Abstract P341: Development of Predictive Models for Cardiovascular Health to Support Its Use in Real-world Data

Circulation ◽  
2020 ◽  
Vol 141 (Suppl_1) ◽  
Author(s):  
Hui Hu ◽  
Jiang Bian ◽  
Thomas A Pearson ◽  
Heather S Lipkind ◽  
Yi Zheng ◽  
...  
Keyword(s):  
Physical Activity ◽  
Total Cholesterol ◽  
Real World ◽  
Predictive Models ◽  
Cardiovascular Health ◽  
The United States ◽  
The Other ◽  
Gradient Boosting ◽  
Real World Data ◽  
World Data

Life’s Simple 7 (LS7) developed by the American Heart Association (AHA) is a new index of cardiovascular health (CVH). LS7 is comprised of 7 metrics, including 3 health factors (blood pressure [BP], total cholesterol, and glucose) and 4 health behaviors (body mass index [BMI], cigarette smoking, diet, and physical activity). To date, CVH estimates are mainly obtained from national surveys, clinical trials, and cohort studies. Real-world data (RWD) such as electronic health records (EHRs) and claims data and real-world evidence generated from these data are playing an increasing role. However, the lack of information on all 7 CVH metrics in RWD limits the use of the CVH concept in research and preventions based on RWD. Using data from the 1999-2016 National Health and Nutrition Examination Survey (NHANES), we developed predictive models for CVH among adults using 3 metrics (i.e. BP, BMI, and smoking) and sociodemographic factors (i.e. age, gender, race/ethnicity, education, and marital status) which are widely available in RWD. Each CVH metric was categorized into ideal (2 points), intermediate (1 point), or poor (0 point), and then weighted accordingly following LS7 to generate an overall CVH score (0-14 points) with a higher score indicating better CVH. Individuals with more than 4 ideal CVH metrics were determined as having ideal CVH. In addition, we also developed models using 4 CVH metrics (i.e. BP, BMI, and smoking + one of the other 4 metrics). The data were randomly divided into training (80%) and testing (20%) sets. Gradient boosting decision trees models were trained using the CatBoost library with hyper-parameters tuned by a grid search based on 5-fold cross validations. A total of 45,614 individuals aged 18 years and older in 1999-2016 NHANES were included. The models with 3 CVH metrics (i.e. BP, BMI, and smoking) as predictors achieved a test-AUC of 0.95 and a test-RMSE of 1.39. Including one of the other 4 CVH metrics (i.e. total cholesterol, glucose, diet, or physical activity) as a predictor in the models along with the previous 3 metrics (i.e. BP, BMI, and smoking) further improved the predictive performance (test-AUC>0.96 and test-RMSE<1.38). These findings suggested that the 3 CVH metrics (i.e. BP, BMI, and smoking) that are widely available in RWD can be used to accurately estimate CVH among adults in the United States.

scholarly journals Transmission of SARS-CoV-2 Considering Shared Chairs in Outpatient Dialysis: A Real-World Case-Control Study

2021 ◽  
Author(s):  
Ravi Thadhani ◽  
Joanna Willetts ◽  
Catherine Wang ◽  
John Larkin ◽  
Hanjie Zhang ◽  
...  
Keyword(s):  
Real World ◽  
Case Control Study ◽  
The United States ◽  
Hemodialysis Patients ◽  
Case Control ◽  
Positive Patient ◽  
Sensitivity Analyses ◽  
Real World Data ◽  
World Data ◽  
Control Study

AbstractBackgroundSARS-CoV-2 is primarily transmitted through aerosolized droplets; however, the virus can remain transiently viable on surfaces.ObjectiveWe examined transmission within hemodialysis facilities, with a specific focus on the possibility of indirect patient-to-patient transmission through shared dialysis chairs.DesignWe used real-world data from hemodialysis patients treated between February 1st and June 8th, 2020 to perform a case-control study matching each SARS-CoV-2 positive patient (case) to a non-SARS-CoV-2 patient (control) in the same dialysis shift and traced back 14 days to capture possible exposure from chairs sat in by SARS-CoV-2 patients. Cases and controls were matched on age, sex, race, facility, shift date, and treatment count.Setting2,600 hemodialysis facilities in the United States.PatientsAdult (age ≥18 years) hemodialysis patients.MeasurementsConditional logistic regression models tested whether chair exposure after a positive patient conferred a higher risk of SARS-CoV-2 infection to the immediate subsequent patient.ResultsAmong 170,234 hemodialysis patients, 4,782 (2.8%) tested positive for SARS-CoV-2 (mean age 64 years, 44% female). Most facilities (68.5%) had 0 to 1 positive SARS-CoV-2 patient. We matched 2,379 SARS-CoV-2 positive cases to 2,379 non-SARS-CoV-2 controls; 1.30% (95%CI 0.90%, 1.87%) of cases and 1.39% (95%CI 0.97%, 1.97%) of controls were exposed to a chair previously sat in by a shedding SARS-CoV-2 patient. Transmission risk among cases was not significantly different from controls (OR=0.94; 95%CI 0.57 to 1.54; p=0.80). Results remained consistent in adjusted and sensitivity analyses.LimitationAnalysis used real-world data that could contain errors and only considered vertical transmission associated with shared use of dialysis chairs by symptomatic patients.ConclusionsThe risk of indirect patient-to-patient transmission of SARS-CoV-2 infection from dialysis chairs appears to be low.Primary Funding SourceFresenius Medical Care North America; National Institute of Diabetes and Digestive and Kidney Diseases (R01DK130067)

scholarly journals Estimating the Population Benefits and Costs of Rituximab Therapy in the United States from 1998 to 2013 Using Real-World Data

Medical Care ◽  
2016 ◽  
Vol 54 (4) ◽  
pp. 343-349 ◽  
Author(s):  
Mark D. Danese ◽  
Carolina M. Reyes ◽  
Michelle L. Gleeson ◽  
Marc Halperin ◽  
Sandra L. Skettino ◽  
...  
Keyword(s):  
United States ◽  
Real World ◽  
The United States ◽  
Real World Data ◽  
World Data ◽  
Benefits And Costs

scholarly journals Developing a machine learning environmental allergy prediction model from real world data through a novel decentralized mobile study platform.

2020 ◽  
Author(s):  
Chethan Sarabu ◽  
Sandra Steyaert ◽  
Nirav Shah
Keyword(s):  
Machine Learning ◽  
Real World ◽  
Predictive Models ◽  
Clinical Care ◽  
Sensor Data ◽  
Real World Data ◽  
World Data ◽  
Demographic Groups ◽  
Prediction And Prevention ◽  
Wide Range

Environmental allergies cause significant morbidity across a wide range of demographic groups. This morbidity could be mitigated through individualized predictive models capable of guiding personalized preventive measures. We developed a predictive model by integrating smartphone sensor data with symptom diaries maintained by patients. The machine learning model was found to be highly predictive, with an accuracy of 0.801. Such models based on real-world data can guide clinical care for patients and providers, reduce the economic burden of uncontrolled allergies, and set the stage for subsequent research pursuing allergy prediction and prevention. Moreover, this study offers proof-of-principle regarding the feasibility of building clinically useful predictive models from 'messy,' participant derived real-world data.

Real-world outcomes of patients with BRAF-mutated mCRC treated in the United States.

2020 ◽  
Vol 38 (15_suppl) ◽  
pp. 4030-4030
Author(s):  
Matthew Braithwaite ◽  
Christopher Duane Nevala-Plagemann ◽  
Kelsey Baron ◽  
Benjamin Haaland ◽  
Lisa M. Pappas ◽  
...  
Keyword(s):  
United States ◽  
Real World ◽  
Braf Mutation ◽  
The United States ◽  
Survival Outcomes ◽  
Prognostic Impact ◽  
Braf Mutations ◽  
Real World Data ◽  
World Data ◽  
Significant Difference

4030 Background: BRAF mutations portend a poor prognosis in metastatic colorectal cancer (mCRC). Recent trials have hypothesized that using more aggressive triplet-based chemotherapy regimens such as FOLFOXIRI in the frontline setting may improve outcomes in this patient population. In this study, we utilized real-world data to assess whether FOLFOXIRI is being used in the United States (US) and compared survival outcomes in BRAF mutated (BRAFmt) mCRC stratified by first line (1L) therapy. Methods: The nationwide Flatiron Health EHR-derived de-identified database was reviewed for patients diagnosed with mCRC between 2013 and 2018. Patients who had documented BRAF mutation testing and received a standard 1L therapy were included for analysis. Patients who did not have a visit or medication order within 90 days of metastatic diagnosis were excluded to ensure patients were engaged with care at the data-providing institution. Kaplan-Meier and Cox proportional hazard modeling were used to compare survival outcomes stratified by BRAF mutation status and 1L therapy received. Results: A total of 4,454 patients with documented BRAF mutational status were included, of which 3,988 (89.5%) were BRAF wild type (BRAFwt) and 466 (10.5%) were BRAFmt. Median OS was 15.4 months (mo) in the BRAFmt group compared to 28.1 mo in the BRAFwt group (HR 0.48, 95% CI 0.41- 0.56, p < 0.001). Only 3% (n = 16) of BRAFmt patients received 1L FOLFOXIRI +/- bevacizumab with a median OS of 13.8 mo compared to 15.5 mo in patients receiving a chemotherapy doublet (FOLFOX, CAPEOX, or FOLFIRI) +/- bevacizumab (95% CI 4.9 – not reached vs 14.3 – 19.0, p = 0.38). In BRAFmt patients, multivariate analysis (MVA) did not detect a significant improvement in OS with the use of FOLFIRI plus bevacizumab (HR 0.88, 95% CI 0.50-1.56, p = 0.67) or FOLFOX/CAPEOX plus bevacizumab (HR 0.89, 95% CI 0.59 – 1.34, p = 0.58) when compared to chemotherapy doublet alone. A MVA comparing 1L therapies in the BRAFwt group did not detect a significant improvement in OS with bevacizumab plus chemotherapy doublet compared to chemotherapy doublet alone. When stratified by 1L treatment regimen, similar proportions of BRAFmt patients received second line therapy. Conclusions: This analysis of real-world data confirms the negative prognostic impact of BRAF mutations in mCRC and suggests that FOLFOXIRI has not been widely adopted in the management of these patients in the US. We were unable to demonstrate any significant difference in OS of patients with BRAFmt mCRC based on type of 1L therapy received.

scholarly journals Challenges in Phase 4 post-licensure safety studies using real world data in the United States: hepatitis B vaccine example

Vaccine X ◽  
2021 ◽  
pp. 100101
Author(s):  
Katia Bruxvoort ◽  
Lina S. Sy ◽  
Bradley K. Ackerson ◽  
Jeff Slezak ◽  
Lei Qian ◽  
...  
Keyword(s):  
United States ◽  
Hepatitis B ◽  
Real World ◽  
The United States ◽  
Hepatitis B Vaccine ◽  
Real World Data ◽  
World Data ◽  
Safety Studies

scholarly journals Reliability of Conclusions from Early Analyses of Real-World Data for Newly Approved Drugs in Advanced Gastric Cancer in the United States

2020 ◽  
Vol Volume 11 ◽  
pp. 27-43
Author(s):  
Lisa M Hess ◽  
Michael Grabner ◽  
Liya Wang ◽  
Astra M Liepa ◽  
Xiaohong Ivy Li ◽  
...  
Keyword(s):  
United States ◽  
Gastric Cancer ◽  
Advanced Gastric Cancer ◽  
Real World ◽  
The United States ◽  
Real World Data ◽  
World Data ◽  
Approved Drugs

scholarly journals COVID19 Real-World Data for the US and Lessons to Re-Open Business

2020 ◽  
Author(s):  
Pascal J. Goldschmidt-Clermont
Keyword(s):  
Enterprise Resource Planning ◽  
Real World ◽  
Resource Planning ◽  
The United States ◽  
Lessons Learned ◽  
Planning System ◽  
Real World Data ◽  
World Data ◽  
The Us ◽  
Contact Tracking

AbstractIn March of 2020, the COVID19 pandemic had expanded to the United States of America (US). Companies designated as “essential” for the US had to maintain productivity in spite of the growing threat created by the SARS-CoV-2 virus. With this report, we present the response of one such company, the Lennar Corporation, a major homebuilder in the US. Within days, Lennar had implemented a morning health check via its enterprise resource planning system, to identify associates (employees) who were sick, or not in their “usual state of health”. With this survey, Lennar was able to ensure that no one sick would show up to work, and instead, would self-quarantine at home. Furthermore, with thorough contact tracking, associates exposed to COVID19 patients (suspected or RT-PCR test-confirmed), were also asked to self-quarantine. This survey, in addition to other safety measures, such as an overhaul of the company with nearly 50% of the company working from home, prolific communication, and many more measures, Lennar was able to function safely for its associates and successfully as an enterprise. The data that we present here are “real world data” collected in the context of working throughout a dreadful pandemic, and the lessons learned could be helpful to other companies that are preparing to return to work.

scholarly journals Applying real-world data to support regulatory decision — making in the United States

2021 ◽  
Vol 20 (1) ◽  
pp. 64-69
Author(s):  
M. A. Borzova ◽  
А. S. Kolbin
Keyword(s):  
United States ◽  
Decision Making ◽  
Real World ◽  
The United States ◽  
Legal Basis ◽  
Real World Data ◽  
World Data ◽  
Regulatory Decision ◽  
Eurasian Economic Union ◽  
Economic Union

The article describes the legal basis for the application of real-world data to support regulatory decision-making in the United States, as well as the possibility of implementing the relevant approaches in the legislation of the Eurasian Economic Union.

Sign in / Sign up

Export Citation Format

Share Document