Prediction of Recurrence Pattern of Pancreatic Cancer Post-Pancreatic Surgery Using Histology-Based Supervised Machine Learning Algorithms: A Single-Center Retrospective Study View Full Text


Ontology type: schema:ScholarlyArticle     


Article Info

DATE

2022-03-01

AUTHORS

Koki Hayashi, Yoshihiro Ono, Manabu Takamatsu, Atsushi Oba, Hiromichi Ito, Takafumi Sato, Yosuke Inoue, Akio Saiura, Yu Takahashi

ABSTRACT

BackgroundPatients 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 MethodsPatients 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).ResultsIn 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.ConclusionsWe 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. More... »

PAGES

4624-4634

References to SciGraph publications

  • 2018-02-21. Deep learning based tissue analysis predicts outcome in colorectal cancer in SCIENTIFIC REPORTS
  • 2017-04-22. Predictive risk factors for peritoneal recurrence after pancreatic cancer resection and strategies for its prevention in SURGERY TODAY
  • 2019-06-03. Deep learning can predict microsatellite instability directly from histology in gastrointestinal cancer in NATURE MEDICINE
  • 2012-05-04. The Implications of Positive Peritoneal Lavage Cytology in Potentially Resectable Pancreatic Cancer in WORLD JOURNAL OF SURGERY
  • 2001-10. Random Forests in MACHINE LEARNING
  • 2017-06-20. Primary Recurrence in the Lung is Related to Favorable Prognosis in Patients with Pancreatic Cancer and Postoperative Recurrence in WORLD JOURNAL OF SURGERY
  • 2008-12-11. How Uncommon are Isolated Lung Metastases in Colorectal Cancer? A Review from Database of 754 Patients Over 4 Years in JOURNAL OF GASTROINTESTINAL SURGERY
  • 2018-06-14. Implications of the Pattern of Disease Recurrence on Survival Following Pancreatectomy for Pancreatic Ductal Adenocarcinoma in ANNALS OF SURGICAL ONCOLOGY
  • 2019-11-28. Radiologically occult metastatic pancreatic cancer: how can we avoid unbeneficial resection? in LANGENBECK'S ARCHIVES OF SURGERY
  • 2018-10-10. Optimal Extent of Superior Mesenteric Artery Dissection during Pancreaticoduodenectomy for Pancreatic Cancer: Balancing Surgical and Oncological Safety in JOURNAL OF GASTROINTESTINAL SURGERY
  • 2017-01-23. Distal Pancreatectomy with Celiac Axis Resection Combined with Reconstruction of the Left Gastric Artery in JOURNAL OF GASTROINTESTINAL SURGERY
  • 2011-07-02. Pulmonary Resection for Isolated Pancreatic Adenocarcinoma Metastasis: an Analysis of Outcomes and Survival in JOURNAL OF GASTROINTESTINAL SURGERY
  • 2008-03-15. Liver metastasis as an initial recurrence has no impact on the survival of patients with resectable pancreatic adenocarcinoma in LANGENBECK'S ARCHIVES OF SURGERY
  • Identifiers

    URI

    http://scigraph.springernature.com/pub.10.1245/s10434-022-11471-x

    DOI

    http://dx.doi.org/10.1245/s10434-022-11471-x

    DIMENSIONS

    https://app.dimensions.ai/details/publication/pub.1145944672

    PUBMED

    https://www.ncbi.nlm.nih.gov/pubmed/35230581


    Indexing Status Check whether this publication has been indexed by Scopus and Web Of Science using the SN Indexing Status Tool
    Incoming Citations Browse incoming citations for this publication using opencitations.net

    JSON-LD is the canonical representation for SciGraph data.

    TIP: You can open this SciGraph record using an external JSON-LD service: JSON-LD Playground Google SDTT

    [
      {
        "@context": "https://springernature.github.io/scigraph/jsonld/sgcontext.json", 
        "about": [
          {
            "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/11", 
            "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
            "name": "Medical and Health Sciences", 
            "type": "DefinedTerm"
          }, 
          {
            "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/1112", 
            "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
            "name": "Oncology and Carcinogenesis", 
            "type": "DefinedTerm"
          }
        ], 
        "author": [
          {
            "affiliation": {
              "alternateName": "Division of Hepatobiliary and Pancreatic Surgery, Cancer Institute Hospital of the Japanese Foundation for Cancer Research, Koto-ku, Tokyo, Japan", 
              "id": "http://www.grid.ac/institutes/grid.410807.a", 
              "name": [
                "Division of Hepatobiliary and Pancreatic Surgery, Cancer Institute Hospital of the Japanese Foundation for Cancer Research, Koto-ku, Tokyo, Japan"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Hayashi", 
            "givenName": "Koki", 
            "id": "sg:person.015754105744.32", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.015754105744.32"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Division of Hepatobiliary and Pancreatic Surgery, Cancer Institute Hospital of the Japanese Foundation for Cancer Research, Koto-ku, Tokyo, Japan", 
              "id": "http://www.grid.ac/institutes/grid.410807.a", 
              "name": [
                "Division of Hepatobiliary and Pancreatic Surgery, Cancer Institute Hospital of the Japanese Foundation for Cancer Research, Koto-ku, Tokyo, Japan"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Ono", 
            "givenName": "Yoshihiro", 
            "id": "sg:person.01240213665.21", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01240213665.21"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Division of Pathology, Department of Pathology, Cancer Institute, Cancer Institute Hospital of the Japanese Foundation for Cancer Research, Koto-ku, Tokyo, Japan", 
              "id": "http://www.grid.ac/institutes/grid.486756.e", 
              "name": [
                "Division of Pathology, Department of Pathology, Cancer Institute, Cancer Institute Hospital of the Japanese Foundation for Cancer Research, Koto-ku, Tokyo, Japan"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Takamatsu", 
            "givenName": "Manabu", 
            "id": "sg:person.0651113351.24", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0651113351.24"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Division of Hepatobiliary and Pancreatic Surgery, Cancer Institute Hospital of the Japanese Foundation for Cancer Research, Koto-ku, Tokyo, Japan", 
              "id": "http://www.grid.ac/institutes/grid.410807.a", 
              "name": [
                "Division of Hepatobiliary and Pancreatic Surgery, Cancer Institute Hospital of the Japanese Foundation for Cancer Research, Koto-ku, Tokyo, Japan"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Oba", 
            "givenName": "Atsushi", 
            "id": "sg:person.014215735464.23", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.014215735464.23"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Division of Hepatobiliary and Pancreatic Surgery, Cancer Institute Hospital of the Japanese Foundation for Cancer Research, Koto-ku, Tokyo, Japan", 
              "id": "http://www.grid.ac/institutes/grid.410807.a", 
              "name": [
                "Division of Hepatobiliary and Pancreatic Surgery, Cancer Institute Hospital of the Japanese Foundation for Cancer Research, Koto-ku, Tokyo, Japan"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Ito", 
            "givenName": "Hiromichi", 
            "id": "sg:person.011406547173.21", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011406547173.21"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Division of Hepatobiliary and Pancreatic Surgery, Cancer Institute Hospital of the Japanese Foundation for Cancer Research, Koto-ku, Tokyo, Japan", 
              "id": "http://www.grid.ac/institutes/grid.410807.a", 
              "name": [
                "Division of Hepatobiliary and Pancreatic Surgery, Cancer Institute Hospital of the Japanese Foundation for Cancer Research, Koto-ku, Tokyo, Japan"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Sato", 
            "givenName": "Takafumi", 
            "id": "sg:person.013042551555.87", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013042551555.87"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Division of Hepatobiliary and Pancreatic Surgery, Cancer Institute Hospital of the Japanese Foundation for Cancer Research, Koto-ku, Tokyo, Japan", 
              "id": "http://www.grid.ac/institutes/grid.410807.a", 
              "name": [
                "Division of Hepatobiliary and Pancreatic Surgery, Cancer Institute Hospital of the Japanese Foundation for Cancer Research, Koto-ku, Tokyo, Japan"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Inoue", 
            "givenName": "Yosuke", 
            "id": "sg:person.0770623646.53", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0770623646.53"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Department of Hepatobiliary-Pancreatic Surgery, Juntendo University Hospital, Bunkyo-ku, Tokyo, Japan", 
              "id": "http://www.grid.ac/institutes/grid.411966.d", 
              "name": [
                "Division of Hepatobiliary and Pancreatic Surgery, Cancer Institute Hospital of the Japanese Foundation for Cancer Research, Koto-ku, Tokyo, Japan", 
                "Department of Hepatobiliary-Pancreatic Surgery, Juntendo University Hospital, Bunkyo-ku, Tokyo, Japan"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Saiura", 
            "givenName": "Akio", 
            "id": "sg:person.0612301703.87", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0612301703.87"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Division of Hepatobiliary and Pancreatic Surgery, Cancer Institute Hospital of the Japanese Foundation for Cancer Research, Koto-ku, Tokyo, Japan", 
              "id": "http://www.grid.ac/institutes/grid.410807.a", 
              "name": [
                "Division of Hepatobiliary and Pancreatic Surgery, Cancer Institute Hospital of the Japanese Foundation for Cancer Research, Koto-ku, Tokyo, Japan"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Takahashi", 
            "givenName": "Yu", 
            "id": "sg:person.01307772440.53", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01307772440.53"
            ], 
            "type": "Person"
          }
        ], 
        "citation": [
          {
            "id": "sg:pub.10.1023/a:1010933404324", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1024739340", 
              "https://doi.org/10.1023/a:1010933404324"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/s00423-008-0296-4", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1003962277", 
              "https://doi.org/10.1007/s00423-008-0296-4"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/s11605-011-1605-8", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1051232405", 
              "https://doi.org/10.1007/s11605-011-1605-8"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/s00268-017-4068-6", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1086104088", 
              "https://doi.org/10.1007/s00268-017-4068-6"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/s00595-017-1531-9", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1085043240", 
              "https://doi.org/10.1007/s00595-017-1531-9"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/s11605-017-3366-5", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1074192112", 
              "https://doi.org/10.1007/s11605-017-3366-5"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1245/s10434-018-6558-7", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1104607849", 
              "https://doi.org/10.1245/s10434-018-6558-7"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/s11605-018-3995-3", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1107529106", 
              "https://doi.org/10.1007/s11605-018-3995-3"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1038/s41591-019-0462-y", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1116596451", 
              "https://doi.org/10.1038/s41591-019-0462-y"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/s11605-008-0757-7", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1000057302", 
              "https://doi.org/10.1007/s11605-008-0757-7"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/s00423-019-01846-2", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1122984096", 
              "https://doi.org/10.1007/s00423-019-01846-2"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/s00268-012-1622-0", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1023632975", 
              "https://doi.org/10.1007/s00268-012-1622-0"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1038/s41598-018-21758-3", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1101059633", 
              "https://doi.org/10.1038/s41598-018-21758-3"
            ], 
            "type": "CreativeWork"
          }
        ], 
        "datePublished": "2022-03-01", 
        "datePublishedReg": "2022-03-01", 
        "description": "BackgroundPatients 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 MethodsPatients 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).ResultsIn 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.ConclusionsWe 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.", 
        "genre": "article", 
        "id": "sg:pub.10.1245/s10434-022-11471-x", 
        "isAccessibleForFree": false, 
        "isPartOf": [
          {
            "id": "sg:journal.1105545", 
            "issn": [
              "1068-9265", 
              "1534-4681"
            ], 
            "name": "Annals of Surgical Oncology", 
            "publisher": "Springer Nature", 
            "type": "Periodical"
          }, 
          {
            "issueNumber": "7", 
            "type": "PublicationIssue"
          }, 
          {
            "type": "PublicationVolume", 
            "volumeNumber": "29"
          }
        ], 
        "keywords": [
          "pancreatic cancer", 
          "recurrence site", 
          "recurrence patterns", 
          "recurrence events", 
          "single-center retrospective study", 
          "first recurrence site", 
          "further treatment", 
          "timing of recurrence", 
          "distant organ metastasis", 
          "post-pancreatic surgery", 
          "curative surgery", 
          "further surgery", 
          "organ metastasis", 
          "lung metastases", 
          "retrospective study", 
          "poor prognosis", 
          "ResultsIn total", 
          "predictive AUC", 
          "high incidence", 
          "surgery", 
          "recurrence", 
          "patients", 
          "metastasis", 
          "liver", 
          "characteristic curve", 
          "recurrent events", 
          "prognosis", 
          "lung", 
          "first year", 
          "treatment", 
          "MethodsPatients", 
          "BackgroundPatients", 
          "histology", 
          "cancer", 
          "years", 
          "incidence", 
          "nonrecurrence", 
          "AUC", 
          "events", 
          "total", 
          "study", 
          "ConclusionsWe", 
          "indications", 
          "high probability", 
          "patterns", 
          "respective sites", 
          "sites", 
          "training", 
          "timing", 
          "data", 
          "model", 
          "receiver", 
          "curves", 
          "area", 
          "Supervised Machine Learning Algorithms", 
          "supervised machine learning methods", 
          "convolutional neural network", 
          "Machine Learning Algorithms", 
          "method", 
          "machine learning methods", 
          "probability", 
          "learning algorithm", 
          "neural network", 
          "learning methods", 
          "random forest", 
          "terms", 
          "prediction", 
          "machine", 
          "accuracy", 
          "test data", 
          "algorithm", 
          "network", 
          "forest"
        ], 
        "name": "Prediction of Recurrence Pattern of Pancreatic Cancer Post-Pancreatic Surgery Using Histology-Based Supervised Machine Learning Algorithms: A Single-Center Retrospective Study", 
        "pagination": "4624-4634", 
        "productId": [
          {
            "name": "dimensions_id", 
            "type": "PropertyValue", 
            "value": [
              "pub.1145944672"
            ]
          }, 
          {
            "name": "doi", 
            "type": "PropertyValue", 
            "value": [
              "10.1245/s10434-022-11471-x"
            ]
          }, 
          {
            "name": "pubmed_id", 
            "type": "PropertyValue", 
            "value": [
              "35230581"
            ]
          }
        ], 
        "sameAs": [
          "https://doi.org/10.1245/s10434-022-11471-x", 
          "https://app.dimensions.ai/details/publication/pub.1145944672"
        ], 
        "sdDataset": "articles", 
        "sdDatePublished": "2022-10-01T06:50", 
        "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
        "sdPublisher": {
          "name": "Springer Nature - SN SciGraph project", 
          "type": "Organization"
        }, 
        "sdSource": "s3://com-springernature-scigraph/baseset/20221001/entities/gbq_results/article/article_953.jsonl", 
        "type": "ScholarlyArticle", 
        "url": "https://doi.org/10.1245/s10434-022-11471-x"
      }
    ]
     

    Download the RDF metadata as:  json-ld nt turtle xml License info

    HOW TO GET THIS DATA PROGRAMMATICALLY:

    JSON-LD is a popular format for linked data which is fully compatible with JSON.

    curl -H 'Accept: application/ld+json' 'https://scigraph.springernature.com/pub.10.1245/s10434-022-11471-x'

    N-Triples is a line-based linked data format ideal for batch operations.

    curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1245/s10434-022-11471-x'

    Turtle is a human-readable linked data format.

    curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1245/s10434-022-11471-x'

    RDF/XML is a standard XML format for linked data.

    curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1245/s10434-022-11471-x'


     

    This table displays all metadata directly associated to this object as RDF triples.

    249 TRIPLES      21 PREDICATES      111 URIs      90 LITERALS      7 BLANK NODES

    Subject Predicate Object
    1 sg:pub.10.1245/s10434-022-11471-x schema:about anzsrc-for:11
    2 anzsrc-for:1112
    3 schema:author N5f43890162d74117bdf5f0bb257508cf
    4 schema:citation sg:pub.10.1007/s00268-012-1622-0
    5 sg:pub.10.1007/s00268-017-4068-6
    6 sg:pub.10.1007/s00423-008-0296-4
    7 sg:pub.10.1007/s00423-019-01846-2
    8 sg:pub.10.1007/s00595-017-1531-9
    9 sg:pub.10.1007/s11605-008-0757-7
    10 sg:pub.10.1007/s11605-011-1605-8
    11 sg:pub.10.1007/s11605-017-3366-5
    12 sg:pub.10.1007/s11605-018-3995-3
    13 sg:pub.10.1023/a:1010933404324
    14 sg:pub.10.1038/s41591-019-0462-y
    15 sg:pub.10.1038/s41598-018-21758-3
    16 sg:pub.10.1245/s10434-018-6558-7
    17 schema:datePublished 2022-03-01
    18 schema:datePublishedReg 2022-03-01
    19 schema:description BackgroundPatients 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 MethodsPatients 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).ResultsIn 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.ConclusionsWe 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.
    20 schema:genre article
    21 schema:isAccessibleForFree false
    22 schema:isPartOf N0b42f1ec432e4a6a91608e953b8a31ca
    23 N468406fde7214e4eb13e85286230be70
    24 sg:journal.1105545
    25 schema:keywords AUC
    26 BackgroundPatients
    27 ConclusionsWe
    28 Machine Learning Algorithms
    29 MethodsPatients
    30 ResultsIn total
    31 Supervised Machine Learning Algorithms
    32 accuracy
    33 algorithm
    34 area
    35 cancer
    36 characteristic curve
    37 convolutional neural network
    38 curative surgery
    39 curves
    40 data
    41 distant organ metastasis
    42 events
    43 first recurrence site
    44 first year
    45 forest
    46 further surgery
    47 further treatment
    48 high incidence
    49 high probability
    50 histology
    51 incidence
    52 indications
    53 learning algorithm
    54 learning methods
    55 liver
    56 lung
    57 lung metastases
    58 machine
    59 machine learning methods
    60 metastasis
    61 method
    62 model
    63 network
    64 neural network
    65 nonrecurrence
    66 organ metastasis
    67 pancreatic cancer
    68 patients
    69 patterns
    70 poor prognosis
    71 post-pancreatic surgery
    72 prediction
    73 predictive AUC
    74 probability
    75 prognosis
    76 random forest
    77 receiver
    78 recurrence
    79 recurrence events
    80 recurrence patterns
    81 recurrence site
    82 recurrent events
    83 respective sites
    84 retrospective study
    85 single-center retrospective study
    86 sites
    87 study
    88 supervised machine learning methods
    89 surgery
    90 terms
    91 test data
    92 timing
    93 timing of recurrence
    94 total
    95 training
    96 treatment
    97 years
    98 schema:name Prediction of Recurrence Pattern of Pancreatic Cancer Post-Pancreatic Surgery Using Histology-Based Supervised Machine Learning Algorithms: A Single-Center Retrospective Study
    99 schema:pagination 4624-4634
    100 schema:productId N2177635bc0644e768e672f7f54a7c8a6
    101 N27e3a9073a8245a8a0d85addd733d534
    102 Nf9342d5306a3432b86829e87fbdd3e4f
    103 schema:sameAs https://app.dimensions.ai/details/publication/pub.1145944672
    104 https://doi.org/10.1245/s10434-022-11471-x
    105 schema:sdDatePublished 2022-10-01T06:50
    106 schema:sdLicense https://scigraph.springernature.com/explorer/license/
    107 schema:sdPublisher N81a7827ed155462b95bf5e62ffb92749
    108 schema:url https://doi.org/10.1245/s10434-022-11471-x
    109 sgo:license sg:explorer/license/
    110 sgo:sdDataset articles
    111 rdf:type schema:ScholarlyArticle
    112 N0b42f1ec432e4a6a91608e953b8a31ca schema:issueNumber 7
    113 rdf:type schema:PublicationIssue
    114 N1c3e98ca2474446b9e0dd38e0219ff90 rdf:first sg:person.0651113351.24
    115 rdf:rest N690e7d55f7a64235b19a74f95f8aaf84
    116 N1d60ead4cb834cb9b182c4ef8c1f1363 rdf:first sg:person.01240213665.21
    117 rdf:rest N1c3e98ca2474446b9e0dd38e0219ff90
    118 N2177635bc0644e768e672f7f54a7c8a6 schema:name doi
    119 schema:value 10.1245/s10434-022-11471-x
    120 rdf:type schema:PropertyValue
    121 N27e3a9073a8245a8a0d85addd733d534 schema:name dimensions_id
    122 schema:value pub.1145944672
    123 rdf:type schema:PropertyValue
    124 N468406fde7214e4eb13e85286230be70 schema:volumeNumber 29
    125 rdf:type schema:PublicationVolume
    126 N5bfd578d32c04d77a18ed6e77df127d3 rdf:first sg:person.013042551555.87
    127 rdf:rest Nab2c7f903d534bb0bc7843a959328615
    128 N5f43890162d74117bdf5f0bb257508cf rdf:first sg:person.015754105744.32
    129 rdf:rest N1d60ead4cb834cb9b182c4ef8c1f1363
    130 N690e7d55f7a64235b19a74f95f8aaf84 rdf:first sg:person.014215735464.23
    131 rdf:rest Na8e5629555e449d5800ff19cfa51d919
    132 N6bd0c9bf1d004e69badfac499c13372a rdf:first sg:person.0612301703.87
    133 rdf:rest N91dd8ee78362494fac4d126fcd53b233
    134 N81a7827ed155462b95bf5e62ffb92749 schema:name Springer Nature - SN SciGraph project
    135 rdf:type schema:Organization
    136 N91dd8ee78362494fac4d126fcd53b233 rdf:first sg:person.01307772440.53
    137 rdf:rest rdf:nil
    138 Na8e5629555e449d5800ff19cfa51d919 rdf:first sg:person.011406547173.21
    139 rdf:rest N5bfd578d32c04d77a18ed6e77df127d3
    140 Nab2c7f903d534bb0bc7843a959328615 rdf:first sg:person.0770623646.53
    141 rdf:rest N6bd0c9bf1d004e69badfac499c13372a
    142 Nf9342d5306a3432b86829e87fbdd3e4f schema:name pubmed_id
    143 schema:value 35230581
    144 rdf:type schema:PropertyValue
    145 anzsrc-for:11 schema:inDefinedTermSet anzsrc-for:
    146 schema:name Medical and Health Sciences
    147 rdf:type schema:DefinedTerm
    148 anzsrc-for:1112 schema:inDefinedTermSet anzsrc-for:
    149 schema:name Oncology and Carcinogenesis
    150 rdf:type schema:DefinedTerm
    151 sg:journal.1105545 schema:issn 1068-9265
    152 1534-4681
    153 schema:name Annals of Surgical Oncology
    154 schema:publisher Springer Nature
    155 rdf:type schema:Periodical
    156 sg:person.011406547173.21 schema:affiliation grid-institutes:grid.410807.a
    157 schema:familyName Ito
    158 schema:givenName Hiromichi
    159 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011406547173.21
    160 rdf:type schema:Person
    161 sg:person.01240213665.21 schema:affiliation grid-institutes:grid.410807.a
    162 schema:familyName Ono
    163 schema:givenName Yoshihiro
    164 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01240213665.21
    165 rdf:type schema:Person
    166 sg:person.013042551555.87 schema:affiliation grid-institutes:grid.410807.a
    167 schema:familyName Sato
    168 schema:givenName Takafumi
    169 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013042551555.87
    170 rdf:type schema:Person
    171 sg:person.01307772440.53 schema:affiliation grid-institutes:grid.410807.a
    172 schema:familyName Takahashi
    173 schema:givenName Yu
    174 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01307772440.53
    175 rdf:type schema:Person
    176 sg:person.014215735464.23 schema:affiliation grid-institutes:grid.410807.a
    177 schema:familyName Oba
    178 schema:givenName Atsushi
    179 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.014215735464.23
    180 rdf:type schema:Person
    181 sg:person.015754105744.32 schema:affiliation grid-institutes:grid.410807.a
    182 schema:familyName Hayashi
    183 schema:givenName Koki
    184 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.015754105744.32
    185 rdf:type schema:Person
    186 sg:person.0612301703.87 schema:affiliation grid-institutes:grid.411966.d
    187 schema:familyName Saiura
    188 schema:givenName Akio
    189 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0612301703.87
    190 rdf:type schema:Person
    191 sg:person.0651113351.24 schema:affiliation grid-institutes:grid.486756.e
    192 schema:familyName Takamatsu
    193 schema:givenName Manabu
    194 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0651113351.24
    195 rdf:type schema:Person
    196 sg:person.0770623646.53 schema:affiliation grid-institutes:grid.410807.a
    197 schema:familyName Inoue
    198 schema:givenName Yosuke
    199 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0770623646.53
    200 rdf:type schema:Person
    201 sg:pub.10.1007/s00268-012-1622-0 schema:sameAs https://app.dimensions.ai/details/publication/pub.1023632975
    202 https://doi.org/10.1007/s00268-012-1622-0
    203 rdf:type schema:CreativeWork
    204 sg:pub.10.1007/s00268-017-4068-6 schema:sameAs https://app.dimensions.ai/details/publication/pub.1086104088
    205 https://doi.org/10.1007/s00268-017-4068-6
    206 rdf:type schema:CreativeWork
    207 sg:pub.10.1007/s00423-008-0296-4 schema:sameAs https://app.dimensions.ai/details/publication/pub.1003962277
    208 https://doi.org/10.1007/s00423-008-0296-4
    209 rdf:type schema:CreativeWork
    210 sg:pub.10.1007/s00423-019-01846-2 schema:sameAs https://app.dimensions.ai/details/publication/pub.1122984096
    211 https://doi.org/10.1007/s00423-019-01846-2
    212 rdf:type schema:CreativeWork
    213 sg:pub.10.1007/s00595-017-1531-9 schema:sameAs https://app.dimensions.ai/details/publication/pub.1085043240
    214 https://doi.org/10.1007/s00595-017-1531-9
    215 rdf:type schema:CreativeWork
    216 sg:pub.10.1007/s11605-008-0757-7 schema:sameAs https://app.dimensions.ai/details/publication/pub.1000057302
    217 https://doi.org/10.1007/s11605-008-0757-7
    218 rdf:type schema:CreativeWork
    219 sg:pub.10.1007/s11605-011-1605-8 schema:sameAs https://app.dimensions.ai/details/publication/pub.1051232405
    220 https://doi.org/10.1007/s11605-011-1605-8
    221 rdf:type schema:CreativeWork
    222 sg:pub.10.1007/s11605-017-3366-5 schema:sameAs https://app.dimensions.ai/details/publication/pub.1074192112
    223 https://doi.org/10.1007/s11605-017-3366-5
    224 rdf:type schema:CreativeWork
    225 sg:pub.10.1007/s11605-018-3995-3 schema:sameAs https://app.dimensions.ai/details/publication/pub.1107529106
    226 https://doi.org/10.1007/s11605-018-3995-3
    227 rdf:type schema:CreativeWork
    228 sg:pub.10.1023/a:1010933404324 schema:sameAs https://app.dimensions.ai/details/publication/pub.1024739340
    229 https://doi.org/10.1023/a:1010933404324
    230 rdf:type schema:CreativeWork
    231 sg:pub.10.1038/s41591-019-0462-y schema:sameAs https://app.dimensions.ai/details/publication/pub.1116596451
    232 https://doi.org/10.1038/s41591-019-0462-y
    233 rdf:type schema:CreativeWork
    234 sg:pub.10.1038/s41598-018-21758-3 schema:sameAs https://app.dimensions.ai/details/publication/pub.1101059633
    235 https://doi.org/10.1038/s41598-018-21758-3
    236 rdf:type schema:CreativeWork
    237 sg:pub.10.1245/s10434-018-6558-7 schema:sameAs https://app.dimensions.ai/details/publication/pub.1104607849
    238 https://doi.org/10.1245/s10434-018-6558-7
    239 rdf:type schema:CreativeWork
    240 grid-institutes:grid.410807.a schema:alternateName Division of Hepatobiliary and Pancreatic Surgery, Cancer Institute Hospital of the Japanese Foundation for Cancer Research, Koto-ku, Tokyo, Japan
    241 schema:name Division of Hepatobiliary and Pancreatic Surgery, Cancer Institute Hospital of the Japanese Foundation for Cancer Research, Koto-ku, Tokyo, Japan
    242 rdf:type schema:Organization
    243 grid-institutes:grid.411966.d schema:alternateName Department of Hepatobiliary-Pancreatic Surgery, Juntendo University Hospital, Bunkyo-ku, Tokyo, Japan
    244 schema:name Department of Hepatobiliary-Pancreatic Surgery, Juntendo University Hospital, Bunkyo-ku, Tokyo, Japan
    245 Division of Hepatobiliary and Pancreatic Surgery, Cancer Institute Hospital of the Japanese Foundation for Cancer Research, Koto-ku, Tokyo, Japan
    246 rdf:type schema:Organization
    247 grid-institutes:grid.486756.e schema:alternateName Division of Pathology, Department of Pathology, Cancer Institute, Cancer Institute Hospital of the Japanese Foundation for Cancer Research, Koto-ku, Tokyo, Japan
    248 schema:name Division of Pathology, Department of Pathology, Cancer Institute, Cancer Institute Hospital of the Japanese Foundation for Cancer Research, Koto-ku, Tokyo, Japan
    249 rdf:type schema:Organization
     




    Preview window. Press ESC to close (or click here)


    ...