Analysis of electronic medical records using artificial intelligence technologies for lung cancer screening group identification: a systematic review of clinical studies

Background. Lung cancer remains one of the leading causes of mortality, with early detection significantly improving prognosis. Modern approaches require new solutions for more effective screening patient selection.

Aim. To conduct a systematic review of studies applying artificial intelligence (AI) for analyzing socio-demographic data and routine laboratory tests to optimize patient selection for screening and pathology classification.

Materials and methods. A literature search (2014–2024) was conducted in databases including PubMed, ResearchGate, and Scopus. Included studies analyzed the use of AI for lung cancer risk prediction based on sociodemographic data and medical records.

Results. The analysis identified 5 studies of AI-based models that were applied to select candidates for lung cancer screening. Age, smoking, chronic lung disease, and BMI were the most frequently used factors in the AI models. The models demonstrated high sensitivity (up to 92,7 %) and area under the receiver operating characteristic (up to 0.90). The results confirmed that AI can improve the accuracy of patient selection for screening compared to traditional methods.

Conclusion. AI application for lung cancer risk prediction shows substantial potential, especially with combined use of socio-demographic and medical record data. Further studies are needed to improve models and evaluate their clinical impact.

1. Ferlay J., Ervik M., Lam F. et al. Global Cancer Observatory: Cancer Today. Lyon: International Agency for Research on Cancer, 2024. URL: https://gco.iarc.who.int/today.

2. State of oncological care for the population of Russia in 2023. Kaprin A.D., Starinskiy V.V., Shakhzadova A.O., eds. Moscow: MNIOI im. P.A. Gertsena – filial FGBU “NMITS radiologii” Minzdrava Rossii, 2024. 262 p. (In Russ.).

3. Malignant neoplasms in Russia in 2023 (incidence and mortality). Kaprin A.D. et al., eds. Moscow: MNIOI im. P.A. Gertsena – filial FGBU “NMITS radiologii” Minzdrava Rossii, 2024. 276 p. (In Russ.).

4. Toumazis I., Bastani M., Han S.S. et al. Risk-based lung cancer screening: a systematic review. Lung Cancer 2020;147:154–86. DOI: 10.1016/j.lungcan.2020.07.007

5. Koski E., Murphy J. AI in healthcare. Stud Health Technol Inform 2021;284:295–9. DOI: 10.3233/SHTI210619

6. Thong L.T., Chou H.S., Chew H.S.J. et al. Diagnostic test accuracy of artificial intelligence-based imaging for lung cancer screening: a systematic review and meta-analysis. Lung Cancer 2023;176:4–13. DOI: 10.1016/j.lungcan.2022.12.002

7. Hsu Y.C., Tsai Y.H., Weng H.H. et al. Artificial neural networks improve LDCT lung cancer screening: a comparative validation study. BMC Cancer 2020;20(1):1023. DOI: 10.1186/s12885-020-07465-1

8. Chauvie S., De Maggi A., Baralis I. et al. Artificial intelligence and radiomics enhance the positive predictive value of digital chest tomosynthesis for lung cancer detection within SOS clinical trial. Eur Radiol 2020;30(7):4134–40. DOI: 10.1007/s00330-020-06783-z

9. Bach P.B., Kattan M.W., Thornquist M.D. et al. Variations in lung cancer risk among smokers. J Natl Cancer Inst 2003;95(6):470–8. DOI: 10.1093/jnci/95.6.470

10. Tammemägi M.C., Katki H.A., Hocking W.G. et al. Selection criteria for lung-cancer screening. N Engl J Med 2013;368(8):728–36. DOI:10.1056/NEJMoa1211776

11. Katki H.A., Kovalchik S.A., Berg C.D. et al. Development and validation of risk models to select ever-smokers for CT lung cancer screening. JAMA 2016;315(21):2300–11. DOI:10.1001/jama.2016.6255

12. Cheung L.C., Berg C.D., Castle P E. et al. Life-gained-based versus risk-based selection of smokers for lung cancer screening. Ann Intern Med 2019;171(9):623–32. DOI:10.7326/M19-1263

13. Markaki M., Tsamardinos I., Langhammer A. et al. A validated clinical risk prediction model for lung cancer in smokers of all ages and exposure types: a HUNT study. EBioMedicine 2018;31:36–46. DOI: 10.1016/j.ebiom.2022.104187

14. Field J.K., Vulkan D., Davies M.P.A. et al. Liverpool Lung Project lung cancer risk stratification model: calibration and prospective validation. Thorax 2021;76(2):161–8. DOI: 10.1136/thoraxjnl-2020-215158

15. PLCO Lung dataset(s). In: Book PLCO Lung dataset(s). Ed. NIH NCI, 2024. URL: https://cdas.cancer.gov/datasets/plco/21/

16. NLST dataset(s). In: Book NLST dataset(s). Ed. NIH NCI, 2024. URL: https://cdas.cancer.gov/datasets/nlst/

17. Tammemägi M.C., Schmidt H., Martel S. et al. Participant selection for lung cancer screening by risk modelling (the Pan-Canadian Early Detection of Lung Cancer [PanCan] study): a single-arm, prospective study. Lancet Oncol 2017;18(11):1523–31. DOI: 10.1016/S1470-2045(17)30597-1

18. NHIS Data, Questionnaires and Related Documentation. In: Book NHIS Data, Questionnaires and Related Documentation. Ed. CDC, 2024.

19. Marshall R.C., Tiglao S.M., Thiel D. Updated USPSTF screening guidelines may reduce lung cancer deaths. J Fam Pract 2021;70(7):347–9. DOI: 10.12788/jfp.0257

20. Wang X., Zhang Y., Hao S. et al. Prediction of the 1-year risk of incident lung cancer: prospective study using electronic health records from the State of Maine. J Med Internet Res 2019;21(5):e13260. DOI: 10.2196/23586

21. Yeh M.C., Wang Y.H., Yang H.C. et al. Artificial intelligencebased prediction of lung cancer risk using nonimaging electronic medical records: deep learning approach. J Med Internet Res 2021;23(8):e26256. DOI: 10.2196/33519

22. Chandran U., Reps J., Yang R. et al. Machine learning and real-world data to predict lung cancer risk in routine care. Cancer Epidemiol Biomarkers Prev 2023;32(3):337–43. DOI: 10.1158/1055-9965.EPI-22-0873

23. Levi M., Lazebnik T., Kushnir S. et al. Machine learning computational model to predict lung cancer using electronic medical records. Cancer Epidemiol 2024;92:102631. DOI: 10.1016/j.canep.2024.102649

24. Zhang S., Yang L., Xu W. et al. Predicting the risk of lung cancer using machine learning: A large study based on UK Biobank. Medicine (Baltimore) 2024;103(16):e37879. DOI: 10.1097/MD.0000000000037879