Development of childhood asthma prediction models using machine learning approaches
Development of childhood asthma prediction models using machine learning approaches
Background: Respiratory symptoms are common in early life and often transient. It is difficult to identify in which children these will persist and result in asthma. Machine learning (ML) approaches have the potential for better predictive performance and generalisability over existing childhood asthma prediction models. This study applied ML approaches to predict school-age asthma (age 10) in early life (Childhood Asthma Prediction in Early life, CAPE model) and at preschool age (Childhood Asthma Prediction at Preschool age, CAPP model). Methods: Clinical and environmental exposure data was collected from children enrolled in the Isle of Wight Birth Cohort (N = 1368, ∼15% asthma prevalence). Recursive Feature Elimination (RFE) identified an optimal subset of features predictive of school-age asthma for each model. Seven state-of-the-art ML classification algorithms were used to develop prognostic models. Training was performed by applying fivefold cross-validation, imputation, and resampling. Predictive performance was evaluated on the test set. Models were further externally validated in the Manchester Asthma and Allergy Study (MAAS) cohort. Results: RFE identified eight and twelve predictors for the CAPE and CAPP models, respectively. Support Vector Machine (SVM) algorithms provided the best performance for both the CAPE (area under the receiver operating characteristic curve, AUC = 0.71) and CAPP (AUC = 0.82) models. Both models demonstrated good generalisability in MAAS (CAPE 8-year = 0.71, 11-year = 0.71, CAPP 8-year = 0.83, 11-year = 0.79) and excellent sensitivity to predict a subgroup of persistent wheezers. Conclusion: Using ML approaches improved upon the predictive performance of existing regression-based models, with good generalisability and ability to rule in asthma and predict persistent wheeze.
asthma, childhood, machine learning, prediction
e12076
Kothalawala, Dilini, Mahesha
c22b9e92-e60a-44b6-a34b-2eb37a3a1212
Murray, Clare S.
aca69df6-149c-401c-842f-5b2d8042edf1
Simpson, Angela
5591f945-0ead-46a3-a866-b7bea84a2a83
Custovic, Adnan
17d8d092-73b8-44fb-bf48-5cea7b29e3fc
Tapper, William
9d5ddc92-a8dd-4c78-ac67-c5867b62724c
Arshad, Syed
917e246d-2e60-472f-8d30-94b01ef28958
Holloway, John
4bbd77e6-c095-445d-a36b-a50a72f6fe1a
Rezwan, Faisal I
203f8f38-1f5d-485b-ab11-c546b4276338
7 November 2021
Kothalawala, Dilini, Mahesha
c22b9e92-e60a-44b6-a34b-2eb37a3a1212
Murray, Clare S.
aca69df6-149c-401c-842f-5b2d8042edf1
Simpson, Angela
5591f945-0ead-46a3-a866-b7bea84a2a83
Custovic, Adnan
17d8d092-73b8-44fb-bf48-5cea7b29e3fc
Tapper, William
9d5ddc92-a8dd-4c78-ac67-c5867b62724c
Arshad, Syed
917e246d-2e60-472f-8d30-94b01ef28958
Holloway, John
4bbd77e6-c095-445d-a36b-a50a72f6fe1a
Rezwan, Faisal I
203f8f38-1f5d-485b-ab11-c546b4276338
Kothalawala, Dilini, Mahesha, Murray, Clare S., Simpson, Angela, Custovic, Adnan, Tapper, William, Arshad, Syed, Holloway, John and Rezwan, Faisal I
(2021)
Development of childhood asthma prediction models using machine learning approaches.
Clinical and Translational Allergy, 11 (9), , [e12076].
(doi:10.1002/clt2.12076).
Abstract
Background: Respiratory symptoms are common in early life and often transient. It is difficult to identify in which children these will persist and result in asthma. Machine learning (ML) approaches have the potential for better predictive performance and generalisability over existing childhood asthma prediction models. This study applied ML approaches to predict school-age asthma (age 10) in early life (Childhood Asthma Prediction in Early life, CAPE model) and at preschool age (Childhood Asthma Prediction at Preschool age, CAPP model). Methods: Clinical and environmental exposure data was collected from children enrolled in the Isle of Wight Birth Cohort (N = 1368, ∼15% asthma prevalence). Recursive Feature Elimination (RFE) identified an optimal subset of features predictive of school-age asthma for each model. Seven state-of-the-art ML classification algorithms were used to develop prognostic models. Training was performed by applying fivefold cross-validation, imputation, and resampling. Predictive performance was evaluated on the test set. Models were further externally validated in the Manchester Asthma and Allergy Study (MAAS) cohort. Results: RFE identified eight and twelve predictors for the CAPE and CAPP models, respectively. Support Vector Machine (SVM) algorithms provided the best performance for both the CAPE (area under the receiver operating characteristic curve, AUC = 0.71) and CAPP (AUC = 0.82) models. Both models demonstrated good generalisability in MAAS (CAPE 8-year = 0.71, 11-year = 0.71, CAPP 8-year = 0.83, 11-year = 0.79) and excellent sensitivity to predict a subgroup of persistent wheezers. Conclusion: Using ML approaches improved upon the predictive performance of existing regression-based models, with good generalisability and ability to rule in asthma and predict persistent wheeze.
Text
Kothalawala_et_al-CTA_main_manuscript_PURE
- Accepted Manuscript
Text
Kothalawala_et_al-CTA_supplementary_material_PURE
- Accepted Manuscript
More information
Accepted/In Press date: 18 October 2021
Published date: 7 November 2021
Additional Information:
Funding:
University of Southampton Presidential Research Studentship
Medical Research Council
NIHR Southampton Biomedical Research Centre
Manchester Biomedical Research Centre
Keywords:
asthma, childhood, machine learning, prediction
Identifiers
Local EPrints ID: 452033
URI: http://eprints.soton.ac.uk/id/eprint/452033
ISSN: 2045-7022
PURE UUID: d2cd4812-4899-4efa-a1fa-16d5da2b759b
Catalogue record
Date deposited: 09 Nov 2021 17:32
Last modified: 17 Mar 2024 06:54
Export record
Altmetrics
Contributors
Author:
Dilini, Mahesha Kothalawala
Author:
Clare S. Murray
Author:
Angela Simpson
Author:
Adnan Custovic
Author:
Faisal I Rezwan
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics