Precision Drug Theraputics: Risk Prediction in Pharmacoepidemiology
Lead Research Organisation:
University of Strathclyde
Department Name: Inst of Pharmacy and Biomedical Sci
Abstract
Health Data Research UK (HDR UK) is an institute for health and biomedical informatics research. Part of its mission is to transform health care through the application of multidisciplinary team expertise.
This project aims to contribute to the HDR UK mission by applying advanced methodological approaches to build models which will enable outcomes to be predicted for appropriate groups of patients with distinct mechanisms of disease (cardiovascular disease, cancer) or particular responses to treatment (stratified medicine) and to support the development of precision therapeutics.
The objective of the project is to create Clinical Decision Support tools for routine use.
This project aims to contribute to the HDR UK mission by applying advanced methodological approaches to build models which will enable outcomes to be predicted for appropriate groups of patients with distinct mechanisms of disease (cardiovascular disease, cancer) or particular responses to treatment (stratified medicine) and to support the development of precision therapeutics.
The objective of the project is to create Clinical Decision Support tools for routine use.
Technical Summary
The project will develop statistical and machine learning algorithms to analyse NHS datasets to build predictive models to support precision therapeutics focusing on the following two areas:
1) Cancer chemotherapy
2) Cardiovascular therapies
HDR UK will provide the data repositories for linkage of established patient cohorts to further phenotypic resources. This will provide deeper phenotyping and should allow more precise prediction algorithms to be developed. Advanced statistical modelling (logistic regression, least absolute shrinkage and selection operator (LASSO) regression, Bayesian modelling) and machine learning approaches (neural nets, deep learning algorithms) will be used as part of this approach. The precision and incremental value of additional datasets will be assessed as will automated approaches to optimising algorithms. Existing research in the use of Bayesian hierarchical point-mass models, based around body-systems, to detect safety signals in clinical trials may be extended for use in observational studies. This approach is designed to use the additional information given by the relationships within and between body-systems in a statistical analysis.
The outcomes of the project, in this case the prediction models, will be translated into Clinical Decision Support (CDS) tools which will promote learning health systems. User and usability experience data will be captured during CDS design and development. The output will be a prototype intervention suitable for evaluation through the MRC Complex Intervention Framework to support clinicians in making informed choices and highlighting the risks in the different possible prescribing choices.
1) Cancer chemotherapy
2) Cardiovascular therapies
HDR UK will provide the data repositories for linkage of established patient cohorts to further phenotypic resources. This will provide deeper phenotyping and should allow more precise prediction algorithms to be developed. Advanced statistical modelling (logistic regression, least absolute shrinkage and selection operator (LASSO) regression, Bayesian modelling) and machine learning approaches (neural nets, deep learning algorithms) will be used as part of this approach. The precision and incremental value of additional datasets will be assessed as will automated approaches to optimising algorithms. Existing research in the use of Bayesian hierarchical point-mass models, based around body-systems, to detect safety signals in clinical trials may be extended for use in observational studies. This approach is designed to use the additional information given by the relationships within and between body-systems in a statistical analysis.
The outcomes of the project, in this case the prediction models, will be translated into Clinical Decision Support (CDS) tools which will promote learning health systems. User and usability experience data will be captured during CDS design and development. The output will be a prototype intervention suitable for evaluation through the MRC Complex Intervention Framework to support clinicians in making informed choices and highlighting the risks in the different possible prescribing choices.
Organisations
- University of Strathclyde (Lead Research Organisation)
- Karolinska Institute (Collaboration)
- NHS Greater Glasgow and Clyde (NHSGGC) (Collaboration)
- University of Southern Denmark (Collaboration)
- HEALTH DATA RESEARCH UK (Collaboration)
- Uppsala University (Collaboration)
- Norwegian Institute of Public Health (Collaboration)
- British Heart Foundation (BHF) (Collaboration)
- Utrecht University (Collaboration)
- Queen's University Belfast (Fellow)
People |
ORCID iD |
Raymond Carragher (Principal Investigator / Fellow) |
Publications
Carragher R
(2020)
A Bayesian hierarchical approach for multiple outcomes in routinely collected healthcare data.
in Statistics in medicine
Carragher R
(2021)
Assessing safety at the end of clinical trials using system organ classes: A case and comparative study.
in Pharmaceutical statistics
Carragher R
(2020)
c212: An R Package for the Detection of Safety Signals in Clinical Trials Using Body-Systems (System Organ Classes)
in Journal of Open Source Software
Komen JJ
(2022)
Oral anticoagulants in patients with atrial fibrillation at low stroke risk: a multicentre observational study.
in European heart journal
Title | Bayesian Hierarchical Possion Models for Mulitple Grouped Outcomes with Clustering - Simulation Study |
Description | Simulation study of cluster hierarchical outcomes for bhpm (Bayesian Hierarchical Possion Models for Mulitple Grouped Outcomes with Clustering) model fitting, error estimation, and outcome detection. The dataset contains 4 simulations with varying rates. Code for generating and running the simulations is supplied. Bourne shell scripts for automating the simulations on a linux platform are supplied. |
Type Of Material | Database/Collection of data |
Year Produced | 2020 |
Provided To Others? | Yes |
URL | https://pureportal.strath.ac.uk/en/datasets/c8a0433e-042a-4088-9c4b-323943f14953 |
Description | CVD-COVID-UK / COVID-IMPACT Consortium |
Organisation | British Heart Foundation (BHF) |
Country | United Kingdom |
Sector | Charity/Non Profit |
PI Contribution | I have worked on a number of projects associated with the CVD-COVID UK Consortium. |
Collaborator Contribution | In partnetship with eDRIS we curated Scottish healthcare data for use by researchers in multiple UK wide projects |
Impact | We have a pre-pint paper which will be submitted to a journal shortly: Dale CE, Takhar R, Carragher R, Torabi F,, Sofat R. The adverse impact of COVID-19 pandemic on cardiovascular disease prevention and management in England, Scotland and Wales: A population-scale descriptive analysis of trends in medication data. medRxiv 2021.12.31.21268587; https://doi.org/10.1101/2021.12.31.21268587. |
Start Year | 2021 |
Description | CVD-COVID-UK / COVID-IMPACT Consortium |
Organisation | Health Data Research UK |
Country | United Kingdom |
Sector | Private |
PI Contribution | I have worked on a number of projects associated with the CVD-COVID UK Consortium. |
Collaborator Contribution | In partnetship with eDRIS we curated Scottish healthcare data for use by researchers in multiple UK wide projects |
Impact | We have a pre-pint paper which will be submitted to a journal shortly: Dale CE, Takhar R, Carragher R, Torabi F,, Sofat R. The adverse impact of COVID-19 pandemic on cardiovascular disease prevention and management in England, Scotland and Wales: A population-scale descriptive analysis of trends in medication data. medRxiv 2021.12.31.21268587; https://doi.org/10.1101/2021.12.31.21268587. |
Start Year | 2021 |
Description | Cancers Medicines Outcome Program |
Organisation | NHS Greater Glasgow and Clyde (NHSGGC) |
Country | United Kingdom |
Sector | Public |
PI Contribution | The determination of baseline characteristics, outcomes and survival for myeloma patients. |
Collaborator Contribution | Data collection and analysis. Expert medical input. |
Impact | This is a recent collaboration for me. Outputs so far have been the determination of the baseline and survival characteristics for myeloma patients receiving pomalidomide in the West of Scotland. Myeloma results presented at British Oncology Pharmacy Association (BOPA) Annual symposium, 08-10 October 2021. |
Start Year | 2020 |
Description | Oral anticoagulant or no treatment in patients with atrial fibrillation at moderate stroke risk: a multi-centre observational study. |
Organisation | Karolinska Institute |
Country | Sweden |
Sector | Academic/University |
PI Contribution | We helped design the study. We provided the data and analysis for the Scottish section of the study. We participated in the review of the manuscript. |
Collaborator Contribution | Each institution provided the data and analysis for their section. Utrecht University co-ordinated the research, combined the results and produced a manuscript for review. |
Impact | A manuscript: "Oral anticoagulants in patients with atrial fibrillation at low stroke risk: a multicentre observational study" has been published in the European Heart Journal 10/03/2022. |
Start Year | 2020 |
Description | Oral anticoagulant or no treatment in patients with atrial fibrillation at moderate stroke risk: a multi-centre observational study. |
Organisation | Norwegian Institute of Public Health |
Country | Norway |
Sector | Public |
PI Contribution | We helped design the study. We provided the data and analysis for the Scottish section of the study. We participated in the review of the manuscript. |
Collaborator Contribution | Each institution provided the data and analysis for their section. Utrecht University co-ordinated the research, combined the results and produced a manuscript for review. |
Impact | A manuscript: "Oral anticoagulants in patients with atrial fibrillation at low stroke risk: a multicentre observational study" has been published in the European Heart Journal 10/03/2022. |
Start Year | 2020 |
Description | Oral anticoagulant or no treatment in patients with atrial fibrillation at moderate stroke risk: a multi-centre observational study. |
Organisation | University of Southern Denmark |
Country | Denmark |
Sector | Academic/University |
PI Contribution | We helped design the study. We provided the data and analysis for the Scottish section of the study. We participated in the review of the manuscript. |
Collaborator Contribution | Each institution provided the data and analysis for their section. Utrecht University co-ordinated the research, combined the results and produced a manuscript for review. |
Impact | A manuscript: "Oral anticoagulants in patients with atrial fibrillation at low stroke risk: a multicentre observational study" has been published in the European Heart Journal 10/03/2022. |
Start Year | 2020 |
Description | Oral anticoagulant or no treatment in patients with atrial fibrillation at moderate stroke risk: a multi-centre observational study. |
Organisation | Uppsala University |
Country | Sweden |
Sector | Academic/University |
PI Contribution | We helped design the study. We provided the data and analysis for the Scottish section of the study. We participated in the review of the manuscript. |
Collaborator Contribution | Each institution provided the data and analysis for their section. Utrecht University co-ordinated the research, combined the results and produced a manuscript for review. |
Impact | A manuscript: "Oral anticoagulants in patients with atrial fibrillation at low stroke risk: a multicentre observational study" has been published in the European Heart Journal 10/03/2022. |
Start Year | 2020 |
Description | Oral anticoagulant or no treatment in patients with atrial fibrillation at moderate stroke risk: a multi-centre observational study. |
Organisation | Utrecht University |
Department | Division of Pharmacology |
Country | Netherlands |
Sector | Academic/University |
PI Contribution | We helped design the study. We provided the data and analysis for the Scottish section of the study. We participated in the review of the manuscript. |
Collaborator Contribution | Each institution provided the data and analysis for their section. Utrecht University co-ordinated the research, combined the results and produced a manuscript for review. |
Impact | A manuscript: "Oral anticoagulants in patients with atrial fibrillation at low stroke risk: a multicentre observational study" has been published in the European Heart Journal 10/03/2022. |
Start Year | 2020 |
Description | Stroke prevention in atrial fibrillation before and after the introduction of non-vitamin K antagonist oral anticoagulants in four Western European countries |
Organisation | Karolinska Institute |
Country | Sweden |
Sector | Academic/University |
PI Contribution | We provided the data and analysis for the Scottish contribution to the project. |
Collaborator Contribution | All other parties provided the data and analysis for their regions. Utrecht University co-ordinated the projects and authored the manuscript for review. |
Impact | Manuscript: Stroke prevention in atrial fibrillation before and after the introduction of non-vitamin K antagonist oral anticoagulants in four Western European countries currently being reviewed prior to submission. |
Start Year | 2020 |
Description | Stroke prevention in atrial fibrillation before and after the introduction of non-vitamin K antagonist oral anticoagulants in four Western European countries |
Organisation | Norwegian Institute of Public Health |
Country | Norway |
Sector | Public |
PI Contribution | We provided the data and analysis for the Scottish contribution to the project. |
Collaborator Contribution | All other parties provided the data and analysis for their regions. Utrecht University co-ordinated the projects and authored the manuscript for review. |
Impact | Manuscript: Stroke prevention in atrial fibrillation before and after the introduction of non-vitamin K antagonist oral anticoagulants in four Western European countries currently being reviewed prior to submission. |
Start Year | 2020 |
Description | Stroke prevention in atrial fibrillation before and after the introduction of non-vitamin K antagonist oral anticoagulants in four Western European countries |
Organisation | University of Southern Denmark |
Country | Denmark |
Sector | Academic/University |
PI Contribution | We provided the data and analysis for the Scottish contribution to the project. |
Collaborator Contribution | All other parties provided the data and analysis for their regions. Utrecht University co-ordinated the projects and authored the manuscript for review. |
Impact | Manuscript: Stroke prevention in atrial fibrillation before and after the introduction of non-vitamin K antagonist oral anticoagulants in four Western European countries currently being reviewed prior to submission. |
Start Year | 2020 |
Description | Stroke prevention in atrial fibrillation before and after the introduction of non-vitamin K antagonist oral anticoagulants in four Western European countries |
Organisation | Uppsala University |
Country | Sweden |
Sector | Academic/University |
PI Contribution | We provided the data and analysis for the Scottish contribution to the project. |
Collaborator Contribution | All other parties provided the data and analysis for their regions. Utrecht University co-ordinated the projects and authored the manuscript for review. |
Impact | Manuscript: Stroke prevention in atrial fibrillation before and after the introduction of non-vitamin K antagonist oral anticoagulants in four Western European countries currently being reviewed prior to submission. |
Start Year | 2020 |
Description | Stroke prevention in atrial fibrillation before and after the introduction of non-vitamin K antagonist oral anticoagulants in four Western European countries |
Organisation | Utrecht University |
Country | Netherlands |
Sector | Academic/University |
PI Contribution | We provided the data and analysis for the Scottish contribution to the project. |
Collaborator Contribution | All other parties provided the data and analysis for their regions. Utrecht University co-ordinated the projects and authored the manuscript for review. |
Impact | Manuscript: Stroke prevention in atrial fibrillation before and after the introduction of non-vitamin K antagonist oral anticoagulants in four Western European countries currently being reviewed prior to submission. |
Start Year | 2020 |
Title | Bayesian Hierarchical Possion Models for Mulitple Grouped Outcomes with Clustering |
Description | Bayesian methods for the detection of differences in rates of outcomes for multiple treatments for clustered observations. This software was developed for the Risk Prediction in Pharmacoepidemology project as part of a Rutherford Fund Fellowship at Health Data Research (UK), HRDUK@Scotland. |
Type Of Technology | Software |
Year Produced | 2019 |
Impact | The software has been designed for use with observational routinely collected healthcare data which would typically be analysed by time to event models such as Cox proportional hazards models. The software allows multiple related outcomes to be modelled within a single hierarchy. It has been applied to an existing study of direct oral anti-cogulants in Scotland. |
URL | https://github.com/rcarragh/bhpm |