Limitations of using artificial intelligence services to analyze chest x-ray imaging

BACKGROUND: Chest X-ray examination is one of the first radiology areas that started applying artificial intelligence, and it is still used to the present. However, when interpreting X-ray scans using artificial intelligence, radiologists still experience several routine restrictions that should be...

Full description

Saved in:
Bibliographic Details
Main Authors: Yuriy A. Vasilev, Anton V. Vladzymyrskyy, Kirill M. Arzamasov, Igor M. Shulkin, Elena V. Astapenko, Lev D. Pestrenin
Format: Article
Language:English
Published: Eco-Vector 2024-12-01
Series:Digital Diagnostics
Subjects:
Online Access:https://jdigitaldiagnostics.com/DD/article/viewFile/626310/pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850203174322831360
author Yuriy A. Vasilev
Anton V. Vladzymyrskyy
Kirill M. Arzamasov
Igor M. Shulkin
Elena V. Astapenko
Lev D. Pestrenin
author_facet Yuriy A. Vasilev
Anton V. Vladzymyrskyy
Kirill M. Arzamasov
Igor M. Shulkin
Elena V. Astapenko
Lev D. Pestrenin
author_sort Yuriy A. Vasilev
collection DOAJ
description BACKGROUND: Chest X-ray examination is one of the first radiology areas that started applying artificial intelligence, and it is still used to the present. However, when interpreting X-ray scans using artificial intelligence, radiologists still experience several routine restrictions that should be considered in issuing a medical report and require the attention of artificial intelligence developers to further improve the algorithms and increase their efficiency. AIM: To identify restrictions of artificial intelligence services for analyzing chest X-ray images and assesses the clinical significance of these restrictions. MATERIALS AND METHODS: A retrospective analysis was performed for 155 cases of discrepancies between the conclusions of artificial intelligence services and medical reports when analyzing chest X-ray images. All cases included in the study were obtained from the Unified Radiological Information Service of the Unified Medical Information and Analytical System of Moscow. RESULTS: Of the 155 analyzed difference cases, 48 (31.0%) were false-positive and 78 (50.3%) were false-negative cases. The remaining 29 (18.7%) cases were removed from further studies because they were true positive (27) or true negative (2) in the expert review. Most (93.8%) of the 48 false-positive cases were due to the artificial intelligence service mistaking normal chest anatomy (97.8% of cases) or catheter shadow (2.2% of cases) for pneumothorax signs. Overlooked clinically significant pathologies accounted for 22.0% of false-negative scans. Nearly half of these cases (44.4%) were overlooked lung nodules. Lung calcifications (60.9%) were the most common clinically insignificant pathology. CONCLUSIONS: Artificial intelligence services demonstrate a tendency toward over diagnosis. All false-positive cases were associated with erroneous detection of clinically significant pathology: pneumothorax, lung nodules, and pulmonary consolidation. Among false-negative cases, the rate of overlooked clinically significant pathology was low, which accounted for less than one-fourth.
format Article
id doaj-art-e5729eaa537848a8aa7d2e40b0f9ff9d
institution OA Journals
issn 2712-8490
2712-8962
language English
publishDate 2024-12-01
publisher Eco-Vector
record_format Article
series Digital Diagnostics
spelling doaj-art-e5729eaa537848a8aa7d2e40b0f9ff9d2025-08-20T02:11:34ZengEco-VectorDigital Diagnostics2712-84902712-89622024-12-015340742010.17816/DD62631076688Limitations of using artificial intelligence services to analyze chest x-ray imagingYuriy A. Vasilev0https://orcid.org/0000-0002-5283-5961Anton V. Vladzymyrskyy1https://orcid.org/0000-0002-2990-7736Kirill M. Arzamasov2https://orcid.org/0000-0001-7786-0349Igor M. Shulkin3https://orcid.org/0000-0002-7613-5273Elena V. Astapenko4https://orcid.org/0009-0006-6284-2088Lev D. Pestrenin5https://orcid.org/0000-0002-1786-4329Research and Practical Clinical Center for Diagnostics and Telemedicine TechnologiesResearch and Practical Clinical Center for Diagnostics and Telemedicine TechnologiesResearch and Practical Clinical Center for Diagnostics and Telemedicine TechnologiesResearch and Practical Clinical Center for Diagnostics and Telemedicine TechnologiesResearch and Practical Clinical Center for Diagnostics and Telemedicine TechnologiesResearch and Practical Clinical Center for Diagnostics and Telemedicine TechnologiesBACKGROUND: Chest X-ray examination is one of the first radiology areas that started applying artificial intelligence, and it is still used to the present. However, when interpreting X-ray scans using artificial intelligence, radiologists still experience several routine restrictions that should be considered in issuing a medical report and require the attention of artificial intelligence developers to further improve the algorithms and increase their efficiency. AIM: To identify restrictions of artificial intelligence services for analyzing chest X-ray images and assesses the clinical significance of these restrictions. MATERIALS AND METHODS: A retrospective analysis was performed for 155 cases of discrepancies between the conclusions of artificial intelligence services and medical reports when analyzing chest X-ray images. All cases included in the study were obtained from the Unified Radiological Information Service of the Unified Medical Information and Analytical System of Moscow. RESULTS: Of the 155 analyzed difference cases, 48 (31.0%) were false-positive and 78 (50.3%) were false-negative cases. The remaining 29 (18.7%) cases were removed from further studies because they were true positive (27) or true negative (2) in the expert review. Most (93.8%) of the 48 false-positive cases were due to the artificial intelligence service mistaking normal chest anatomy (97.8% of cases) or catheter shadow (2.2% of cases) for pneumothorax signs. Overlooked clinically significant pathologies accounted for 22.0% of false-negative scans. Nearly half of these cases (44.4%) were overlooked lung nodules. Lung calcifications (60.9%) were the most common clinically insignificant pathology. CONCLUSIONS: Artificial intelligence services demonstrate a tendency toward over diagnosis. All false-positive cases were associated with erroneous detection of clinically significant pathology: pneumothorax, lung nodules, and pulmonary consolidation. Among false-negative cases, the rate of overlooked clinically significant pathology was low, which accounted for less than one-fourth.https://jdigitaldiagnostics.com/DD/article/viewFile/626310/pdfartificial intelligencechest x-rayreproducibility of resultsreliability
spellingShingle Yuriy A. Vasilev
Anton V. Vladzymyrskyy
Kirill M. Arzamasov
Igor M. Shulkin
Elena V. Astapenko
Lev D. Pestrenin
Limitations of using artificial intelligence services to analyze chest x-ray imaging
Digital Diagnostics
artificial intelligence
chest x-ray
reproducibility of results
reliability
title Limitations of using artificial intelligence services to analyze chest x-ray imaging
title_full Limitations of using artificial intelligence services to analyze chest x-ray imaging
title_fullStr Limitations of using artificial intelligence services to analyze chest x-ray imaging
title_full_unstemmed Limitations of using artificial intelligence services to analyze chest x-ray imaging
title_short Limitations of using artificial intelligence services to analyze chest x-ray imaging
title_sort limitations of using artificial intelligence services to analyze chest x ray imaging
topic artificial intelligence
chest x-ray
reproducibility of results
reliability
url https://jdigitaldiagnostics.com/DD/article/viewFile/626310/pdf
work_keys_str_mv AT yuriyavasilev limitationsofusingartificialintelligenceservicestoanalyzechestxrayimaging
AT antonvvladzymyrskyy limitationsofusingartificialintelligenceservicestoanalyzechestxrayimaging
AT kirillmarzamasov limitationsofusingartificialintelligenceservicestoanalyzechestxrayimaging
AT igormshulkin limitationsofusingartificialintelligenceservicestoanalyzechestxrayimaging
AT elenavastapenko limitationsofusingartificialintelligenceservicestoanalyzechestxrayimaging
AT levdpestrenin limitationsofusingartificialintelligenceservicestoanalyzechestxrayimaging