Predicting survival after transarterial chemoembolization for hepatocellular carcinoma using a neural network: A Pilot Study
- Publication type:
- Journal article
- Metadata:
-
- Autoren
- Aline Maehringer-Kunz
- Franziska Wagner
- Felix Hahn
- Arndt Weinmann
- Sebastian Brodehl
- Sebastian Schotten
- Jan B Hinrichs
- Christoph Dueber
- Peter R Galle
- Daniel Pinto dos Santos
- Roman Kloeckner
- Autoren-URL
- https://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=fis-test-1&SrcAuth=WosAPI&KeyUT=WOS:000509267100001&DestLinkType=FullRecord&DestApp=WOS_CPL
- DOI
- 10.1111/liv.14380
- eISSN
- 1478-3231
- Externe Identifier
- Clarivate Analytics Document Solution ID: KR3ZF
- PubMed Identifier: 31943703
- ISSN
- 1478-3223
- Ausgabe der Veröffentlichung
- 3
- Zeitschrift
- LIVER INTERNATIONAL
- Schlüsselwörter
- chemoembolization
- diagnostic accuracy study
- hepatocellular carcinoma
- neural network
- Paginierung
- 694 - 703
- Datum der Veröffentlichung
- 2020
- Status
- Published
- Titel
- Predicting survival after transarterial chemoembolization for hepatocellular carcinoma using a neural network: A Pilot Study
- Sub types
- Article
- Ausgabe der Zeitschrift
- 40
Data source: Web of Science (Lite)
- Other metadata sources:
-
- Abstract
- <jats:title>Abstract</jats:title><jats:sec><jats:title>Background and aims</jats:title><jats:p>Deciding when to repeat and when to stop transarterial chemoembolization (TACE) in patients with hepatocellular carcinoma (HCC) can be difficult even for experienced investigators. Our aim was to develop a survival prediction model for such patients undergoing TACE using novel machine learning algorithms and to compare it to conventional prediction scores, ART, ABCR and SNACOR.</jats:p></jats:sec><jats:sec><jats:title>Methods</jats:title><jats:p>For this retrospective analysis, 282 patients who underwent TACE for HCC at our tertiary referral centre between January 2005 and December 2017 were included in the final analysis. We built an artificial neural network (ANN) including all parameters used by the aforementioned risk scores and other clinically meaningful parameters. Following an 80:20 split, the first 225 patients were used for training; the more recently treated 20% were used for validation.</jats:p></jats:sec><jats:sec><jats:title>Results</jats:title><jats:p>The ANN had a promising performance at predicting 1‐year survival, with an area under the ROC curve (AUC) of 0.77 ± 0.13. Internal validation yielded an AUC of 0.83 ± 0.06, a positive predictive value of 87.5% and a negative predictive value of 68.0%. The sensitivity was 77.8% and specificity 81.0%. In a head‐to‐head comparison, the ANN outperformed the aforementioned scoring systems, which yielded lower AUCs (SNACOR 0.73 ± 0.07, ABCR 0.70 ± 0.07 and ART 0.54 ± 0.08). This difference reached significance for ART (<jats:italic>P</jats:italic> < .001); for ABCR and SNACOR significance was not reached (<jats:italic>P</jats:italic> = .143 and <jats:italic>P</jats:italic> = .201).</jats:p></jats:sec><jats:sec><jats:title>Conclusions</jats:title><jats:p>Artificial neural networks could be better at predicting patient survival after TACE for HCC than traditional scoring systems. Once established, such prediction models could easily be deployed in clinical routine and help determine optimal patient care.</jats:p></jats:sec>
- Autoren
- Aline Mähringer‐Kunz
- Franziska Wagner
- Felix Hahn
- Arndt Weinmann
- Sebastian Brodehl
- Sebastian Schotten
- Jan B Hinrichs
- Christoph Düber
- Peter R Galle
- Daniel Pinto dos Santos
- Roman Kloeckner
- DOI
- 10.1111/liv.14380
- eISSN
- 1478-3231
- ISSN
- 1478-3223
- Ausgabe der Veröffentlichung
- 3
- Zeitschrift
- Liver International
- Sprache
- en
- Online publication date
- 2020
- Paginierung
- 694 - 703
- Datum der Veröffentlichung
- 2020
- Status
- Published
- Herausgeber
- Wiley
- Herausgeber URL
- http://dx.doi.org/10.1111/liv.14380
- Datum der Datenerfassung
- 2023
- Titel
- Predicting survival after transarterial chemoembolization for hepatocellular carcinoma using a neural network: A Pilot Study
- Ausgabe der Zeitschrift
- 40
Data source: Crossref
- Abstract
- <h4>Background and aims</h4>Deciding when to repeat and when to stop transarterial chemoembolization (TACE) in patients with hepatocellular carcinoma (HCC) can be difficult even for experienced investigators. Our aim was to develop a survival prediction model for such patients undergoing TACE using novel machine learning algorithms and to compare it to conventional prediction scores, ART, ABCR and SNACOR.<h4>Methods</h4>For this retrospective analysis, 282 patients who underwent TACE for HCC at our tertiary referral centre between January 2005 and December 2017 were included in the final analysis. We built an artificial neural network (ANN) including all parameters used by the aforementioned risk scores and other clinically meaningful parameters. Following an 80:20 split, the first 225 patients were used for training; the more recently treated 20% were used for validation.<h4>Results</h4>The ANN had a promising performance at predicting 1-year survival, with an area under the ROC curve (AUC) of 0.77 ± 0.13. Internal validation yielded an AUC of 0.83 ± 0.06, a positive predictive value of 87.5% and a negative predictive value of 68.0%. The sensitivity was 77.8% and specificity 81.0%. In a head-to-head comparison, the ANN outperformed the aforementioned scoring systems, which yielded lower AUCs (SNACOR 0.73 ± 0.07, ABCR 0.70 ± 0.07 and ART 0.54 ± 0.08). This difference reached significance for ART (P < .001); for ABCR and SNACOR significance was not reached (P = .143 and P = .201).<h4>Conclusions</h4>Artificial neural networks could be better at predicting patient survival after TACE for HCC than traditional scoring systems. Once established, such prediction models could easily be deployed in clinical routine and help determine optimal patient care.
- Addresses
- Department of Diagnostic and Interventional Radiology, University Medical Center of the Johannes Gutenberg-University Mainz, Mainz, Germany.
- Autoren
- Aline Mähringer-Kunz
- Franziska Wagner
- Felix Hahn
- Arndt Weinmann
- Sebastian Brodehl
- Sebastian Schotten
- Jan B Hinrichs
- Christoph Düber
- Peter R Galle
- Daniel Pinto Dos Santos
- Roman Kloeckner
- DOI
- 10.1111/liv.14380
- eISSN
- 1478-3231
- Externe Identifier
- PubMed Identifier: 31943703
- Open access
- false
- ISSN
- 1478-3223
- Ausgabe der Veröffentlichung
- 3
- Zeitschrift
- Liver international : official journal of the International Association for the Study of the Liver
- Schlüsselwörter
- Humans
- Carcinoma, Hepatocellular
- Liver Neoplasms
- Treatment Outcome
- Chemoembolization, Therapeutic
- Retrospective Studies
- Pilot Projects
- Neural Networks, Computer
- Sprache
- eng
- Medium
- Print-Electronic
- Online publication date
- 2020
- Paginierung
- 694 - 703
- Datum der Veröffentlichung
- 2020
- Status
- Published
- Publisher licence
- CC BY
- Datum der Datenerfassung
- 2020
- Titel
- Predicting survival after transarterial chemoembolization for hepatocellular carcinoma using a neural network: A Pilot Study.
- Sub types
- Journal Article
- Ausgabe der Zeitschrift
- 40
Data source: Europe PubMed Central
- Abstract
- BACKGROUND AND AIMS: Deciding when to repeat and when to stop transarterial chemoembolization (TACE) in patients with hepatocellular carcinoma (HCC) can be difficult even for experienced investigators. Our aim was to develop a survival prediction model for such patients undergoing TACE using novel machine learning algorithms and to compare it to conventional prediction scores, ART, ABCR and SNACOR. METHODS: For this retrospective analysis, 282 patients who underwent TACE for HCC at our tertiary referral centre between January 2005 and December 2017 were included in the final analysis. We built an artificial neural network (ANN) including all parameters used by the aforementioned risk scores and other clinically meaningful parameters. Following an 80:20 split, the first 225 patients were used for training; the more recently treated 20% were used for validation. RESULTS: The ANN had a promising performance at predicting 1-year survival, with an area under the ROC curve (AUC) of 0.77 ± 0.13. Internal validation yielded an AUC of 0.83 ± 0.06, a positive predictive value of 87.5% and a negative predictive value of 68.0%. The sensitivity was 77.8% and specificity 81.0%. In a head-to-head comparison, the ANN outperformed the aforementioned scoring systems, which yielded lower AUCs (SNACOR 0.73 ± 0.07, ABCR 0.70 ± 0.07 and ART 0.54 ± 0.08). This difference reached significance for ART (P < .001); for ABCR and SNACOR significance was not reached (P = .143 and P = .201). CONCLUSIONS: Artificial neural networks could be better at predicting patient survival after TACE for HCC than traditional scoring systems. Once established, such prediction models could easily be deployed in clinical routine and help determine optimal patient care.
- Date of acceptance
- 2020
- Autoren
- Aline Mähringer-Kunz
- Franziska Wagner
- Felix Hahn
- Arndt Weinmann
- Sebastian Brodehl
- Sebastian Schotten
- Jan B Hinrichs
- Christoph Düber
- Peter R Galle
- Daniel Pinto Dos Santos
- Roman Kloeckner
- Autoren-URL
- https://www.ncbi.nlm.nih.gov/pubmed/31943703
- DOI
- 10.1111/liv.14380
- eISSN
- 1478-3231
- Ausgabe der Veröffentlichung
- 3
- Zeitschrift
- Liver Int
- Schlüsselwörter
- chemoembolization
- diagnostic accuracy study
- hepatocellular carcinoma
- neural network
- Carcinoma, Hepatocellular
- Chemoembolization, Therapeutic
- Humans
- Liver Neoplasms
- Neural Networks, Computer
- Pilot Projects
- Retrospective Studies
- Treatment Outcome
- Sprache
- eng
- Country
- United States
- Paginierung
- 694 - 703
- Datum der Veröffentlichung
- 2020
- Status
- Published
- Datum, an dem der Datensatz öffentlich gemacht wurde
- 2021
- Titel
- Predicting survival after transarterial chemoembolization for hepatocellular carcinoma using a neural network: A Pilot Study.
- Sub types
- Journal Article
- Ausgabe der Zeitschrift
- 40
Data source: PubMed
- Author's licence
- CC-BY
- Autoren
- Aline Mähringer-Kunz
- Franziska Wagner
- Felix Hahn
- Arndt Weinmann
- Sebastian Brodehl
- Sebastian Schotten
- Jan B Hinrichs
- Christoph Düber
- Peter R Galle
- Daniel Pinto dos Santos
- Roman Kloeckner
- Hosting institution
- Universitätsbibliothek Mainz
- Sammlungen
- JGU-Publikationen
- Resource version
- Published version
- DOI
- 10.1111/liv.14380
- File(s) embargoed
- false
- Open access
- true
- ISSN
- 1478-3231
- Ausgabe der Veröffentlichung
- 3
- Zeitschrift
- Liver international
- Schlüsselwörter
- 610 Medizin
- 610 Medical sciences
- Sprache
- eng
- Open access status
- Open Access
- Paginierung
- 694 - 703
- Datum der Veröffentlichung
- 2020
- Public URL
- https://openscience.ub.uni-mainz.de/handle/20.500.12030/6321
- Herausgeber
- Wiley-Blackwell
- Herausgeber URL
- https://doi.org/10.1111/liv.14380
- Datum der Datenerfassung
- 2021
- Datum, an dem der Datensatz öffentlich gemacht wurde
- 2021
- Zugang
- Public
- Titel
- Predicting survival after transarterial chemoembolization for hepatocellular carcinoma using a neural network : a pilot study
- Ausgabe der Zeitschrift
- 40
Files
mähringer-kunz_aline-predicting_sur-20210826101204684.pdf
Data source: OPENSCIENCE.UB
- Beziehungen:
- Property of