Baseline characteristics of TB patients.
<div><p>Despite advancements in detection and treatment, tuberculosis (TB), an infectious illness caused by the Mycobacterium TB bacteria, continues to pose a serious threat to world health. The TB diagnosis phase includes a patient’s medical history, physical examination, chest X-rays,...
Saved in:
| Main Author: | |
|---|---|
| Other Authors: | , , , , , |
| Published: |
2024
|
| Subjects: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1852025907211927552 |
|---|---|
| author | Shaik Ahamed Fayaz (19859670) |
| author2 | Lakshmanan Babu (19859673) Loganathan Paridayal (19859676) Mahalingam Vasantha (533710) Palaniyandi Paramasivam (19859679) Karuppasamy Sundarakumar (19859682) Chinnaiyan Ponnuraja (430196) |
| author2_role | author author author author author author |
| author_facet | Shaik Ahamed Fayaz (19859670) Lakshmanan Babu (19859673) Loganathan Paridayal (19859676) Mahalingam Vasantha (533710) Palaniyandi Paramasivam (19859679) Karuppasamy Sundarakumar (19859682) Chinnaiyan Ponnuraja (430196) |
| author_role | author |
| dc.creator.none.fl_str_mv | Shaik Ahamed Fayaz (19859670) Lakshmanan Babu (19859673) Loganathan Paridayal (19859676) Mahalingam Vasantha (533710) Palaniyandi Paramasivam (19859679) Karuppasamy Sundarakumar (19859682) Chinnaiyan Ponnuraja (430196) |
| dc.date.none.fl_str_mv | 2024-10-16T17:27:40Z |
| dc.identifier.none.fl_str_mv | 10.1371/journal.pone.0309151.t003 |
| dc.relation.none.fl_str_mv | https://figshare.com/articles/dataset/Baseline_characteristics_of_TB_patients_/27243468 |
| dc.rights.none.fl_str_mv | CC BY 4.0 info:eu-repo/semantics/openAccess |
| dc.subject.none.fl_str_mv | Science Policy Infectious Diseases Environmental Sciences not elsewhere classified Biological Sciences not elsewhere classified Information Systems not elsewhere classified receiver operating characteristic patient &# 8217 na &# 239 many studies done infectious illness caused machine learning algorithms 909 ), precision 90 %), recall 75 %) among mycobacterium tb bacteria sputum culture conversion 1236 ptb patients multiple ml models predictive ml algorithm predict treatment success sputum culture tb ), treatment success statistical algorithms predictive performance 72 %), 60 %) ml algorithm ptb patients ptb ). tb patients pulmonary tb better algorithm best algorithm ml models world health unseen data treatment period serious threat salient finding physical examination national institute molecular testing methodology may medical history laboratory procedures historical data highest accuracy high performance given treatment dt model decision tree data analysis chest x artificial intelligence 80 %. |
| dc.title.none.fl_str_mv | Baseline characteristics of TB patients. |
| dc.type.none.fl_str_mv | Dataset info:eu-repo/semantics/publishedVersion dataset |
| description | <div><p>Despite advancements in detection and treatment, tuberculosis (TB), an infectious illness caused by the Mycobacterium TB bacteria, continues to pose a serious threat to world health. The TB diagnosis phase includes a patient’s medical history, physical examination, chest X-rays, and laboratory procedures, such as molecular testing and sputum culture. In artificial intelligence (AI), machine learning (ML) is an advanced study of statistical algorithms that can learn from historical data and generalize the results to unseen data. There are not many studies done on the ML algorithm that enables the prediction of treatment success for patients with pulmonary TB (PTB). The objective of this study is to identify an effective and predictive ML algorithm to evaluate the detection of treatment success in PTB patients and to compare the predictive performance of the ML models. In this retrospective study, a total of 1236 PTB patients who were given treatment under a randomized controlled clinical trial at the ICMR-National Institute for Research in Tuberculosis, Chennai, India were considered for data analysis. The multiple ML models were developed and tested to identify the best algorithm to predict the sputum culture conversion of TB patients during the treatment period. In this study, decision tree (DT), random forest (RF), support vector machine (SVM) and naïve bayes (NB) models were validated with high performance by achieving an area under the curve (AUC) of receiver operating characteristic (ROC) greater than 80%. The salient finding of the study is that the DT model was produced as a better algorithm with the highest accuracy (92.72%), an AUC (0.909), precision (95.90%), recall (95.60%) and F1-score (95.75%) among the ML models. This methodology may be used to study the precise ML model classification for predicting the treatment success of TB patients during the treatment period.</p></div> |
| eu_rights_str_mv | openAccess |
| id | Manara_8af55a1b87b48ff4fa9bb4d1b2bcd0b6 |
| identifier_str_mv | 10.1371/journal.pone.0309151.t003 |
| network_acronym_str | Manara |
| network_name_str | ManaraRepo |
| oai_identifier_str | oai:figshare.com:article/27243468 |
| publishDate | 2024 |
| repository.mail.fl_str_mv | |
| repository.name.fl_str_mv | |
| repository_id_str | |
| rights_invalid_str_mv | CC BY 4.0 |
| spelling | Baseline characteristics of TB patients.Shaik Ahamed Fayaz (19859670)Lakshmanan Babu (19859673)Loganathan Paridayal (19859676)Mahalingam Vasantha (533710)Palaniyandi Paramasivam (19859679)Karuppasamy Sundarakumar (19859682)Chinnaiyan Ponnuraja (430196)Science PolicyInfectious DiseasesEnvironmental Sciences not elsewhere classifiedBiological Sciences not elsewhere classifiedInformation Systems not elsewhere classifiedreceiver operating characteristicpatient &# 8217na &# 239many studies doneinfectious illness causedmachine learning algorithms909 ), precision90 %), recall75 %) amongmycobacterium tb bacteriasputum culture conversion1236 ptb patientsmultiple ml modelspredictive ml algorithmpredict treatment successsputum culturetb ),treatment successstatistical algorithmspredictive performance72 %),60 %)ml algorithmptb patientsptb ).tb patientspulmonary tbbetter algorithmbest algorithmml modelsworld healthunseen datatreatment periodserious threatsalient findingphysical examinationnational institutemolecular testingmethodology maymedical historylaboratory procedureshistorical datahighest accuracyhigh performancegiven treatmentdt modeldecision treedata analysischest xartificial intelligence80 %.<div><p>Despite advancements in detection and treatment, tuberculosis (TB), an infectious illness caused by the Mycobacterium TB bacteria, continues to pose a serious threat to world health. The TB diagnosis phase includes a patient’s medical history, physical examination, chest X-rays, and laboratory procedures, such as molecular testing and sputum culture. In artificial intelligence (AI), machine learning (ML) is an advanced study of statistical algorithms that can learn from historical data and generalize the results to unseen data. There are not many studies done on the ML algorithm that enables the prediction of treatment success for patients with pulmonary TB (PTB). The objective of this study is to identify an effective and predictive ML algorithm to evaluate the detection of treatment success in PTB patients and to compare the predictive performance of the ML models. In this retrospective study, a total of 1236 PTB patients who were given treatment under a randomized controlled clinical trial at the ICMR-National Institute for Research in Tuberculosis, Chennai, India were considered for data analysis. The multiple ML models were developed and tested to identify the best algorithm to predict the sputum culture conversion of TB patients during the treatment period. In this study, decision tree (DT), random forest (RF), support vector machine (SVM) and naïve bayes (NB) models were validated with high performance by achieving an area under the curve (AUC) of receiver operating characteristic (ROC) greater than 80%. The salient finding of the study is that the DT model was produced as a better algorithm with the highest accuracy (92.72%), an AUC (0.909), precision (95.90%), recall (95.60%) and F1-score (95.75%) among the ML models. This methodology may be used to study the precise ML model classification for predicting the treatment success of TB patients during the treatment period.</p></div>2024-10-16T17:27:40ZDatasetinfo:eu-repo/semantics/publishedVersiondataset10.1371/journal.pone.0309151.t003https://figshare.com/articles/dataset/Baseline_characteristics_of_TB_patients_/27243468CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/272434682024-10-16T17:27:40Z |
| spellingShingle | Baseline characteristics of TB patients. Shaik Ahamed Fayaz (19859670) Science Policy Infectious Diseases Environmental Sciences not elsewhere classified Biological Sciences not elsewhere classified Information Systems not elsewhere classified receiver operating characteristic patient &# 8217 na &# 239 many studies done infectious illness caused machine learning algorithms 909 ), precision 90 %), recall 75 %) among mycobacterium tb bacteria sputum culture conversion 1236 ptb patients multiple ml models predictive ml algorithm predict treatment success sputum culture tb ), treatment success statistical algorithms predictive performance 72 %), 60 %) ml algorithm ptb patients ptb ). tb patients pulmonary tb better algorithm best algorithm ml models world health unseen data treatment period serious threat salient finding physical examination national institute molecular testing methodology may medical history laboratory procedures historical data highest accuracy high performance given treatment dt model decision tree data analysis chest x artificial intelligence 80 %. |
| status_str | publishedVersion |
| title | Baseline characteristics of TB patients. |
| title_full | Baseline characteristics of TB patients. |
| title_fullStr | Baseline characteristics of TB patients. |
| title_full_unstemmed | Baseline characteristics of TB patients. |
| title_short | Baseline characteristics of TB patients. |
| title_sort | Baseline characteristics of TB patients. |
| topic | Science Policy Infectious Diseases Environmental Sciences not elsewhere classified Biological Sciences not elsewhere classified Information Systems not elsewhere classified receiver operating characteristic patient &# 8217 na &# 239 many studies done infectious illness caused machine learning algorithms 909 ), precision 90 %), recall 75 %) among mycobacterium tb bacteria sputum culture conversion 1236 ptb patients multiple ml models predictive ml algorithm predict treatment success sputum culture tb ), treatment success statistical algorithms predictive performance 72 %), 60 %) ml algorithm ptb patients ptb ). tb patients pulmonary tb better algorithm best algorithm ml models world health unseen data treatment period serious threat salient finding physical examination national institute molecular testing methodology may medical history laboratory procedures historical data highest accuracy high performance given treatment dt model decision tree data analysis chest x artificial intelligence 80 %. |