Utilizing Machine Learning for Pre- and Postoperative Assessment of Patients Undergoing Resection for BCLC-0, A and B Hepatocellular Carcinoma: Implications for Resection Beyond the BCLC Guidelines
Background There is an ongoing debate about expanding the resection criteria for hepatocellular carcinoma (HCC) beyond the Barcelona Clinic Liver Cancer (BCLC) guidelines. We sought to determine the factors that held the most prognostic weight in the pre- and postoperative setting for each BCLC stag...
Gespeichert in:
| Veröffentlicht in: | Annals of surgical oncology 2020-03, Vol.27 (3), p.866-874 |
|---|---|
| Hauptverfasser: | , , , , , , , , , , , , , , , , , , , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 874 |
|---|---|
| container_issue | 3 |
| container_start_page | 866 |
| container_title | Annals of surgical oncology |
| container_volume | 27 |
| creator | Tsilimigras, Diamantis I. Mehta, Rittal Moris, Dimitrios Sahara, Kota Bagante, Fabio Paredes, Anghela Z. Farooq, Ayesha Ratti, Francesca Marques, Hugo P. Silva, Silvia Soubrane, Olivier Lam, Vincent Poultsides, George A. Popescu, Irinel Grigorie, Razvan Alexandrescu, Sorin Martel, Guillaume Workneh, Aklile Guglielmi, Alfredo Hugh, Tom Aldrighetti, Luca Endo, Itaru Pawlik, Timothy M. |
| description | Background
There is an ongoing debate about expanding the resection criteria for hepatocellular carcinoma (HCC) beyond the Barcelona Clinic Liver Cancer (BCLC) guidelines. We sought to determine the factors that held the most prognostic weight in the pre- and postoperative setting for each BCLC stage by applying a machine learning method.
Methods
Patients who underwent resection for BCLC-0, A and B HCC between 2000 and 2017 were identified from an international multi-institutional database. A Classification and Regression Tree (CART) model was used to generate homogeneous groups of patients relative to overall survival (OS) based on pre- and postoperative factors.
Results
Among 976 patients, 63 (6.5%) had BCLC-0, 745 (76.3%) had BCLC-A, and 168 (17.2%) had BCLC-B HCC. Five-year OS among BCLC-0/A and BCLC-B patients was 64.2% versus 50.2%, respectively (
p
= 0.011). The preoperative CART model selected α-fetoprotein (AFP) and Charlson comorbidity score (CCS) as the first and second most important preoperative factors of OS among BCLC-0/A patients, whereas radiologic tumor burden score (TBS) was the best predictor of OS among BCLC-B patients. The postoperative CART model revealed lymphovascular invasion as the best postoperative predictor of OS among BCLC-0/A patients, whereas TBS remained the best predictor of long-term outcomes among BCLC-B patients in the postoperative setting. On multivariable analysis, pathologic TBS independently predicted worse OS among BCLC-0/A (hazard ratio [HR] 1.04, 95% confidence interval [CI] 1.02–1.07) and BCLC-B patients (HR 1.13, 95% CI 1.06–1.19) undergoing resection.
Conclusion
Prognostic stratification of patients undergoing resection for HCC within and beyond the BCLC resection criteria should include assessment of AFP and comorbidities for BCLC-0/A patients, as well as tumor burden for BCLC-B patients. |
| doi_str_mv | 10.1245/s10434-019-08025-z |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_miscellaneous_2312804340</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2312804340</sourcerecordid><originalsourceid>FETCH-LOGICAL-c447t-97b2ec049d5ee21fbee42ec40d52cd40766b3259ef29f21b77a5a1122337e703</originalsourceid><addsrcrecordid>eNp9kc1u1DAUhSMEoj_wAiyQJTYsGvBvnLCbiaCtNIgRateRk9xMXSX24Jsgdd6P98LJFCqxYOWr43M-X-skyRtGPzAu1UdkVAqZUlakNKdcpYdnySlTUZJZzp7HmWZ5WvBMnSRniPeUMi2oepmcCJYVmSiy0-TX7Wh7e7BuR76a5s46IBswwc1C5wPZBkiJcS3Zehz9HoIZ7U8gK0RAHMCNxHdkG8U4Irl1LYSdn8PfAaEZrXcLZl1uypRekNXCWpMr2JvRN9D3U28CKU1orPOD-USuh31vGzMncYk-gdbw4GN6vIOFRy4n20IfV8ZXyYvO9AivH8_z5ObL55vyKt18u7wuV5u0kVKPaaFrDg2VRasAOOtqABkFSVvFm1ZSnWW14KqAjhcdZ7XWRhnGOBdCg6biPHl_xO6D_zEBjtVgcf6EceAnrLhgPJ87ma3v_rHe-ym4uFx0KapZrgsVXfzoaoJHDNBV-2AHEx4qRqu54-rYcRU7rpaOq0MMvX1ET_UA7d_In1KjQRwNGK_cDsLT2__B_gbrM7PQ</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2350718795</pqid></control><display><type>article</type><title>Utilizing Machine Learning for Pre- and Postoperative Assessment of Patients Undergoing Resection for BCLC-0, A and B Hepatocellular Carcinoma: Implications for Resection Beyond the BCLC Guidelines</title><source>SpringerLink Journals - AutoHoldings</source><creator>Tsilimigras, Diamantis I. ; Mehta, Rittal ; Moris, Dimitrios ; Sahara, Kota ; Bagante, Fabio ; Paredes, Anghela Z. ; Farooq, Ayesha ; Ratti, Francesca ; Marques, Hugo P. ; Silva, Silvia ; Soubrane, Olivier ; Lam, Vincent ; Poultsides, George A. ; Popescu, Irinel ; Grigorie, Razvan ; Alexandrescu, Sorin ; Martel, Guillaume ; Workneh, Aklile ; Guglielmi, Alfredo ; Hugh, Tom ; Aldrighetti, Luca ; Endo, Itaru ; Pawlik, Timothy M.</creator><creatorcontrib>Tsilimigras, Diamantis I. ; Mehta, Rittal ; Moris, Dimitrios ; Sahara, Kota ; Bagante, Fabio ; Paredes, Anghela Z. ; Farooq, Ayesha ; Ratti, Francesca ; Marques, Hugo P. ; Silva, Silvia ; Soubrane, Olivier ; Lam, Vincent ; Poultsides, George A. ; Popescu, Irinel ; Grigorie, Razvan ; Alexandrescu, Sorin ; Martel, Guillaume ; Workneh, Aklile ; Guglielmi, Alfredo ; Hugh, Tom ; Aldrighetti, Luca ; Endo, Itaru ; Pawlik, Timothy M.</creatorcontrib><description>Background
There is an ongoing debate about expanding the resection criteria for hepatocellular carcinoma (HCC) beyond the Barcelona Clinic Liver Cancer (BCLC) guidelines. We sought to determine the factors that held the most prognostic weight in the pre- and postoperative setting for each BCLC stage by applying a machine learning method.
Methods
Patients who underwent resection for BCLC-0, A and B HCC between 2000 and 2017 were identified from an international multi-institutional database. A Classification and Regression Tree (CART) model was used to generate homogeneous groups of patients relative to overall survival (OS) based on pre- and postoperative factors.
Results
Among 976 patients, 63 (6.5%) had BCLC-0, 745 (76.3%) had BCLC-A, and 168 (17.2%) had BCLC-B HCC. Five-year OS among BCLC-0/A and BCLC-B patients was 64.2% versus 50.2%, respectively (
p
= 0.011). The preoperative CART model selected α-fetoprotein (AFP) and Charlson comorbidity score (CCS) as the first and second most important preoperative factors of OS among BCLC-0/A patients, whereas radiologic tumor burden score (TBS) was the best predictor of OS among BCLC-B patients. The postoperative CART model revealed lymphovascular invasion as the best postoperative predictor of OS among BCLC-0/A patients, whereas TBS remained the best predictor of long-term outcomes among BCLC-B patients in the postoperative setting. On multivariable analysis, pathologic TBS independently predicted worse OS among BCLC-0/A (hazard ratio [HR] 1.04, 95% confidence interval [CI] 1.02–1.07) and BCLC-B patients (HR 1.13, 95% CI 1.06–1.19) undergoing resection.
Conclusion
Prognostic stratification of patients undergoing resection for HCC within and beyond the BCLC resection criteria should include assessment of AFP and comorbidities for BCLC-0/A patients, as well as tumor burden for BCLC-B patients.</description><identifier>ISSN: 1068-9265</identifier><identifier>EISSN: 1534-4681</identifier><identifier>DOI: 10.1245/s10434-019-08025-z</identifier><identifier>PMID: 31696396</identifier><language>eng</language><publisher>Cham: Springer International Publishing</publisher><subject>Hepatobiliary Tumors ; Hepatocellular carcinoma ; Learning algorithms ; Liver cancer ; Machine learning ; Medicine ; Medicine & Public Health ; Oncology ; Postoperative period ; Surgery ; Surgical Oncology ; α-Fetoprotein</subject><ispartof>Annals of surgical oncology, 2020-03, Vol.27 (3), p.866-874</ispartof><rights>Society of Surgical Oncology 2019</rights><rights>Annals of Surgical Oncology is a copyright of Springer, (2019). All Rights Reserved.</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c447t-97b2ec049d5ee21fbee42ec40d52cd40766b3259ef29f21b77a5a1122337e703</citedby><cites>FETCH-LOGICAL-c447t-97b2ec049d5ee21fbee42ec40d52cd40766b3259ef29f21b77a5a1122337e703</cites><orcidid>0000-0002-7994-9870</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://link.springer.com/content/pdf/10.1245/s10434-019-08025-z$$EPDF$$P50$$Gspringer$$H</linktopdf><linktohtml>$$Uhttps://link.springer.com/10.1245/s10434-019-08025-z$$EHTML$$P50$$Gspringer$$H</linktohtml><link.rule.ids>314,777,781,27905,27906,41469,42538,51300</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/31696396$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Tsilimigras, Diamantis I.</creatorcontrib><creatorcontrib>Mehta, Rittal</creatorcontrib><creatorcontrib>Moris, Dimitrios</creatorcontrib><creatorcontrib>Sahara, Kota</creatorcontrib><creatorcontrib>Bagante, Fabio</creatorcontrib><creatorcontrib>Paredes, Anghela Z.</creatorcontrib><creatorcontrib>Farooq, Ayesha</creatorcontrib><creatorcontrib>Ratti, Francesca</creatorcontrib><creatorcontrib>Marques, Hugo P.</creatorcontrib><creatorcontrib>Silva, Silvia</creatorcontrib><creatorcontrib>Soubrane, Olivier</creatorcontrib><creatorcontrib>Lam, Vincent</creatorcontrib><creatorcontrib>Poultsides, George A.</creatorcontrib><creatorcontrib>Popescu, Irinel</creatorcontrib><creatorcontrib>Grigorie, Razvan</creatorcontrib><creatorcontrib>Alexandrescu, Sorin</creatorcontrib><creatorcontrib>Martel, Guillaume</creatorcontrib><creatorcontrib>Workneh, Aklile</creatorcontrib><creatorcontrib>Guglielmi, Alfredo</creatorcontrib><creatorcontrib>Hugh, Tom</creatorcontrib><creatorcontrib>Aldrighetti, Luca</creatorcontrib><creatorcontrib>Endo, Itaru</creatorcontrib><creatorcontrib>Pawlik, Timothy M.</creatorcontrib><title>Utilizing Machine Learning for Pre- and Postoperative Assessment of Patients Undergoing Resection for BCLC-0, A and B Hepatocellular Carcinoma: Implications for Resection Beyond the BCLC Guidelines</title><title>Annals of surgical oncology</title><addtitle>Ann Surg Oncol</addtitle><addtitle>Ann Surg Oncol</addtitle><description>Background
There is an ongoing debate about expanding the resection criteria for hepatocellular carcinoma (HCC) beyond the Barcelona Clinic Liver Cancer (BCLC) guidelines. We sought to determine the factors that held the most prognostic weight in the pre- and postoperative setting for each BCLC stage by applying a machine learning method.
Methods
Patients who underwent resection for BCLC-0, A and B HCC between 2000 and 2017 were identified from an international multi-institutional database. A Classification and Regression Tree (CART) model was used to generate homogeneous groups of patients relative to overall survival (OS) based on pre- and postoperative factors.
Results
Among 976 patients, 63 (6.5%) had BCLC-0, 745 (76.3%) had BCLC-A, and 168 (17.2%) had BCLC-B HCC. Five-year OS among BCLC-0/A and BCLC-B patients was 64.2% versus 50.2%, respectively (
p
= 0.011). The preoperative CART model selected α-fetoprotein (AFP) and Charlson comorbidity score (CCS) as the first and second most important preoperative factors of OS among BCLC-0/A patients, whereas radiologic tumor burden score (TBS) was the best predictor of OS among BCLC-B patients. The postoperative CART model revealed lymphovascular invasion as the best postoperative predictor of OS among BCLC-0/A patients, whereas TBS remained the best predictor of long-term outcomes among BCLC-B patients in the postoperative setting. On multivariable analysis, pathologic TBS independently predicted worse OS among BCLC-0/A (hazard ratio [HR] 1.04, 95% confidence interval [CI] 1.02–1.07) and BCLC-B patients (HR 1.13, 95% CI 1.06–1.19) undergoing resection.
Conclusion
Prognostic stratification of patients undergoing resection for HCC within and beyond the BCLC resection criteria should include assessment of AFP and comorbidities for BCLC-0/A patients, as well as tumor burden for BCLC-B patients.</description><subject>Hepatobiliary Tumors</subject><subject>Hepatocellular carcinoma</subject><subject>Learning algorithms</subject><subject>Liver cancer</subject><subject>Machine learning</subject><subject>Medicine</subject><subject>Medicine & Public Health</subject><subject>Oncology</subject><subject>Postoperative period</subject><subject>Surgery</subject><subject>Surgical Oncology</subject><subject>α-Fetoprotein</subject><issn>1068-9265</issn><issn>1534-4681</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2020</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><recordid>eNp9kc1u1DAUhSMEoj_wAiyQJTYsGvBvnLCbiaCtNIgRateRk9xMXSX24Jsgdd6P98LJFCqxYOWr43M-X-skyRtGPzAu1UdkVAqZUlakNKdcpYdnySlTUZJZzp7HmWZ5WvBMnSRniPeUMi2oepmcCJYVmSiy0-TX7Wh7e7BuR76a5s46IBswwc1C5wPZBkiJcS3Zehz9HoIZ7U8gK0RAHMCNxHdkG8U4Irl1LYSdn8PfAaEZrXcLZl1uypRekNXCWpMr2JvRN9D3U28CKU1orPOD-USuh31vGzMncYk-gdbw4GN6vIOFRy4n20IfV8ZXyYvO9AivH8_z5ObL55vyKt18u7wuV5u0kVKPaaFrDg2VRasAOOtqABkFSVvFm1ZSnWW14KqAjhcdZ7XWRhnGOBdCg6biPHl_xO6D_zEBjtVgcf6EceAnrLhgPJ87ma3v_rHe-ym4uFx0KapZrgsVXfzoaoJHDNBV-2AHEx4qRqu54-rYcRU7rpaOq0MMvX1ET_UA7d_In1KjQRwNGK_cDsLT2__B_gbrM7PQ</recordid><startdate>20200301</startdate><enddate>20200301</enddate><creator>Tsilimigras, Diamantis I.</creator><creator>Mehta, Rittal</creator><creator>Moris, Dimitrios</creator><creator>Sahara, Kota</creator><creator>Bagante, Fabio</creator><creator>Paredes, Anghela Z.</creator><creator>Farooq, Ayesha</creator><creator>Ratti, Francesca</creator><creator>Marques, Hugo P.</creator><creator>Silva, Silvia</creator><creator>Soubrane, Olivier</creator><creator>Lam, Vincent</creator><creator>Poultsides, George A.</creator><creator>Popescu, Irinel</creator><creator>Grigorie, Razvan</creator><creator>Alexandrescu, Sorin</creator><creator>Martel, Guillaume</creator><creator>Workneh, Aklile</creator><creator>Guglielmi, Alfredo</creator><creator>Hugh, Tom</creator><creator>Aldrighetti, Luca</creator><creator>Endo, Itaru</creator><creator>Pawlik, Timothy M.</creator><general>Springer International Publishing</general><general>Springer Nature B.V</general><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>3V.</scope><scope>7TO</scope><scope>7X7</scope><scope>7XB</scope><scope>88E</scope><scope>8AO</scope><scope>8FI</scope><scope>8FJ</scope><scope>8FK</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>BENPR</scope><scope>CCPQU</scope><scope>FYUFA</scope><scope>GHDGH</scope><scope>H94</scope><scope>K9.</scope><scope>M0S</scope><scope>M1P</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>7X8</scope><orcidid>https://orcid.org/0000-0002-7994-9870</orcidid></search><sort><creationdate>20200301</creationdate><title>Utilizing Machine Learning for Pre- and Postoperative Assessment of Patients Undergoing Resection for BCLC-0, A and B Hepatocellular Carcinoma: Implications for Resection Beyond the BCLC Guidelines</title><author>Tsilimigras, Diamantis I. ; Mehta, Rittal ; Moris, Dimitrios ; Sahara, Kota ; Bagante, Fabio ; Paredes, Anghela Z. ; Farooq, Ayesha ; Ratti, Francesca ; Marques, Hugo P. ; Silva, Silvia ; Soubrane, Olivier ; Lam, Vincent ; Poultsides, George A. ; Popescu, Irinel ; Grigorie, Razvan ; Alexandrescu, Sorin ; Martel, Guillaume ; Workneh, Aklile ; Guglielmi, Alfredo ; Hugh, Tom ; Aldrighetti, Luca ; Endo, Itaru ; Pawlik, Timothy M.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c447t-97b2ec049d5ee21fbee42ec40d52cd40766b3259ef29f21b77a5a1122337e703</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2020</creationdate><topic>Hepatobiliary Tumors</topic><topic>Hepatocellular carcinoma</topic><topic>Learning algorithms</topic><topic>Liver cancer</topic><topic>Machine learning</topic><topic>Medicine</topic><topic>Medicine & Public Health</topic><topic>Oncology</topic><topic>Postoperative period</topic><topic>Surgery</topic><topic>Surgical Oncology</topic><topic>α-Fetoprotein</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Tsilimigras, Diamantis I.</creatorcontrib><creatorcontrib>Mehta, Rittal</creatorcontrib><creatorcontrib>Moris, Dimitrios</creatorcontrib><creatorcontrib>Sahara, Kota</creatorcontrib><creatorcontrib>Bagante, Fabio</creatorcontrib><creatorcontrib>Paredes, Anghela Z.</creatorcontrib><creatorcontrib>Farooq, Ayesha</creatorcontrib><creatorcontrib>Ratti, Francesca</creatorcontrib><creatorcontrib>Marques, Hugo P.</creatorcontrib><creatorcontrib>Silva, Silvia</creatorcontrib><creatorcontrib>Soubrane, Olivier</creatorcontrib><creatorcontrib>Lam, Vincent</creatorcontrib><creatorcontrib>Poultsides, George A.</creatorcontrib><creatorcontrib>Popescu, Irinel</creatorcontrib><creatorcontrib>Grigorie, Razvan</creatorcontrib><creatorcontrib>Alexandrescu, Sorin</creatorcontrib><creatorcontrib>Martel, Guillaume</creatorcontrib><creatorcontrib>Workneh, Aklile</creatorcontrib><creatorcontrib>Guglielmi, Alfredo</creatorcontrib><creatorcontrib>Hugh, Tom</creatorcontrib><creatorcontrib>Aldrighetti, Luca</creatorcontrib><creatorcontrib>Endo, Itaru</creatorcontrib><creatorcontrib>Pawlik, Timothy M.</creatorcontrib><collection>PubMed</collection><collection>CrossRef</collection><collection>ProQuest Central (Corporate)</collection><collection>Oncogenes and Growth Factors Abstracts</collection><collection>Health & Medical Collection</collection><collection>ProQuest Central (purchase pre-March 2016)</collection><collection>Medical Database (Alumni Edition)</collection><collection>ProQuest Pharma Collection</collection><collection>Hospital Premium Collection</collection><collection>Hospital Premium Collection (Alumni Edition)</collection><collection>ProQuest Central (Alumni) (purchase pre-March 2016)</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central</collection><collection>ProQuest One Community College</collection><collection>Health Research Premium Collection</collection><collection>Health Research Premium Collection (Alumni)</collection><collection>AIDS and Cancer Research Abstracts</collection><collection>ProQuest Health & Medical Complete (Alumni)</collection><collection>Health & Medical Collection (Alumni Edition)</collection><collection>Medical Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>MEDLINE - Academic</collection><jtitle>Annals of surgical oncology</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Tsilimigras, Diamantis I.</au><au>Mehta, Rittal</au><au>Moris, Dimitrios</au><au>Sahara, Kota</au><au>Bagante, Fabio</au><au>Paredes, Anghela Z.</au><au>Farooq, Ayesha</au><au>Ratti, Francesca</au><au>Marques, Hugo P.</au><au>Silva, Silvia</au><au>Soubrane, Olivier</au><au>Lam, Vincent</au><au>Poultsides, George A.</au><au>Popescu, Irinel</au><au>Grigorie, Razvan</au><au>Alexandrescu, Sorin</au><au>Martel, Guillaume</au><au>Workneh, Aklile</au><au>Guglielmi, Alfredo</au><au>Hugh, Tom</au><au>Aldrighetti, Luca</au><au>Endo, Itaru</au><au>Pawlik, Timothy M.</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Utilizing Machine Learning for Pre- and Postoperative Assessment of Patients Undergoing Resection for BCLC-0, A and B Hepatocellular Carcinoma: Implications for Resection Beyond the BCLC Guidelines</atitle><jtitle>Annals of surgical oncology</jtitle><stitle>Ann Surg Oncol</stitle><addtitle>Ann Surg Oncol</addtitle><date>2020-03-01</date><risdate>2020</risdate><volume>27</volume><issue>3</issue><spage>866</spage><epage>874</epage><pages>866-874</pages><issn>1068-9265</issn><eissn>1534-4681</eissn><abstract>Background
There is an ongoing debate about expanding the resection criteria for hepatocellular carcinoma (HCC) beyond the Barcelona Clinic Liver Cancer (BCLC) guidelines. We sought to determine the factors that held the most prognostic weight in the pre- and postoperative setting for each BCLC stage by applying a machine learning method.
Methods
Patients who underwent resection for BCLC-0, A and B HCC between 2000 and 2017 were identified from an international multi-institutional database. A Classification and Regression Tree (CART) model was used to generate homogeneous groups of patients relative to overall survival (OS) based on pre- and postoperative factors.
Results
Among 976 patients, 63 (6.5%) had BCLC-0, 745 (76.3%) had BCLC-A, and 168 (17.2%) had BCLC-B HCC. Five-year OS among BCLC-0/A and BCLC-B patients was 64.2% versus 50.2%, respectively (
p
= 0.011). The preoperative CART model selected α-fetoprotein (AFP) and Charlson comorbidity score (CCS) as the first and second most important preoperative factors of OS among BCLC-0/A patients, whereas radiologic tumor burden score (TBS) was the best predictor of OS among BCLC-B patients. The postoperative CART model revealed lymphovascular invasion as the best postoperative predictor of OS among BCLC-0/A patients, whereas TBS remained the best predictor of long-term outcomes among BCLC-B patients in the postoperative setting. On multivariable analysis, pathologic TBS independently predicted worse OS among BCLC-0/A (hazard ratio [HR] 1.04, 95% confidence interval [CI] 1.02–1.07) and BCLC-B patients (HR 1.13, 95% CI 1.06–1.19) undergoing resection.
Conclusion
Prognostic stratification of patients undergoing resection for HCC within and beyond the BCLC resection criteria should include assessment of AFP and comorbidities for BCLC-0/A patients, as well as tumor burden for BCLC-B patients.</abstract><cop>Cham</cop><pub>Springer International Publishing</pub><pmid>31696396</pmid><doi>10.1245/s10434-019-08025-z</doi><tpages>9</tpages><orcidid>https://orcid.org/0000-0002-7994-9870</orcidid><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 1068-9265 |
| ispartof | Annals of surgical oncology, 2020-03, Vol.27 (3), p.866-874 |
| issn | 1068-9265 1534-4681 |
| language | eng |
| recordid | cdi_proquest_miscellaneous_2312804340 |
| source | SpringerLink Journals - AutoHoldings |
| subjects | Hepatobiliary Tumors Hepatocellular carcinoma Learning algorithms Liver cancer Machine learning Medicine Medicine & Public Health Oncology Postoperative period Surgery Surgical Oncology α-Fetoprotein |
| title | Utilizing Machine Learning for Pre- and Postoperative Assessment of Patients Undergoing Resection for BCLC-0, A and B Hepatocellular Carcinoma: Implications for Resection Beyond the BCLC Guidelines |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-19T16%3A10%3A28IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Utilizing%20Machine%20Learning%20for%20Pre-%20and%20Postoperative%20Assessment%20of%20Patients%20Undergoing%20Resection%20for%20BCLC-0,%20A%20and%20B%20Hepatocellular%20Carcinoma:%20Implications%20for%20Resection%20Beyond%20the%20BCLC%20Guidelines&rft.jtitle=Annals%20of%20surgical%20oncology&rft.au=Tsilimigras,%20Diamantis%20I.&rft.date=2020-03-01&rft.volume=27&rft.issue=3&rft.spage=866&rft.epage=874&rft.pages=866-874&rft.issn=1068-9265&rft.eissn=1534-4681&rft_id=info:doi/10.1245/s10434-019-08025-z&rft_dat=%3Cproquest_cross%3E2312804340%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2350718795&rft_id=info:pmid/31696396&rfr_iscdi=true |