Asthma prediction via affinity graph enhanced classifier: a machine learning approach based on routine blood biomarkers
- PMID: 38268004
- PMCID: PMC10809685
- DOI: 10.1186/s12967-024-04866-9
Asthma prediction via affinity graph enhanced classifier: a machine learning approach based on routine blood biomarkers
Abstract
Background: Asthma is a chronic respiratory disease affecting millions of people worldwide, but early detection can be challenging due to the time-consuming nature of the traditional technique. Machine learning has shown great potential in the prompt prediction of asthma. However, because of the inherent complexity of asthma-related patterns, current models often fail to capture the correlation between data samples, limiting their accuracy. Our objective was to use our novel model to address the above problem via an Affinity Graph Enhanced Classifier (AGEC) to improve predictive accuracy.
Methods: The clinical dataset used in this study consisted of 152 samples, where 24 routine blood markers were extracted as features to participate in the classification due to their ease of sourcing and relevance to asthma. Specifically, our model begins by constructing a projection matrix to reduce the dimensionality of the feature space while preserving the most discriminative features. Simultaneously, an affinity graph is learned through the resulting subspace to capture the internal relationship between samples better. Leveraging domain knowledge from the affinity graph, a new classifier (AGEC) is introduced for asthma prediction. AGEC's performance was compared with five state-of-the-art predictive models.
Results: Experimental findings reveal the superior predictive capabilities of AGEC in asthma prediction. AGEC achieved an accuracy of 72.50%, surpassing FWAdaBoost (61.02%), MLFE (60.98%), SVR (64.01%), SVM (69.80%) and ERM (68.40%). These results provide evidence that capturing the correlation between samples can enhance the accuracy of asthma prediction. Moreover, the obtained [Formula: see text] values also suggest that the differences between our model and other models are statistically significant, and the effect of our model does not exist by chance.
Conclusion: As observed from the experimental results, advanced statistical machine learning approaches such as AGEC can enable accurate diagnosis of asthma. This finding holds promising implications for improving asthma management.
Keywords: Affinity graph; Asthma; Asthma prediction; Feature selection.
© 2024. The Author(s).
Conflict of interest statement
The authors declare that they have no competing financial interests.
Figures
Similar articles
-
Combining handcrafted features with latent variables in machine learning for prediction of radiation-induced lung damage.Med Phys. 2019 May;46(5):2497-2511. doi: 10.1002/mp.13497. Epub 2019 Apr 8. Med Phys. 2019. PMID: 30891794 Free PMC article.
-
Leveraging AI and Machine Learning to Develop and Evaluate a Contextualized User-Friendly Cough Audio Classifier for Detecting Respiratory Diseases: Protocol for a Diagnostic Study in Rural Tanzania.JMIR Res Protoc. 2024 Apr 23;13:e54388. doi: 10.2196/54388. JMIR Res Protoc. 2024. PMID: 38652526 Free PMC article.
-
Integration of Cancer Genomics Data for Tree-based Dimensionality Reduction and Cancer Outcome Prediction.Mol Inform. 2020 Mar;39(3):e1900028. doi: 10.1002/minf.201900028. Epub 2019 Sep 6. Mol Inform. 2020. PMID: 31490641
-
Does machine learning have a role in the prediction of asthma in children?Paediatr Respir Rev. 2022 Mar;41:51-60. doi: 10.1016/j.prrv.2021.06.002. Epub 2021 Jun 9. Paediatr Respir Rev. 2022. PMID: 34210588 Review.
-
Data-driven modeling and prediction of blood glucose dynamics: Machine learning applications in type 1 diabetes.Artif Intell Med. 2019 Jul;98:109-134. doi: 10.1016/j.artmed.2019.07.007. Epub 2019 Jul 26. Artif Intell Med. 2019. PMID: 31383477 Review.
References
-
- Talha SAAM, MagzoubAlhaj OS, Elhag A. Evaluation of asthma control assessment in school-age asthmatic children. J Med-Clin Res Rev. 2022;6:1–6. doi: 10.33425/2639-944X.1279. - DOI
-
- Busse WW, Wenzel SE, Casale TB, FitzGerald JM, Rice MS, Daizadeh N, Deniz Y, Patel N, Harel S, Rowe PJ, et al. Baseline FeNO as a prognostic biomarker for subsequent severe asthma exacerbations in patients with uncontrolled, moderate-to-severe asthma receiving placebo in the LIBERTY ASTHMA QUEST study: a post-hoc analysis. Lancet Respir Med. 2021;9(10):1165–1173. doi: 10.1016/S2213-2600(21)00124-7. - DOI - PubMed
Publication types
MeSH terms
Substances
Grants and funding
LinkOut - more resources
Full Text Sources
Medical
Research Materials