Literature DB >> 31785526

Examining the impact of data quality and completeness of electronic health records on predictions of patients' risks of cardiovascular disease.

Yan Li1, Matthew Sperrin1, Glen P Martin1, Darren M Ashcroft2, Tjeerd Pieter van Staa3.   

Abstract

OBJECTIVE: To assess the extent of variation of data quality and completeness of electronic health records and impact on the robustness of risk predictions of incident cardiovascular disease (CVD) using a risk prediction tool that is based on routinely collected data (QRISK3).
DESIGN: Longitudinal cohort study. SETTINGS: 392 general practices (including 3.6 million patients) linked to hospital admission data.
METHODS: Variation in data quality was assessed using Sáez's stability metrics quantifying outlyingness of each practice. Statistical frailty models evaluated whether accuracy of QRISK3 predictions on individual predictions and effects of overall risk factors (linear predictor) varied between practices.
RESULTS: There was substantial heterogeneity between practices in CVD incidence unaccounted for by QRISK3. In the lowest quintile of statistical frailty, a QRISK3 predicted risk of 10 % for female was in a range between 7.1 % and 9.0 % when incorporating practice variability into the statistical frailty models; for the highest quintile, this was 10.9%-16.4%. Data quality (using Saez metrics) and completeness were comparable across different levels of statistical frailty. For example, recording of missing information on ethnicity was 55.7 %, 62.7 %, 57.8 %, 64.8 % and 62.1 % for practices from lowest to highest quintiles of statistical frailty respectively. The effects of risk factors did not vary between practices with little statistical variation of beta coefficients.
CONCLUSIONS: The considerable unmeasured heterogeneity in CVD incidence between practices was not explained by variations in data quality or effects of risk factors. QRISK3 risk prediction should be supplemented with clinical judgement and evidence of additional risk factors.
Copyright © 2019 Elsevier B.V. All rights reserved.

Entities:  

Keywords:  CVD risk prediction; Electronic health records; Practice variability; QRISK; Random slope model; Statistical frailty model

Mesh:

Year:  2019        PMID: 31785526     DOI: 10.1016/j.ijmedinf.2019.104033

Source DB:  PubMed          Journal:  Int J Med Inform        ISSN: 1386-5056            Impact factor:   4.046


  5 in total

1.  Developing a Data Quality Standard Primer for Cardiovascular Risk Assessment from Electronic Health Record Data Using the DataGauge Process.

Authors:  Franck Diaz-Garelli; Andrew Long; Michael P Bancks; Alain G Bertoni; Adhithya Narayanan; Brian J Wells
Journal:  AMIA Annu Symp Proc       Date:  2022-02-21

2.  The Elements of Data Sharing.

Authors:  Zhang Zhang; Shuhui Song; Jun Yu; Wenming Zhao; Jingfa Xiao; Yiming Bao
Journal:  Genomics Proteomics Bioinformatics       Date:  2020-04-28       Impact factor: 7.691

3.  The data-collection on adverse effects of anti-HIV drugs (D:A:D) model for predicting cardiovascular events: External validation in a diverse cohort of people living with HIV.

Authors:  Ifedioranma Anikpo; Afiba Manza-A Agovi; Matthew J Cvitanovich; Frank Lonergan; Marc Johnson; Rohit P Ojha
Journal:  HIV Med       Date:  2021-08-19       Impact factor: 3.094

4.  Clinical, epidemiological aspects, and trends of Hepatitis B in Brazil from 2007 to 2018.

Authors:  Cathianne Sacramento Pinto; Galileu Barbosa Costa; Ivan Bezerra Allaman; Sandra Rocha Gadelha
Journal:  Sci Rep       Date:  2021-07-07       Impact factor: 4.379

5.  Application of ensemble machine learning algorithms on lifestyle factors and wearables for cardiovascular risk prediction.

Authors:  Weiting Huang; Tan Wei Ying; Woon Loong Calvin Chin; Lohendran Baskaran; Ong Eng Hock Marcus; Khung Keong Yeo; Ng See Kiong
Journal:  Sci Rep       Date:  2022-01-20       Impact factor: 4.379

  5 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.