessment can be advanced by combining best features of each network.

Comparison of Empiric Antibiotics for Acute Osteomyelitis in Children

OBJECTIVES Broad-spectrum antibiotics are commonly used for the empiric treatment of acute hematogenous osteomyelitis and often target methicillin-resistant Staphylococcus aureus (MRSA) with medication-associated risk and unknown treatment benefit. We aimed to compare clinical outcomes among patients with osteomyelitis who did and did not receive initial antibiotics used to target MRSA. METHODS A retrospective cohort study of 974 hospitalized children 2 to 18 years old using the Pediatric Health Information System database, augmented with clinical data. Rates of hospital readmission, repeat MRI and 72-hour improvement in inflammatory markers were compared between treatment groups. RESULTS Repeat MRI within 7 and 180 days was more frequent among patients who received initial MRSA coverage versus methicillin-sensitive S aureus (MSSA)-only coverage (8.6% vs 4.1% within 7 days [P = .02] and 12% vs 5.8% within 180 days [P < .01], respectively). Ninety- and 180-day hospital readmission rates were similar between coverage groups (9.0% vs 8.7% [P = .87] and 10.9% vs 11.2% [P = .92], respectively). Patients with MRSA- and MSSA-only coverage had similar rates of 72-hour improvement in C-reactive protein values, but patients with MRSA coverage had a lower rate of 72-hour white blood cell count normalization compared with patients with MSSA-only coverage (4.2% vs 16.4%; P = .02). CONCLUSIONS In this study of children hospitalized with acute hematogenous osteomyelitis, early antibiotic treatment used to target MRSA was associated with a higher rate of repeat MRI compared with early antibiotic treatment used to target MSSA but not MRSA. Hospital readmission rates were similar for both treatment groups.

Dietary Management Software for Chronic Kidney Disease: Current Status and Open Issues

Chronic kidney disease (CKD) affects about 10 % of the population worldwide. Millions of people die prematurely from CKD each year. Dietary restrictions can slow the progression of CKD and improve outcomes. In recent years, introduction of new technologies has enabled patients to better manage their own dietary intake and health. Several dietary management software tools are currently available providing personalized nutrition and diet management advice for CKD patients. In this paper, we provide an overview of these software tools and discuss some open issues and possible solutions, in hope of stimulating future research in consumer health informatics for CKD.

VIRGO: Virtual Identity Resolution on the Go

We present here the design, development and testing of an open-source software system supporting on-the-fly identity resolution, VIRGO: Virtual Identity Resolution on the Go. The system implements the open source Choice Maker algorithms and it was developed using a service oriented architecture (SOA) approach, which allows its use either as a standalone service or integrated in any SOA workflow. The system performance in our test case achieves the following merit figures, accuracy: 0.992, sensitivity: 0.981 and specificity: 0.992, and it shows linear scaling with the number of records considered. To demonstrate integration into a SOA framework we show how to incorporate VIRGO into the Open Further framework to perform record linkage when federating health records from multiple sources to identify cohorts for clinical research.

A Service Oriented Framework to Assess the Quality of Electronic Health Data for Clinical Research

Retrospective/observational clinical research studies are dependent on the secondary use of electronic health record (EHR) data for obtaining important results about the effectiveness of different medical interventions. In contrast to traditional clinical trials these studies provide results from real-world clinical settings, but suffer from data quality issues. Therefore, it is important to take into account the nature and quality of data when designing these studies in order to differentiate between true and artifactual variations [1]. We are developing a service-oriented framework to assess the quality of EHR data.