ARTIFICIAL INTELLIGENCE (AI) IN THE DIAGNOSIS OF PATHOLOGIST-CONFIRMED LUNG CANCER: A SYSTEMATIC REVIEW AND A DIAGNOSTIC TEST ACCURACY (DTA) META-ANALYSIS
Keywords:
Artificial Intelligence, Pathologist-Confirmed Lung Cancer, DTAAbstract
Objectives
Lung cancer continues to be the primary cause of cancer-related deaths globally, with early detection essential for enhancing survival rates. Notwithstanding progress in imaging and pathology, existing diagnostic techniques encounter constraints including elevated false-positive rates, inter-observer variability, and difficulties in detecting smaller, early-stage nodules such as ground-glass nodules (GGNs). Artificial Intelligence (AI) provides prospective answers by improving diagnostic accuracy and efficiency. The objective of this study is to assess the efficacy of AI algorithms in diagnosing pathologist-confirmed lung cancer, emphasizing their diagnostic accuracy and potential to transform clinical practice.
Methods
A systematic review and meta-analysis were performed in accordance with PRISMA recommendations. A thorough literature search was conducted utilizing the Cochrane Library and PubMed until May 7, 2025, employing keywords pertinent to lung neoplasms and artificial intelligence. The inclusion criteria targeted research utilizing AI for the diagnosis of lung cancer, emphasizing diagnostic accuracy as the principal outcome. Data were extracted and evaluated for quality, and a meta-analysis was performed using Review Manager version 5.4, utilizing random-effects models to address clinical heterogeneity.
Results
The meta-analysis comprised six investigations with an aggregate sample size of 486 participants. AI methods, including Support Vector Machines, Random Forests, Artificial Neural Networks, and Computer-aided Diagnosis systems, had an overall sensitivity of 79.0% and specificity of 80,2%. The positive predictive value was 68.9%, while the negative predictive value was 87,3%, signifying a high reliability of negative test outcomes. AI algorithms have considerable expertise in diagnosing lung cancer, with the potential to augment early detection and increase patient outcomes. Standardizing AI models and integrating unpublished data may augment the robustness of forthcoming analyses.
Conclusion
AI possesses significant potential to enhance lung cancer diagnosis, providing advantages for both patients and healthcare professionals. Notwithstanding current obstacles, continuous research and development, coupled with meticulous application in clinical settings, may result in substantial progress in the early identification and therapy of cancer.
References
Schabath MB, Aberle DR. MILD trial, strong confirmation of lung cancer screening efficacy. Nat Rev Clin Oncol. 2019 Sep 22;16(9):529–30.
Naidich DP, Marshall CH, Gribbin C, Arams RS, McCauley DI. Low-dose CT of the lungs: preliminary observations. Radiology. 1990 Jun;175(3):729–31.
Nawa T, Nakagawa T, Kusano S, Kawasaki Y, Sugawara Y, Nakata H. Lung Cancer Screening Using Low-Dose Spiral CT. Chest. 2002 Jul;122(1):15–20.
Hubers AJ, Heideman DAM, Duin S, Witte BI, de Koning HJ, Groen HJM, et al. DNA hypermethylation analysis in sputum of asymptomatic subjects at risk for lung cancer participating in the NELSON trial: argument for maximum screening interval of 2 years. J Clin Pathol. 2017 Mar;70(3):250–4.
Zhang L, Pu D, Liu D, Wang Y, Luo W, Tang H, et al. Identification and validation of novel circulating biomarkers for early diagnosis of lung cancer. Lung Cancer. 2019 Sep;135:130–7.
Hirsch FR, Franklin WA, Gazdar AF, Bunn PA. Early detection of lung cancer: clinical perspectives of recent advances in biology and radiology. Clin Cancer Res. 2001 Jan;7(1):5–22.
Hirsch FR, Franklin WA, Gazdar AF, Bunn PA. Early detection of lung cancer: clinical perspectives of recent advances in biology and radiology. Clin Cancer Res. 2001 Jan;7(1):5–22.
Yang D, Liu Y, Bai C, Wang X, Powell CA. Epidemiology of lung cancer and lung cancer screening programs in China and the United States. Cancer Lett. 2020 Jan;468:82–7.
Tammemägi MC, Katki HA, Hocking WG, Church TR, Caporaso N, Kvale PA, et al. Selection Criteria for Lung-Cancer Screening. New England Journal of Medicine. 2013 Feb 21;368(8):728–36.
Setio AAA, Traverso A, de Bel T, Berens MSN, Bogaard C van den, Cerello P, et al. Validation, comparison, and combination of algorithms for automatic detection of pulmonary nodules in computed tomography images: The LUNA16 challenge. Med Image Anal. 2017 Dec;42:1–13.
Hosny A, Aerts HJWL. Artificial intelligence for global health. Science (1979). 2019 Nov 22;366(6468):955–6.
Loverdos K, Fotiadis A, Kontogianni C, Iliopoulou M, Gaga M. Lung nodules: A comprehensive review on current approach and management. Ann Thorac Med. 2019;14(4):226.
Loverdos K, Fotiadis A, Kontogianni C, Iliopoulou M, Gaga M. Lung nodules: A comprehensive review on current approach and management. Ann Thorac Med. 2019;14(4):226.
Han G, Liu X, Zheng G, Wang M, Huang S. Automatic recognition of 3D GGO CT imaging signs through the fusion of hybrid resampling and layer-wise fine-tuning CNNs. Med Biol Eng Comput. 2018 Dec 6;56(12):2201–12.
Chen D, Dai C, Xiermaimaiti K, Mao R, Chen Y, Chen C. New horizons in surgical treatment of ground-glass nodules of the lung: experience and controversies. Ther Clin Risk Manag. 2018 Jan;Volume 14:203–11.
Goo JM, Park CM, Lee HJ. Ground-Glass Nodules on Chest CT as Imaging Biomarkers in the Management of Lung Adenocarcinoma. American Journal of Roentgenology. 2011 Mar;196(3):533–43.
Kochanny SE, Pearson AT. Academics as leaders in the cancer artificial intelligence revolution. Cancer. 2021 Mar 29;127(5):664–71.
Krarup MMK, Krokos G, Subesinghe M, Nair A, Fischer BM. Artificial Intelligence for the Characterization of Pulmonary Nodules, Lung Tumors and Mediastinal Nodes on PET/CT. Semin Nucl Med. 2021 Mar;51(2):143–56.
Tang X. The role of artificial intelligence in medical imaging research. BJR|Open. 2020 Nov;2(1):20190031.
Organization WH. Generating evidence for artificial intelligence-based medical devices: a framework for training, validation and evaluation. In: Generating evidence for artificial intelligence-based medical devices: a framework for training, validation and evaluation. 2021.
Soffer S, Ben-Cohen A, Shimon O, Amitai MM, Greenspan H, Klang E. Convolutional Neural Networks for Radiologic Images: A Radiologist’s Guide. Radiology. 2019 Mar;290(3):590–606.
Bluemke DA, Moy L, Bredella MA, Ertl-Wagner BB, Fowler KJ, Goh VJ, et al. Assessing Radiology Research on Artificial Intelligence: A Brief Guide for Authors, Reviewers, and Readers—From the Radiology Editorial Board. Radiology. 2020 Mar;294(3):487–9.
Zhan Y, Wang Y, Zhang W, Ying B, Wang C. Diagnostic Accuracy of the Artificial Intelligence Methods in Medical Imaging for Pulmonary Tuberculosis: A Systematic Review and Meta-Analysis. J Clin Med. 2022 Dec 30;12(1):303.
Bi WL, Hosny A, Schabath MB, Giger ML, Birkbak NJ, Mehrtash A, et al. Artificial intelligence in cancer imaging: Clinical challenges and applications. CA Cancer J Clin. 2019 Mar 5;69(2):127–57.
S. Alshuhri M, Al-Musawi SG, Al-Alwany AA, Uinarni H, Rasulova I, Rodrigues P, et al. Artificial intelligence in cancer diagnosis: Opportunities and challenges. Pathol Res Pract. 2024 Jan;253:154996.
Chen Z, Lin L, Wu C, Li C, Xu R, Sun Y. Artificial intelligence for assisting cancer diagnosis and treatment in the era of precision medicine. Cancer Commun. 2021 Nov 6;41(11):1100–15.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Maren Irgiwi Fadlilah, Wijaya Hadi Suryanto (Author)
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Authors publishing here keep copyright but grant the journal first publication rights, under a Creative Commons Attribution-NonCommercial 4.0 License. They can distribute their work non-exclusively elsewhere with an acknowledgment of its first publication in this journal. Posting the work online before and during submission for earlier and greater citation is encouraged, reflecting Open Access benefits.
