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
. 2021 Mar 25;16(3):e0249206.
doi: 10.1371/journal.pone.0249206. eCollection 2021.

Artificial neural networks versus LASSO regression for the prediction of long-term survival after surgery for invasive IPMN of the pancreas

Linus Aronsson  1 , Roland Andersson  1 , Daniel Ansari  1
Affiliations

Artificial neural networks versus LASSO regression for the prediction of long-term survival after surgery for invasive IPMN of the pancreas

Linus Aronsson et al. PLoS One. .

Abstract

Prediction of long-term survival in patients with invasive intraductal papillary mucinous neoplasm (IPMN) of the pancreas may aid in patient assessment, risk stratification and personalization of treatment. This study aimed to investigate the predictive ability of artificial neural networks (ANN) and LASSO regression in terms of 5-year disease-specific survival. ANN work in a non-linear fashion, having a potential advantage in analysis of variables with complex correlations compared to regression models. LASSO is a type of regression analysis facilitating variable selection and regularization. A total of 440 patients undergoing surgical treatment for invasive IPMN of the pancreas registered in the Surveillance, Epidemiology and End Results (SEER) database between 2004 and 2016 were analyzed. The dataset was prior to analysis randomly split into a modelling and test set (7:3). The accuracy, precision and F1 score for predicting mortality were 0.82, 0.83 and 0.89, respectively for ANN with variable selection compared to 0.79, 0.85 and 0.87, respectively for the LASSO-model. ANN using all variables showed similar accuracy, precision and F1 score of 0.81, 0.85 and 0.88, respectively compared to a logistic regression analysis. McNemar´s test showed no statistical difference between the models. The models showed high and similar performance with regard to accuracy and precision for predicting 5-year survival status.

PubMed Disclaimer

Conflict of interest statement

The authors have declared that no competing interests exist.

Figures

Fig 1
Fig 1. Flow chart of selection of cases for prediction analysis.
Fig 2
Fig 2. Schematic structure of the applied multilayer perceptron neural network with three layers.
Fig 3
Fig 3. Venn diagram on recall (sensitivity) of ANN model 1 and LASSO regression model.
Seven correctly classified by ANN and not LASSO, 1 by LASSO and not ANN, 87 by both models and 4 not correctly classified by any model.
Fig 4
Fig 4. Venn diagram on recall (sensitivity) of ANN model 2 and logistic regression model.
Three correctly classified by ANN and not LASSO, 2 by LASSO and not ANN, 87 by both models and 7 not correctly classified by any model.
See this image and copyright information in PMC

References

    1. Adsay V, Mino-Kenudson M, Furukawa T, Basturk O, Zamboni G, Marchegiani G, et al.. Pathologic Evaluation and Reporting of Intraductal Papillary Mucinous Neoplasms of the Pancreas and Other Tumoral Intraepithelial Neoplasms of Pancreatobiliary Tract: Recommendations of Verona Consensus Meeting. Ann Surg. 2016;263(1):162–77. 10.1097/SLA.0000000000001173 - DOI - PMC - PubMed
    1. Tanaka M, Fernandez-Del Castillo C, Kamisawa T, Jang JY, Levy P, Ohtsuka T, et al.. Revisions of international consensus Fukuoka guidelines for the management of IPMN of the pancreas. Pancreatology. 2017;17(5):738–53. 10.1016/j.pan.2017.07.007 - DOI - PubMed
    1. European Study Group on Cystic Tumours of the P. European evidence-based guidelines on pancreatic cystic neoplasms. Gut. 2018;67(5):789–804. 10.1136/gutjnl-2018-316027 - DOI - PMC - PubMed
    1. Aronsson L, Marinko S, Ansari D, Andersson R. Adjuvant therapy in invasive intraductal papillary mucinous neoplasm (IPMN) of the pancreas: a systematic review. Ann Transl Med. 2019;7(22):689. 10.21037/atm.2019.10.37 - DOI - PMC - PubMed
    1. Aronsson L, Bengtsson A, Toren W, Andersson R, Ansari D. Intraductal papillary mucinous carcinoma versus pancreatic ductal adenocarcinoma: A systematic review and meta-analysis. Int J Surg. 2019;71:91–9. 10.1016/j.ijsu.2019.09.014 - DOI - PubMed

Publication types