scholarly journals Familial relationships in electronic health records (EHR) v2

2019 ◽  
Author(s):  
Zhouzerui Liu ◽  
Nicholas Tatonetti
Keyword(s):  
New York ◽  
Electronic Health Records ◽  
Linear Time ◽  
Medical Center ◽  
Data Encryption ◽  
Columbia University ◽  
Patient Privacy ◽  
Health Records ◽  
Familial Relationships ◽  
Electronic Health

AbstractHeritability is an important statistic for evaluating genetic contribution to phenotypes. Estimating heritability, however, requires a laborious recruitment of a large number of relatives. Electronic health records (EHR) contain massive relative information in emergency contact forms. Recently, we presented RIFTEHR, an algorithm for extracting relationships from EHR. Here, we present an updated version and reconstructed 4.2 million familial relationships from the latest New York-Presbyterian/Columbia University Irving Medical Center (CUIMC) EHR system. The number of updated relationships is 30 percent more than the last version. We present a new implementation of RIFTEHR, which runs in linear time, thus largely improves the speed of the algorithm. We also present a data encryption method, to protect patient privacy in running the algorithm. These resources can be used for generalized use of familial relationships from EHR in genetic studies.

scholarly journals Estimate of disease heritability using 7.4 million familial relationships inferred from electronic health records

2016 ◽  
Author(s):  
Fernanda Polubriaginof ◽  
Rami Vanguri ◽  
Kayla Quinnies ◽  
Gillian M. Belbin ◽  
Alexandre Yahi ◽  
...  
Keyword(s):  
Electronic Health Records ◽  
Patient Privacy ◽  
Next Of Kin ◽  
Health Records ◽  
Familial Relationships ◽  
Wide Range ◽  
Causes Of Disease ◽  
Contact Data ◽  
Electronic Health ◽  
Patient Emergency

AbstractHeritability is essential for understanding the biological causes of disease, but requires laborious patient recruitment and phenotype ascertainment. Electronic health records (EHR) passively capture a wide range of clinically relevant data and provide a novel resource for studying the heritability of traits that are not typically accessible. EHRs contain next-of-kin information collected via patient emergency contact forms, but until now, these data have gone unused in research. We mined emergency contact data at three academic medical centers and identified millions of familial relationships while maintaining patient privacy. Identified relationships were consistent with genetically-derived relatedness. We used EHR data to compute heritability estimates for 500 disease phenotypes. Overall, estimates were consistent with literature and between sites. Inconsistencies were indicative of limitations and opportunities unique to EHR research. These analyses provide a novel validation of the use of EHRs for genetics and disease research.One Sentence SummaryWe demonstrate that next-of-kin information can be used to identify familial relationships in the EHR, providing unique opportunities for precision medicine studies.

scholarly journals The Postencounter Form System: Viewpoint on Efficient Data Collection Within Electronic Health Records (Preprint)

2019 ◽  
Author(s):  
Philip Held ◽  
Randy A Boley ◽  
Walter G Faig ◽  
John A O'Toole ◽  
Imran Desai ◽  
...  
Keyword(s):  
Electronic Health Records ◽  
Medical Center ◽  
Health Records ◽  
Clinical Notes ◽  
The Road ◽  
Clinical Encounters ◽  
Efficient Data ◽  
Data Points ◽  
Electronic Health ◽  
Using Data

UNSTRUCTURED Electronic health records (EHRs) offer opportunities for research and improvements in patient care. However, challenges exist in using data from EHRs due to the volume of information existing within clinical notes, which can be labor intensive and costly to transform into usable data with existing strategies. This case report details the collaborative development and implementation of the postencounter form (PEF) system into the EHR at the Road Home Program at Rush University Medical Center in Chicago, IL to address these concerns with limited burden to clinical workflows. The PEF system proved to be an effective tool with over 98% of all clinical encounters including a completed PEF within 5 months of implementation. In addition, the system has generated over 325,188 unique, readily-accessible data points in under 4 years of use. The PEF system has since been deployed to other settings demonstrating that the system may have broader clinical utility.

scholarly journals Signs of the 2009 Influenza Pandemic in the New York-Presbyterian Hospital Electronic Health Records

PLoS ONE ◽  
2010 ◽  
Vol 5 (9) ◽  
pp. e12658 ◽  
Author(s):  
Hossein Khiabanian ◽  
Antony B. Holmes ◽  
Brendan J. Kelly ◽  
Mrinalini Gururaj ◽  
George Hripcsak ◽  
...  
Keyword(s):  
New York ◽  
Electronic Health Records ◽  
Influenza Pandemic ◽  
Health Records ◽  
Presbyterian Hospital ◽  
Electronic Health ◽  
2009 Influenza Pandemic

scholarly journals The OpenDeID corpus for patient de-identification

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Jitendra Jonnagaddala ◽  
Aipeng Chen ◽  
Sean Batongbacal ◽  
Chandini Nekkantti
Keyword(s):  
Electronic Health Records ◽  
Health Information ◽  
Sensitive Information ◽  
Protected Health Information ◽  
Patient Privacy ◽  
Health Records ◽  
Automatic Methods ◽  
Electronic Health ◽  
Pathology Reports ◽  
Privacy And Confidentiality

AbstractFor research purposes, protected health information is often redacted from unstructured electronic health records to preserve patient privacy and confidentiality. The OpenDeID corpus is designed to assist development of automatic methods to redact sensitive information from unstructured electronic health records. We retrieved 4548 unstructured surgical pathology reports from four urban Australian hospitals. The corpus was developed by two annotators under three different experimental settings. The quality of the annotations was evaluated for each setting. Specifically, we employed serial annotations, parallel annotations, and pre-annotations. Our results suggest that the pre-annotations approach is not reliable in terms of quality when compared to the serial annotations but can drastically reduce annotation time. The OpenDeID corpus comprises 2,100 pathology reports from 1,833 cancer patients with an average of 737.49 tokens and 7.35 protected health information entities annotated per report. The overall inter annotator agreement and deviation scores are 0.9464 and 0.9726, respectively. Realistic surrogates are also generated to make the corpus suitable for distribution to other researchers.

scholarly journals Federated Learning of Electronic Health Records Improves Mortality Prediction in Patients Hospitalized with COVID-19

2020 ◽  
Author(s):  
Akhil Vaid ◽  
Suraj K Jaladanki ◽  
Jie Xu ◽  
Shelly Teng ◽  
Arvind Kumar ◽  
...  
Keyword(s):  
Electronic Health Records ◽  
Large Datasets ◽  
Mortality Prediction ◽  
Patient Privacy ◽  
Local Data ◽  
Health Records ◽  
Electronic Health ◽  
Mlp Model ◽  
Combined Data ◽  
Better Than

Machine learning (ML) models require large datasets which may be siloed across different healthcare institutions. Using federated learning, a ML technique that avoids locally aggregating raw clinical data across multiple institutions, we predict mortality within seven days in hospitalized COVID-19 patients. Patient data was collected from Electronic Health Records (EHRs) from five hospitals within the Mount Sinai Health System (MSHS). Logistic Regression with L1 regularization (LASSO) and Multilayer Perceptron (MLP) models were trained using local data at each site, a pooled model with combined data from all five sites, and a federated model that only shared parameters with a central aggregator. Both the federated LASSO and federated MLP models performed better than their local model counterparts at four hospitals. The federated MLP model also outperformed the federated LASSO model at all hospitals. Federated learning shows promise in COVID-19 EHR data to develop robust predictive models without compromising patient privacy.

scholarly journals Scaling-up social needs screening in practice: a retrospective, cross-sectional analysis of data from electronic health records from Bronx county, New York, USA

BMJ Open ◽  
2021 ◽  
Vol 11 (9) ◽  
pp. e053633
Author(s):  
Kevin P Fiori ◽  
Caroline G Heller ◽  
Anna Flattau ◽  
Nicole R Harris-Hollingsworth ◽  
Amanda Parsons ◽  
...  
Keyword(s):  
Primary Care ◽  
New York ◽  
Electronic Health Records ◽  
Social Care ◽  
Social Needs ◽  
Cross Sectional ◽  
Health Records ◽  
Care Practices ◽  
Electronic Health ◽  
Primary Care Practices

ObjectivesThere has been renewed focus on health systems integrating social care to improve health outcomes with relatively less related research focusing on ‘real-world’ practice. This study describes a health system’s experience from 2018 to 2020, following the successful pilot in 2017, to scale social needs screening of patients within a large urban primary care ambulatory network.SettingAcademic medical centre with an ambulatory network of 18 primary care practices located in an urban county in New York City (USA).ParticipantsThis retrospective, cross-sectional study used electronic health records of 244 764 patients who had a clinical visit between 10 April 2018 and 8 December 2019 across any one of 18 primary care practices.MethodsWe organised measures using the RE-AIM framework domains of reach and adoption to ascertain the number of patients who were screened and the number of providers who adopted screening and associated documentation, respectively. We used descriptive statistics to summarise factors comparing patients screened versus those not screened, the prevalence of social needs screening and adoption across 18 practices.ResultsBetween April 2018 and December 2019, 53 093 patients were screened for social needs, representing approximately 21.7% of the patients seen. Almost one-fifth (19.6%) of patients reported at least one unmet social need. The percentage of screened patients varied by both practice location (range 1.6%–81.6%) and specialty within practices. 51.8% of providers (n=1316) screened at least one patient.ConclusionsThese findings demonstrate both the potential and challenges of integrating social care in practice. We observed significant variability in uptake across the health system. More research is needed to better understand factors driving adoption and may include harmonising workflows, establishing unified targets and using data to drive improvement.

Development and validation of a pancreatic cancer prediction model from electronic health records using machine learning.

2020 ◽  
Vol 38 (4_suppl) ◽  
pp. 679-679
Author(s):  
Limor Appelbaum ◽  
Jose Pablo Cambronero ◽  
Karla Pollick ◽  
George Silva ◽  
Jennifer P. Stevens ◽  
...  
Keyword(s):  
Machine Learning ◽  
Feature Selection ◽  
Electronic Health Records ◽  
Medical Center ◽  
Characteristic Curve ◽  
External Validation ◽  
Data Driven ◽  
Health Records ◽  
Clinical Correlates ◽  
Electronic Health

679 Background: Pancreatic Adenocarcinoma (PDAC) is often diagnosed at an advanced stage. We sought to develop a model for early PDAC prediction in the general population, using electronic health records (EHRs) and machine learning. Methods: We used three EHR datasets from Beth-Israel Deaconess Medical Center (BIDMC) and Partners Healthcare (PHC): 1. “BIDMC-Development-Data” (BIDMC-DD) for model development, using a feed-forward neural network (NN) and L2-regularized logistic regression,randomly split (80:20) into training and test groups. We tuned hyperparameters using cross-validation in training, and report performance on the test split. 2. “BIDMC-Large-Data” (BIDMC-LD) to re-fit and calibrate models. 3. “PHC-Data” for external validation. We evaluate using Area Under the Receiver Operating Characteristic Curve (AUC) and compute 95% CI using empirical bootstrap over test data. PDAC patients were selected using ICD9/-10 codes and validated with tumor registries. In contrast to prior work, we did not predefine feature sets based on known clinical correlates and instead employed data-driven feature selection, specifically importance-based feature pruning, regularization, and manual validation, to identify diagnostic-based features. Results: BIDMC-DD included demographics, diagnoses, labs and medications for 1018 patients (cases = 509; age-sex paired controls). BIDMC-LD included diagnoses for 547,917 patients (cases = 509), and PHC included diagnoses for 160,593 patients (cases = 408). We compared our approach to adapted and re-fitted published baselines. With a 365-day lead-time, NN obtained a BIDMC-DD test AUC of 0.84 (CI 0.79 - 0.90) versus the previous best baseline AUC of 0.70 (CI 0.62 - 0.78). We also validated using BIDMC-DD’s test cancer patients and BIDMC LD controls. The AUC was 0.71 (CI 0.67 - 0.76) at the 365-day cutoff. NN’s external validation AUC on PHC-Data was 0.71 (CI 0.63 - 0.79), outperforming an existing model’s AUC of 0.61 (CI 0.52 - 0.70) (Baecker et al, 2019). Conclusions: Models based on data-driven feature selection outperform models that use predefined sets of known clinical correlates and can help in early prediction of PDAC development.

Legal and Ethical Considerations in the Implementation of Electronic Health Records

2017 ◽  
pp. 960-973
Author(s):  
Karen Ervin
Keyword(s):  
United States ◽  
Electronic Health Records ◽  
Relevant Literature ◽  
Database Systems ◽  
The United States ◽  
Patient Privacy ◽  
Health Records ◽  
Electronic Health ◽  
Health Database ◽  
State Library

This chapter examines the literature of healthcare in the United States during the transitioning to electronic records. Key government legislation, such as the Health Insurance Portability and Accountability Act (HIPAA) and the Health Information Technology for Economic and Clinical Health Act (HITECH), which were part of the American Recovery and Reinvestment Act (ARRA) and the Affordable Health Care Act, are reviewed. The review concentrates on patient privacy issues, how they have been addressed in these acts, and what recommendations for improvement have been found in the literature. A comparison of the adoption of electronic health records on a nationwide scale in three countries is included. England, Australia, and the United States are all embarking in and are at different stages of implementing nationwide electronic health database systems. The resources used in locating relevant literature were PubMed, Medline, Highwire Press, State Library of Pennsylvania, and Google Scholar databases.

Sign in / Sign up

Export Citation Format

Share Document