Machine Learning-Based Feature Selection and Classification for the Experimental Diagnosis of <i>Trypanosoma cruzi</i>
Chagas disease, caused by the <i>Trypanosoma cruzi</i> (<i>T. cruzi</i>) parasite, is the third most common parasitosis worldwide. Most of the infected subjects can remain asymptomatic without an opportune and early detection or an objective diagnostic is not conducted. Frequ...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-03-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/11/5/785 |
| _version_ | 1797475368838365184 |
|---|---|
| author | Nidiyare Hevia-Montiel Jorge Perez-Gonzalez Antonio Neme Paulina Haro |
| author_facet | Nidiyare Hevia-Montiel Jorge Perez-Gonzalez Antonio Neme Paulina Haro |
| author_sort | Nidiyare Hevia-Montiel |
| collection | DOAJ |
| description | Chagas disease, caused by the <i>Trypanosoma cruzi</i> (<i>T. cruzi</i>) parasite, is the third most common parasitosis worldwide. Most of the infected subjects can remain asymptomatic without an opportune and early detection or an objective diagnostic is not conducted. Frequently, the disease manifests itself after a long time, accompanied by severe heart disease or by sudden death. Thus, the diagnosis is a complex and challenging process where several factors must be considered. In this paper, a novel pipeline is presented integrating temporal data from four modalities (electrocardiography signals, echocardiography images, Doppler spectrum, and ELISA antibody titers), multiple features selection analyses by a univariate analysis and a machine learning-based selection. The method includes an automatic dichotomous classification of animal status (control vs. infected) based on Random Forest, Extremely Randomized Trees, Decision Trees, and Support Vector Machine. The most relevant multimodal attributes found were ELISA (IgGT, IgG1, IgG2a), electrocardiography (SR mean, QT and ST intervals), ascending aorta Doppler signals, and echocardiography (left ventricle diameter during diastole). Concerning automatic classification from selected features, the best accuracy of control vs. acute infection groups was 93.3 ± 13.3% for cross-validation and 100% in the final test; for control vs. chronic infection groups, it was 100% and 100%, respectively. We conclude that the proposed machine learning-based approach can be of help to obtain a robust and objective diagnosis in early <i>T. cruzi</i> infection stages. |
| first_indexed | 2024-03-09T20:43:10Z |
| format | Article |
| id | doaj.art-d1c4cae1ba6b4455bfde741aa844eeec |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-09T20:43:10Z |
| publishDate | 2022-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-d1c4cae1ba6b4455bfde741aa844eeec2023-11-23T22:53:56ZengMDPI AGElectronics2079-92922022-03-0111578510.3390/electronics11050785Machine Learning-Based Feature Selection and Classification for the Experimental Diagnosis of <i>Trypanosoma cruzi</i>Nidiyare Hevia-Montiel0Jorge Perez-Gonzalez1Antonio Neme2Paulina Haro3Unidad Académica del Instituto de Investigaciones en Matemáticas Aplicadas y en Sistemas del Estado de Yucatán, Universidad Nacional Autónoma de México, Mérida 97302, Yucatán, MexicoUnidad Académica del Instituto de Investigaciones en Matemáticas Aplicadas y en Sistemas del Estado de Yucatán, Universidad Nacional Autónoma de México, Mérida 97302, Yucatán, MexicoUnidad Académica del Instituto de Investigaciones en Matemáticas Aplicadas y en Sistemas del Estado de Yucatán, Universidad Nacional Autónoma de México, Mérida 97302, Yucatán, MexicoInstituto de Investigaciones en Ciencias Veterinarias, Universidad Autónoma de Baja California, Mexicali 21386, Baja California, MexicoChagas disease, caused by the <i>Trypanosoma cruzi</i> (<i>T. cruzi</i>) parasite, is the third most common parasitosis worldwide. Most of the infected subjects can remain asymptomatic without an opportune and early detection or an objective diagnostic is not conducted. Frequently, the disease manifests itself after a long time, accompanied by severe heart disease or by sudden death. Thus, the diagnosis is a complex and challenging process where several factors must be considered. In this paper, a novel pipeline is presented integrating temporal data from four modalities (electrocardiography signals, echocardiography images, Doppler spectrum, and ELISA antibody titers), multiple features selection analyses by a univariate analysis and a machine learning-based selection. The method includes an automatic dichotomous classification of animal status (control vs. infected) based on Random Forest, Extremely Randomized Trees, Decision Trees, and Support Vector Machine. The most relevant multimodal attributes found were ELISA (IgGT, IgG1, IgG2a), electrocardiography (SR mean, QT and ST intervals), ascending aorta Doppler signals, and echocardiography (left ventricle diameter during diastole). Concerning automatic classification from selected features, the best accuracy of control vs. acute infection groups was 93.3 ± 13.3% for cross-validation and 100% in the final test; for control vs. chronic infection groups, it was 100% and 100%, respectively. We conclude that the proposed machine learning-based approach can be of help to obtain a robust and objective diagnosis in early <i>T. cruzi</i> infection stages.https://www.mdpi.com/2079-9292/11/5/785machine learningfeature selectionmultivariate analysisclassificationChagas disease<i>Trypanosoma cruzi</i> |
| spellingShingle | Nidiyare Hevia-Montiel Jorge Perez-Gonzalez Antonio Neme Paulina Haro Machine Learning-Based Feature Selection and Classification for the Experimental Diagnosis of <i>Trypanosoma cruzi</i> Electronics machine learning feature selection multivariate analysis classification Chagas disease <i>Trypanosoma cruzi</i> |
| title | Machine Learning-Based Feature Selection and Classification for the Experimental Diagnosis of <i>Trypanosoma cruzi</i> |
| title_full | Machine Learning-Based Feature Selection and Classification for the Experimental Diagnosis of <i>Trypanosoma cruzi</i> |
| title_fullStr | Machine Learning-Based Feature Selection and Classification for the Experimental Diagnosis of <i>Trypanosoma cruzi</i> |
| title_full_unstemmed | Machine Learning-Based Feature Selection and Classification for the Experimental Diagnosis of <i>Trypanosoma cruzi</i> |
| title_short | Machine Learning-Based Feature Selection and Classification for the Experimental Diagnosis of <i>Trypanosoma cruzi</i> |
| title_sort | machine learning based feature selection and classification for the experimental diagnosis of i trypanosoma cruzi i |
| topic | machine learning feature selection multivariate analysis classification Chagas disease <i>Trypanosoma cruzi</i> |
| url | https://www.mdpi.com/2079-9292/11/5/785 |
| work_keys_str_mv | AT nidiyareheviamontiel machinelearningbasedfeatureselectionandclassificationfortheexperimentaldiagnosisofitrypanosomacruzii AT jorgeperezgonzalez machinelearningbasedfeatureselectionandclassificationfortheexperimentaldiagnosisofitrypanosomacruzii AT antonioneme machinelearningbasedfeatureselectionandclassificationfortheexperimentaldiagnosisofitrypanosomacruzii AT paulinaharo machinelearningbasedfeatureselectionandclassificationfortheexperimentaldiagnosisofitrypanosomacruzii |