scholarly journals Representation learning for clinical time series prediction tasks in electronic health records

2019 ◽  
Vol 19 (S8) ◽  
Author(s):  
Tong Ruan ◽  
Liqi Lei ◽  
Yangming Zhou ◽  
Jie Zhai ◽  
Le Zhang ◽  
...  
Keyword(s):  
Electronic Health Records ◽  
Time Series Prediction ◽  
Improve Patient Care ◽  
Representation Learning ◽  
Mortality Prediction ◽  
Systematic Bias ◽  
Health Records ◽  
Prediction Task ◽  
Electronic Health ◽  
Sequential Information

Abstract Background Electronic health records (EHRs) provide possibilities to improve patient care and facilitate clinical research. However, there are many challenges faced by the applications of EHRs, such as temporality, high dimensionality, sparseness, noise, random error and systematic bias. In particular, temporal information is difficult to effectively use by traditional machine learning methods while the sequential information of EHRs is very useful. Method In this paper, we propose a general-purpose patient representation learning approach to summarize sequential EHRs. Specifically, a recurrent neural network based denoising autoencoder (RNN-DAE) is employed to encode inhospital records of each patient into a low dimensional dense vector. Results Based on EHR data collected from Shuguang Hospital affiliated to Shanghai University of Traditional Chinese Medicine, we experimentally evaluate our proposed RNN-DAE method on both mortality prediction task and comorbidity prediction task. Extensive experimental results show that our proposed RNN-DAE method outperforms existing methods. In addition, we apply the “Deep Feature” represented by our proposed RNN-DAE method to track similar patients with t-SNE, which also achieves some interesting observations. Conclusion We propose an effective unsupervised RNN-DAE method to summarize patient sequential information in EHR data. Our proposed RNN-DAE method is useful on both mortality prediction task and comorbidity prediction task.

scholarly journals Deep representation learning of electronic health records to unlock patient stratification at scale

2020 ◽  
Vol 3 (1) ◽  
Author(s):  
Isotta Landi ◽  
Benjamin S. Glicksberg ◽  
Hao-Chih Lee ◽  
Sarah Cherng ◽  
Giulia Landi ◽  
...  
Keyword(s):  
Electronic Health Records ◽  
Representation Learning ◽  
Patient Stratification ◽  
Health Records ◽  
Electronic Health

scholarly journals AutoScore: A Machine Learning–Based Automatic Clinical Score Generator and Its Application to Mortality Prediction Using Electronic Health Records

10.2196/21798 ◽  
2020 ◽  
Vol 8 (10) ◽  
pp. e21798 ◽  
Author(s):  
Feng Xie ◽  
Bibhas Chakraborty ◽  
Marcus Eng Hock Ong ◽  
Benjamin Alan Goldstein ◽  
Nan Liu
Keyword(s):  
Machine Learning ◽  
Logistic Regression ◽  
Electronic Health Records ◽  
Clinical Score ◽  
Mortality Prediction ◽  
Fine Tuning ◽  
Health Records ◽  
Scoring Model ◽  
Benchmark Database ◽  
Electronic Health

Background Risk scores can be useful in clinical risk stratification and accurate allocations of medical resources, helping health providers improve patient care. Point-based scores are more understandable and explainable than other complex models and are now widely used in clinical decision making. However, the development of the risk scoring model is nontrivial and has not yet been systematically presented, with few studies investigating methods of clinical score generation using electronic health records. Objective This study aims to propose AutoScore, a machine learning–based automatic clinical score generator consisting of 6 modules for developing interpretable point-based scores. Future users can employ the AutoScore framework to create clinical scores effortlessly in various clinical applications. Methods We proposed the AutoScore framework comprising 6 modules that included variable ranking, variable transformation, score derivation, model selection, score fine-tuning, and model evaluation. To demonstrate the performance of AutoScore, we used data from the Beth Israel Deaconess Medical Center to build a scoring model for mortality prediction and then compared the data with other baseline models using the receiver operating characteristic analysis. A software package in R 3.5.3 (R Foundation) was also developed to demonstrate the implementation of AutoScore. Results Implemented on the data set with 44,918 individual admission episodes of intensive care, the AutoScore-created scoring models performed comparably well as other standard methods (ie, logistic regression, stepwise regression, least absolute shrinkage and selection operator, and random forest) in terms of predictive accuracy and model calibration but required fewer predictors and presented high interpretability and accessibility. The nine-variable, AutoScore-created, point-based scoring model achieved an area under the curve (AUC) of 0.780 (95% CI 0.764-0.798), whereas the model of logistic regression with 24 variables had an AUC of 0.778 (95% CI 0.760-0.795). Moreover, the AutoScore framework also drives the clinical research continuum and automation with its integration of all necessary modules. Conclusions We developed an easy-to-use, machine learning–based automatic clinical score generator, AutoScore; systematically presented its structure; and demonstrated its superiority (predictive performance and interpretability) over other conventional methods using a benchmark database. AutoScore will emerge as a potential scoring tool in various medical applications.

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 Case Report Medical Eponyms

2012 ◽  
Vol 03 (03) ◽  
pp. 349-355 ◽  
Author(s):  
L.N. Guptha Munugoor Baskaran ◽  
P.J. Greco ◽  
D.C. Kaelber
Keyword(s):  
Case Report ◽  
Electronic Health Records ◽  
Patient Care ◽  
Improve Patient Care ◽  
Clinical Informatics ◽  
Health Records ◽  
Electronic Health ◽  
Informatics Tools ◽  
Improve Patient

SummaryMedical eponyms are medical words derived from people’s names. Eponyms, especially similar sounding eponyms, may be confusing to people trying to use them because the terms themselves do not contain physiologically descriptive words about the condition they refer to. Through the use of electronic health records (EHRs), embedded applied clinical informatics tools including synonyms and pick lists that include physiologically descriptive terms associated with any eponym appearing in the EHR can significantly enhance the correct use of medical eponyms. Here we describe a case example of two similar sounding medical eponyms – Wegener’s disease and Wegner’s disease – which were confused in our EHR. We describe our solution to address this specific example and our suggestions and accomplishments developing more generalized approaches to dealing with medical eponyms in EHRs. Integrating brief physiologically descriptive terms with medical eponyms provides an applied clinical informatics opportunity to improve patient care.

Sign in / Sign up

Export Citation Format

Share Document