scholarly journals Extraction of Information Related to Adverse Drug Events from Electronic Health Record Notes: Design of an End-to-End Model Based on Deep Learning

10.2196/12159 ◽  
2018 ◽  
Vol 6 (4) ◽  
pp. e12159 ◽  
Author(s):  
Fei Li ◽  
Weisong Liu ◽  
Hong Yu
Keyword(s):  
Deep Learning ◽  
Electronic Health Record ◽  
Adverse Drug Events ◽  
Health Record ◽  
Model Based ◽  
End To End ◽  
Electronic Health

scholarly journals Early detection of sepsis utilizing deep learning on electronic health record event sequences

2020 ◽  
Vol 104 ◽  
pp. 101820 ◽  
Author(s):  
Simon Meyer Lauritsen ◽  
Mads Ellersgaard Kalør ◽  
Emil Lund Kongsgaard ◽  
Katrine Meyer Lauritsen ◽  
Marianne Johansson Jørgensen ◽  
...  
Keyword(s):  
Deep Learning ◽  
Early Detection ◽  
Electronic Health Record ◽  
Health Record ◽  
Event Sequences ◽  
Electronic Health

scholarly journals Model-Based Algorithms for Detecting Peripheral Artery Disease Using Administrative Data From an Electronic Health Record Data System: Algorithm Development Study

10.2196/18542 ◽  
2020 ◽  
Vol 8 (8) ◽  
pp. e18542 ◽  
Author(s):  
Elizabeth Hope Weissler ◽  
Steven J Lippmann ◽  
Michelle M Smerek ◽  
Rachael A Ward ◽  
Aman Kansal ◽  
...  
Keyword(s):  
Electronic Health Record ◽  
Health System ◽  
Administrative Data ◽  
Peripheral Artery Disease ◽  
Health Record ◽  
Peripheral Artery ◽  
Model Based ◽  
Diagnosis Codes ◽  
Electronic Health ◽  
Artery Disease

Background Peripheral artery disease (PAD) affects 8 to 10 million Americans, who face significantly elevated risks of both mortality and major limb events such as amputation. Unfortunately, PAD is relatively underdiagnosed, undertreated, and underresearched, leading to wide variations in treatment patterns and outcomes. Efforts to improve PAD care and outcomes have been hampered by persistent difficulties identifying patients with PAD for clinical and investigatory purposes. Objective The aim of this study is to develop and validate a model-based algorithm to detect patients with peripheral artery disease (PAD) using data from an electronic health record (EHR) system. Methods An initial query of the EHR in a large health system identified all patients with PAD-related diagnosis codes for any encounter during the study period. Clinical adjudication of PAD diagnosis was performed by chart review on a random subgroup. A binary logistic regression to predict PAD was built and validated using a least absolute shrinkage and selection operator (LASSO) approach in the adjudicated patients. The algorithm was then applied to the nonsampled records to further evaluate its performance. Results The initial EHR data query using 406 diagnostic codes yielded 15,406 patients. Overall, 2500 patients were randomly selected for ground truth PAD status adjudication. In the end, 108 code flags remained after removing rarely- and never-used codes. We entered these code flags plus administrative encounter, imaging, procedure, and specialist flags into a LASSO model. The area under the curve for this model was 0.862. Conclusions The algorithm we constructed has two main advantages over other approaches to the identification of patients with PAD. First, it was derived from a broad population of patients with many different PAD manifestations and treatment pathways across a large health system. Second, our model does not rely on clinical notes and can be applied in situations in which only administrative billing data (eg, large administrative data sets) are available. A combination of diagnosis codes and administrative flags can accurately identify patients with PAD in large cohorts.

scholarly journals The Use of Synthetic Electronic Health Record Data and Deep Learning to Improve Timing of High-Risk Heart Failure Surgical Intervention by Predicting Proximity to Catastrophic Decompensation

2020 ◽  
Vol 2 ◽  
Author(s):  
Aixia Guo ◽  
Randi E. Foraker ◽  
Robert M. MacGregor ◽  
Faraz M. Masood ◽  
Brian P. Cupps ◽  
...  
Keyword(s):  
Machine Learning ◽  
Heart Failure ◽  
Deep Learning ◽  
High Risk ◽  
Electronic Health Record ◽  
Surgical Intervention ◽  
Health Record ◽  
Predictive Capability ◽  
Clinical Tool ◽  
Electronic Health

Objective: Although many clinical metrics are associated with proximity to decompensation in heart failure (HF), none are individually accurate enough to risk-stratify HF patients on a patient-by-patient basis. The dire consequences of this inaccuracy in risk stratification have profoundly lowered the clinical threshold for application of high-risk surgical intervention, such as ventricular assist device placement. Machine learning can detect non-intuitive classifier patterns that allow for innovative combination of patient feature predictive capability. A machine learning-based clinical tool to identify proximity to catastrophic HF deterioration on a patient-specific basis would enable more efficient direction of high-risk surgical intervention to those patients who have the most to gain from it, while sparing others. Synthetic electronic health record (EHR) data are statistically indistinguishable from the original protected health information, and can be analyzed as if they were original data but without any privacy concerns. We demonstrate that synthetic EHR data can be easily accessed and analyzed and are amenable to machine learning analyses.Methods: We developed synthetic data from EHR data of 26,575 HF patients admitted to a single institution during the decade ending on 12/31/2018. Twenty-seven clinically-relevant features were synthesized and utilized in supervised deep learning and machine learning algorithms (i.e., deep neural networks [DNN], random forest [RF], and logistic regression [LR]) to explore their ability to predict 1-year mortality by five-fold cross validation methods. We conducted analyses leveraging features from prior to/at and after/at the time of HF diagnosis.Results: The area under the receiver operating curve (AUC) was used to evaluate the performance of the three models: the mean AUC was 0.80 for DNN, 0.72 for RF, and 0.74 for LR. Age, creatinine, body mass index, and blood pressure levels were especially important features in predicting death within 1-year among HF patients.Conclusions: Machine learning models have considerable potential to improve accuracy in mortality prediction, such that high-risk surgical intervention can be applied only in those patients who stand to benefit from it. Access to EHR-based synthetic data derivatives eliminates risk of exposure of EHR data, speeds time-to-insight, and facilitates data sharing. As more clinical, imaging, and contractile features with proven predictive capability are added to these models, the development of a clinical tool to assist in timing of intervention in surgical candidates may be possible.

scholarly journals Using the Diffusion of Innovations Theory to Assess Socio-Technical Factors in Planning the Implementation of an Electronic Health Record Alert across Multiple Primary Care Clinics

2016 ◽  
Vol 23 (1) ◽  
pp. 450 ◽  
Author(s):  
Ching-Pin Lin ◽  
Janelle Guirguis-Blake ◽  
Gina A. Keppel ◽  
Sharon Dobie ◽  
Justin Osborn ◽  
...  
Keyword(s):  
Primary Care ◽  
Organizational Culture ◽  
Electronic Health Record ◽  
Diffusion Of Innovations ◽  
Adverse Drug Events ◽  
The United States ◽  
Health Record ◽  
Diffusion Of Innovations Theory ◽  
Primary Care Clinics ◽  
Electronic Health

Background: Adverse drug events (ADEs) are a leading cause of death in the United States. Patients with stage 3 and 4 chronic kidney disease (CKD) are at particular risk because many medications are cleared by the kidneys. Alerts in the electronic health record (EHR) about drug appropriateness and dosing at the time of prescription have been shown to reduce ADEs for patients with stage 3 and 4 CKD in inpatient settings, but more research is needed about the implementation and effectiveness of such alerts in outpatient settings.Objective:  To explore factors that might inform the implementation of an electronic drug–disease alert for patients with CKD in primary care clinics, using Rogers’ diffusion of innovations theory as an analytic framework.Methods: Interviews were conducted with key informants in four diverse clinics using various EHR systems. Interviews were audio recorded and transcribed. results Although all clinics had a current method for calculating glomerular filtration rate (GFR), clinics were heterogeneous with regard to current electronic decision support practices, quality improvement resources, and organizational culture and structure.Conclusion: Understanding variation in organizational culture and infrastructure across primary care clinics is important in planning implementation of an intervention to reduce ADEs among patients with CKD.

scholarly journals Model-Based Algorithms for Detecting Peripheral Artery Disease Using Administrative Data From an Electronic Health Record Data System: Algorithm Development Study (Preprint)

2020 ◽  
Author(s):  
Elizabeth Hope Weissler ◽  
Steven J Lippmann ◽  
Michelle M Smerek ◽  
Rachael A Ward ◽  
Aman Kansal ◽  
...  
Keyword(s):  
Electronic Health Record ◽  
Health System ◽  
Administrative Data ◽  
Peripheral Artery Disease ◽  
Health Record ◽  
Peripheral Artery ◽  
Model Based ◽  
Diagnosis Codes ◽  
Electronic Health ◽  
Artery Disease

BACKGROUND Peripheral artery disease (PAD) affects 8 to 10 million Americans, who face significantly elevated risks of both mortality and major limb events such as amputation. Unfortunately, PAD is relatively underdiagnosed, undertreated, and underresearched, leading to wide variations in treatment patterns and outcomes. Efforts to improve PAD care and outcomes have been hampered by persistent difficulties identifying patients with PAD for clinical and investigatory purposes. OBJECTIVE The aim of this study is to develop and validate a model-based algorithm to detect patients with peripheral artery disease (PAD) using data from an electronic health record (EHR) system. METHODS An initial query of the EHR in a large health system identified all patients with PAD-related diagnosis codes for any encounter during the study period. Clinical adjudication of PAD diagnosis was performed by chart review on a random subgroup. A binary logistic regression to predict PAD was built and validated using a least absolute shrinkage and selection operator (LASSO) approach in the adjudicated patients. The algorithm was then applied to the nonsampled records to further evaluate its performance. RESULTS The initial EHR data query using 406 diagnostic codes yielded 15,406 patients. Overall, 2500 patients were randomly selected for ground truth PAD status adjudication. In the end, 108 code flags remained after removing rarely- and never-used codes. We entered these code flags plus administrative encounter, imaging, procedure, and specialist flags into a LASSO model. The area under the curve for this model was 0.862. CONCLUSIONS The algorithm we constructed has two main advantages over other approaches to the identification of patients with PAD. First, it was derived from a broad population of patients with many different PAD manifestations and treatment pathways across a large health system. Second, our model does not rely on clinical notes and can be applied in situations in which only administrative billing data (eg, large administrative data sets) are available. A combination of diagnosis codes and administrative flags can accurately identify patients with PAD in large cohorts.

Sign in / Sign up

Export Citation Format

Share Document