Intrainstitutional EHR collections for patient-level information retrieval

2017 ◽  
Vol 68 (11) ◽  
pp. 2636-2648 ◽  
Author(s):  
Stephen Wu ◽  
Sijia Liu ◽  
Yanshan Wang ◽  
Tamara Timmons ◽  
Harsha Uppili ◽  
...  
Keyword(s):  
Information Retrieval ◽  
Patient Level ◽  
Level Information

scholarly journals Evaluation of patient-level retrieval from electronic health record data for a cohort discovery task

JAMIA Open ◽  
2020 ◽  
Vol 3 (3) ◽  
pp. 395-404 ◽  
Author(s):  
Steven R Chamberlin ◽  
Steven D Bedrick ◽  
Aaron M Cohen ◽  
Yanshan Wang ◽  
Andrew Wen ◽  
...  
Keyword(s):  
Information Retrieval ◽  
Test Collection ◽  
Electronic Health Record Data ◽  
Patient Cohort ◽  
Patient Level ◽  
Medical Centers ◽  
Level Information ◽  
Electronic Health ◽  
Boolean Queries ◽  
Information Retrieval Methods

Abstract Objective Growing numbers of academic medical centers offer patient cohort discovery tools to their researchers, yet the performance of systems for this use case is not well understood. The objective of this research was to assess patient-level information retrieval methods using electronic health records for different types of cohort definition retrieval. Materials and Methods We developed a test collection consisting of about 100 000 patient records and 56 test topics that characterized patient cohort requests for various clinical studies. Automated information retrieval tasks using word-based approaches were performed, varying 4 different parameters for a total of 48 permutations, with performance measured using B-Pref. We subsequently created structured Boolean queries for the 56 topics for performance comparisons. In addition, we performed a more detailed analysis of 10 topics. Results The best-performing word-based automated query parameter settings achieved a mean B-Pref of 0.167 across all 56 topics. The way a topic was structured (topic representation) had the largest impact on performance. Performance not only varied widely across topics, but there was also a large variance in sensitivity to parameter settings across the topics. Structured queries generally performed better than automated queries on measures of recall and precision but were still not able to recall all relevant patients found by the automated queries. Conclusion While word-based automated methods of cohort retrieval offer an attractive solution to the labor-intensive nature of this task currently used at many medical centers, we generally found suboptimal performance in those approaches, with better performance obtained from structured Boolean queries. Future work will focus on using the test collection to develop and evaluate new approaches to query structure, weighting algorithms, and application of semantic methods.

scholarly journals COMPARABILITY OF BIOLOGICAL AGING MEASURES IN THE NATIONAL HEALTH AND NUTRITION EXAMINATION STUDY, 1999-2002

2019 ◽  
Vol 3 (Supplement_1) ◽  
pp. S479-S479
Author(s):  
Waylon J Hastings ◽  
Daniel Belsky ◽  
Idan Shalev
Keyword(s):  
Risk Factors ◽  
Telomere Length ◽  
Cellular Level ◽  
Biological Age ◽  
Effect Sizes ◽  
Chronological Age ◽  
Biological Aging ◽  
Patient Level ◽  
Age Related ◽  
Level Information

Abstract Biological processes of aging are thought to be modifiable causes of many chronic diseases. Measures of biological aging could provide sensitive endpoints for studies of risk factors hypothesized to shorten healthy lifespan and/or interventions that extend it. However, uncertainty remains about how to measure biological aging and if proposed measures assess the same thing. We tested four proposed measures of biological aging with available data from NHANES 1999-2002: Klemera-Doubal method (KDM) Biological Age, homeostatic dysregulation, Levine Method (LM) Biological Age, and leukocyte telomere length. All measures of biological aging were correlated with chronological age. KDM Biological Age, homeostatic dysregulation, and LM Biological Age were all significantly associated with each other, but were each not associated with telomere length. NHANES participants with older biological ages performed worse on tests of physical, cognitive, perceptual, and subjective functions known to decline with advancing chronological age and thought to mediate age-related disability. Further, NHANES participants with higher levels of exposure to life-course risk factors were measured as having older biological ages. In both sets of analyses, effect-sizes tended to be larger for KDM Biological Age, homeostatic dysregulation, and LM Biological Age as compared to telomere length. Composite measures combining cellular- and patient-level information tended to have the largest effect-sizes. The cellular-level aging biomarker telomere length may measure different aspects of the aging process relative to the patient-level physiological measures. Studies aiming to test if risk factors accelerate aging or if interventions may slow aging should not treat proposed measures of biological aging as interchangeable.

Intelligent Information Personalization

2011 ◽  
pp. 118-146 ◽  
Author(s):  
Syed Sibte Raza Abidi
Keyword(s):  
Information Retrieval ◽  
User Model ◽  
Functional Requirements ◽  
Future Outlook ◽  
Web Based ◽  
Level Information ◽  
Intelligent Information ◽  
Intelligent Methods ◽  
Traditional Approaches ◽  
Information Personalization

This chapter introduces intelligent information personalization as an approach to personalize the webbased information retrieval experiences based on an individual’s interests, needs and goals. We present intelligent techniques to dynamically compose new personalized information by adapting existing web-based information in line with a dynamic user-model, whilst simultaneously addressing linguistic, factual and functional requirements. This chapter will highlight the different facets, tasks and issues concerning intelligent information personalization to guide researchers in designing intelligent information personalization applications. The chapter presents intelligent methods that address information personalization at the content level as opposed to the traditional approaches that focus on interface level information personalization. To assist researchers in designing intelligent information personalization applications we present our information personalization framework, named AdWISE (Adaptive Webmediated Information and Services Environment), to demonstrate how to systematically integrate various intelligent methods to achieve information personalization. We will conclude with a commentary on the future outlook for intelligent information personalization.

Disproportionality methods for pharmacovigilance in longitudinal observational databases

2011 ◽  
Vol 22 (1) ◽  
pp. 39-56 ◽  
Author(s):  
Ivan Zorych ◽  
David Madigan ◽  
Patrick Ryan ◽  
Andrew Bate
Keyword(s):  
Data Mining ◽  
Drug Safety ◽  
Spontaneous Report ◽  
Health Claims ◽  
Data Sources ◽  
Patient Level ◽  
Number Of Patients ◽  
Level Information ◽  
Report System ◽  
Safety Signals

Data mining disproportionality methods (PRR, ROR, EBGM, IC, etc.) are commonly used to identify drug safety signals in spontaneous report system (SRS) databases. Newer data sources such as longitudinal observational databases (LOD) provide time-stamped patient-level information and overcome some of the SRS limitations such as an absence of the denominator, total number of patients who consume a drug, and limited temporal information. Application of the disproportionality methods to LODs has not been widely explored. The scale of the LOD data provides an interesting computational challenge. Larger health claims databases contain information on more than 50 million patients and each patient has records for up to 10 years. In this article we systematically explore the application of commonly used disproportionality methods to simulated and real LOD data.

scholarly journals Identifying the predictors of avoidable emergency department attendance after contact with the NHS 111 phone service: analysis of 16.6 million calls to 111 in England in 2015–2017

BMJ Open ◽  
2020 ◽  
Vol 10 (3) ◽  
pp. e032043
Author(s):  
Mark Egan ◽  
Filip Murar ◽  
James Lawrence ◽  
Hannah Burd
Keyword(s):  
Primary Care ◽  
Emergency Department ◽  
Regression Model ◽  
Healthcare Service ◽  
Self Care ◽  
Emergency Department Attendance ◽  
Patient Level ◽  
Level Information ◽  
Phone Service

ObjectivesTo measure the frequency of patients making avoidable emergency department (ED) attendances after contact with NHS 111 and to examine whether these attendances can be predicted reliably.DesignAnalysis of 16 563 946 calls made to 111, where each call was linked with a record of whether the patient attended ED within 24 hours.SettingAll regions of England from March 2015 to October 2017.Participants and dataOur main regression model used a sample of 10 954 783 calls, each with detailed patient-level information.Main outcomeWhether patients made an unadvised, non-urgent type 1 ED (‘avoidable') attendance within 24 hours of calling 111.ResultsOf 16 563 946 calls to 111, 12 894 561 (77.8%) were not advised to go to ED (ie, they were advised to either attend primary care, attend another non-ED healthcare service or to self-care). Of the calls where the patient was not advised to go to the ED, 691 783 (5.4%) resulted in the patient making an avoidable ED attendance within 24 hours. Among other factors, calls were less likely to result in these attendances when they received clinical input (adjusted OR 0.52, 95% CI 0.51 to 0.53) but were more likely when the patient was female (OR 1.07, 95% CI 1.06 to 1.08) or aged 0–4 years (OR 1.34, 95% CI 1.33 to 1.35).ConclusionsFor every 20 calls where 111 did not advise people to attend the ED, 1 resulted in avoidable ED attendance within 24 hours. These avoidable attendances could be predicted, to a certain extent, based on call characteristics. It may be possible to use this information to help 111 call handlers identify which callers are at higher risk of these attendances.

Abstract 18447: Peri-operative Atrial Fibrillation (POAF) Complicating Non-cardiothoracic Surgery: A Systematic Review

Circulation ◽  
2015 ◽  
Vol 132 (suppl_3) ◽  
Author(s):  
Joshua Wenner ◽  
Karan Bami ◽  
Himabindu Samardhi ◽  
Pablo Nery ◽  
David Birnie ◽  
...  
Keyword(s):  
Atrial Fibrillation ◽  
Systematic Review ◽  
De Novo ◽  
Cardiothoracic Surgery ◽  
Adverse Outcomes ◽  
Exclusion Criteria ◽  
Single Episode ◽  
Patient Level ◽  
Level Information ◽  
The Usa

Introduction: More than 37 million non cardiothoracic operations are performed in the USA per annum. Single studies have reported that peri-operative atrial fibrillation (POAF) complicates non-cardiac surgery in ≤12% of patients. It is not clear if POAF is associated with adverse outcomes. Purpose: We conducted a systematic review to determine the frequency and implications of POAF. Methods: We conducted a literature search of MEDLINE, Embase, HTA, Cochrane, and Pubmed databases. We defined POAF as a single episode of AF confirmed by ECG within 30 days of non cardiothoracic surgery. Inclusion criteria were published manuscripts and abstracts containing patient level information. We excluded studies which were not published in English, described cardiothoracic surgery, were missing patient-level AF data or included patients aged <18 years. Results: Our search produced 4445 publications, from which 716 abstracts and 534 manuscripts were identified for review. After applying inclusion/exclusion criteria, 225 manuscripts were analysed. Combining all studies, POAF occurred in 18789/650120 patients (2.9%, n=172, median [IQR] 2.2% [0.9-5.8]). Among 37 prospective studies, POAF occurred in 517/10990 patients (4.7%, n=37, 3.23% [1.0-8.8]). AF was prospectively identified pre-op in 875/26596 (3.3%, n=18, 9.0% [5.5-13.1]) and post-op in 472/14719 (3.2%, n=18, 8.8% [5.5-13.0]). In 135 retrospective studies, POAF occurred in 18272/639130 patients (2.9% n=135, 2.13 [0.8-4.4]). In retrospective analyses, AF was pre-existent in 49756/2440489, (2.0%, n=44, 6.7% [4.3-13.1]) and de novo in 12043/1641875, (0.7%, n=23, 6.0% [1.6-12.3]). Stratifying by surgery type, POAF was most common in vascular (104/1380, 7.5%), followed by orthopaedic (128/2384, 5.4%), and neurosurgical (197/4390, 4.5%) patients. Patient outcomes were not systematically reported: at 1 year, mortality occurred in 927/4136 (22.4%) POAF patients, compared to 8498/63746 (13.3%) non-POAF patients (n=7). Conclusions: POAF occurred in 2.9% of 650120 patients and was associated with a 68% increase in mortality. Prospective research is required to determine whether any specific intervention(s) in POAF patients will improve outcomes.

Sign in / Sign up

Export Citation Format

Share Document