Aline Mähringer-Kunz1, Franziska Wagner1, Felix Hahn1, Arndt Weinmann2,3, Sebastian Brodehl4, Sebastian Schotten1, Jan B Hinrichs5, Christoph Düber1, Peter R Galle2, Daniel Pinto Dos Santos6, Roman Kloeckner1. 1. Department of Diagnostic and Interventional Radiology, University Medical Center of the Johannes Gutenberg-University Mainz, Mainz, Germany. 2. Department of Internal Medicine, University Medical Center of the Johannes Gutenberg-University Mainz, Mainz, Germany. 3. Clinical Registry Unit (CRU), University Medical Center of the Johannes Gutenberg-University Mainz, Mainz, Germany. 4. Institute for Informatics, Johannes Gutenberg-University Mainz, Mainz, Germany. 5. Department of Interventional and Diagnostic Radiology, Hannover Medical School, Hanover, Germany. 6. Department of Radiology, University Hospital Cologne, Cologne, Germany.
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.
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.
Authors: Lukas Müller; Aline Mähringer-Kunz; Timo Alexander Auer; Uli Fehrenbach; Bernhard Gebauer; Johannes Haubold; Jens M Theysohn; Moon-Sung Kim; Jens Kleesiek; Thierno D Diallo; Michel Eisenblätter; Dominik Bettinger; Verena Steinle; Philipp Mayer; David Zopfs; Daniel Pinto Dos Santos; Roman Kloeckner Journal: Eur Radiol Date: 2022-08-20 Impact factor: 7.034
Authors: Lukas Müller; Aline Mähringer-Kunz; Simon Johannes Gairing; Friedrich Foerster; Arndt Weinmann; Fabian Bartsch; Lisa-Katharina Heuft; Janine Baumgart; Christoph Düber; Felix Hahn; Roman Kloeckner Journal: J Clin Med Date: 2021-05-12 Impact factor: 4.241
Authors: Lukas Müller; Felix Hahn; Aline Mähringer-Kunz; Fabian Stoehr; Simon J Gairing; Friedrich Foerster; Arndt Weinmann; Peter R Galle; Jens Mittler; Daniel Pinto Dos Santos; Michael B Pitton; Christoph Düber; Roman Kloeckner Journal: Front Oncol Date: 2021-06-10 Impact factor: 6.244