Koki Hayashi1, Yoshihiro Ono1, Manabu Takamatsu2, Atsushi Oba1, Hiromichi Ito1, Takafumi Sato1, Yosuke Inoue1, Akio Saiura1,3, Yu Takahashi4. 1. Division of Hepatobiliary and Pancreatic Surgery, Cancer Institute Hospital of the Japanese Foundation for Cancer Research, Koto-ku, Tokyo, Japan. 2. Division of Pathology, Department of Pathology, Cancer Institute, Cancer Institute Hospital of the Japanese Foundation for Cancer Research, Koto-ku, Tokyo, Japan. manabu.takamatsu@jfcr.or.jp. 3. Department of Hepatobiliary-Pancreatic Surgery, Juntendo University Hospital, Bunkyo-ku, Tokyo, Japan. 4. Division of Hepatobiliary and Pancreatic Surgery, Cancer Institute Hospital of the Japanese Foundation for Cancer Research, Koto-ku, Tokyo, Japan. yu.takahashi@jfcr.or.jp.
Abstract
BACKGROUND: Patients with pancreatic cancer (PC) have poor prognosis and a high incidence of recurrence. Since further treatment is applicable for specific recurrent events, it is important to predict recurrence patterns after surgery. This study aimed to identify and predict early and late recurrence patterns of PC using a histology-based machine learning model. PATIENTS AND METHODS: Patients who underwent upfront curative surgery for PC between 2001 and 2014 were included. The timing of recurrence and prognosis of each first recurrence site were examined. A histology-based supervised machine learning method, which combined convolutional neural networks and random forest, was used to predict the recurrence and respective sites of metastasis. Accuracy was evaluated using area under the receiver operating characteristic curve (AUC). RESULTS: In total, 524 patients were included. Recurrence in the liver accounted for 47.8% of all recurrence events in the first year after surgery. Meanwhile, recurrence in the lung occurred later and could become apparent more than 5 years post-surgery, with indications for further surgery. In terms of substantial distant organ metastases, liver and lung metastases were identified as representative early and late recurrence events. The predictive AUCs of the machine learning model for training and test data were 1.000 and 0.861, respectively, and for predicting nonrecurrence were 1.000 for both. CONCLUSIONS: We identified the liver and lung as early and late recurrence sites, which could be distinguished with high probability using a machine learning model. Prediction of recurrence sites using this model may be useful for further treatment of patients with PC.
BACKGROUND: Patients with pancreatic cancer (PC) have poor prognosis and a high incidence of recurrence. Since further treatment is applicable for specific recurrent events, it is important to predict recurrence patterns after surgery. This study aimed to identify and predict early and late recurrence patterns of PC using a histology-based machine learning model. PATIENTS AND METHODS: Patients who underwent upfront curative surgery for PC between 2001 and 2014 were included. The timing of recurrence and prognosis of each first recurrence site were examined. A histology-based supervised machine learning method, which combined convolutional neural networks and random forest, was used to predict the recurrence and respective sites of metastasis. Accuracy was evaluated using area under the receiver operating characteristic curve (AUC). RESULTS: In total, 524 patients were included. Recurrence in the liver accounted for 47.8% of all recurrence events in the first year after surgery. Meanwhile, recurrence in the lung occurred later and could become apparent more than 5 years post-surgery, with indications for further surgery. In terms of substantial distant organ metastases, liver and lung metastases were identified as representative early and late recurrence events. The predictive AUCs of the machine learning model for training and test data were 1.000 and 0.861, respectively, and for predicting nonrecurrence were 1.000 for both. CONCLUSIONS: We identified the liver and lung as early and late recurrence sites, which could be distinguished with high probability using a machine learning model. Prediction of recurrence sites using this model may be useful for further treatment of patients with PC.
Authors: Vincent P Groot; Neda Rezaee; Wenchuan Wu; John L Cameron; Elliot K Fishman; Ralph H Hruban; Matthew J Weiss; Lei Zheng; Christopher L Wolfgang; Jin He Journal: Ann Surg Date: 2018-05 Impact factor: 12.969
Authors: M Tanaka; A L Mihaljevic; P Probst; M Heckler; U Klaiber; U Heger; M W Büchler; T Hackert Journal: Br J Surg Date: 2019-08-27 Impact factor: 6.939
Authors: Vincent P Groot; Georgios Gemenetzis; Alex B Blair; Ding Ding; Ammar A Javed; Richard A Burkhart; Jun Yu; Inne H Borel Rinkes; I Quintus Molenaar; John L Cameron; Elliot K Fishman; Ralph H Hruban; Matthew J Weiss; Christopher L Wolfgang; Jin He Journal: Ann Surg Oncol Date: 2018-06-14 Impact factor: 5.344