scholarly journals A unified framework identifies new links between plasma lipids and diseases from electronic medical records across large-scale cohorts

2021 ◽  
Author(s):  
Yogasudha Veturi ◽  
Anastasia Lucas ◽  
Yuki Bradford ◽  
Daniel Hui ◽  
Scott Dudek ◽  
...  
Keyword(s):  
Electronic Medical Records ◽  
Medical Records ◽  
Large Scale ◽  
Plasma Lipids ◽  
Unified Framework

scholarly journals Information Extraction from Electronic Medical Records Using Multitask Recurrent Neural Network with Contextual Word Embedding

2019 ◽  
Vol 9 (18) ◽  
pp. 3658 ◽  
Author(s):  
Jianliang Yang ◽  
Yuenan Liu ◽  
Minghui Qian ◽  
Chenghua Guan ◽  
Xiangfei Yuan
Keyword(s):  
Electronic Medical Records ◽  
Medical Records ◽  
Large Scale ◽  
Short Term Memory ◽  
Conditional Random Field ◽  
Named Entity Recognition ◽  
Recognition Task ◽  
Entity Recognition ◽  
Language Models ◽  
Named Entity

Clinical named entity recognition is an essential task for humans to analyze large-scale electronic medical records efficiently. Traditional rule-based solutions need considerable human effort to build rules and dictionaries; machine learning-based solutions need laborious feature engineering. For the moment, deep learning solutions like Long Short-term Memory with Conditional Random Field (LSTM–CRF) achieved considerable performance in many datasets. In this paper, we developed a multitask attention-based bidirectional LSTM–CRF (Att-biLSTM–CRF) model with pretrained Embeddings from Language Models (ELMo) in order to achieve better performance. In the multitask system, an additional task named entity discovery was designed to enhance the model’s perception of unknown entities. Experiments were conducted on the 2010 Informatics for Integrating Biology & the Bedside/Veterans Affairs (I2B2/VA) dataset. Experimental results show that our model outperforms the state-of-the-art solution both on the single model and ensemble model. Our work proposes an approach to improve the recall in the clinical named entity recognition task based on the multitask mechanism.

scholarly journals Auditing service delivery in glaucoma clinics using visual field records: a feasibility study

2019 ◽  
Vol 4 (1) ◽  
pp. e000352
Author(s):  
Stephen R Kelly ◽  
Susan R Bryan ◽  
John M Sparrow ◽  
David P Crabb
Keyword(s):  
Visual Field ◽  
Service Delivery ◽  
Electronic Medical Records ◽  
Medical Records ◽  
Large Scale ◽  
Health Service Delivery ◽  
Mean Deviation ◽  
Normal Limits ◽  
Field Analyser

ObjectiveThis study aimed to demonstrate that large-scale visual field (VF) data can be extracted from electronic medical records (EMRs) and to assess the feasibility of calculating metrics from these data that could be used to audit aspects of service delivery of glaucoma care.Method and analysisHumphrey visual field analyser (HFA) data were extracted from Medisoft EMRs from five regionally different clinics in England in November 2015, resulting in 602 439 records from 73 994 people. Target patients were defined as people in glaucoma clinics with measurable and sustained VF loss in at least one eye (HFA mean deviation (MD) outside normal limits ≥2 VFs). Metrics for VF reliability, stage of VF loss at presentation, speed of MD loss, predicted loss of sight years (bilateral VF impairment) and frequency of VFs were calculated.ResultsOne-third of people (34.8%) in the EMRs had measurable and repeatable VF loss and were subject to analyses (n=25 760 patients). Median (IQR) age and presenting MD in these patients were 71 (61, 78) years and −6 (–10, –4) dB, respectively. In 19 264 patients with >4 years follow-up, median (IQR) MD loss was −0.2 (−0.8, 0.3) dB/year and median (IQR) intervals between VF examinations was 11 (8, 16) months. Metrics predicting loss of sight years and reliability of examinations varied between centres (p<0.001).ConclusionThis study illustrates the feasibility of assessing aspects of health service delivery in glaucoma clinics through analysis of VF databases. Proposed metrics could be useful for blindness prevention from glaucoma in secondary care centres.

scholarly journals Using electronic medical records to enable large-scale studies in psychiatry: treatment resistant depression as a model

2011 ◽  
Vol 42 (1) ◽  
pp. 41-50 ◽  
Author(s):  
R. H. Perlis ◽  
D. V. Iosifescu ◽  
V. M. Castro ◽  
S. N. Murphy ◽  
V. S. Gainer ◽  
...  
Keyword(s):  
Electronic Medical Records ◽  
Gold Standard ◽  
Medical Records ◽  
Large Scale ◽  
Clinical Investigation ◽  
Antidepressant Treatment ◽  
Billing Data ◽  
Cross Sectional ◽  
Longitudinal Outcomes ◽  
Co Morbidity

BackgroundElectronic medical records (EMR) provide a unique opportunity for efficient, large-scale clinical investigation in psychiatry. However, such studies will require development of tools to define treatment outcome.MethodNatural language processing (NLP) was applied to classify notes from 127 504 patients with a billing diagnosis of major depressive disorder, drawn from out-patient psychiatry practices affiliated with multiple, large New England hospitals. Classifications were compared with results using billing data (ICD-9 codes) alone and to a clinical gold standard based on chart review by a panel of senior clinicians. These cross-sectional classifications were then used to define longitudinal treatment outcomes, which were compared with a clinician-rated gold standard.ResultsModels incorporating NLP were superior to those relying on billing data alone for classifying current mood state (area under receiver operating characteristic curve of 0.85–0.88 v. 0.54–0.55). When these cross-sectional visits were integrated to define longitudinal outcomes and incorporate treatment data, 15% of the cohort remitted with a single antidepressant treatment, while 13% were identified as failing to remit despite at least two antidepressant trials. Non-remitting patients were more likely to be non-Caucasian (p<0.001).ConclusionsThe application of bioinformatics tools such as NLP should enable accurate and efficient determination of longitudinal outcomes, enabling existing EMR data to be applied to clinical research, including biomarker investigations. Continued development will be required to better address moderators of outcome such as adherence and co-morbidity.

scholarly journals Comparison of Efficacy and Safety of Rosuvastatin, Atorvastatin and Pravastatin among Dyslipidemic Diabetic Patients

2013 ◽  
Vol 2013 ◽  
pp. 1-7 ◽  
Author(s):  
Lolwa Barakat ◽  
Amin Jayyousi ◽  
Abdulbari Bener ◽  
Bilal Zuby ◽  
Mahmoud Zirie
Keyword(s):  
Renal Function ◽  
Electronic Medical Records ◽  
Medical Records ◽  
Large Scale ◽  
Population Based ◽  
Diabetic Patients ◽  
Population Based Study ◽  
Number Of Patients ◽  
Second Year ◽  
New Onset

Objectives. To investigate the efficacy and the safety of the three most commonly prescribed statins (rosuvastatin, atorvastatin, and pravastatin) for managing dyslipidemia among diabetic patients in Qatar. Subjects and Methods. This retrospective observational population-based study included 350 consecutive diabetes patients who were diagnosed with dyslipidemia and prescribed any of the indicated statins between September 2005 and September 2009. Data was collected by review of the Pharmacy Database, the Electronic Medical Records Database (EMR viewer), and the Patient's Medical Records. Comparisons of lipid profile measurements at baseline and at first- and second-year intervals were taken. Results. Rosuvastatin (10 mg) was the most effective at reducing LDL-C (29.03%). Atorvastatin reduced LDL-C the most at a dose of 40 mg (22.8%), and pravastatin reduced LDL-C the most at a dose of 20 mg (20.3%). All three statins were safe in relation to muscular and hepatic functions. In relation to renal function, atorvastatin was the safest statin as it resulted in the least number of patients at the end of 2 years of treatment with the new onset of microalbuminuria (10.9%) followed by rosuvastatin (14.3%) and then pravastatin (26.6%). Conclusion. In the Qatari context, the most effective statin at reducing LDL-C was rosuvastatin 10 mg. Atorvastatin was the safest statin in relation to renal function. Future large-scale prospective studies are needed to confirm these results.

Best Practices for Reducing Interface Errors in Electronic Medical Records

2021 ◽  
Vol 65 (1) ◽  
pp. 904-907
Author(s):  
Paige Lawton ◽  
Janel Ingraham ◽  
Beth Blickensderfer
Keyword(s):  
Best Practices ◽  
Hybrid Systems ◽  
Electronic Medical Records ◽  
Patient Outcomes ◽  
Medical Records ◽  
Large Scale ◽  
Information Control ◽  
Error Prevention ◽  
Interface Modification ◽  
Control And Management

As Electronic Medical Records (EMR) become increasingly prevalent, the application of human factors principles is essential to facilitate efficiency and usability of these systems and, in turn, to reduce adverse patient outcomes due to user errors relating to the EMR. This paper describes five “best practices” found in the literature which aim to prevent error in the use of Electronic Medical Records. These practices are: Watermarking, Information Control and Management, Hybrid Systems, Cross-Checking Methodology, and Interface Modification. The paper describes each practice and examines the research underlying each approach. Although some practices may be easier to apply than others, they all merit further research and have potential for error prevention on a large scale.

System Replacement to a New HIS and Data Warehouse

2012 ◽  
Vol 16 (1) ◽  
pp. 38-41
Author(s):  
Masayuki Honda ◽  
◽  
Takehiro Matsumoto
Keyword(s):  
Data Warehouse ◽  
Electronic Medical Records ◽  
Medical Records ◽  
Large Scale ◽  
Best Practice ◽  
Transaction Processing ◽  
Hospital Information Systems ◽  
University Hospital ◽  
Analytical Processing ◽  
High Level

Large-scale hospital information systems (HIS) generally consist of (i) online transaction processing (OLTP) and (ii) online analytical processing (OLAP) systems. Electronic medical records (EMR) are a major OLTP element. The data warehouse (DWH) assumes many important OLAP roles and maintains an institution’s medical care at a high level by providing EMR with the best practice cases available. This article focuses mainly on why OLTP and OLAP are needed and what roles the DWH plays, which means that the DWH has its own utilities and supplementary merits. The background of this discussion is closely related to the HIS at Nagasaki University Hospital introduced before the DWH is discussed.

scholarly journals The systematic use of metabolomic epidemiology, biobanks, and electronic medical records for precision medicine initiatives in asthma: findings suggest new guidelines to optimize treatment

2021 ◽  
Author(s):  
Priyadarshini Kachroo ◽  
Isobel Stewart ◽  
Rachel Kelly ◽  
Meryl Stav ◽  
Kevin Mendez ◽  
...  
Keyword(s):  
Precision Medicine ◽  
Electronic Medical Records ◽  
Medical Records ◽  
Large Scale ◽  
Inhaled Corticosteroids ◽  
Public Health Problem ◽  
Epidemiological Studies ◽  
Metabolomic Profiling ◽  
New Guidelines ◽  
Prevalent Asthma

Abstract The application of large-scale metabolomic profiling provides new opportunities to realize the potential of omics-based precision medicine with regard to asthma. We leveraged over 14,000 individuals from four distinct epidemiological studies. We identified and independently replicated seventeen steroid metabolites that were significantly reduced in individuals with prevalent asthma. Importantly steroid levels were reduced among all individuals with asthma regardless of medication use; however, the largest reduction was associated with inhaled corticosteroids use (ICS) that was further confirmed in a four-year ICS clinical trial. Cortisol levels extracted from electronic medical records confirmed that cortisol is reduced among asthmatics taking ICS over the entire 24-hour period, compared with all other groups. Clinical-grade adrenal suppression in asthmatics on ICS, resulting from substantial reductions in steroid metabolites, represents a larger public health problem than previously recognized. Regular cortisol testing may identify at-risk individuals, enabling personalized treatment modifications and improving overall patient care.

Multi-Task Learning for Symptom Name Recognition and Severity Assessment in Electronic Medical Records (Preprint)

2019 ◽  
Author(s):  
Ying Shen ◽  
Buzhou Tang ◽  
Yaliang Li ◽  
Nan Du
Keyword(s):  
Electronic Medical Records ◽  
Medical Records ◽  
Representation Learning ◽  
Severity Assessment ◽  
Learning Approaches ◽  
Unified Framework ◽  
Task Learning ◽  
Classification Of Diseases ◽  
The Rich ◽  
Improved Performance

BACKGROUND Severity classification of diseases and symptoms in electronic medical records (EMRs) is very important in medicine and the life sciences, as it facilitates an easier understanding of medical documents by physicians. However, existing methods perform symptom name recognition and severity assessment tasks separately, which requires very large amounts of expert time and effort and neglects the rich correlations in information between tasks. OBJECTIVE The task of predicting symptom name and severity simultaneously from informative but noisy EMRs is important yet challenging in practice. There is a strong motivation to develop new methods that can effectively perform these two tasks. METHODS In this paper, we explore multi-task learning approaches to integrate symptom name recognition and severity assessment in a unified framework, motivated by the fact that these two tasks can benefit each other. To fulfill the goal of learn the correlation between these two tasks, we propose a novel cluster-based knowledge-aware learning scheme to reduce semantic ambiguity for name recognition and enrich sentence representation learning for severity assessment. RESULTS Symptom classification emerges from the cooperation of several machine learning modes and from the ontology we have developed and released. The experiments performed on synthetic dataset demonstrate the effectiveness of the proposed method and the improved performance of both tasks. We also consider a practical testbed application - symptom severity assessment and diagnosis inference - to test and validate our method and assess its impact in real-world clinical settings. CONCLUSIONS Our proposed model can provide symptom knowledge and implications for clinicians and patients as a reference and has remarkable applicability and generality, outperforming competitors and defining the state-of-the-art. The gastrointestinal ontology and severity assessment corpus are accessible via: https://github.com/shenyingpku/MTL CLINICALTRIAL N/A

Sign in / Sign up

Export Citation Format

Share Document