S3 Identification of Patients at Risk for Pancreatic Cancer in a 3-Year Timeframe Based on Machine Learning Algorithms in the Electronic Health Record

Introduction: Patients with peripheral artery disease (PAD) are at high risk of major adverse cardiac and cerebrovascular events (MACCE). However, no currently available risk scores accurately delineate which patients are most likely to sustain an event, creating a missed opportunity for more aggressive risk factor management. We set out to develop a novel predictive model - based on automated machine learning algorithms using electronic health record (EHR) data - with the aim of identifying which PAD patients are most likely to have an adverse outcome during follow-up. Methods: Data were derived from patients with a diagnosis of PAD at our institution. Novel machine-learning algorithms including random forest and penalized regression predictive models were developed using structured and unstructured data that including lab values, diagnosis codes, medications, and clinical notes. Patients were matched for total follow-up time to remove length of patient records as a biasing factor in our predictive models. Results: After matching for length of follow-up, 3,807 patients were included in our models. A total of 1,269 patients had a MACCE event after PAD diagnosis. The median time to MACCE was 2.8 years after PAD diagnosis. Utilizing 1,492 different variables extracted from the EHR, our best predictive model was able to very accurately predict which patients would go on to have a MACCE event after diagnosis of PAD with an AUC of 0.98, with a sensitivity, specificity and positive predictive value of 0.90, 0.96, and 0.93, respectively. Conclusions: Hypothesis-free, machine-learning algorithms using freely available data in the EHR can accurately predict which PAD patients are most likely to go on to develop future MACCE. While these findings require validation in an independent data set, there is hope that these informatics approaches can be applied to the medical record in an automated fashion to risk stratify patients with vascular disease and identify those who might benefit from more aggressive disease management in real-time.

Download Full-text

Predicting readmission and death after hospital discharge: a comparison of conventional frailty measurement with an electronic health record-based score

Age and Ageing ◽

10.1093/ageing/afab043 ◽

2021 ◽

Author(s):

Yong Yong Tew ◽

Juen Hao Chan ◽

Polly Keeling ◽

Susan D Shenkin ◽

Alasdair MacLullich ◽

...

Keyword(s):

At Risk ◽

Electronic Health Record ◽

Hospital Discharge ◽

Risk Score ◽

Primary Outcome ◽

Risk Scores ◽

Health Record ◽

Co Morbidity ◽

Patients At Risk ◽

Electronic Health

Abstract Background frailty measurement may identify patients at risk of decline after hospital discharge, but many measures require specialist review and/or additional testing. Objective to compare validated frailty tools with routine electronic health record (EHR) data at hospital discharge, for associations with readmission or death. Design observational cohort study. Setting hospital ward. Subjects consented cardiology inpatients ≥70 years old within 24 hours of discharge. Methods patients underwent Fried, Short Physical Performance Battery (SPPB), PRISMA-7 and Clinical Frailty Scale (CFS) assessments. An EHR risk score was derived from the proportion of 31 possible frailty markers present. Electronic follow-up was completed for a primary outcome of 90-day readmission or death. Secondary outcomes were mortality and days alive at home (‘home time’) at 12 months. Results in total, 186 patients were included (79 ± 6 years old, 64% males). The primary outcome occurred in 55 (30%) patients. Fried (hazard ratio [HR] 1.47 per standard deviation [SD] increase, 95% confidence interval [CI] 1.18–1.81, P < 0.001), CFS (HR 1.24 per SD increase, 95% CI 1.01–1.51, P = 0.04) and EHR risk scores (HR 1.35 per SD increase, 95% CI 1.02–1.78, P = 0.04) were independently associated with the primary outcome after adjustment for age, sex and co-morbidity, but the SPPB and PRISMA-7 were not. The EHR risk score was independently associated with mortality and home time at 12 months. Conclusions frailty measurement at hospital discharge identifies patients at risk of poorer outcomes. An EHR-based risk score appeared equivalent to validated frailty tools and may be automated to screen patients at scale, but this requires further validation.

Download Full-text

1651. Describing the Tuberculosis Infection Cascade of Care Based on Electronic Health Record Data

Open Forum Infectious Diseases ◽

10.1093/ofid/ofaa439.1829 ◽

2020 ◽

Vol 7 (Supplement_1) ◽

pp. S813-S814

Author(s):

Laura A Vonnahme ◽

Jonathan Todd ◽

Jon Puro ◽

Jee Oakley ◽

Matthew Jones ◽

...

Keyword(s):

At Risk ◽

Electronic Health Record ◽

Tuberculosis Infection ◽

Health Record ◽

Populations At Risk ◽

Cascade Of Care ◽

Patients At Risk ◽

Electronic Health ◽

Not At Risk ◽

Positive Results

Abstract Background Appropriate screening of individuals to detect latent tuberculosis infection (LTBI) is a critical step for achieving tuberculosis (TB) elimination in the US; >80% of TB cases are attributed to LTBI reactivation. TB infection testing and treatment must engage community health clinics where populations at risk seek care. However, there are significant data knowledge gaps in the current LTBI cascade of care (CoC) in this setting. We used an electronic health record (EHR) database from OCHIN, Inc., to characterize the LTBI CoC and identify potential future interventions. Methods We extracted a cohort of patients from 2012–2016 EHR data; we stratified by whether patients were at risk for TB based on meeting at least one of the following criteria: non-US born or non-English language preference, homelessness, encounter at correctional facility, history of close contact with a TB case, or being immunocompromised. Along each step of the LTBI CoC, we determined the proportions with a test for TB infection, with available test results, with a positive test, with an LTBI diagnosis, and with LTBI treatment prescribed. We used Χ 2 tests to compare the LTBI CoCs among patients at risk with those classified as not at risk. Results Of nearly 2.2 million patient records, 701,467 (32.0%) met criteria for being at risk for TB; 84,422 at risk (12.0%) were tested; 65,562 (77.7%) had available results, of whom 9,624 (14.7%) were positive. Among those with positive results, 6,958 (72.3%) had an LTBI diagnosis, of whom 1,732 (24.9%) were prescribed treatment. Among those classified as not at risk, fewer were tested (66,773 [4.5%], p< 0.001) and had positive results (2,500 [3.7%], p< 0.0001). Among those with positive results, 1,998 (80.0%) had an LTBI diagnosis, of whom 395 (19.8%) initiated treatment. Conclusion This study highlights gaps in the LTBI CoC, and where interventions are most needed. The largest gaps were in testing patients at risk, as 88% were not tested, and treatment, as 75% diagnosed with LTBI were not treated. Just under half (44%) of all TB tests appeared to be performed in persons with little risk for TB; this is a substantial amount of testing given very few begin treatment. Resources could be redirected to increase screening and treatment among populations at risk. Disclosures All Authors: No reported disclosures

Download Full-text

Development of a Prediction Model for Incident Atrial Fibrillation using Machine Learning Applied to Harmonized Electronic Health Record Data

10.1101/520866 ◽

2019 ◽

Cited By ~ 1

Author(s):

Premanand Tiwari ◽

Katie Colborn ◽

Derek E. Smith ◽

Fuyong Xing ◽

Debashis Ghosh ◽

...

Keyword(s):

Machine Learning ◽

Atrial Fibrillation ◽

Electronic Health Record ◽

Data Reduction ◽

Machine Learning Algorithms ◽

Common Data Model ◽

Health Record ◽

Electronic Health Record Data ◽

Hyperparameter Selection ◽

Electronic Health

AbstractAtrial fibrillation (AF) is the most common sustained cardiac arrhythmia, whose early detection could lead to significant improvements in outcomes through appropriate prescription of anticoagulation. Although a variety of methods exist for screening for AF, there is general agreement that a targeted approach would be preferred. Implicit within this approach is the need for an efficient method for identification of patients at risk. In this investigation, we examined the strengths and weaknesses of an approach based on application of machine-learning algorithms to electronic health record (EHR) data that has been harmonized to the Observational Medical Outcomes Partnership (OMOP) common data model. We examined data from a total of 2.3M individuals, of whom 1.16% developed incident AF over designated 6-month time intervals. We examined and compared several approaches for data reduction, sample balancing (re-sampling) and predictive modeling using cross-validation for hyperparameter selection, and out-of-sample testing for validation. Although no approach provided outstanding classification accuracy, we found that the optimal approach for prediction of 6-month incident AF used a random forest classifier, raw features (no data reduction), and synthetic minority oversampling technique (SMOTE) resampling (F1 statistic 0.12, AUC 0.65). This model performed better than a predictive model based only on known AF risk factors, and highlighted the importance of using resampling methods to optimize ML approaches to imbalanced data as exists in EHRs. Further studies using EHR data in other medical systems are needed to validate the clinical applicability of these findings.

Download Full-text