Abstract
The critical scenario in public health triggered by COVID-19 intensified the demand for predictive models to assist in the diagnosis and prognosis of patients affected by this disease. This work evaluates several machine learning classifiers to predict the risk of COVID-19 mortality based on information available at the time of admission. We also apply a visualization technique based on a state-of-the-art explainability approach which, combined with a dimensionality reduction technique, allows drawing insights into the relationship between the features taken into account by the classifiers in their predictions. Our experiments on two real datasets showed promising results, reaching a sensitivity of up to 84% and an AUROC of 92% (95% CI, [0.89–0.95]).
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Ethics committee approval: HCPA 32314720.8.0000.5327, HMV 32314720.8.3001.5330.
- 2.
- 3.
- 4.
References
Aas, K., Jullum, M., Løland, A.: Explaining individual predictions when features are dependent: accurate approximations to Shapley values. Artif. Intell. 298, 103502 (2021)
Alballa, N., Al-Turaiki, I.: Machine learning approaches in Covid-19 diagnosis, mortality, and severity risk prediction: a review. Inf. Med. Unlocked 24, 100564 (2021)
Araújo, D.C., Veloso, A.A., Borges, K.B.G., das Graças Carvalho, M.: Prognosing the risk of Covid-19 death through a machine learning-based routine blood panel: a retrospective study in brazil. IJMEDI 165, 104835 (2022)
Broberg, C.S., Kovacs, A.H., Sadeghi, S., et al.: Covid-19 in adults with congenital heart disease. JACC 77(13), 1644–1655 (2021)
Covino, M., Sandroni, C., Santoro, M., et al.: Predicting intensive care unit admission and death for Covid-19 patients in the emergency department using early warning scores. Resuscitation 156, 84–91 (2020)
Futoma, J., Simons, M., Panch, T., et al.: The myth of generalisability in clinical research and machine learning in health care. Lancet Digit. Health 2(9), 489–492 (2020)
Hall, M.A.: Correlation-based feature selection for machine learning. Ph.D. thesis, The University of Waikato (1999)
Huang, X., Marques-Silva, J.: The inadequacy of Shapley values for explainability. arXiv preprint arXiv:2302.08160 (2023)
Knight, S.R., Ho, A., Pius, R., et al.: Risk stratification of patients admitted to hospital with Covid-19 using the ISARIC WHO clinical characterisation protocol: development and validation of the 4C mortality score. BMJ 370, m3339 (2020)
Lundberg, S.M., Erion, G.G., Lee, S.I.: Consistent individualized feature attribution for tree ensembles. arXiv preprint arXiv:1802.03888 (2018)
Lundberg, S.M., Lee, S.I.: A unified approach to interpreting model predictions. In: Advances in Neural Information Processing Systems, vol. 30 (2017)
Van der Maaten, L., Hinton, G.: Visualizing data using t-SNE. JMLR 9(11), 2579–2605 (2008)
Miranda de Paiva, B.B., Delfino-Pereira, P., de Andrade, C.M.V., et al.: Effectiveness, explainability and reliability of machine meta-learning methods for predicting mortality in patients with COVID-19: results of the Brazilian COVID-19 registry. medRxiv (2021)
Qin, Z., Zhang, C., Wang, T., Zhang, S.: Cost sensitive classification in data mining. In: Advanced Data Mining and Applications, pp. 1–11 (2010)
Rostami, M., Mansouritorghabeh, H.: D-dimer level in COVID-19 infection: a systematic review. Exp. Rev. Hematol. 13(11), 1265–1275 (2020)
Subudhi, S., Verma, A., Patel, A.B.: Prognostic machine learning models for Covid-19 to facilitate decision making. IJCP 74(12), e13685 (2020)
Wynants, L., Van Calster, B., Collins, G.S., et al.: Prediction models for diagnosis and prognosis of COVID-19: systematic review and critical appraisal. bmj 369, m1328 (2020)
Yadaw, A.S., Li, Y., Bose, S., et al.: Clinical features of COVID-19 mortality: development and validation of a clinical prediction model. Lancet Digt. Health 2(10), E516–E525 (2020)
Yang, J.: Fast TreeSHAP: accelerating SHAP value computation for trees. arXiv preprint arXiv:2109.09847 (2021)
Zhao, Z., Chen, A., Hou, W., et al.: Prediction model and risk scores of ICU admission and mortality in COVID-19. PLoS ONE 15(7), e0236618 (2020)
Acknowledgment
This work has been financed in part by CAPES Finance Code 001 and CNPq/Brazil.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Kuhn, D.M., de Loreto, M.S., Recamonde-Mendoza, M., Comba, J.L.D., Moreira, V.P. (2023). Explainability of COVID-19 Classification Models Using Dimensionality Reduction of SHAP Values. In: Naldi, M.C., Bianchi, R.A.C. (eds) Intelligent Systems. BRACIS 2023. Lecture Notes in Computer Science(), vol 14195. Springer, Cham. https://doi.org/10.1007/978-3-031-45368-7_27
Download citation
DOI: https://doi.org/10.1007/978-3-031-45368-7_27
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-45367-0
Online ISBN: 978-3-031-45368-7
eBook Packages: Computer ScienceComputer Science (R0)