OTDOncology Treatment Discovery3083-49962981-8079Bio-Byword Scientific Publishing Pty. Ltd.10.26689/OTD.v4i3.15718ArticleArtificial Intelligence Risk Prediction Model for PICC Catheter-related Venous Thrombosis in Cancer Patients: A Systematic Reviewhttps://artdesignp.com/journal/OTD/4/3/10.26689/OTD.v4i3.15718YangXi,WangRui,FuQinglan,QiuLanying,FuXiaowei2026432026-10-20Background: Despite the growing number of models predicting the risk of cancer-associated PICC catheter-related venous thrombosis, comprehensive evaluations of artificial intelligence (AI) and machine learning (ML) prediction models remain scarce. Objective: This systematic review aims to evaluate the methodological quality, predictive performance, and clinical applicability of ML models for PICC-related thrombosis in patients with cancer, with a specific focus on risk of bias and adherence to reporting guidelines. Methods: A systematic search was performed across PubMed, Embase, Scopus, Web of Science, the Cochrane Library, and CINAHL. The study protocol was registered with PROSPERO prior to data collection, and the review adhered to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. The search sought to identify all relevant studies published from database inception to December 30, 2025. Literature screening and data extraction were performed independently by two investigators. Finally, model quality was evaluated using the PROBAST+AI framework, integrating reported model performance metrics. Results: A total of seven studies were included, wherein all developed models demonstrated an Area Under the Curve (AUC) exceeding 0.7. The six most frequently utilized machine learning algorithms were Random Forest (RF; 28.57%), Least Absolute Shrinkage and Selection Operator (Lasso; 17.86%), Boosting (10.71%), Support Vector Machine (SVM; 7.14%), Logistic Regression (LR; 7.14%), and Artificial Neural Network (ANN; 7.14%). Overall, the included studies exhibited a high risk of bias, although clinical applicability was deemed acceptable. Conclusions: Current evidence indicates that machine learning models are effective in predicting PICC-related thromboembolism in patients with cancer. However, the majority of current models are limited by suboptimal methodological quality, a lack of external validation, and restricted generalizability. Future research should prioritize external validation and focus on developing clinical decision support tools to facilitate seamless integration into clinical practice.Peripherally inserted central catheter-related venous thrombosis, Neoplasms, Risk prediction, Machine learning, Systematic review

[1]   Chen P, Zhu B, Wan G, et al., 2021, The Incidence of Asymptomatic Thrombosis Related to Peripherally Inserted Central Catheter in Adults: A Systematic Review and Meta-Analysis. Nurs Open, 8: 2249–2261. [2]   Luo L, Jing XM, Wang GR, et al., 2016, Peripherally Inserted Central Catheter-Related Upper Extremity Venous Thrombosis in Oncology Patients: A Prospective Study Based on Doppler Sonography. J Ultrasound Med, 35: 1759–1763. [3]   Fallouh N, McGuirk HM, Flanders SA, et al., 2015, Peripherally Inserted Central Catheter-Associated Deep Vein Thrombosis: A Narrative Review. Am J Med, 128: 722–738. [4]   Chen P, Wan G, Zhu B, 2021, Incidence and Risk Factors of Symptomatic Thrombosis Related to Peripherally Inserted Central Catheter in Patients with Lung Cancer. J Adv Nurs, 77: 1284–1292. [5]   Lopez-Rubio M, Lago-Rodriguez MO, Ordieres-Ortega L, et al., 2024, A Comprehensive Review of Catheter-Related Thrombosis. J Clin Med, 13: 7818. [6]   Chopra V, Kaatz S, Conlon A, et al., 2017, The Michigan Risk Score to Predict Peripherally Inserted Central Catheter-Associated Thrombosis. J Thromb Haemost, 15: 1951–1962. [7]   Seeley MA, Santiago M, Shott S, 2007, Prediction Tool for Thrombi Associated with Peripherally Inserted Central Catheters. J Infus Nurs, 30: 280–286. [8]   Autar R, 1996, Nursing Assessment of Clients at Risk of Deep Vein Thrombosis (DVT): The Autar DVT Scale. J Adv Nurs, 23: 763–770. [9]   Caprini JA, 2005, Thrombosis Risk Assessment as a Guide to Quality Patient Care. Dis Mon, 51: 70–78. [10] Dhillon SK, Ganggayah MD, Sinnadurai S, et al., 2022, Theory and Practice of Integrating Machine Learning and Conventional Statistics in Medical Data Analysis. Diagnostics (Basel), 12: 2526. [11] Yu MY, Yoo HY, Han GI, et al., 2025, Comparing the Performance of Machine Learning Models and Conventional Risk Scores for Predicting Major Adverse Cardiovascular Cerebrovascular Events After Percutaneous Coronary Intervention in Patients with Acute Myocardial Infarction: Systematic Review and Meta-Analysis. J Med Internet Res, 27: e76215. [12] Moons KGM, Damen JAA, Kaul T, et al., 2025, PROBAST+AI: An Updated Quality, Risk of Bias, and Applicability Assessment Tool for Prediction Models Using Regression or Artificial Intelligence Methods. BMJ, 388: e082505. [13] Page MJ, McKenzie JE, Bossuyt PM, et al., 2021, The PRISMA 2020 Statement: An Updated Guideline for Reporting Systematic Reviews. BMJ, 372: n71. [14] Aromataris E, Lockwood C, Porritt K, et al., JBI Manual for Evidence Synthesis. JBI Manual for Evidence Synthesis, visited on January 20. 2026, https://jbi-global-wiki.refined.site/space/MANUAL/4685837/jbi-global-wiki.refined.site. [15] Moons KG, de Groot JA, Bouwmeester W, et al., 2014, Critical Appraisal and Data Extraction for Systematic Reviews of Prediction Modelling Studies: The CHARMS Checklist. PLoS Med, 11: e1001744. [16] An T, Han H, Xie J, et al., 2025, Enhancing Prediction and Stratifying Risk: Machine Learning and Bayesian-Learning Models for Catheter-Related Thrombosis in Chemotherapy Patients. BMC Cancer, 25: 552. [17] Liu S, Zhang F, Xie L, et al., 2019, Machine Learning Approaches for Risk Assessment of Peripherally Inserted Central Catheter-Related Vein Thrombosis in Hospitalized Patients with Cancer. Int J Med Inform, 129: 175–183. [18] Hu H, Wu Z, Zhao J, 2024, Peripherally Inserted Central-Related Upper Extremity Deep Vein Thrombosis and Machine Learning. Vascular, 32: 1346–1351. [19] Fu J, Cai W, Zeng B, et al., 2022, Development and Validation of a Predictive Model for Peripherally Inserted Central Catheter-Related Thrombosis in Breast Cancer Patients Based on Artificial Neural Network: A Prospective Cohort Study. Int J Nurs Stud, 135: 104341. [20] Ma G, Chen S, Peng S, et al., 2025, Construction and Validation of a Nomogram Prediction Model for the Catheter-Related Thrombosis Risk of Central Venous Access Devices in Patients with Cancer: A Prospective Machine Learning Study. J Thromb Thrombolysis, 58: 220–231. [21] Zhang F, Ye G, Chen P, et al., 2024, Comparative Predictive Modeling for PICC Line Complications in Oncology: A Retrospective Study. Br J Hosp Med (Lond), 85: 1–15. [22] Li Y, Nie S, Wang L, et al., 2024, Integrating Deep Learning in Public Health: A Novel Approach to PICC-RVT Risk Assessment. Front Public Health, 12: 1445425. [23] Van Calster B, van Smeden M, De Cock B, et al., 2020, Regression Shrinkage Methods for Clinical Prediction Models Do Not Guarantee Improved Performance: Simulation Study. Stat Methods Med Res, 29: 3166–3178. [24] Riley RD, Snell KIE, Martin GP, et al., 2021, Penalization and Shrinkage Methods Produced Unreliable Clinical Prediction Models Especially When Sample Size Was Small. J Clin Epidemiol, 132: 88–96. [25] van den Goorbergh R, van Smeden M, Timmerman D, et al., 2022, The Harm of Class Imbalance Corrections for Risk Prediction Models: Illustration and Simulation Using Logistic Regression. J Am Med Inform Assoc, 29: 1525–1534. [26] Carriero A, Luijken K, de Hond A, et al., 2025, The Harms of Class Imbalance Corrections for Machine Learning Based Prediction Models: A Simulation Study. Stat Med, 44: e10320. [27] Adlung L, Cohen Y, Mor U, et al., 2021, Machine Learning in Clinical Decision Making. Med, 2: 642–665. [28] Deng RX, Zhu XL, Zhang AB, et al., 2023, Machine Learning Algorithm as a Prognostic Tool for Venous Thromboembolism in Allogeneic Transplant Patients. Transplant Cell Ther, 29: 57.e1–57.e10. [29] Maharana K, Mondal S, Nemade B, 2022, A Review: Data Pre-Processing and Data Augmentation Techniques. Glob Transit Proc, 3: 91–99. [30] Nijman S, Leeuwenberg AM, Beekers I, et al., 2022, Missing Data Is Poorly Handled and Reported in Prediction Model Studies Using Machine Learning: A Literature Review. J Clin Epidemiol, 142: 218–229. [31] Rockenschaub P, Hilbert A, Kossen T, et al., 2024, The Impact of Multi-Institution Datasets on the Generalizability of Machine Learning Prediction Models in the ICU. Crit Care Med, 52: 1710–1721. [32] de Jong VMT, Moons KGM, Eijkemans MJC, et al., 2021, Developing More Generalizable Prediction Models from Pooled Studies and Large Clustered Data Sets. Stat Med, 40: 3533–3559.