Back

A diagnostic and economic evaluation of the complex artificial intelligence algorithm aimed to detect 10 pathologies on the chest CT images

Chernina, V. Y.; Belyaev, M. G.; Silin, A. Y.; Avetisov, I. O.; Pyatnitskiy, I. A.; Petrash, E. A.; Basova, M. V.; Sinitsyn, V. E.; Omelyanovskiy, V. V.; Gombolevskiy, V. A.

2023-04-25 radiology and imaging
10.1101/2023.04.19.23288584
Show abstract

BackgroundArtificial intelligence (AI) technologies can help solve the significant problem of missed findings in radiology studies. An important issue is assessing the economic benefits of implementing AI. Aimto evaluate the frequency of missed pathologies detection and the economic potential of AI technology for chest CT, validated by expert radiologists, compared with radiologists without access to AI in a private medical center. MethodsAn observational, single-center retrospective study was conducted. The study included chest CTs without IV contrast performed from 01.06.2022 to 31.07.2022 in "Yauza Hospital" LLC, Moscow. The CTs were processed using a complex AI algorithm for ten pathologies: pulmonary infiltrates, typical for viral pneumonia (COVID-19 in pandemic conditions); lung nodules; pleural effusion; pulmonary emphysema; thoracic aortic dilatation; pulmonary trunk dilatation; coronary artery calcification; adrenal hyperplasia; osteoporosis (vertebral body height and density changes). Two experts analyzed CTs and compared results with AI. Further routing was determined according to clinical guidelines for all findings initially detected and missed by radiologists. The lost potential revenue (LPR) was calculated for each patient according to the hospital price list. ResultsFrom the final 160 CTs, the AI identified 90 studies (56%) with pathologies, of which 81 studies (51%) were missing at least one pathology in the report. The "second-stage" LPR for all pathologies from 81 patients was RUB 2,847,760 ($37,251 or CNY 256,218). LPR only for those pathologies missed by radiologists but detected by AI was RUB 2,065,360 ($27,017 or CNY 185,824). ConclusionUsing AI for chest CTs as an "assistant" to the radiologist can significantly reduce the number of missed abnormalities. AI usage can bring 3.6 times more benefits compared to the standard model without AI. The use of complex AI for chest CT can be cost-effective.

Matching journals

The top 5 journals account for 50% of the predicted probability mass.

1
European Radiology
○ based on 11 papers
Top 0.1%
18.3%
2
PLOS ONE
● based on 1737 papers
Top 36%
13.5%
3
Scientific Reports
○ based on 701 papers
Top 13%
11.0%
4
Annals of Translational Medicine
○ based on 14 papers
Top 0.2%
6.3%
5
Diagnostics
○ based on 36 papers
Top 0.3%
5.7%
50% of probability mass above
6
Journal of Clinical Medicine
○ based on 77 papers
Top 2%
5.4%
7
Cureus
○ based on 64 papers
Top 6%
2.6%
8
Heliyon
○ based on 57 papers
Top 2%
2.6%
9
Archives of Clinical and Biomedical Research
○ based on 18 papers
Top 0.3%
2.5%
10
Journal of Magnetic Resonance Imaging
○ based on 10 papers
Top 1%
1.9%
11
Brain and Behavior
○ based on 19 papers
Top 2%
1.4%
12
Medicine
○ based on 29 papers
Top 5%
1.4%
13
Computers in Biology and Medicine
○ based on 39 papers
Top 5%
1.3%
14
Frontiers in Medicine
○ based on 99 papers
Top 14%
1.3%
15
PeerJ
◐ based on 46 papers
Top 7%
1.3%
16
Informatics in Medicine Unlocked
○ based on 11 papers
Top 2%
1.3%
17
JMIR Medical Informatics
◐ based on 16 papers
Top 4%
0.9%
18
Nature Medicine
○ based on 88 papers
Top 14%
0.9%
19
Frontiers in Oncology
○ based on 34 papers
Top 5%
0.9%
20
PLOS Digital Health
● based on 88 papers
Top 11%
0.9%
21
Stroke: Vascular and Interventional Neurology
○ based on 12 papers
Top 1%
0.9%
22
Nature Communications
○ based on 483 papers
Top 38%
0.9%
23
JMIRx Med
◐ based on 29 papers
Top 5%
0.9%
24
BMJ Open
● based on 553 papers
Top 51%
0.7%
25
Frontiers in Artificial Intelligence
○ based on 11 papers
Top 2%
0.7%