AI could save chest x-ray interpretation time of radiologists
A new study found that using artificial intelligence improved the efficacy of radiologists by shortening the reading times of chest radiographs for radiologists. The study results were published in the journal npj Digital Medicine.
Artificial intelligence (AI) has been used extensively for radiology research, and as commercial AI software has grown in popularity, more attempts have been made to show the program's effectiveness in real-world applications due to clinical necessity. Previous literature showed that integrating AI into mammography, brain computed tomography (CT), and the detection of bone fractures has improved the diagnostic performance of radiologists. As chest radiographs are the most commonly performed imaging studies, timely interpretation of critical lesions is quite necessary. Research has shown that the application of AI for CXR has affected the reading times and workload of radiologists. As there is uncertainty on how it affects, researchers have conducted a study to observe how AI affects the actual reading times of radiologists in the daily interpretation of CXRs in real-world clinical practice.
The reading times of radiologists' CXR interpretations were gathered from September to December 2021 with their consent. The same radiologist measured reading time as the amount of time, measured in seconds, between opening CXRs and transcribing the picture. The radiologists were able to consult the findings of commercial AI software for two months (the AI-aided phase) since it was incorporated for all CXRs. The radiologists were automatically rendered blind to the AI outcomes for the next two months (AI-unaided period).
Key findings:
- A total of 11 radiologists participated, and 18,680 CXRs were included.
- Using AI significantly reduced the total reading times, compared to no use (13.3 s vs. 14.8 s, p < 0.001).
- When there was no abnormality detected by AI, reading times were shorter with AI use (mean 10.8 s vs. 13.1 s, p < 0.001).
- Reading times did not differ according to AI use despite any abnormality detected by AI (mean 18.6 s vs. 18.4 s, p = 0.452).
- Reading times increased as abnormality scores increased, and a more significant increase was observed with AI use (coefficient 0.09 vs. 0.06, p < 0.001).
Thus, the use of AI could significantly reduce reading times and also increase efficacy.
Further reading: Shin, H.J., Han, K., Ryu, L. et al. The impact of artificial intelligence on the reading times of radiologists for chest radiographs. npj Digit. Med. 6, 82 (2023). https://doi.org/10.1038/s41746-023-00829-4
Disclaimer: This website is primarily for healthcare professionals. The content here does not replace medical advice and should not be used as medical, diagnostic, endorsement, treatment, or prescription advice. Medical science evolves rapidly, and we strive to keep our information current. If you find any discrepancies, please contact us at corrections@medicaldialogues.in. Read our Correction Policy here. Nothing here should be used as a substitute for medical advice, diagnosis, or treatment. We do not endorse any healthcare advice that contradicts a physician's guidance. Use of this site is subject to our Terms of Use, Privacy Policy, and Advertisement Policy. For more details, read our Full Disclaimer here.
NOTE: Join us in combating medical misinformation. If you encounter a questionable health, medical, or medical education claim, email us at factcheck@medicaldialogues.in for evaluation.