Artificial intelligence: a useful tool in active tuberculosis screening among vulnerable groups in Romania - advantages and limitations
IntroductionDespite advances in diagnostic technologies for tuberculosis (TB), global control of this disease requires improved technologies for active case finding in selected vulnerable populations. The integration of artificial intelligence (AI) into imaging modalities has been anticipated to ass...
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-02-01
|
| Series: | Frontiers in Public Health |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fpubh.2025.1433450/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1825206729605906432 |
|---|---|
| author | Beatrice Mahler Beatrice Mahler Beatrice Mahler Alexandru Stoichiță Alexandru Stoichiță Alexandru Stoichiță Dragoș Băiceanu Dragoș Băiceanu Traian-Constantin Panciu Traian-Constantin Panciu Dragoș Dendrino Dragoș Dendrino Mihaela Mihai Mihaela Mihai Raluca Bobocea Elmira Ibraim Elmira Ibraim Mara Bălteanu Mara Bălteanu Oana Popescu Oana Popescu Mădălina Oana Burecu Mădălina Oana Burecu Ioana Mădălina Moșteanu Ioana Mădălina Moșteanu Vanessa Veronese Radu Matache Radu Matache Ioana Munteanu Ioana Munteanu Ioana Munteanu Cristina Popa Cristina Popa Justina Antonela Dragomir Justina Antonela Dragomir Justina Antonela Dragomir |
| author_facet | Beatrice Mahler Beatrice Mahler Beatrice Mahler Alexandru Stoichiță Alexandru Stoichiță Alexandru Stoichiță Dragoș Băiceanu Dragoș Băiceanu Traian-Constantin Panciu Traian-Constantin Panciu Dragoș Dendrino Dragoș Dendrino Mihaela Mihai Mihaela Mihai Raluca Bobocea Elmira Ibraim Elmira Ibraim Mara Bălteanu Mara Bălteanu Oana Popescu Oana Popescu Mădălina Oana Burecu Mădălina Oana Burecu Ioana Mădălina Moșteanu Ioana Mădălina Moșteanu Vanessa Veronese Radu Matache Radu Matache Ioana Munteanu Ioana Munteanu Ioana Munteanu Cristina Popa Cristina Popa Justina Antonela Dragomir Justina Antonela Dragomir Justina Antonela Dragomir |
| author_sort | Beatrice Mahler |
| collection | DOAJ |
| description | IntroductionDespite advances in diagnostic technologies for tuberculosis (TB), global control of this disease requires improved technologies for active case finding in selected vulnerable populations. The integration of artificial intelligence (AI) into imaging modalities has been anticipated to assume a pivotal position in conjunction with traditional bacteriological diagnostic approaches, especially in the active diagnosis of vulnerable groups.MethodsThe study was conducted as a prospective investigation spanning from November 2019 to October 2023, in Romania’s national TB screening project. From total of 92,368 tested participants, 404 patients were included in the study, with 202 individuals diagnosed with TB and 202 individuals serving as controls. The initial interpretation of radiological images was performed by AI X-Vision software and patients with suspicious findings were confirmed to have TB using GeneXpert testing. The objective of this study is to discover a threshold at which the AI score can accurately assess the risk of TB, regardless of the patient’s medical background.ResultsThe study involved a number of 404 people, among whom 202 were diagnosed with TB out of a total of 92,368 participants, and the remaining 202 patients represent the control group. The current study highlighted, at an AI threshold value of 0.4, that 89% of the screened people benefited from a correct assessment using the AI associated with the radiological examination. ROC curve analysis indicates an AUC of 0.923 (95% CI:0.893–0.947; significance level p < 0.0001) which shows that the test has a high capacity to accurately detect individuals with TB and also to rule out those who do not have the disease, with sensitivity 87.1, specificity 91.6 and criterion >0.3585.ConclusionOur study brings to the fore the significance of integrating AI software X-vision with bacteriological diagnosis in detecting TB among vulnerable groups in Romania. This underscores the imperative at the global level to develop solutions in the prompt diagnosis of TB, particularly within vulnerable groups. |
| format | Article |
| id | doaj-art-8b18860b7fa748b1a58a03a1acbe81fb |
| institution | Kabale University |
| issn | 2296-2565 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Public Health |
| spelling | doaj-art-8b18860b7fa748b1a58a03a1acbe81fb2025-02-07T06:49:36ZengFrontiers Media S.A.Frontiers in Public Health2296-25652025-02-011310.3389/fpubh.2025.14334501433450Artificial intelligence: a useful tool in active tuberculosis screening among vulnerable groups in Romania - advantages and limitationsBeatrice Mahler0Beatrice Mahler1Beatrice Mahler2Alexandru Stoichiță3Alexandru Stoichiță4Alexandru Stoichiță5Dragoș Băiceanu6Dragoș Băiceanu7Traian-Constantin Panciu8Traian-Constantin Panciu9Dragoș Dendrino10Dragoș Dendrino11Mihaela Mihai12Mihaela Mihai13Raluca Bobocea14Elmira Ibraim15Elmira Ibraim16Mara Bălteanu17Mara Bălteanu18Oana Popescu19Oana Popescu20Mădălina Oana Burecu21Mădălina Oana Burecu22Ioana Mădălina Moșteanu23Ioana Mădălina Moșteanu24Vanessa Veronese25Radu Matache26Radu Matache27Ioana Munteanu28Ioana Munteanu29Ioana Munteanu30Cristina Popa31Cristina Popa32Justina Antonela Dragomir33Justina Antonela Dragomir34Justina Antonela Dragomir35Pneumology II Department, Faculty of Medicine, "Carol Davila" University of Medicine and Pharmacy, Bucharest, RomaniaPneumology Clinic, "Marius Nasta" Institute of Pneumology, Bucharest, RomaniaTuberculosis Screening Program, "Marius Nasta" Institute of Pneumology, Bucharest, RomaniaPneumology II Department, Faculty of Medicine, "Carol Davila" University of Medicine and Pharmacy, Bucharest, RomaniaPneumology Clinic, "Marius Nasta" Institute of Pneumology, Bucharest, RomaniaTuberculosis Screening Program, "Marius Nasta" Institute of Pneumology, Bucharest, RomaniaTuberculosis Screening Program, "Marius Nasta" Institute of Pneumology, Bucharest, RomaniaResearch Department, "Marius Nasta" Institute of Pneumology, Bucharest, RomaniaTuberculosis Screening Program, "Marius Nasta" Institute of Pneumology, Bucharest, RomaniaResearch Department, "Marius Nasta" Institute of Pneumology, Bucharest, RomaniaTuberculosis Screening Program, "Marius Nasta" Institute of Pneumology, Bucharest, RomaniaFaculty of Management, Bucharest University of Economic Studies, Bucharest, RomaniaTuberculosis Screening Program, "Marius Nasta" Institute of Pneumology, Bucharest, RomaniaDepartment of Statistics and Econometrics, Faculty of Economic Cybernetics, Statistics and Informatics, The Bucharest University of Economic Studies, Bucharest, RomaniaPneumology Clinic, "Marius Nasta" Institute of Pneumology, Bucharest, RomaniaTuberculosis Screening Program, "Marius Nasta" Institute of Pneumology, Bucharest, RomaniaResearch Department, "Marius Nasta" Institute of Pneumology, Bucharest, RomaniaPneumology Clinic, "Marius Nasta" Institute of Pneumology, Bucharest, RomaniaFaculty of Medicine, "Titu Maiorescu" University, Bucharest, RomaniaPneumology Clinic, "Marius Nasta" Institute of Pneumology, Bucharest, RomaniaTuberculosis Screening Program, "Marius Nasta" Institute of Pneumology, Bucharest, RomaniaPneumology Clinic, "Marius Nasta" Institute of Pneumology, Bucharest, RomaniaTuberculosis Screening Program, "Marius Nasta" Institute of Pneumology, Bucharest, RomaniaTuberculosis Screening Program, "Marius Nasta" Institute of Pneumology, Bucharest, RomaniaFaculty of Medicine, University of Medicine and Pharmacy of Craiova, Craiova, RomaniaThe Special Programme for Research & Training in Tropical Diseases, World Health Organization, Geneva, SwitzerlandPneumology II Department, Faculty of Medicine, "Carol Davila" University of Medicine and Pharmacy, Bucharest, RomaniaPneumology Clinic, "Marius Nasta" Institute of Pneumology, Bucharest, RomaniaPneumology Clinic, "Marius Nasta" Institute of Pneumology, Bucharest, RomaniaTuberculosis Screening Program, "Marius Nasta" Institute of Pneumology, Bucharest, RomaniaFaculty of Medicine, "Titu Maiorescu" University, Bucharest, RomaniaPneumology Clinic, "Marius Nasta" Institute of Pneumology, Bucharest, RomaniaTuberculosis Screening Program, "Marius Nasta" Institute of Pneumology, Bucharest, RomaniaPneumology II Department, Faculty of Medicine, "Carol Davila" University of Medicine and Pharmacy, Bucharest, RomaniaPneumology Clinic, "Marius Nasta" Institute of Pneumology, Bucharest, RomaniaTuberculosis Screening Program, "Marius Nasta" Institute of Pneumology, Bucharest, RomaniaIntroductionDespite advances in diagnostic technologies for tuberculosis (TB), global control of this disease requires improved technologies for active case finding in selected vulnerable populations. The integration of artificial intelligence (AI) into imaging modalities has been anticipated to assume a pivotal position in conjunction with traditional bacteriological diagnostic approaches, especially in the active diagnosis of vulnerable groups.MethodsThe study was conducted as a prospective investigation spanning from November 2019 to October 2023, in Romania’s national TB screening project. From total of 92,368 tested participants, 404 patients were included in the study, with 202 individuals diagnosed with TB and 202 individuals serving as controls. The initial interpretation of radiological images was performed by AI X-Vision software and patients with suspicious findings were confirmed to have TB using GeneXpert testing. The objective of this study is to discover a threshold at which the AI score can accurately assess the risk of TB, regardless of the patient’s medical background.ResultsThe study involved a number of 404 people, among whom 202 were diagnosed with TB out of a total of 92,368 participants, and the remaining 202 patients represent the control group. The current study highlighted, at an AI threshold value of 0.4, that 89% of the screened people benefited from a correct assessment using the AI associated with the radiological examination. ROC curve analysis indicates an AUC of 0.923 (95% CI:0.893–0.947; significance level p < 0.0001) which shows that the test has a high capacity to accurately detect individuals with TB and also to rule out those who do not have the disease, with sensitivity 87.1, specificity 91.6 and criterion >0.3585.ConclusionOur study brings to the fore the significance of integrating AI software X-vision with bacteriological diagnosis in detecting TB among vulnerable groups in Romania. This underscores the imperative at the global level to develop solutions in the prompt diagnosis of TB, particularly within vulnerable groups.https://www.frontiersin.org/articles/10.3389/fpubh.2025.1433450/fulltuberculosisartificial intelligencecomputer-aided detectionRomaniascreeningvulnerable populations |
| spellingShingle | Beatrice Mahler Beatrice Mahler Beatrice Mahler Alexandru Stoichiță Alexandru Stoichiță Alexandru Stoichiță Dragoș Băiceanu Dragoș Băiceanu Traian-Constantin Panciu Traian-Constantin Panciu Dragoș Dendrino Dragoș Dendrino Mihaela Mihai Mihaela Mihai Raluca Bobocea Elmira Ibraim Elmira Ibraim Mara Bălteanu Mara Bălteanu Oana Popescu Oana Popescu Mădălina Oana Burecu Mădălina Oana Burecu Ioana Mădălina Moșteanu Ioana Mădălina Moșteanu Vanessa Veronese Radu Matache Radu Matache Ioana Munteanu Ioana Munteanu Ioana Munteanu Cristina Popa Cristina Popa Justina Antonela Dragomir Justina Antonela Dragomir Justina Antonela Dragomir Artificial intelligence: a useful tool in active tuberculosis screening among vulnerable groups in Romania - advantages and limitations Frontiers in Public Health tuberculosis artificial intelligence computer-aided detection Romania screening vulnerable populations |
| title | Artificial intelligence: a useful tool in active tuberculosis screening among vulnerable groups in Romania - advantages and limitations |
| title_full | Artificial intelligence: a useful tool in active tuberculosis screening among vulnerable groups in Romania - advantages and limitations |
| title_fullStr | Artificial intelligence: a useful tool in active tuberculosis screening among vulnerable groups in Romania - advantages and limitations |
| title_full_unstemmed | Artificial intelligence: a useful tool in active tuberculosis screening among vulnerable groups in Romania - advantages and limitations |
| title_short | Artificial intelligence: a useful tool in active tuberculosis screening among vulnerable groups in Romania - advantages and limitations |
| title_sort | artificial intelligence a useful tool in active tuberculosis screening among vulnerable groups in romania advantages and limitations |
| topic | tuberculosis artificial intelligence computer-aided detection Romania screening vulnerable populations |
| url | https://www.frontiersin.org/articles/10.3389/fpubh.2025.1433450/full |
| work_keys_str_mv | AT beatricemahler artificialintelligenceausefultoolinactivetuberculosisscreeningamongvulnerablegroupsinromaniaadvantagesandlimitations AT beatricemahler artificialintelligenceausefultoolinactivetuberculosisscreeningamongvulnerablegroupsinromaniaadvantagesandlimitations AT beatricemahler artificialintelligenceausefultoolinactivetuberculosisscreeningamongvulnerablegroupsinromaniaadvantagesandlimitations AT alexandrustoichita artificialintelligenceausefultoolinactivetuberculosisscreeningamongvulnerablegroupsinromaniaadvantagesandlimitations AT alexandrustoichita artificialintelligenceausefultoolinactivetuberculosisscreeningamongvulnerablegroupsinromaniaadvantagesandlimitations AT alexandrustoichita artificialintelligenceausefultoolinactivetuberculosisscreeningamongvulnerablegroupsinromaniaadvantagesandlimitations AT dragosbaiceanu artificialintelligenceausefultoolinactivetuberculosisscreeningamongvulnerablegroupsinromaniaadvantagesandlimitations AT dragosbaiceanu artificialintelligenceausefultoolinactivetuberculosisscreeningamongvulnerablegroupsinromaniaadvantagesandlimitations AT traianconstantinpanciu artificialintelligenceausefultoolinactivetuberculosisscreeningamongvulnerablegroupsinromaniaadvantagesandlimitations AT traianconstantinpanciu artificialintelligenceausefultoolinactivetuberculosisscreeningamongvulnerablegroupsinromaniaadvantagesandlimitations AT dragosdendrino artificialintelligenceausefultoolinactivetuberculosisscreeningamongvulnerablegroupsinromaniaadvantagesandlimitations AT dragosdendrino artificialintelligenceausefultoolinactivetuberculosisscreeningamongvulnerablegroupsinromaniaadvantagesandlimitations AT mihaelamihai artificialintelligenceausefultoolinactivetuberculosisscreeningamongvulnerablegroupsinromaniaadvantagesandlimitations AT mihaelamihai artificialintelligenceausefultoolinactivetuberculosisscreeningamongvulnerablegroupsinromaniaadvantagesandlimitations AT ralucabobocea artificialintelligenceausefultoolinactivetuberculosisscreeningamongvulnerablegroupsinromaniaadvantagesandlimitations AT elmiraibraim artificialintelligenceausefultoolinactivetuberculosisscreeningamongvulnerablegroupsinromaniaadvantagesandlimitations AT elmiraibraim artificialintelligenceausefultoolinactivetuberculosisscreeningamongvulnerablegroupsinromaniaadvantagesandlimitations AT marabalteanu artificialintelligenceausefultoolinactivetuberculosisscreeningamongvulnerablegroupsinromaniaadvantagesandlimitations AT marabalteanu artificialintelligenceausefultoolinactivetuberculosisscreeningamongvulnerablegroupsinromaniaadvantagesandlimitations AT oanapopescu artificialintelligenceausefultoolinactivetuberculosisscreeningamongvulnerablegroupsinromaniaadvantagesandlimitations AT oanapopescu artificialintelligenceausefultoolinactivetuberculosisscreeningamongvulnerablegroupsinromaniaadvantagesandlimitations AT madalinaoanaburecu artificialintelligenceausefultoolinactivetuberculosisscreeningamongvulnerablegroupsinromaniaadvantagesandlimitations AT madalinaoanaburecu artificialintelligenceausefultoolinactivetuberculosisscreeningamongvulnerablegroupsinromaniaadvantagesandlimitations AT ioanamadalinamosteanu artificialintelligenceausefultoolinactivetuberculosisscreeningamongvulnerablegroupsinromaniaadvantagesandlimitations AT ioanamadalinamosteanu artificialintelligenceausefultoolinactivetuberculosisscreeningamongvulnerablegroupsinromaniaadvantagesandlimitations AT vanessaveronese artificialintelligenceausefultoolinactivetuberculosisscreeningamongvulnerablegroupsinromaniaadvantagesandlimitations AT radumatache artificialintelligenceausefultoolinactivetuberculosisscreeningamongvulnerablegroupsinromaniaadvantagesandlimitations AT radumatache artificialintelligenceausefultoolinactivetuberculosisscreeningamongvulnerablegroupsinromaniaadvantagesandlimitations AT ioanamunteanu artificialintelligenceausefultoolinactivetuberculosisscreeningamongvulnerablegroupsinromaniaadvantagesandlimitations AT ioanamunteanu artificialintelligenceausefultoolinactivetuberculosisscreeningamongvulnerablegroupsinromaniaadvantagesandlimitations AT ioanamunteanu artificialintelligenceausefultoolinactivetuberculosisscreeningamongvulnerablegroupsinromaniaadvantagesandlimitations AT cristinapopa artificialintelligenceausefultoolinactivetuberculosisscreeningamongvulnerablegroupsinromaniaadvantagesandlimitations AT cristinapopa artificialintelligenceausefultoolinactivetuberculosisscreeningamongvulnerablegroupsinromaniaadvantagesandlimitations AT justinaantoneladragomir artificialintelligenceausefultoolinactivetuberculosisscreeningamongvulnerablegroupsinromaniaadvantagesandlimitations AT justinaantoneladragomir artificialintelligenceausefultoolinactivetuberculosisscreeningamongvulnerablegroupsinromaniaadvantagesandlimitations AT justinaantoneladragomir artificialintelligenceausefultoolinactivetuberculosisscreeningamongvulnerablegroupsinromaniaadvantagesandlimitations |