Keywords
Assisted diagnostic system
Digestive system tumors
Diagnosis and treatment effect
Diagnostic accuracy
Submitted : 2025-12-11
Accepted : 2025-12-26
Published : 2026-01-10
Abstract
Objective: To explore the application effect of an artificial intelligence (AI)-assisted diagnostic system in the clinical diagnosis and treatment of digestive system tumors (including gastric cancer, colorectal cancer, liver cancer, etc.), providing evidence-based support for improving the efficiency and accuracy of diagnosis and treatment of digestive system tumors. Methods: A total of 200 patients with digestive system tumors admitted to our hospital from January 2022 to December 2024 were selected and divided into an observation group (n = 100, receiving AI-assisted diagnosis combined with conventional diagnosis and treatment) and a control group (n = 100, receiving conventional diagnosis and treatment) according to the random number table method. The differences in diagnostic and treatment indicators between the two groups were compared. Results: The diagnostic time in the observation group was 18.25 ± 3.68 minutes, significantly shorter than that in the control group (35.72 ± 5.14 minutes) (t = 25.36, P < 0.001). The missed diagnosis rate and misdiagnosis rate in the observation group were 2.00% (2/100) and 1.00% (1/100), respectively, significantly lower than those in the control group [8.00% (8/100) and 7.00% (7/100), respectively] (χ2 = 4.01, 5.03, both P < 0.05). Conclusion: The AI-assisted diagnostic system can significantly improve the diagnostic accuracy of digestive system tumors, shorten the diagnostic and treatment time, and reduce the missed diagnosis and misdiagnosis rates, demonstrating high application value in the clinical diagnosis and treatment of digestive system tumors.
References
Cai Y, 2024, Research on Medical Expenses, Service Utilization, Survival, and Their Relationships Among Hospitalized Patients with Malignant Tumors in China, dissertation, Jilin University.
Guo X, Jiang Z, 2022, New Advances in the Diagnosis and Treatment of Lung Cancer, Northwest University Press, 404.
Chai S, Huo B, Huo X, 2024, Radiation Particle Therapy for Thoracic Tumors, People’s Medical Publishing House, 819.
Wen C, 2023, Construction and Clinical Application Research of an Artificial Intelligence Diagnostic Model for Breast Cancer Based on Contrast-Enhanced Mammography, dissertation, Southern Medical University.
Xu W, Li B, Xu Y, et al., 2021, Establishment and Clinical Testing of an Automatic Recognition Model for Gastroscopic Images of Atrophic Gastritis-Gastric Cancer Based on a Fast Regional Convolutional Neural Network. World Science and Technology-Modernization of Traditional Chinese Medicine, 23(09): 3274–3280.
Han D, Li Q, Cai W, et al., 2019, Research and Application of Artificial Intelligence in Medical Imaging. Big Data, 5(01): 39–67.
Li F, Liang X, Wang D, et al., 2025, AI Diagnosis in Ophthalmology: Challenges and Solutions in the Real World. Science Observer, 20(01): 1–21.
Ma L, Bao C, Li Q, et al., 2022, Design and Application of a Clinical Big Data Management System for Tumors. Engineering Sciences, 24(06): 127–136.
Lin L, Zeng X, Zhen Z, et al., 2025, Innovations in Artificial Intelligence and Big Data Technologies Support Precision Oncology. Chinese Journal of Cell Biology, 47(03): 450–464.
Yu H, 2024, A Prospective, Randomized, Placebo-Parallel Controlled Clinical Study on Accelerating Gastrointestinal Function Recovery After Digestive Tract Tumor Surgery by Infusing “Ginseng and Rhubarb Decoction” Through a Jejunal Nutrition Tube, dissertation, Changchun University of Chinese Medicine.
Yuan Y, Luo F, 2022, Screening and Diagnosis of Early Autism Patients Assisted by Artificial Intelligence. Advances in Psychological Science, 30(10): 2303–2320.
Zhang L, 2024, The Proposal of the MARKED Multi-Label Model and Its Application in Risk Assessment of Surgical Complications, dissertation, Peking Union Medical College.