2022
DOI: 10.1177/01410768221131897
|View full text |Cite
|
Sign up to set email alerts
|

Using national electronic health records for pandemic preparedness: validation of a parsimonious model for predicting excess deaths among those with COVID-19–a data-driven retrospective cohort study

Abstract: Objectives To use national, pre- and post-pandemic electronic health records (EHR) to develop and validate a scenario-based model incorporating baseline mortality risk, infection rate (IR) and relative risk (RR) of death for prediction of excess deaths. Design An EHR-based, retrospective cohort study. Setting Linked EHR in Clinical Practice Research Datalink (CPRD); and linked EHR and COVID-19 data in England provided in NHS Digital Trusted Research Environment (TRE). Participants In the development (CPRD) and… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1

Citation Types

0
4
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
3
2

Relationship

1
4

Authors

Journals

citations
Cited by 5 publications
(4 citation statements)
references
References 27 publications
0
4
0
Order By: Relevance
“…Predictive models have garnered signi cant attention and undergone substantial enhancements over the past decade, thanks to advancements in machine learning and computer technology. Historically, some classic prediction models served primarily as tools for approximating disease risk and aiding medical decision-making 15,16,17 . Unlike most diagnostic criteria, which typically consider one or two risk factors with a xed cutoff for risk categorization, predictive models incorporate a wide array of novel parameters.…”
Section: Discussionmentioning
confidence: 99%
See 1 more Smart Citation
“…Predictive models have garnered signi cant attention and undergone substantial enhancements over the past decade, thanks to advancements in machine learning and computer technology. Historically, some classic prediction models served primarily as tools for approximating disease risk and aiding medical decision-making 15,16,17 . Unlike most diagnostic criteria, which typically consider one or two risk factors with a xed cutoff for risk categorization, predictive models incorporate a wide array of novel parameters.…”
Section: Discussionmentioning
confidence: 99%
“…Thus, a parsimonious model is well-suited for health management on mobile platforms. Parsimonious models have already been applied in a wide range of diseases, including COVID-19 [15][16][17][18][19] , artery disease 20 , acute kidney injury 21 , osteoporosis 22 , and hepatobiliary diseases 23,24 . Various modeling techniques such as logistic regression 15,18 , deep learning 16,19,[22][23][24] , and machine-learning based genetic evolution algorithm 20,21 have been employed in these contexts.…”
Section: Introductionmentioning
confidence: 99%
“…Moreover, pandemic monitoring has focused on metrics of infection, excluding NCDs as a risk factor or indirect outcome. 9 …”
Section: Introductionmentioning
confidence: 99%
“…A new research paper examines the potential of patient health records to estimate excess deaths in a pandemic, and finds that this is entirely feasible. 3 As crisis after crisis sweeps the globe, new applications of technology and new ways to use available data are central to preventing and responding to health crises — such as the one Lebanon finds itself gripped by. 4…”
mentioning
confidence: 99%