Detecting new lung cancer cases using artificial intelligence: clinical and economic evaluation of a retrospective analysis of computed tomography scans 2 years after the COVID-19 pandemic
Bibliographic record
Abstract
BACKGROUND: Chest computed tomography (CT) is the main modality used to diagnose lung lesions caused by COVID-19 infection. Since 2020, the use of this modality in the Krasnoyarsk krai has increased. However, the incidence of lung cancer decreased by 5.2%. The current situation has raised concerns about missing radiographic signs typical of lung cancer and has stimulated the search for new diagnostic modalities using artificial intelligence (AI) for data analysis. AIM: The aim of the study was to evaluate the feasibility of using an AI algorithm to search for lung nodules based on chest CT data obtained during the COVID-19 pandemic to identify lung cancer. MATERIALS AND METHODS: The retrospective study included chest CT scans of patients from Krasnoyarsk krai diagnosed with COVID-19 reported in the PACS base between 1 November 2020 and 28 February 2021. The interval between chest CT and AI analysis ranged from two years and one month to two years and five months. Chest-IRA algorithm was used. AI detected lung nodules with a volume greater than 100 mm3. The radiologists divided the results into three groups based on the potential for lung cancer. The assessment of the economic benefits of using the AI algorithm considered the cost of wages and savings in the treatment of early stage lung cancer, which affects gross regional product. RESULTS: The AI algorithm identified nodules in 484 out of 10,500 CT scans. A total of 192 patients with a high potential for lung cancer, 103 with no signs and 60 with inconclusive signs were identified, and 112 patients with a high and moderate potential for lung cancer did not seek medical care. AI confirmed 100 (28.2%) histologically proven cases of lung cancer, with stages I–II detected in 35%. Using AI instead of radiologists would save 25 months and 4 days of work, which is equal to 2 million 430 thousand rubles. Expected budget savings due to early detection of lung cancer vary from 10 million 600 thousand to 12 million 500 thousand rubles for each 10,500 CTs. The total economic effect for a five year period would be from 259 million 400 thousand rubles to 305 million 100 thousand rubles. CONCLUSIONS: The use of AI to evaluate chest CT scans demonstrates high performance in identifying lung nodules, including those in patients with COVID-19, confirming its potential use for early detection of incidental lung nodules that might otherwise be missed.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.009 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.003 | 0.002 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".