Diagnostic accuracy of adenosine deaminase for pleural tuberculosis in a low prevalence setting: A machine learning approach within a 7-year prospective multi-center study.
<h4>Objective</h4>To analyze the performance of adenosine deaminase in pleural fluid combined with other parameters routinely measured in clinical practice and assisted by machine learning algorithms for the diagnosis of pleural tuberculosis in a low prevalence setting, and secondly, to...
Guardado en:
| Autores principales: | , , , , , , , , , , , , , , , |
|---|---|
| Formato: | article |
| Lenguaje: | EN |
| Publicado: |
Public Library of Science (PLoS)
2021
|
| Materias: | |
| Acceso en línea: | https://doaj.org/article/19525dbc8dbd489d8ae39d02d91cf854 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| id |
oai:doaj.org-article:19525dbc8dbd489d8ae39d02d91cf854 |
|---|---|
| record_format |
dspace |
| spelling |
oai:doaj.org-article:19525dbc8dbd489d8ae39d02d91cf8542021-12-02T20:04:22ZDiagnostic accuracy of adenosine deaminase for pleural tuberculosis in a low prevalence setting: A machine learning approach within a 7-year prospective multi-center study.1932-620310.1371/journal.pone.0259203https://doaj.org/article/19525dbc8dbd489d8ae39d02d91cf8542021-01-01T00:00:00Zhttps://doi.org/10.1371/journal.pone.0259203https://doaj.org/toc/1932-6203<h4>Objective</h4>To analyze the performance of adenosine deaminase in pleural fluid combined with other parameters routinely measured in clinical practice and assisted by machine learning algorithms for the diagnosis of pleural tuberculosis in a low prevalence setting, and secondly, to identify effusions that are non-tuberculous and most likely malignant.<h4>Patients and methods</h4>We prospectively analyzed 230 consecutive patients diagnosed with lymphocytic exudative pleural effusion from March 2013 to June 2020. Diagnosis according to the composite reference standard was achieved in all cases. Pre-test probability of pleural tuberculosis was 3.8% throughout the study period. Parameters included were: levels of adenosine deaminase, pH, glucose, proteins, and lactate dehydrogenase, red and white cell counts and lymphocyte percentage in pleural fluid, as well as age. We tested six different machine learning-based classifiers to categorize the patients. Two different classifications were performed: a) tuberculous/non-tuberculous and b) tuberculous/malignant/other.<h4>Results</h4>Out of a total of 230 patients with pleural effusion included in the study, 124 were diagnosed with malignant effusion and 44 with pleural tuberculosis, while 62 were given other diagnoses. In the tuberculous/non-tuberculous classification, and taking into account the validation predictions, the support vector machine yielded the best result: an AUC of 0.98, accuracy of 97%, sensitivity of 91%, and specificity of 98%, whilst in the tuberculous/malignant/other classification, this type of classifier yielded an overall accuracy of 80%. With this three-class classifier, the same sensitivity and specificity was achieved in the tuberculous/other classification, but it also allowed the correct classification of 90% of malignant cases.<h4>Conclusion</h4>The level of adenosine deaminase in pleural fluid together with cell count, other routine biochemical parameters and age, combined with a machine-learning approach, is suitable for the diagnosis of pleural tuberculosis in a low prevalence scenario. Secondly, non-tuberculous effusions that are suspected to be malignant may also be identified with adequate accuracy.Alberto Garcia-ZamalloaDiego VicenteRafael ArnayArantzazu ArrospideJorge TaboadaIván Castilla-RodríguezUrko AguirreNekane MúgicaLadislao AldamaBorja AguinagaldeMontserrat JimenezEdurne BikuñaMiren Begoña BasauriMarta AlonsoEmilio Perez-Trallerowith the Gipuzkoa Pleura Group ConsortiumPublic Library of Science (PLoS)articleMedicineRScienceQENPLoS ONE, Vol 16, Iss 11, p e0259203 (2021) |
| institution |
DOAJ |
| collection |
DOAJ |
| language |
EN |
| topic |
Medicine R Science Q |
| spellingShingle |
Medicine R Science Q Alberto Garcia-Zamalloa Diego Vicente Rafael Arnay Arantzazu Arrospide Jorge Taboada Iván Castilla-Rodríguez Urko Aguirre Nekane Múgica Ladislao Aldama Borja Aguinagalde Montserrat Jimenez Edurne Bikuña Miren Begoña Basauri Marta Alonso Emilio Perez-Trallero with the Gipuzkoa Pleura Group Consortium Diagnostic accuracy of adenosine deaminase for pleural tuberculosis in a low prevalence setting: A machine learning approach within a 7-year prospective multi-center study. |
| description |
<h4>Objective</h4>To analyze the performance of adenosine deaminase in pleural fluid combined with other parameters routinely measured in clinical practice and assisted by machine learning algorithms for the diagnosis of pleural tuberculosis in a low prevalence setting, and secondly, to identify effusions that are non-tuberculous and most likely malignant.<h4>Patients and methods</h4>We prospectively analyzed 230 consecutive patients diagnosed with lymphocytic exudative pleural effusion from March 2013 to June 2020. Diagnosis according to the composite reference standard was achieved in all cases. Pre-test probability of pleural tuberculosis was 3.8% throughout the study period. Parameters included were: levels of adenosine deaminase, pH, glucose, proteins, and lactate dehydrogenase, red and white cell counts and lymphocyte percentage in pleural fluid, as well as age. We tested six different machine learning-based classifiers to categorize the patients. Two different classifications were performed: a) tuberculous/non-tuberculous and b) tuberculous/malignant/other.<h4>Results</h4>Out of a total of 230 patients with pleural effusion included in the study, 124 were diagnosed with malignant effusion and 44 with pleural tuberculosis, while 62 were given other diagnoses. In the tuberculous/non-tuberculous classification, and taking into account the validation predictions, the support vector machine yielded the best result: an AUC of 0.98, accuracy of 97%, sensitivity of 91%, and specificity of 98%, whilst in the tuberculous/malignant/other classification, this type of classifier yielded an overall accuracy of 80%. With this three-class classifier, the same sensitivity and specificity was achieved in the tuberculous/other classification, but it also allowed the correct classification of 90% of malignant cases.<h4>Conclusion</h4>The level of adenosine deaminase in pleural fluid together with cell count, other routine biochemical parameters and age, combined with a machine-learning approach, is suitable for the diagnosis of pleural tuberculosis in a low prevalence scenario. Secondly, non-tuberculous effusions that are suspected to be malignant may also be identified with adequate accuracy. |
| format |
article |
| author |
Alberto Garcia-Zamalloa Diego Vicente Rafael Arnay Arantzazu Arrospide Jorge Taboada Iván Castilla-Rodríguez Urko Aguirre Nekane Múgica Ladislao Aldama Borja Aguinagalde Montserrat Jimenez Edurne Bikuña Miren Begoña Basauri Marta Alonso Emilio Perez-Trallero with the Gipuzkoa Pleura Group Consortium |
| author_facet |
Alberto Garcia-Zamalloa Diego Vicente Rafael Arnay Arantzazu Arrospide Jorge Taboada Iván Castilla-Rodríguez Urko Aguirre Nekane Múgica Ladislao Aldama Borja Aguinagalde Montserrat Jimenez Edurne Bikuña Miren Begoña Basauri Marta Alonso Emilio Perez-Trallero with the Gipuzkoa Pleura Group Consortium |
| author_sort |
Alberto Garcia-Zamalloa |
| title |
Diagnostic accuracy of adenosine deaminase for pleural tuberculosis in a low prevalence setting: A machine learning approach within a 7-year prospective multi-center study. |
| title_short |
Diagnostic accuracy of adenosine deaminase for pleural tuberculosis in a low prevalence setting: A machine learning approach within a 7-year prospective multi-center study. |
| title_full |
Diagnostic accuracy of adenosine deaminase for pleural tuberculosis in a low prevalence setting: A machine learning approach within a 7-year prospective multi-center study. |
| title_fullStr |
Diagnostic accuracy of adenosine deaminase for pleural tuberculosis in a low prevalence setting: A machine learning approach within a 7-year prospective multi-center study. |
| title_full_unstemmed |
Diagnostic accuracy of adenosine deaminase for pleural tuberculosis in a low prevalence setting: A machine learning approach within a 7-year prospective multi-center study. |
| title_sort |
diagnostic accuracy of adenosine deaminase for pleural tuberculosis in a low prevalence setting: a machine learning approach within a 7-year prospective multi-center study. |
| publisher |
Public Library of Science (PLoS) |
| publishDate |
2021 |
| url |
https://doaj.org/article/19525dbc8dbd489d8ae39d02d91cf854 |
| work_keys_str_mv |
AT albertogarciazamalloa diagnosticaccuracyofadenosinedeaminaseforpleuraltuberculosisinalowprevalencesettingamachinelearningapproachwithina7yearprospectivemulticenterstudy AT diegovicente diagnosticaccuracyofadenosinedeaminaseforpleuraltuberculosisinalowprevalencesettingamachinelearningapproachwithina7yearprospectivemulticenterstudy AT rafaelarnay diagnosticaccuracyofadenosinedeaminaseforpleuraltuberculosisinalowprevalencesettingamachinelearningapproachwithina7yearprospectivemulticenterstudy AT arantzazuarrospide diagnosticaccuracyofadenosinedeaminaseforpleuraltuberculosisinalowprevalencesettingamachinelearningapproachwithina7yearprospectivemulticenterstudy AT jorgetaboada diagnosticaccuracyofadenosinedeaminaseforpleuraltuberculosisinalowprevalencesettingamachinelearningapproachwithina7yearprospectivemulticenterstudy AT ivancastillarodriguez diagnosticaccuracyofadenosinedeaminaseforpleuraltuberculosisinalowprevalencesettingamachinelearningapproachwithina7yearprospectivemulticenterstudy AT urkoaguirre diagnosticaccuracyofadenosinedeaminaseforpleuraltuberculosisinalowprevalencesettingamachinelearningapproachwithina7yearprospectivemulticenterstudy AT nekanemugica diagnosticaccuracyofadenosinedeaminaseforpleuraltuberculosisinalowprevalencesettingamachinelearningapproachwithina7yearprospectivemulticenterstudy AT ladislaoaldama diagnosticaccuracyofadenosinedeaminaseforpleuraltuberculosisinalowprevalencesettingamachinelearningapproachwithina7yearprospectivemulticenterstudy AT borjaaguinagalde diagnosticaccuracyofadenosinedeaminaseforpleuraltuberculosisinalowprevalencesettingamachinelearningapproachwithina7yearprospectivemulticenterstudy AT montserratjimenez diagnosticaccuracyofadenosinedeaminaseforpleuraltuberculosisinalowprevalencesettingamachinelearningapproachwithina7yearprospectivemulticenterstudy AT edurnebikuna diagnosticaccuracyofadenosinedeaminaseforpleuraltuberculosisinalowprevalencesettingamachinelearningapproachwithina7yearprospectivemulticenterstudy AT mirenbegonabasauri diagnosticaccuracyofadenosinedeaminaseforpleuraltuberculosisinalowprevalencesettingamachinelearningapproachwithina7yearprospectivemulticenterstudy AT martaalonso diagnosticaccuracyofadenosinedeaminaseforpleuraltuberculosisinalowprevalencesettingamachinelearningapproachwithina7yearprospectivemulticenterstudy AT emiliopereztrallero diagnosticaccuracyofadenosinedeaminaseforpleuraltuberculosisinalowprevalencesettingamachinelearningapproachwithina7yearprospectivemulticenterstudy AT withthegipuzkoapleuragroupconsortium diagnosticaccuracyofadenosinedeaminaseforpleuraltuberculosisinalowprevalencesettingamachinelearningapproachwithina7yearprospectivemulticenterstudy |
| _version_ |
1718375588052336640 |