Predicting the risk of asthma attacks in children, adolescents and adults: protocol for a machine learning algorithm derived from a primary care-based retrospective cohort

Introduction Most asthma attacks and subsequent deaths are potentially preventable. We aim to develop a prognostic tool for identifying patients at high risk of asthma attacks in primary care by leveraging advances in machine learning.Methods and analysis Current prognostic tools use logistic regres...

Full description

Saved in:
Bibliographic Details
Main Authors: Aziz Sheikh, Syed Ahmar Shah, Mome Mukherjee
Format: Article
Language:English
Published: BMJ Publishing Group 2020-07-01
Series:BMJ Open
Online Access:https://bmjopen.bmj.com/content/10/7/e036099.full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846141043103236096
author Aziz Sheikh
Syed Ahmar Shah
Mome Mukherjee
author_facet Aziz Sheikh
Syed Ahmar Shah
Mome Mukherjee
author_sort Aziz Sheikh
collection DOAJ
description Introduction Most asthma attacks and subsequent deaths are potentially preventable. We aim to develop a prognostic tool for identifying patients at high risk of asthma attacks in primary care by leveraging advances in machine learning.Methods and analysis Current prognostic tools use logistic regression to develop a risk scoring model for asthma attacks. We propose to build on this by systematically applying various well-known machine learning techniques to a large longitudinal deidentified primary care database, the Optimum Patient Care Research Database, and comparatively evaluate their performance with the existing logistic regression model and against each other. Machine learning algorithms vary in their predictive abilities based on the dataset and the approach to analysis employed. We will undertake feature selection, classification (both one-class and two-class classifiers) and performance evaluation. Patients who have had actively treated clinician-diagnosed asthma, aged 8–80 years and with 3 years of continuous data, from 2016 to 2018, will be selected. Risk factors will be obtained from the first year, while the next 2 years will form the outcome period, in which the primary endpoint will be the occurrence of an asthma attack.Ethics and dissemination We have obtained approval from OPCRD’s Anonymous Data Ethics Protocols and Transparency (ADEPT) Committee. We will seek ethics approval from The University of Edinburgh’s Research Ethics Group (UREG). We aim to present our findings at scientific conferences and in peer-reviewed journals.
format Article
id doaj-art-292cdff4513d453e8333d5871e1e9054
institution Kabale University
issn 2044-6055
language English
publishDate 2020-07-01
publisher BMJ Publishing Group
record_format Article
series BMJ Open
spelling doaj-art-292cdff4513d453e8333d5871e1e90542024-12-04T20:30:09ZengBMJ Publishing GroupBMJ Open2044-60552020-07-0110710.1136/bmjopen-2019-036099Predicting the risk of asthma attacks in children, adolescents and adults: protocol for a machine learning algorithm derived from a primary care-based retrospective cohortAziz Sheikh0Syed Ahmar Shah1Mome Mukherjee2Usher Institute, The University of Edinburgh, Edinburgh, UKUsher Institute of Population Health Sciences and Informatics, The University of Edinburgh, Edinburgh, UK1 Asthma UK Centre for Applied Research, Centre for Medical Informatics, Usher Institute, The University of Edinburgh, Edinburgh, United KingdomIntroduction Most asthma attacks and subsequent deaths are potentially preventable. We aim to develop a prognostic tool for identifying patients at high risk of asthma attacks in primary care by leveraging advances in machine learning.Methods and analysis Current prognostic tools use logistic regression to develop a risk scoring model for asthma attacks. We propose to build on this by systematically applying various well-known machine learning techniques to a large longitudinal deidentified primary care database, the Optimum Patient Care Research Database, and comparatively evaluate their performance with the existing logistic regression model and against each other. Machine learning algorithms vary in their predictive abilities based on the dataset and the approach to analysis employed. We will undertake feature selection, classification (both one-class and two-class classifiers) and performance evaluation. Patients who have had actively treated clinician-diagnosed asthma, aged 8–80 years and with 3 years of continuous data, from 2016 to 2018, will be selected. Risk factors will be obtained from the first year, while the next 2 years will form the outcome period, in which the primary endpoint will be the occurrence of an asthma attack.Ethics and dissemination We have obtained approval from OPCRD’s Anonymous Data Ethics Protocols and Transparency (ADEPT) Committee. We will seek ethics approval from The University of Edinburgh’s Research Ethics Group (UREG). We aim to present our findings at scientific conferences and in peer-reviewed journals.https://bmjopen.bmj.com/content/10/7/e036099.full
spellingShingle Aziz Sheikh
Syed Ahmar Shah
Mome Mukherjee
Predicting the risk of asthma attacks in children, adolescents and adults: protocol for a machine learning algorithm derived from a primary care-based retrospective cohort
BMJ Open
title Predicting the risk of asthma attacks in children, adolescents and adults: protocol for a machine learning algorithm derived from a primary care-based retrospective cohort
title_full Predicting the risk of asthma attacks in children, adolescents and adults: protocol for a machine learning algorithm derived from a primary care-based retrospective cohort
title_fullStr Predicting the risk of asthma attacks in children, adolescents and adults: protocol for a machine learning algorithm derived from a primary care-based retrospective cohort
title_full_unstemmed Predicting the risk of asthma attacks in children, adolescents and adults: protocol for a machine learning algorithm derived from a primary care-based retrospective cohort
title_short Predicting the risk of asthma attacks in children, adolescents and adults: protocol for a machine learning algorithm derived from a primary care-based retrospective cohort
title_sort predicting the risk of asthma attacks in children adolescents and adults protocol for a machine learning algorithm derived from a primary care based retrospective cohort
url https://bmjopen.bmj.com/content/10/7/e036099.full
work_keys_str_mv AT azizsheikh predictingtheriskofasthmaattacksinchildrenadolescentsandadultsprotocolforamachinelearningalgorithmderivedfromaprimarycarebasedretrospectivecohort
AT syedahmarshah predictingtheriskofasthmaattacksinchildrenadolescentsandadultsprotocolforamachinelearningalgorithmderivedfromaprimarycarebasedretrospectivecohort
AT momemukherjee predictingtheriskofasthmaattacksinchildrenadolescentsandadultsprotocolforamachinelearningalgorithmderivedfromaprimarycarebasedretrospectivecohort