Diagnostic value of combined CT artificial intelligence (AI) system and lung cancer biomarkers in pulmonary nodule evaluation

Lile Wang; Shuying You; Jianyi Zhou; Mo Liang; Ruicheng Hu; Lile Wang; Shuying You; Jianyi Zhou; Mo Liang; Ruicheng Hu

doi:10.3934/publichealth.2025059

AIMS Public Health

2025, Volume 12, Issue 4: 1157-1171. doi: 10.3934/publichealth.2025059

Previous Article Next Article

Research article

Diagnostic value of combined CT artificial intelligence (AI) system and lung cancer biomarkers in pulmonary nodule evaluation

1.
Department of Respiratory Medicine, Hunan Provincial People's Hospital, The First Affiliated Hospital of Hunan Normal University, Changsha 410016, China
2.
Department of Respiratory Medicine, The Second People's Hospital of Hunan Province, Brain Hospital of Hunan Province, Changsha 412007, China

Received: 01 August 2025 Revised: 29 October 2025 Accepted: 12 November 2025 Published: 15 December 2025

Objective
To analyze the diagnostic value of a Computed Tomography (CT) artificial intelligence (AI) system combined with lung cancer biomarkers for pulmonary nodules.
Methods
A retrospective analysis was conducted on 200 patients with pulmonary nodules treated at our hospital from February 2021 to January 2025. Based on pathological results, patients were divided into a benign group and a malignant group. The two groups were compared in terms of baseline data and lung cancer biomarkers, including carcinoembryonic antigen (CEA), neuron-specific enolase (NSE), cytokeratin 19 fragment 21–1 (CYFRA 21–1), squamous cell carcinoma antigen (SCCA), and pro-gastrin-releasing peptide (ProGRP). The sensitivity, specificity, accuracy, misdiagnosis rate, and missed diagnosis rate of the CT/AI system alone and in combination with lung cancer biomarkers were analyzed.
Results
There were no statistically significant differences between the benign group (134 cases) and malignant group (66 cases) regarding sex, lobulation sign, spiculation sign, solitary pulmonary nodule (SPN), or mean CT value (P > 0.05). However, the benign group had significantly lower age, years of smoking, chronic lung disease, pure ground-glass nodules (pGGN), nodule diameter, irregular nodules, bronchial changes, and vascular changes compared to the malignant group (P < 0.05). Levels of CEA, NSE, CYFRA 21–1, SCCA, and ProGRP were also significantly lower in the benign group than in the malignant group (P < 0.05). Taking pathology as the reference standard, the CT/AI system alone had a sensitivity of 71.21% (47/66), specificity of 85.07% (114/134), accuracy of 80.50% (161/200), misdiagnosis rate of 19.50% (39/200), and missed diagnosis rate of 28.79% (19/66). In contrast, the CT/AI system combined with lung cancer biomarkers had a sensitivity of 92.42% (61/66), specificity of 93.28% (125/134), accuracy of 93.00% (186/200), misdiagnosis rate of 7.00% (14/200), and missed diagnosis rate of 7.58% (5/66), with all diagnostic parameters significantly improved compared with the CT/AI system alone (P < 0.05). Logistic regression analysis showed that age, smoking for >20 years, chronic lung disease, nodule diameter, irregular nodules, bronchial changes, vascular changes, NSE, CYFRA 21–1, and SCCA were all risk factors for malignant pulmonary nodules (P < 0.05). Receiver operating characteristic (ROC) curve analysis demonstrated that age, nodule type, chronic lung disease, nodule morphology, bronchial changes, and vascular changes had modest value for predicting malignant pulmonary nodules, with AUCs of 0.586, 0.750, 0.707, 0.601, 0.580, and 0.565, respectively. Smoking, nodule diameter, CEA, NSE, CYFRA 21–1, SCCA, and ProGRP had better predictive value, with AUCs of 0.840, 0.944, 0.958, 0.922, 0.856, 0.978, and 0.990, respectively. The combined diagnosis of all indicators achieved an AUC of 0.993.
Conclusion
The CT/AI system combined with lung cancer biomarkers demonstrates high sensitivity and specificity in diagnosing the nature of pulmonary nodules. Moreover, the occurrence of malignant pulmonary nodules is significantly associated with factors such as age, smoking, and chronic lung disease.
- CT/AI system,
- lung cancer biomarkers,
- pulmonary nodules,
- sensitivity,
- specificity
Citation: Lile Wang, Shuying You, Jianyi Zhou, Mo Liang, Ruicheng Hu. Diagnostic value of combined CT artificial intelligence (AI) system and lung cancer biomarkers in pulmonary nodule evaluation[J]. AIMS Public Health, 2025, 12(4): 1157-1171. doi: 10.3934/publichealth.2025059

Related Papers:

Abstract

Objective

To analyze the diagnostic value of a Computed Tomography (CT) artificial intelligence (AI) system combined with lung cancer biomarkers for pulmonary nodules.

Methods

A retrospective analysis was conducted on 200 patients with pulmonary nodules treated at our hospital from February 2021 to January 2025. Based on pathological results, patients were divided into a benign group and a malignant group. The two groups were compared in terms of baseline data and lung cancer biomarkers, including carcinoembryonic antigen (CEA), neuron-specific enolase (NSE), cytokeratin 19 fragment 21–1 (CYFRA 21–1), squamous cell carcinoma antigen (SCCA), and pro-gastrin-releasing peptide (ProGRP). The sensitivity, specificity, accuracy, misdiagnosis rate, and missed diagnosis rate of the CT/AI system alone and in combination with lung cancer biomarkers were analyzed.

Results

There were no statistically significant differences between the benign group (134 cases) and malignant group (66 cases) regarding sex, lobulation sign, spiculation sign, solitary pulmonary nodule (SPN), or mean CT value (P > 0.05). However, the benign group had significantly lower age, years of smoking, chronic lung disease, pure ground-glass nodules (pGGN), nodule diameter, irregular nodules, bronchial changes, and vascular changes compared to the malignant group (P < 0.05). Levels of CEA, NSE, CYFRA 21–1, SCCA, and ProGRP were also significantly lower in the benign group than in the malignant group (P < 0.05). Taking pathology as the reference standard, the CT/AI system alone had a sensitivity of 71.21% (47/66), specificity of 85.07% (114/134), accuracy of 80.50% (161/200), misdiagnosis rate of 19.50% (39/200), and missed diagnosis rate of 28.79% (19/66). In contrast, the CT/AI system combined with lung cancer biomarkers had a sensitivity of 92.42% (61/66), specificity of 93.28% (125/134), accuracy of 93.00% (186/200), misdiagnosis rate of 7.00% (14/200), and missed diagnosis rate of 7.58% (5/66), with all diagnostic parameters significantly improved compared with the CT/AI system alone (P < 0.05). Logistic regression analysis showed that age, smoking for >20 years, chronic lung disease, nodule diameter, irregular nodules, bronchial changes, vascular changes, NSE, CYFRA 21–1, and SCCA were all risk factors for malignant pulmonary nodules (P < 0.05). Receiver operating characteristic (ROC) curve analysis demonstrated that age, nodule type, chronic lung disease, nodule morphology, bronchial changes, and vascular changes had modest value for predicting malignant pulmonary nodules, with AUCs of 0.586, 0.750, 0.707, 0.601, 0.580, and 0.565, respectively. Smoking, nodule diameter, CEA, NSE, CYFRA 21–1, SCCA, and ProGRP had better predictive value, with AUCs of 0.840, 0.944, 0.958, 0.922, 0.856, 0.978, and 0.990, respectively. The combined diagnosis of all indicators achieved an AUC of 0.993.

Conclusion

The CT/AI system combined with lung cancer biomarkers demonstrates high sensitivity and specificity in diagnosing the nature of pulmonary nodules. Moreover, the occurrence of malignant pulmonary nodules is significantly associated with factors such as age, smoking, and chronic lung disease.

Ethical approval

This study was approved by the Ethics Committee of Hunan Provincial People's Hospital (The First Affiliated Hospital of Hunan Normal University), approval number 202577.

Funding

This study was supported by the following funding sources: Hunan Provincial Natural Science Foundation (2023JJ40380), Hunan Provincial Health Commission Project (202203022853), Hunan Provincial Clinical medical technology innovation guide project (2021SK50807), Huxiang Young Talent Support Program (2020RC3068), and Hunan Provincial People's Hospital Ren Shu Fund Project (RS202104).

Authors' contributions

Lile Wang was responsible for drafting and revising the manuscript. Shuying You was responsible for formatting and editing the manuscript. Jianyi Zhou was responsible for collecting the research data. Mo Liang was responsible for preparing the manuscript figures. Ruicheng Hu was responsible for designing the study.

Conflict of interest

The authors have no commercial or other associations that might pose a conflict of interest.

References

[1]	Huang G, Wei X, Tang H, et al. (2021) A systematic review and meta-analysis of diagnostic performance and physicians' perceptions of artificial intelligence (AI)-assisted CT diagnostic technology for the classification of pulmonary nodules. J Thorac Dis 13: 4797-4811. https://doi.org/10.21037/jtd-21-810
[2]	Chen D, Yang L, Zhang W, et al. (2024) Prevalence and management of pulmonary nodules: a systematic review and meta-analysis. J Thorac Dis 16: 4619-4632. https://doi.org/10.21037/jtd-24-874
[3]	Weir-McCall JR, Joyce S, Clegg A, et al. (2020) Dynamic contrast-enhanced computed tomography for the diagnosis of solitary pulmonary nodules: a systematic review and meta-analysis. Eur Radiol 30: 3310-3323. https://doi.org/10.1007/s00330-020-06661-8
[4]	Vindum HH, Kristensen K, Christensen NL, et al. (2023) Outcome of Incidental Pulmonary Nodules in a Real-World Setting. Clin Lung Cancer 24: 673-681. https://doi.org/10.1016/j.cllc.2023.09.003
[5]	Tandon YK, Bartholmai BJ, Koo CW (2020) Putting artificial intelligence (AI) on the spot: machine learning evaluation of pulmonary nodules. J Thorac Dis 12: 6954-6965. https://doi.org/10.21037/jtd-2019-cptn-03
[6]	de Margerie-Mellon C, Chassagnon G (2023) Artificial intelligence: A critical review of applications for lung nodule and lung cancer. Diagn Interv Imaging 104: 11-17. https://doi.org/10.1016/j.diii.2022.11.007
[7]	Gan T, An W, Long Y, et al. (2024) Correlation between carcinoembryonic antigen (CEA) expression and EGFR mutations in non-small-cell lung cancer: a meta-analysis. Clin Transl Oncol 26: 991-1000. https://doi.org/10.1007/s12094-023-03339-7
[8]	Liu D, Wu D, Ni J, et al. (2025) NSE and ProGRP Are Promising Markers for Diagnosis, Efficacy Evaluation, Follow-Up Monitoring, and Prognosis of Small Cell Esophageal Carcinoma. Thorac Cancer 16: e70026. https://doi.org/10.1111/1759-7714.70026
[9]	Bi H, Yin L, Fang W, et al. (2023) Association of CEA, NSE, CYFRA 21–1, SCC-Ag, and ProGRP with Clinicopathological Characteristics and Chemotherapeutic Outcomes of Lung Cancer. Lab Med 54: 372-379. https://doi.org/10.1093/labmed/lmac122
[10]	Muley T, Herth FJ, Heussel CP, et al. (2024) Prognostic value of tumor markers ProGRP, NSE and CYFRA 21–1 in patients with small cell lung cancer and chemotherapy-induced remission. Tumour Biol 46: S219-S232. https://doi.org/10.3233/TUB-230016
[11]	Chinese Thoracic Society.Chinese expert consensus on diagnosis of early lung cancer (2023 Edition). Zhonghua Jie He He Hu Xi Za Zhi (2023) 46: 1-18. https://doi.org/10.3760/cma.j.cn112147-20220712-00592
[12]	Graham RN, Baldwin DR, Callister ME, et al. (2016) Return of the pulmonary nodule: the radiologist's key role in implementing the 2015 BTS guidelines on the investigation and management of pulmonary nodules. Br J Radiol 89: 20150776. https://doi.org/10.1259/bjr.20150776
[13]	Chinese Thoracic Society, Chinese Medical Association, Chinese Alliance Against Lung Cancer Expert Group.Chinese expert consensus on diagnosis and treatment of pulmonary nodules (2024). Zhonghua Jie He He Hu Xi Za Zhi (2024) 47: 716-729. https://doi.org/10.3760/cma.j.cn112147-20231109-00300
[14]	Barta JA, Farjah F, Thomson CC, et al. (2024) The American Cancer Society National Lung Cancer Roundtable strategic plan: Optimizing strategies for lung nodule evaluation and management. Cancer 130: 4177-4187. https://doi.org/10.1002/cncr.35181
[15]	Wulaningsih W, Villamaria C, Akram A, et al. (2024) Deep Learning Models for Predicting Malignancy Risk in CT-Detected Pulmonary Nodules: A Systematic Review and Meta-analysis. Lung 202: 625-636. https://doi.org/10.1007/s00408-024-00706-1
[16]	Liu D, Zhao Y, Liu B (2024) The effectiveness of deep learning model in differentiating benign and malignant pulmonary nodules on spiral CT. Technol Health Care 32: 5129-5140. https://doi.org/10.3233/THC-241079
[17]	van den Berk IAH, Jacobs C, Kanglie MMNP, et al. (2024) An AI deep learning algorithm for detecting pulmonary nodules on ultra-low-dose CT in an emergency setting: a reader study. Eur Radiol Exp 8: 132. https://doi.org/10.1186/s41747-024-00518-1
[18]	Pei Q, Luo Y, Chen Y, et al. (2022) Artificial intelligence in clinical applications for lung cancer: diagnosis, treatment and prognosis. Clin Chem Lab Med 60: 1974-1983. https://doi.org/10.1515/cclm-2022-0291
[19]	Prosper AE, Kammer MN, Maldonado F, et al. (2023) Expanding Role of Advanced Image Analysis in CT-detected Indeterminate Pulmonary Nodules and Early Lung Cancer Characterization. Radiology 309: e222904. https://doi.org/10.1148/radiol.222904
[20]	Murchison JT, Ritchie G, Senyszak D, et al. (2022) Validation of a deep learning computer aided system for CT based lung nodule detection, classification, and growth rate estimation in a routine clinical population. PLoS One 17: e0266799. https://doi.org/10.1371/journal.pone.0266799
[21]	Ziyad SR, Radha V, Vayyapuri T (2020) Overview of Computer Aided Detection and Computer Aided Diagnosis Systems for Lung Nodule Detection in Computed Tomography. Curr Med Imaging Rev 16: 16-26. https://doi.org/10.2174/1573405615666190206153321
[22]	Takahashi EA, Koo CW, White DB, et al. (2018) Prospective Pilot Evaluation of Radiologists and Computer-aided Pulmonary Nodule Detection on Ultra-low-Dose CT With Tin Filtration. J Thorac Imaging 33: 396-401. https://doi.org/10.1097/RTI.0000000000000348
[23]	Kuo YS, Zheng MY, Huang MF, et al. (2020) Association of Divergent Carcinoembryonic Antigen Patterns and Lung Cancer Progression. Sci Rep 10: 2066. https://doi.org/10.1038/s41598-020-59031-1
[24]	Holdenrieder S, Wehnl B, Hettwer K, et al. (2017) Carcinoembryonic antigen and cytokeratin-19 fragments for assessment of therapy response in non-small cell lung cancer: a systematic review and meta-analysis. Br J Cancer 116: 1037-1045. https://doi.org/10.1038/bjc.2017.45
[25]	Mueller R, Yasmin-Karim S, DeCosmo K, et al. (2020) Increased carcinoembryonic antigen expression on the surface of lung cancer cells using gold nanoparticles during radiotherapy. Phys Med 27: 236-242. https://doi.org/10.1016/j.ejmp.2020.06.024
[26]	Rumende CM, Sugianto GCK, Rinaldi I, et al. (2020) The Association of Carcinoembryonic Antigen and Cytokeratin-19 Fragments 21–1 Levels with One-Year Survival of Advanced Non-Small Cell Lung Carcinoma at Cipto Mangunkusumo Hospital: A Retrospective Cohort Study. Acta Med Indones 52: 140-146.
[27]	Gao J, Zhang L, Peng K, et al. (2022) Diagnostic value of serum tumor markers CEA, CYFRA21-1, SCCAg, NSE and ProGRP for lung cancers of different pathological types. Nan Fang Yi Ke Da Xue Xue Bao 42: 886-891. https://doi.org/10.12122/j.issn.1673-4254.2022.06.12
[28]	Trulson I, Klawonn F, von Pawel J, et al. (2024) Improvement of differential diagnosis of lung cancer by use of multiple protein tumor marker combinations. Tumour Biol 46: S81-S98. https://doi.org/10.3233/TUB-230021
[29]	Hou X, Wu M, Chen J, et al. (2024) Establishment and verification of a prediction model based on clinical characteristics and computed tomography radiomics parameters for distinguishing benign and malignant pulmonary nodules. J Thorac Dis 16: 1984-1995. https://doi.org/10.21037/jtd-23-1400
[30]	Wang C, Shao J, He Y, et al. (2024) Data-driven risk stratification and precision management of pulmonary nodules detected on chest computed tomography. Nat Med 30: 3184-3195. https://doi.org/10.1038/s41591-024-03211-3
[31]	Kudo Y, Nakamura T, Matsubayashi J, et al. (2024) AI-driven Characterization of Solid Pulmonary Nodules on CT Imaging for Enhanced Malignancy Prediction in Small-sized Lung Adenocarcinoma. Clin Lung Cancer 25: 431-439. https://doi.org/10.1016/j.cllc.2024.04.015
[32]	Kong D, Zhang J, Shan W, et al. (2022) Evaluation of Radiomics Models Based on Computed Tomography for Distinguishing Between Benign and Malignant Thyroid Nodules. J Comput Assist Tomogr 46: 978-985. https://doi.org/10.1097/RCT.0000000000001352
[33]	Liu A, Wang Z, Yang Y, et al. (2020) Preoperative diagnosis of malignant pulmonary nodules in lung cancer screening with a radiomics nomogram. Cancer Commun (Lond) 40: 16-24. https://doi.org/10.1002/cac2.12002
[34]	Liu Y, Dai S, Liu Z, et al. (2024) Serum tumor markers and outcomes in lung cancer patients with brain metastases: a retrospective longitudinal cohort study. Transl Lung Cancer Res 13: 2282-2295. https://doi.org/10.21037/tlcr-24-404
[35]	Yang X, Xiao Y, Zhou Y, et al. (2023) Dynamic monitoring of serum tumor markers as prognostic factors in patients with advanced non-small-cell lung cancer treated with first-line immunotherapy: a multicenter retrospective study. Ther Adv Med Oncol 31: 17588359231206282. https://doi.org/10.1177/17588359231206282
[36]	Arzamasov K, Vasilev Y, Zelenova M, et al. (2024) Independent evaluation of the accuracy of 5 artificial intelligence software for detecting lung nodules on chest X-rays. Quant Imaging Med Surg 14: 5288-5303. https://doi.org/10.21037/qims-24-160
[37]	Kirshenboim Z, Gilat EK, Carl L, et al. (2024) Retrospectively assessing evaluation and management of artificial-intelligence detected nodules on uninterpreted chest radiographs in the era of radiologists shortage. Eur J Radiol 170: 111241. https://doi.org/10.1016/j.ejrad.2023.111241
[38]	Takamatsu A, Ueno M, Yoshida K, et al. (2024) Performance of artificial intelligence-based software for the automatic detection of lung lesions on chest radiographs of patients with suspected lung cancer. Jpn J Radiol 42: 291-299. https://doi.org/10.1007/s11604-023-01503-1
[39]	Peeters D, Alves N, Venkadesh KV, et al. (2024) Enhancing a deep learning model for pulmonary nodule malignancy risk estimation in chest CT with uncertainty estimation. Eur Radiol 34: 6639-6651. https://doi.org/10.1007/s00330-024-10714-7
[40]	Liu B, Chi W, Li X, et al. (2020) Evolving the pulmonary nodules diagnosis from classical approaches to deep learning-aided decision support: three decades' development course and future prospect. J Cancer Res Clin Oncol 146: 153-185. https://doi.org/10.1007/s00432-019-03098-5
[41]	Li J, Zhou L, Zhan Y, et al. (2022) How does the artificial intelligence-based image-assisted technique help physicians in diagnosis of pulmonary adenocarcinoma? A randomized controlled experiment of multicenter physicians in China. J Am Med Inform Assoc 29: 2041-2049. https://doi.org/10.1093/jamia/ocac179

Reader Comments

Your name:*

Email:*
© 2025 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)