Fiona M. Callaghan

Automatic Tuberculosis Screening Using Chest Radiographs

Tuberculosis is a major health threat in many regions of the world. Opportunistic infections in immunocompromised HIV/AIDS patients and multi-drug-resistant bacterial strains have exacerbated the problem, while diagnosing tuberculosis still remains a challenge. When left undiagnosed and thus untreated, mortality rates of patients with tuberculosis are high. Standard diagnostics still rely on methods developed in the last century. They are slow and often unreliable. In an effort to reduce the burden of the disease, this paper presents our automated approach for detecting tuberculosis in conventional posteroanterior chest radiographs. We first extract the lung region using a graph cut segmentation method. For this lung region, we compute a set of texture and shape features, which enable the X-rays to be classified as normal or abnormal using a binary classifier. We measure the performance of our system on two datasets: a set collected by the tuberculosis control program of our local countys health department in the United States, and a set collected by Shenzhen Hospital, China. The proposed computer-aided diagnostic system for TB screening, which is ready for field deployment, achieves a performance that approaches the performance of human experts. We achieve an area under the ROC curve (AUC) of 87% (78.3% accuracy) for the first set, and an AUC of 90% (84% accuracy) for the second set. For the first set, we compare our system performance with the performance of radiologists. When trying not to miss any positive cases, radiologists achieve an accuracy of about 82% on this set, and their false positive rate is about half of our systems rate.

Lower short- and long-term mortality associated with overweight and obesity in a large cohort study of adult intensive care unit patients

IntroductionTwo thirds of United States adults are overweight or obese, which puts them at higher risk of developing chronic diseases and of death compared with normal-weight individuals. However, recent studies have found that overweight and obesity by themselves may be protective in some contexts, such as hospitalization in an intensive care unit (ICU). Our objective was to determine the relation between body mass index (BMI) and mortality at 30 days and 1 year after ICU admission.MethodsWe performed a cohort analysis of 16,812 adult patients from MIMIC-II, a large database of ICU patients at a tertiary care hospital in Boston, Massachusetts. The data were originally collected during the course of clinical care, and we subsequently extracted our dataset independent of the study outcome.ResultsCompared with normal-weight patients, obese patients had 26% and 43% lower mortality risk at 30 days and 1 year after ICU admission, respectively (odds ratio (OR), 0.74; 95% confidence interval (CI), 0.64 to 0.86) and 0.57 (95% CI, 0.49 to 0.67)); overweight patients had nearly 20% and 30% lower mortality risk (OR, 0.81; 95% CI, 0.70 to 0.93) and OR, 0.68 (95% CI, 0.59 to 0.79)). Severely obese patients (BMI ≥ 40 kg/m2) did not have a significant survival advantage at 30 days (OR, 0.94; 95% CI, 0.74 to 1.20), but did have 30% lower mortality risk at 1 year (OR, 0.70 (95% CI, 0.54 to 0.90)). No significant difference in admission acuity or ICU and hospital length of stay was found across BMI categories.ConclusionOur study supports the hypothesis that patients who are overweight or obese have improved survival both 30 days and 1 year after ICU admission.

Use of internist's free time by ambulatory care Electronic Medical Record systems.

Methods | The Medical Expenditure Panel Survey is a nationally representative longitudinal household survey of health care use and expenditures for noninstitutionalized US civilians.2 The present study used 2010 Household Component and Prescribed Medicines files, which included information on the drug name, days of supply, and amount paid. Information on days of supply was not available before 2010. The institutional review board of the University of Tennessee Health Science Center approved the study and waived the need for informed consent. The study evaluated adults (aged >18 years) who had received at least 1 prescription drug in 2010. Users of the GDDP were defined as individuals who had used the GDDP at least once. If a prescribed medicine event had the total amount paid and days of supply equivalent to any GDDP offerings, the GDDP was coded as 1 (the coding was otherwise 0). Typical GDDP offerings were

Combining structured and unstructured data to identify a cohort of ICU patients who received dialysis.

4 for 30-day supplies and

A comparison of the accuracy of clinical decisions based on full-text articles and on journal abstracts alone: a study among residents in a tertiary care hospital.

10 for 90-day supplies as provided by Walmart, Target, and Kroger. Rite Aid, CVS, Walgreens, and Kmart had other GDDP offerings. Andersen’s3 behavioral model was used to identify factors associated with use of the GDDP. The logistic regression procedure in SAS, version 9.4 (SAS Institute Inc), was used to predict probabilities for different patient groups while controlling for complex survey sampling. We assumed that all prescription drug users had an opportunity to use the GDDP. We also assumed that physician prescribing behaviors, pharmacist practice styles, and pharmacy benefit designs occurred independently of each factor affecting use of the GDDP.

Usefulness of two clinical chorioamnionitis definitions in predicting neonatal infectious outcomes: a systematic review.

OBJECTIVE To develop a generalizable method for identifying patient cohorts from electronic health record (EHR) data-in this case, patients having dialysis-that uses simple information retrieval (IR) tools. METHODS We used the coded data and clinical notes from the 24,506 adult patients in the Multiparameter Intelligent Monitoring in Intensive Care database to identify patients who had dialysis. We used SQL queries to search the procedure, diagnosis, and coded nursing observations tables based on ICD-9 and local codes. We used a domain-specific search engine to find clinical notes containing terms related to dialysis. We manually validated the available records for a 10% random sample of patients who potentially had dialysis and a random sample of 200 patients who were not identified as having dialysis based on any of the sources. RESULTS We identified 1844 patients that potentially had dialysis: 1481 from the three coded sources and 1624 from the clinical notes. Precision for identifying dialysis patients based on available data was estimated to be 78.4% (95% CI 71.9% to 84.2%) and recall was 100% (95% CI 86% to 100%). CONCLUSIONS Combining structured EHR data with information from clinical notes using simple queries increases the utility of both types of data for cohort identification. Patients identified by more than one source are more likely to meet the inclusion criteria; however, including patients found in any of the sources increases recall. This method is attractive because it is available to researchers with access to EHR data and off-the-shelf IR tools.

Comparison of Electronic Pharmacy Prescription Records With Manually Collected Medication Histories in an Emergency Department

Background Many clinicians depend solely on journal abstracts to guide clinical decisions. Objectives This study aims to determine if there are differences in the accuracy of responses to simulated cases between resident physicians provided with an abstract only and those with full-text articles. It also attempts to describe their information-seeking behaviour. Methods Seventy-seven resident physicians from four specialty departments of a tertiary care hospital completed a paper-based questionnaire with clinical simulation cases, then randomly assigned to two intervention groups—access to abstracts-only and access to both abstracts and full-text. While having access to medical literature, they completed an online version of the same questionnaire. Findings The average improvement across departments was not significantly different between the abstracts-only group and the full-text group (p=0.44), but when accounting for an interaction between intervention and department, the effect was significant (p=0.049) with improvement greater with full-text in the surgery department. Overall, the accuracy of responses was greater after the provision of either abstracts-only or full-text (p<0.0001). Although some residents indicated that ‘accumulated knowledge’ was sufficient to respond to the patient management questions, in most instances (83% of cases) they still sought medical literature. Conclusions Our findings support studies that doctors will use evidence when convenient and current evidence improved clinical decisions. The accuracy of decisions improved after the provision of evidence. Clinical decisions guided by full-text articles were more accurate than those guided by abstracts alone, but the results seem to be driven by a significant difference in one department.

The pattern of name tokens in narrative clinical text and a comparison of five systems for redacting them

OBJECTIVE To assess the usefulness of two definitions of acute clinical chorioamnionitis (ACCA) in predicting risk of neonatal infectious outcomes (NIO) and mortality, the first definition requiring maternal fever alone (Fever), and the second requiring ≥ 1 Gibbs criterion besides fever (Fever + 1). STUDY DESIGN PubMed, Web of Science, and the Cochrane Database of Systematic Reviews were searched from January 1, 1979 to April 9, 2013. Twelve studies were reviewed (of 316 articles identified): three studies with term patients, four with preterm premature rupture of membranes (PPROM) patients, and five mixed studies with mixed gestational ages and/or membrane status (intact and/or ruptured). RESULTS Both definitions demonstrated an increased NIO risk for ACCA versus non-ACCA patients, with an odds ratio increase for the Fever + 1 definition that was about twofold larger than the Fever definition. CONCLUSION As the Fever definition demonstrated increased NIO risk for ACCA versus non-ACCA patients, the Fever alone ACCA definition should be used to trigger future clinical treatment in many clinical situations.

High vitamin B12 levels are not associated with increased mortality risk for ICU patients after adjusting for liver function: A cohort study

STUDY OBJECTIVE Medication history is an essential part of patient assessment in emergency care. Patient-reported medication history can be incomplete. We study whether an electronic pharmacy-sourced prescription record can supplement the patient-reported history. METHODS In a community hospital, we compared the patient-reported history obtained by triage nurses to a proprietary electronic pharmacy record in all emergency department (ED) patients during 3 months. RESULTS Of 9,426 triaged patients, 5,001 (53%) had at least 1 (mean 7.7) prescription medication in the full-year electronic pharmacy record. Counting only recent prescription medications (supply lasting to at least 7 days before the ED visit), 3,688 patients (39%) had at least 1 (mean 4.0) recent medication. After adjustment for possible false-positive results, recent electronic prescription medication record enriched the patient-reported history by 28% (adding 1.1 drugs per patient). However, only 60% of patients with any active prescription medications from either source had any recent prescription medications in their electronic pharmacy record. CONCLUSION The electronic pharmacy prescription record augments the manually collected history.

Use of Electronic Health Record Data to Evaluate the Impact of Race on 30-Day Mortality in Patients Admitted to the Intensive Care Unit.

Objective To understand the factors that influence success in scrubbing personal names from narrative text. Materials and methods We developed a scrubber, the NLM Name Scrubber (NLM-NS), to redact personal names from narrative clinical reports, hand tagged words in a set of gold standard narrative reports as personal names or not, and measured the scrubbing success of NLM-NS and that of four other scrubbing/name recognition tools (MIST, MITdeid, LingPipe, and ANNIE/GATE) against the gold standard reports. We ran three comparisons which used increasingly larger name lists. Results The test reports contained more than 1 million words, of which 2388 were patient and 20 160 were provider name tokens. NLM-NS failed to scrub only 2 of the 2388 instances of patient name tokens. Its sensitivity was 0.999 on both patient and provider name tokens and missed fewer instances of patient name tokens in all comparisons with other scrubbers. MIST produced the best all token specificity and F-measure for name instances in our most relevant study (study 2), with values of 0.997 and 0.938, respectively. In that same comparison, NLM-NS was second best, with values of 0.986 and 0.748, respectively, and MITdeid was a close third, with values of 0.985 and 0.796 respectively. With the addition of the Clinical Center name list to their native name lists, Ling Pipe, MITdeid, MIST, and ANNIE/GATE all improved substantially. MITdeid and Ling Pipe gained the most—reaching patient name sensitivity of 0.995 (F-measure=0.705) and 0.989 (F-measure=0.386), respectively. Discussion The privacy risk due to two name tokens missed by NLM-NS was statistically negligible, since neither individual could be distinguished among more than 150 000 people listed in the US Social Security Registry. Conclusions The nature and size of name lists have substantial influences on scrubbing success. The use of very large name lists with frequency statistics accounts for much of NLM-NS scrubbing success.