The utility of artificial intelligence in identifying radiological evidence of lung cancer and pulmonary tuberculosis in a high-burden tuberculosis setting
Background. Artificial intelligence (AI), using deep learning (DL) systems, can be utilised to detect radiological changes of various pulmonary diseases. Settings with a high burden of tuberculosis (TB) and people living with HIV can potentially benefit from the use of AI to augment resource-co...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
South African Medical Association
2024-05-01
|
| Series: | South African Medical Journal |
| Subjects: | |
| Online Access: | https://samajournals.co.za/index.php/samj/article/view/1846 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823860569114935296 |
|---|---|
| author | Z Z Nxumalo E M Irusen B W Allwood M Tadepalli J Bassi C F N Koegelenberg |
| author_facet | Z Z Nxumalo E M Irusen B W Allwood M Tadepalli J Bassi C F N Koegelenberg |
| author_sort | Z Z Nxumalo |
| collection | DOAJ |
| description |
Background. Artificial intelligence (AI), using deep learning (DL) systems, can be utilised to detect radiological changes of various pulmonary diseases. Settings with a high burden of tuberculosis (TB) and people living with HIV can potentially benefit from the use of AI to augment resource-constrained healthcare systems.
Objective. To assess the utility of qXR software (AI) in detecting radiological changes compatible with lung cancer or pulmonary TB (PTB).
Methods. We performed an observational study in a tertiary institution that serves a population with a high burden of lung cancer and PTB. In total, 382 chest radiographs that had a confirmed diagnosis were assessed: 127 with lung cancer, 144 with PTB and 111 normal. These chest radiographs were de-identified and randomly uploaded by a blinded investigator into qXR software. The output was generated as probability scores from predefined threshold values.
Results. The overall sensitivity of the qXR in detecting lung cancer was 84% (95% confidence interval (CI) 80 - 87%), specificity 91% (95% CI 84 - 96%) and positive predictive value of 97% (95% CI 95 - 99%). For PTB, it had a sensitivity of 90% (95% CI 87 - 93%) and specificity of 79% (95% CI 73 - 84%) and negative predictive value of 85% (95% CI 79 - 91%).
Conclusion. The qXR software was sensitive and specific in categorising chest radiographs as consistent with lung cancer or TB, and can potentially aid in the earlier detection and management of these diseases.
|
| format | Article |
| id | doaj-art-5d2b2c2e8c5e48f7bd04af652e48dcee |
| institution | Kabale University |
| issn | 0256-9574 2078-5135 |
| language | English |
| publishDate | 2024-05-01 |
| publisher | South African Medical Association |
| record_format | Article |
| series | South African Medical Journal |
| spelling | doaj-art-5d2b2c2e8c5e48f7bd04af652e48dcee2025-02-10T12:26:03ZengSouth African Medical AssociationSouth African Medical Journal0256-95742078-51352024-05-01114610.7196/SAMJ.2024.v114i6.1846The utility of artificial intelligence in identifying radiological evidence of lung cancer and pulmonary tuberculosis in a high-burden tuberculosis settingZ Z Nxumalo0https://orcid.org/0009-0004-4859-4810E M Irusen1https://orcid.org/0000-0002-2134-3251B W Allwood2https://orcid.org/0000-0003-0421-2978M Tadepalli3https://orcid.org/0000-0002-8632-9231J Bassi4https://orcid.org/0009-0004-5808-6553C F N Koegelenberg5https://orcid.org/0000-0002-5563-8429Division of Pulmonology, Department of Medicine, Faculty of Medicine and Health Sciences, Stellenbosch University and Tygerberg Hospital, Cape Town, South AfricaDivision of Pulmonology, Department of Medicine, Faculty of Medicine and Health Sciences, Stellenbosch University and Tygerberg Hospital, Cape Town, South AfricaDivision of Pulmonology, Department of Medicine, Faculty of Medicine and Health Sciences, Stellenbosch University and Tygerberg Hospital, Cape Town, South AfricaQure.ai, Mumbai, IndiaQure.ai, Mumbai, IndiaDivision of Pulmonology, Department of Medicine, Faculty of Medicine and Health Sciences, Stellenbosch University and Tygerberg Hospital, Cape Town, South Africa Background. Artificial intelligence (AI), using deep learning (DL) systems, can be utilised to detect radiological changes of various pulmonary diseases. Settings with a high burden of tuberculosis (TB) and people living with HIV can potentially benefit from the use of AI to augment resource-constrained healthcare systems. Objective. To assess the utility of qXR software (AI) in detecting radiological changes compatible with lung cancer or pulmonary TB (PTB). Methods. We performed an observational study in a tertiary institution that serves a population with a high burden of lung cancer and PTB. In total, 382 chest radiographs that had a confirmed diagnosis were assessed: 127 with lung cancer, 144 with PTB and 111 normal. These chest radiographs were de-identified and randomly uploaded by a blinded investigator into qXR software. The output was generated as probability scores from predefined threshold values. Results. The overall sensitivity of the qXR in detecting lung cancer was 84% (95% confidence interval (CI) 80 - 87%), specificity 91% (95% CI 84 - 96%) and positive predictive value of 97% (95% CI 95 - 99%). For PTB, it had a sensitivity of 90% (95% CI 87 - 93%) and specificity of 79% (95% CI 73 - 84%) and negative predictive value of 85% (95% CI 79 - 91%). Conclusion. The qXR software was sensitive and specific in categorising chest radiographs as consistent with lung cancer or TB, and can potentially aid in the earlier detection and management of these diseases. https://samajournals.co.za/index.php/samj/article/view/1846Utility, artificial intelligence, pulmonary tuberculosis, lung cancer, computer aided detection. |
| spellingShingle | Z Z Nxumalo E M Irusen B W Allwood M Tadepalli J Bassi C F N Koegelenberg The utility of artificial intelligence in identifying radiological evidence of lung cancer and pulmonary tuberculosis in a high-burden tuberculosis setting South African Medical Journal Utility, artificial intelligence, pulmonary tuberculosis, lung cancer, computer aided detection. |
| title | The utility of artificial intelligence in identifying radiological evidence of lung cancer and pulmonary tuberculosis in a high-burden tuberculosis setting |
| title_full | The utility of artificial intelligence in identifying radiological evidence of lung cancer and pulmonary tuberculosis in a high-burden tuberculosis setting |
| title_fullStr | The utility of artificial intelligence in identifying radiological evidence of lung cancer and pulmonary tuberculosis in a high-burden tuberculosis setting |
| title_full_unstemmed | The utility of artificial intelligence in identifying radiological evidence of lung cancer and pulmonary tuberculosis in a high-burden tuberculosis setting |
| title_short | The utility of artificial intelligence in identifying radiological evidence of lung cancer and pulmonary tuberculosis in a high-burden tuberculosis setting |
| title_sort | utility of artificial intelligence in identifying radiological evidence of lung cancer and pulmonary tuberculosis in a high burden tuberculosis setting |
| topic | Utility, artificial intelligence, pulmonary tuberculosis, lung cancer, computer aided detection. |
| url | https://samajournals.co.za/index.php/samj/article/view/1846 |
| work_keys_str_mv | AT zznxumalo theutilityofartificialintelligenceinidentifyingradiologicalevidenceoflungcancerandpulmonarytuberculosisinahighburdentuberculosissetting AT emirusen theutilityofartificialintelligenceinidentifyingradiologicalevidenceoflungcancerandpulmonarytuberculosisinahighburdentuberculosissetting AT bwallwood theutilityofartificialintelligenceinidentifyingradiologicalevidenceoflungcancerandpulmonarytuberculosisinahighburdentuberculosissetting AT mtadepalli theutilityofartificialintelligenceinidentifyingradiologicalevidenceoflungcancerandpulmonarytuberculosisinahighburdentuberculosissetting AT jbassi theutilityofartificialintelligenceinidentifyingradiologicalevidenceoflungcancerandpulmonarytuberculosisinahighburdentuberculosissetting AT cfnkoegelenberg theutilityofartificialintelligenceinidentifyingradiologicalevidenceoflungcancerandpulmonarytuberculosisinahighburdentuberculosissetting AT zznxumalo utilityofartificialintelligenceinidentifyingradiologicalevidenceoflungcancerandpulmonarytuberculosisinahighburdentuberculosissetting AT emirusen utilityofartificialintelligenceinidentifyingradiologicalevidenceoflungcancerandpulmonarytuberculosisinahighburdentuberculosissetting AT bwallwood utilityofartificialintelligenceinidentifyingradiologicalevidenceoflungcancerandpulmonarytuberculosisinahighburdentuberculosissetting AT mtadepalli utilityofartificialintelligenceinidentifyingradiologicalevidenceoflungcancerandpulmonarytuberculosisinahighburdentuberculosissetting AT jbassi utilityofartificialintelligenceinidentifyingradiologicalevidenceoflungcancerandpulmonarytuberculosisinahighburdentuberculosissetting AT cfnkoegelenberg utilityofartificialintelligenceinidentifyingradiologicalevidenceoflungcancerandpulmonarytuberculosisinahighburdentuberculosissetting |