Cargando…

An Explainable Machine Learning Pipeline for Stroke Prediction on Imbalanced Data

Stroke is an acute neurological dysfunction attributed to a focal injury of the central nervous system due to reduced blood flow to the brain. Nowadays, stroke is a global threat associated with premature death and huge economic consequences. Hence, there is an urgency to model the effect of several...

Descripción completa

Detalles Bibliográficos
Autores principales: Kokkotis, Christos, Giarmatzis, Georgios, Giannakou, Erasmia, Moustakidis, Serafeim, Tsatalas, Themistoklis, Tsiptsios, Dimitrios, Vadikolias, Konstantinos, Aggelousis, Nikolaos
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9600473/
https://www.ncbi.nlm.nih.gov/pubmed/36292081
http://dx.doi.org/10.3390/diagnostics12102392
_version_ 1784816851291734016
author Kokkotis, Christos
Giarmatzis, Georgios
Giannakou, Erasmia
Moustakidis, Serafeim
Tsatalas, Themistoklis
Tsiptsios, Dimitrios
Vadikolias, Konstantinos
Aggelousis, Nikolaos
author_facet Kokkotis, Christos
Giarmatzis, Georgios
Giannakou, Erasmia
Moustakidis, Serafeim
Tsatalas, Themistoklis
Tsiptsios, Dimitrios
Vadikolias, Konstantinos
Aggelousis, Nikolaos
author_sort Kokkotis, Christos
collection PubMed
description Stroke is an acute neurological dysfunction attributed to a focal injury of the central nervous system due to reduced blood flow to the brain. Nowadays, stroke is a global threat associated with premature death and huge economic consequences. Hence, there is an urgency to model the effect of several risk factors on stroke occurrence, and artificial intelligence (AI) seems to be the appropriate tool. In the present study, we aimed to (i) develop reliable machine learning (ML) prediction models for stroke disease; (ii) cope with a typical severe class imbalance problem, which is posed due to the stroke patients’ class being significantly smaller than the healthy class; and (iii) interpret the model output for understanding the decision-making mechanism. The effectiveness of the proposed ML approach was investigated in a comparative analysis with six well-known classifiers with respect to metrics that are related to both generalization capability and prediction accuracy. The best overall false-negative rate was achieved by the Multi-Layer Perceptron (MLP) classifier (18.60%). Shapley Additive Explanations (SHAP) were employed to investigate the impact of the risk factors on the prediction output. The proposed AI method could lead to the creation of advanced and effective risk stratification strategies for each stroke patient, which would allow for timely diagnosis and the right treatments.
format Online
Article
Text
id pubmed-9600473
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-96004732022-10-27 An Explainable Machine Learning Pipeline for Stroke Prediction on Imbalanced Data Kokkotis, Christos Giarmatzis, Georgios Giannakou, Erasmia Moustakidis, Serafeim Tsatalas, Themistoklis Tsiptsios, Dimitrios Vadikolias, Konstantinos Aggelousis, Nikolaos Diagnostics (Basel) Article Stroke is an acute neurological dysfunction attributed to a focal injury of the central nervous system due to reduced blood flow to the brain. Nowadays, stroke is a global threat associated with premature death and huge economic consequences. Hence, there is an urgency to model the effect of several risk factors on stroke occurrence, and artificial intelligence (AI) seems to be the appropriate tool. In the present study, we aimed to (i) develop reliable machine learning (ML) prediction models for stroke disease; (ii) cope with a typical severe class imbalance problem, which is posed due to the stroke patients’ class being significantly smaller than the healthy class; and (iii) interpret the model output for understanding the decision-making mechanism. The effectiveness of the proposed ML approach was investigated in a comparative analysis with six well-known classifiers with respect to metrics that are related to both generalization capability and prediction accuracy. The best overall false-negative rate was achieved by the Multi-Layer Perceptron (MLP) classifier (18.60%). Shapley Additive Explanations (SHAP) were employed to investigate the impact of the risk factors on the prediction output. The proposed AI method could lead to the creation of advanced and effective risk stratification strategies for each stroke patient, which would allow for timely diagnosis and the right treatments. MDPI 2022-10-01 /pmc/articles/PMC9600473/ /pubmed/36292081 http://dx.doi.org/10.3390/diagnostics12102392 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Kokkotis, Christos
Giarmatzis, Georgios
Giannakou, Erasmia
Moustakidis, Serafeim
Tsatalas, Themistoklis
Tsiptsios, Dimitrios
Vadikolias, Konstantinos
Aggelousis, Nikolaos
An Explainable Machine Learning Pipeline for Stroke Prediction on Imbalanced Data
title An Explainable Machine Learning Pipeline for Stroke Prediction on Imbalanced Data
title_full An Explainable Machine Learning Pipeline for Stroke Prediction on Imbalanced Data
title_fullStr An Explainable Machine Learning Pipeline for Stroke Prediction on Imbalanced Data
title_full_unstemmed An Explainable Machine Learning Pipeline for Stroke Prediction on Imbalanced Data
title_short An Explainable Machine Learning Pipeline for Stroke Prediction on Imbalanced Data
title_sort explainable machine learning pipeline for stroke prediction on imbalanced data
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9600473/
https://www.ncbi.nlm.nih.gov/pubmed/36292081
http://dx.doi.org/10.3390/diagnostics12102392
work_keys_str_mv AT kokkotischristos anexplainablemachinelearningpipelineforstrokepredictiononimbalanceddata
AT giarmatzisgeorgios anexplainablemachinelearningpipelineforstrokepredictiononimbalanceddata
AT giannakouerasmia anexplainablemachinelearningpipelineforstrokepredictiononimbalanceddata
AT moustakidisserafeim anexplainablemachinelearningpipelineforstrokepredictiononimbalanceddata
AT tsatalasthemistoklis anexplainablemachinelearningpipelineforstrokepredictiononimbalanceddata
AT tsiptsiosdimitrios anexplainablemachinelearningpipelineforstrokepredictiononimbalanceddata
AT vadikoliaskonstantinos anexplainablemachinelearningpipelineforstrokepredictiononimbalanceddata
AT aggelousisnikolaos anexplainablemachinelearningpipelineforstrokepredictiononimbalanceddata
AT kokkotischristos explainablemachinelearningpipelineforstrokepredictiononimbalanceddata
AT giarmatzisgeorgios explainablemachinelearningpipelineforstrokepredictiononimbalanceddata
AT giannakouerasmia explainablemachinelearningpipelineforstrokepredictiononimbalanceddata
AT moustakidisserafeim explainablemachinelearningpipelineforstrokepredictiononimbalanceddata
AT tsatalasthemistoklis explainablemachinelearningpipelineforstrokepredictiononimbalanceddata
AT tsiptsiosdimitrios explainablemachinelearningpipelineforstrokepredictiononimbalanceddata
AT vadikoliaskonstantinos explainablemachinelearningpipelineforstrokepredictiononimbalanceddata
AT aggelousisnikolaos explainablemachinelearningpipelineforstrokepredictiononimbalanceddata