scholarly journals Validation of an algorithm using inpatient electronic health records to determine the presence and severity of cirrhosis in patients with hepatocellular carcinoma in England: an observational study

BMJ Open ◽  
2019 ◽  
Vol 9 (7) ◽  
pp. e028571 ◽  
Author(s):  
Robert J Driver ◽  
Vinay Balachandrakumar ◽  
Anya Burton ◽  
Jessica Shearer ◽  
Amy Downing ◽  
...  
Keyword(s):  
Hepatocellular Carcinoma ◽  
Liver Disease ◽  
Observational Study ◽  
Electronic Health Records ◽  
Disease Severity ◽  
Health Records ◽  
Derivation Cohort ◽  
Electronic Health ◽  
Clinical Records ◽  
New Diagnosis

ObjectivesOutcomes in hepatocellular carcinoma (HCC) are determined by both cancer characteristics and liver disease severity. This study aims to validate the use of inpatient electronic health records to determine liver disease severity from treatment and procedure codes.DesignRetrospective observational study.SettingTwo National Health Service (NHS) cancer centres in England.Participants339 patients with a new diagnosis of HCC between 2007 and 2016.Main outcomeUsing inpatient electronic health records, we have developed an optimised algorithm to identify cirrhosis and determine liver disease severity in a population with HCC. The diagnostic accuracy of the algorithm was optimised using clinical records from one NHS Trust and it was externally validated using anonymised data from another centre.ResultsThe optimised algorithm has a positive predictive value (PPV) of 99% for identifying cirrhosis in the derivation cohort, with a sensitivity of 86% (95% CI 82% to 90%) and a specificity of 98% (95% CI 96% to 100%). The sensitivity for detecting advanced stage cirrhosis is 80% (95% CI 75% to 87%) and specificity is 98% (95% CI 96% to 100%), with a PPV of 89%.ConclusionsOur optimised algorithm, based on inpatient electronic health records, reliably identifies and stages cirrhosis in patients with HCC. This highlights the potential of routine health data in population studies to stratify patients with HCC according to liver disease severity.

scholarly journals An exploratory phenome wide association study linking asthma and liver disease genetic variants to electronic health records from the Estonian Biobank

PLoS ONE ◽  
2019 ◽  
Vol 14 (4) ◽  
pp. e0215026 ◽  
Author(s):  
Glen James ◽  
Sulev Reisberg ◽  
Kaido Lepik ◽  
Nicholas Galwey ◽  
Paul Avillach ◽  
...  
Keyword(s):  
Liver Disease ◽  
Electronic Health Records ◽  
Association Study ◽  
Genetic Variants ◽  
Health Records ◽  
Electronic Health

scholarly journals Derivation and Validation of Essential Predictors and Risk Index for Early Detection of Diabetic Retinopathy Using Electronic Health Records

2021 ◽  
Vol 10 (7) ◽  
pp. 1473
Author(s):  
Ru Wang ◽  
Zhuqi Miao ◽  
Tieming Liu ◽  
Mei Liu ◽  
Kristine Grdinovac ◽  
...  
Keyword(s):  
Diabetic Retinopathy ◽  
Early Detection ◽  
Electronic Health Records ◽  
Predictive Model ◽  
Validation Cohort ◽  
Risk Index ◽  
Diabetic Patients ◽  
Health Records ◽  
Derivation Cohort ◽  
Electronic Health

Diabetic retinopathy (DR) is a leading cause for blindness among working-aged adults. The growing prevalence of diabetes urges for cost-effective tools to improve the compliance of eye examinations for early detection of DR. The objective of this research is to identify essential predictors and develop predictive technologies for DR using electronic health records. We conducted a retrospective analysis on a derivation cohort with 3749 DR and 94,127 non-DR diabetic patients. In the analysis, an ensemble predictor selection method was employed to find essential predictors among 26 variables in demographics, duration of diabetes, complications and laboratory results. A predictive model and a risk index were built based on the selected, essential predictors, and then validated using another independent validation cohort with 869 DR and 6448 non-DR diabetic patients. Out of the 26 variables, 10 were identified to be essential for predicting DR. The predictive model achieved a 0.85 AUC on the derivation cohort and a 0.77 AUC on the validation cohort. For the risk index, the AUCs were 0.81 and 0.73 on the derivation and validation cohorts, respectively. The predictive technologies can provide an early warning sign that motivates patients to comply with eye examinations for early screening and potential treatments.

scholarly journals Predicting Hepatocellular Carcinoma With Minimal Features From Electronic Health Records: Development of a Deep Learning Model

JMIR Cancer ◽  
10.2196/19812 ◽  
2021 ◽  
Vol 7 (4) ◽  
pp. e19812
Author(s):  
Chia-Wei Liang ◽  
Hsuan-Chia Yang ◽  
Md Mohaimenul Islam ◽  
Phung Anh Alex Nguyen ◽  
Yi-Ting Feng ◽  
...  
Keyword(s):  
Neural Network ◽  
Hepatocellular Carcinoma ◽  
Deep Learning ◽  
Electronic Health Records ◽  
Network Model ◽  
Neural Network Model ◽  
Learning Model ◽  
Health Records ◽  
Electronic Health ◽  
Deep Learning Model

Background Hepatocellular carcinoma (HCC), usually known as hepatoma, is the third leading cause of cancer mortality globally. Early detection of HCC helps in its treatment and increases survival rates. Objective The aim of this study is to develop a deep learning model, using the trend and severity of each medical event from the electronic health record to accurately predict the patients who will be diagnosed with HCC in 1 year. Methods Patients with HCC were screened out from the National Health Insurance Research Database of Taiwan between 1999 and 2013. To be included, the patients with HCC had to register as patients with cancer in the catastrophic illness file and had to be diagnosed as a patient with HCC in an inpatient admission. The control cases (non-HCC patients) were randomly sampled from the same database. We used age, gender, diagnosis code, drug code, and time information as the input variables of a convolution neural network model to predict those patients with HCC. We also inspected the highly weighted variables in the model and compared them to their odds ratio at HCC to understand how the predictive model works Results We included 47,945 individuals, 9553 of whom were patients with HCC. The area under the receiver operating curve (AUROC) of the model for predicting HCC risk 1 year in advance was 0.94 (95% CI 0.937-0.943), with a sensitivity of 0.869 and a specificity 0.865. The AUROC for predicting HCC patients 7 days, 6 months, 1 year, 2 years, and 3 years early were 0.96, 0.94, 0.94, 0.91, and 0.91, respectively. Conclusions The findings of this study show that the convolutional neural network model has immense potential to predict the risk of HCC 1 year in advance with minimal features available in the electronic health records.

scholarly journals Recording of weight in electronic health records: an observational study in general practice

2018 ◽  
Vol 19 (1) ◽  
Author(s):  
Lisa D. M. Verberne ◽  
Markus M. J. Nielen ◽  
Chantal J. Leemrijse ◽  
Robert A. Verheij ◽  
Roland D. Friele
Keyword(s):  
General Practice ◽  
Observational Study ◽  
Electronic Health Records ◽  
Health Records ◽  
Electronic Health

scholarly journals Generating sequential electronic health records using dual adversarial autoencoder

2020 ◽  
Vol 27 (9) ◽  
pp. 1411-1419 ◽  
Author(s):  
Dongha Lee ◽  
Hwanjo Yu ◽  
Xiaoqian Jiang ◽  
Deevakar Rogith ◽  
Meghana Gudala ◽  
...  
Keyword(s):  
Electronic Health Records ◽  
Predictive Modeling ◽  
Medical Information ◽  
Real Data ◽  
Generative Models ◽  
Generative Adversarial Networks ◽  
Health Records ◽  
Clinical Databases ◽  
Electronic Health ◽  
Clinical Records

Abstract Objective Recent studies on electronic health records (EHRs) started to learn deep generative models and synthesize a huge amount of realistic records, in order to address significant privacy issues surrounding the EHR. However, most of them only focus on structured records about patients’ independent visits, rather than on chronological clinical records. In this article, we aim to learn and synthesize realistic sequences of EHRs based on the generative autoencoder. Materials and Methods We propose a dual adversarial autoencoder (DAAE), which learns set-valued sequences of medical entities, by combining a recurrent autoencoder with 2 generative adversarial networks (GANs). DAAE improves the mode coverage and quality of generated sequences by adversarially learning both the continuous latent distribution and the discrete data distribution. Using the MIMIC-III (Medical Information Mart for Intensive Care-III) and UT Physicians clinical databases, we evaluated the performances of DAAE in terms of predictive modeling, plausibility, and privacy preservation. Results Our generated sequences of EHRs showed the comparable performances to real data for a predictive modeling task, and achieved the best score in plausibility evaluation conducted by medical experts among all baseline models. In addition, differentially private optimization of our model enables to generate synthetic sequences without increasing the privacy leakage of patients’ data. Conclusions DAAE can effectively synthesize sequential EHRs by addressing its main challenges: the synthetic records should be realistic enough not to be distinguished from the real records, and they should cover all the training patients to reproduce the performance of specific downstream tasks.

Sign in / Sign up

Export Citation Format

Share Document