Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2025 Jun;32(6):4085-4093.
doi: 10.1245/s10434-025-17032-2. Epub 2025 Feb 20.

Machine Learning-Driven Modeling to Predict Postdischarge Venous Thromboembolism After Pancreatectomy for Pancreas Cancer

Kaleem S Ahmed #  1 , Sheriff M Issaka #  1 , Clayton T Marcinak  1 , Sehar S Virani  2 , Taylor Jaraczewski  3 , Majid Afshar  4   5 , Anoop Mayampurath  4   5 , Matthew M Churpek  4   5 , Jomol Mathew  6 , Syed Nabeel Zafar  7
Affiliations

Machine Learning-Driven Modeling to Predict Postdischarge Venous Thromboembolism After Pancreatectomy for Pancreas Cancer

Kaleem S Ahmed et al. Ann Surg Oncol. 2025 Jun.

Abstract

Background: Postdischarge venous thromboembolism (pdVTE) is a life-threatening complication following resection for pancreatic cancer (PC). While national guidelines recommend extended chemoprophylaxis for all, adherence is low and ranges from 1.5 to 44%. Predicting a patient's pdVTE risk would enable a more tailored approach to extended chemoprophylaxis, better balancing the cost and risks of overtreatment. We aimed to demonstrate the feasibility of using machine learning models to predict pdVTE.

Patients and methods: We analyzed data from patients undergoing pancreatectomy for PC using the National Surgical Quality Improvement Program database between 2014 and 2020. Predictive classification models were trained and independently tested on features available at the time of discharge including demographics, clinical, laboratory, cancer, and surgery-specific variables. We developed and compared logistic regression (LR), decision tree (DT), random forest (RF), and gradient boosting (GB) models to predict the development of pdVTE. Model performance and feature importance were evaluated.

Results: The study included a total of 51,916 patients, with 743 (1.4%) experiencing pdVTE. The best-performing GB, RF, and DT models achieved area under the curve (AUC) scores of 0.83, 0.80, and 0.80, respectively, demonstrating superior performance compared with the traditional LR (AUC = 0.72) model. The GB model achieved a specificity of 99%, sensitivity of 0.40%, and area under the precision recall curve of 0.34. The most important variables were intraoperative antibiotic use, blood transfusion, length of stay, and postoperative infections.

Conclusions: Machine learning models can reliably identify patients who are at high risk for pdVTE. Such models should be used to inform prescription of extended VTE prophylaxis.

Keywords: Clinical decision support; Machine learning; Pancreatectomy; Pancreatic cancer; Risk prediction; Venous thromboembolism.

PubMed Disclaimer

Conflict of interest statement

Disclosures: The authors declare that they have no conflict of interest.

References

    1. Aiken TJ, King R, Russell MM, Regenbogen SE, Lawson E, Zafar SN. Venous thromboembolism prophylaxis following colorectal surgery: a survey of American Society of Colon and Rectal Surgery (ASCRS) member surgeons. J Thromb Thrombolysis. 2023;55(2):376–81. https://doi.org/10.1007/s11239-022-02733-2 . - DOI - PubMed
    1. Mallick S, Aiken T, Varley P, et al. Readmissions from venous thromboembolism after complex cancer surgery. JAMA Surg. 2022;157(4):312–20. https://doi.org/10.1001/jamasurg.2021.7126 . - DOI - PubMed - PMC
    1. Krepline AN, Christians KK, George B, et al. Venous thromboembolism prophylaxis during neoadjuvant therapy for resectable and borderline resectable pancreatic cancer—Is it indicated? J Surg Oncol. 2016;114(5):581–6. https://doi.org/10.1002/jso.24361 . - DOI - PubMed
    1. Larsen AC, Brøndum Frøkjaer J, Wishwanath Iyer V, et al. Venous thrombosis in pancreaticobiliary tract cancer: outcome and prognostic factors. J Thromb Haemost JTH. 2015;13(4):555–62. https://doi.org/10.1111/jth.12843 . - DOI - PubMed
    1. Lyman GH, Khorana AA, Falanga A, et al. American Society of Clinical Oncology guideline: recommendations for venous thromboembolism prophylaxis and treatment in patients with cancer. J Clin Oncol Off J Am Soc Clin Oncol. 2007;25(34):5490–505. https://doi.org/10.1200/JCO.2007.14.1283 . - DOI

LinkOut - more resources