Искусственный интеллект для прогнозирования отдаленных результатов лечения больных колоректальным раком (систематический обзор и метаанализ)

ЦЕЛЬ: оценить эффективность алгоритмов искусственного интеллекта для прогнозирования отдаленных результатов лечения больных колоректальным раком (КРР) на основе клинических данных.

МАТЕРИАЛЫ И МЕТОДЫ: проведен систематический поиск научных публикаций за 2015–2024 гг. в базах данных PubMed, ScienceDirect, MedRxiv, BioRxiv и Google Scholar. Включены оригинальные исследования, применявшие методы машинного обучения и глубокого обучения исключительно на основе клинических данных для прогнозирования рецидива КРР. Из 657106 выявленных публикаций критериям включения соответствовали 43 исследования, из которых 12 вошли в метаанализ. Оценивались общая площадь под ROC-кривой (AUC), показатели гетерогенности (I², τ², Q-тест), наличие публикационного смещения и чувствительность результатов. Чувствительность результатов метаанализа была подтверждена методом leave-one-out.

РЕЗУЛЬТАТЫ: по результатам проведенного анализа было установлено, что наиболее часто применяемыми алгоритмами были Random Forest (67%), Support Vector Machine (51%) и XGBoost (37%). Общая объединённая прогностическая точность моделей машинного обучения в прогнозировании общей выживаемость КРР показала очень хорошие результаты — AUC = 0,86 (95% ДИ: 0,82–0,89). Вместе с тем, выявлена значительная межисследовательская гетерогенность (I² = 97,6%, p < 0,001) и умеренное публикационное смещение.

ЗАКЛЮЧЕНИЕ: высокая прогностическая точность моделей ИИ подтверждает их потенциал для интеграции в клиническую практику при прогнозировании рецидива КРР. Однако существенная гетерогенность между исследованиями ограничивает возможность прямого сравнения эффективности различных алгоритмов и требует осторожности в интерпретации результатов.

1. Jeon Y, et al. Machine learning based prediction of recurrence after curative resection for rectal cancer. PLoS One. 2023;18(12):e0290141.

2. Tang M, et al. Machine learning based prognostic model of Chinese medicine affecting the recurrence and metastasis of I-III stage colorectal cancer: A retrospective study in China. Front Oncol. 2022;12:1044344.

3. Ting WC, et al. Machine Learning in Prediction of Second Primary Cancer and Recurrence in Colorectal Cancer. Int J Med Sci. 2020;17(3):280–291.

4. Achilonu OJ, et al. Predicting Colorectal Cancer Recurrence and Patient Survival Using Supervised Machine Learning Approach: A South African Population-Based Study. Front Public Health. 2021;9:694306.

5. Chen PC, et al. A Prediction Model for Tumor Recurrence in Stage II-III Colorectal Cancer Patients: From a Machine Learning Model to Genomic Profiling. Biomedicines. 2022;10(2):340.

6. Alinia S, et al. Predicting mortality and recurrence in colorectal cancer: Comparative assessment of predictive models. Heliyon. 2024;10(6):e27854.

7. Kayikcioglu E, et al. Machine learning for predicting colon cancer recurrence. Surgical Oncology. 2024;54:102079.

8. Susič D, et al. Artificial intelligence based personalized predictive survival among colorectal cancer patients. Comput Methods Programs Biomed. 2023;231:107435.

9. Gupta P, et al. Prediction of Colon Cancer Stages and Survival Period with Machine Learning Approach. Cancers (Basel). 2019; 11(12).

10. Hu J, et al. Construction and validation of a progression prediction model for locally advanced rectal cancer patients received neoadjuvant chemoradiotherapy followed by total mesorectal excision based on machine learning. Front Oncol. 2023;13:1231508.

11. Leonard G, et al. Machine Learning Improves Prediction Over Logistic Regression on Resected Colon Cancer Patients. J Surg Res. 2022;275:181–193.

12. Nopour R. Development of Prediction Model for 5-year Survival of Colorectal Cancer. Cancer Inform. 2024;23:11769351241275889.

13. Ji XL, et al. Prognostic prediction models for postoperative patients with stage I to III colorectal cancer based on machine learning. World J Gastrointest Oncol. 2024;16(12):4597–4613.

14. Buk Cardoso L, et al. Machine learning for predicting survival of colorectal cancer patients. Sci Rep. 2023;13(1):8874.

15. Kos FT, et al. Comparison of Different Machine Learning Models for Predicting Long-Term Overall Survival in Non-metastatic Colorectal Cancers. Cureus. 2024;16(12):e75713.

16. Osman MH, et al. Machine Learning Model for Predicting Postoperative Survival of Patients with Colorectal Cancer. Cancer Res Treat. 2022;54(2):517–524.

17. Rodriguez PJ, et al. Using Machine Learning to Leverage Biomarker Change and Predict Colorectal Cancer Recurrence. JCO Clin Cancer Inform. 2023;7:e2300066.

18. Chi S, et al. Semi-supervised learning to improve generalizability of risk prediction models. J Biomed Inform. 2019;92:103117.

19. Kudo SE, et al. Artificial Intelligence System to Determine Risk of T1 Colorectal Cancer Metastasis to Lymph Node. Gastroenterology. 2021;160(4):1075–1084.e2.

20. Wang X, et al. Development and validation of artificial intelligence models for preoperative prediction of inferior mesenteric artery lymph nodes metastasis in left colon and rectal cancer. Eur J Surg Oncol. 2022;48(12):2475–2486.

21. Han T. et al. Application of artificial intelligence in a real-world research for predicting the risk of liver metastasis in T1 colorectal cancer. Cancer Cell Int. 2022;22(1):28.

22. Kasai, S, et al. The Effectiveness of Machine Learning in Predicting Lateral Lymph Node Metastasis From Lower Rectal Cancer: A Single Center Development and Validation Study. Ann Gastroenterol Surg. 2022;6(1):92–100.

23. Masum S, et al. Data analytics and artificial intelligence in predicting length of stay, readmission, and mortality: a populationbased study of surgical management of colorectal cancer. Discov Oncol. 2022;13(1):11.

24. Woźniack, A, Książek W, Mrowczyk P. A Novel Approach for Predicting the Survival of Colorectal Cancer Patients Using Machine Learning Techniques and Advanced Parameter Optimization Methods. Cancers (Basel). 2024. 16(18).

25. Oliveira T, et al. Survivability Prediction of Colorectal Cancer Patients: A System with Evolving Features for Continuous Improvement. Sensors (Basel). 2018; 18(9).

26. Qiu, B, et al. Application of machine learning techniques in realworld research to predict the risk of liver metastasis in rectal cancer. Front Oncol. 2022;12:1065468.

27. Liu Y, et al. Utilizing machine learning algorithms for predicting risk factors for bone metastasis from right-sided colon carcinoma after complete mesocolic excision: a 10-year retrospective multicenter study. Discov Oncol. 2024;15(1):463.

28. Li X, et al. Preoperative Albumin to Alkaline Phosphatase Ratio and Inflammatory Burden Index for Rectal Cancer Prognostic Nomogram-Construction: Based on Multiple Machine Learning. J Inflamm Res. 2024;17:11161–11174.

29. Qiu B, et al. A machine learning-based model for predicting distant metastasis in patients with rectal cancer. Front Oncol. 2023;13:1235121.

30. Xing Y, et al. Development of prediction models for liver metastasis in colorectal cancer based on machine learning: a populationlevel study. Transl Cancer Res. 2024;13(11):5943–5952.

31. Zhao B, et al. Using machine learning to construct nomograms for patients with metastatic colon cancer. Colorectal Dis. 2020;22(8):914–922.

32. Orafaie A, et al. The association of preoperative hematologic parameters with short-term clinical outcomes in rectal cancer: A feature importance analysis. Cancer Med. 2024;13(10):e7225.

33. Tian Y, et al. Spatially varying effects of predictors for the survival prediction of nonmetastatic colorectal Cancer. BMC Cancer. 2018;18(1):1084.

34. Wei R, et al. Construction and validation of machine learning models for predicting distant metastases in newly diagnosed colorectal cancer patients: A large-scale and real-world cohort study. Cancer Med. 2024;13(5):e6971.

35. Liu Y, et al. Identification of high-risk factors for recurrence of colon cancer following complete mesocolic excision: An 8-year retrospective study. PLoS One. 2023;18(8):e0289621.

36. Ishizaki T, et al. Predictive modelling for high-risk stage II colon cancer using auto-artificial intelligence. Tech Coloproctol. 2023;27(3):183–188.

37. Bibault JE, Chang DT, Xing L. Development and validation of a model to predict survival in colorectal cancer using a gradientboosted machine. Gut. 2021;70(5):884–889. 38. Amygdalos I, et al. Novel machine learning algorithm can identify patients at risk of poor overall survival following curative resection for colorectal liver metastases. J Hepatobiliary Pancreat Sci. 2023;30(5):602–614.

38. Piao ZH, Ge R, Lu L. An artificial intelligence prediction model outperforms conventional guidelines in predicting lymph node metastasis of T1 colorectal cancer. Front Oncol. 2023;13:1229998.

39. Yang X, et al. Predicting Colorectal Cancer Survival Using Timeto-Event Machine Learning: Retrospective Cohort Study. J Med Internet Res. 2023;25:e44417.

40. Mohammadi G, et al. Classification and Diagnostic Prediction of Colorectal Cancer Mortality Based on Machine Learning Algorithms: A Multicenter National Study. Asian Pac J Cancer Prev. 2024;25(1):333–342.

41. Zhang W, et al. Development and validation of an artificial intelligence prediction model and a survival risk stratification for lung metastasis in colorectal cancer from highly imbalanced data: A multicenter retrospective study. Eur J Surg Oncol. 2023;49(12):107107.

42. Li J, et al. An interpretable deep learning framework for predicting liver metastases in postoperative colorectal cancer patients using natural language processing and clinical data integration. Cancer Med. 2023;12(18):19337–19351.