A novel machine learning algorithm to predict disease free survival after resection of hepatocellular carcinoma.
Hepatectomy
artificial intelligence
clinical oncology
hepatocellular carcinoma (HCC)
machine learning (ML)
Journal
Annals of translational medicine
ISSN: 2305-5839
Titre abrégé: Ann Transl Med
Pays: China
ID NLM: 101617978
Informations de publication
Date de publication:
Apr 2020
Apr 2020
Historique:
entrez:
13
5
2020
pubmed:
13
5
2020
medline:
13
5
2020
Statut:
ppublish
Résumé
Due to organ shortage, liver transplantation (LT) in hepatocellular carcinoma (HCC) patients can only be offered subsidiary to other curative treatments, including liver resection (LR). We aimed at developing and validating a machine-learning algorithm (ML) to predict which patients are sufficiently treated by LR. Twenty-six preoperatively available routine laboratory values along with standard clinical-pathological parameters [including the modified Glascow Prognostic Score (mGPS), the Kings Score (KS) and the Model of Endstage Liver Disease (MELD)] were retrieved from 181 patients who underwent partial LR due to HCC in non-cirrhosis or compensated cirrhosis from January 2007 through March 2018 at our institution. These data were processed using a Random Forest (RF)-based workflow, which included preprocessing, recursive feature elimination (RFE), resampling, training and cross-validation of the RF model. A subset of untouched patient data was used as a test cohort. Basing on the RF prediction, test data could be stratified according to high (HR) or low risk (LR) profile characteristics. RFE analysis provided 6 relevant outcome predictors: mGPS, aPTT, CRP, largest tumor size, number of lesions and age at time of operation. After down-sampling, the predictive value of our model was 0.788 (0.658-0.919) for early DFS. 16.7% of HR and 74.2% of LR patients survived 2 years of follow-up (P<0.001). Our RF model, based solely on clinical parameters, proved to be a powerful predictor of DFS. These results warrant a prospective study to improve the model for selection of suitable candidates for LR as alternative to transplantation. The predictive model is available online: tiny.cc/hcc_model.
Sections du résumé
BACKGROUND
BACKGROUND
Due to organ shortage, liver transplantation (LT) in hepatocellular carcinoma (HCC) patients can only be offered subsidiary to other curative treatments, including liver resection (LR). We aimed at developing and validating a machine-learning algorithm (ML) to predict which patients are sufficiently treated by LR.
METHODS
METHODS
Twenty-six preoperatively available routine laboratory values along with standard clinical-pathological parameters [including the modified Glascow Prognostic Score (mGPS), the Kings Score (KS) and the Model of Endstage Liver Disease (MELD)] were retrieved from 181 patients who underwent partial LR due to HCC in non-cirrhosis or compensated cirrhosis from January 2007 through March 2018 at our institution. These data were processed using a Random Forest (RF)-based workflow, which included preprocessing, recursive feature elimination (RFE), resampling, training and cross-validation of the RF model. A subset of untouched patient data was used as a test cohort. Basing on the RF prediction, test data could be stratified according to high (HR) or low risk (LR) profile characteristics.
RESULTS
RESULTS
RFE analysis provided 6 relevant outcome predictors: mGPS, aPTT, CRP, largest tumor size, number of lesions and age at time of operation. After down-sampling, the predictive value of our model was 0.788 (0.658-0.919) for early DFS. 16.7% of HR and 74.2% of LR patients survived 2 years of follow-up (P<0.001).
CONCLUSIONS
CONCLUSIONS
Our RF model, based solely on clinical parameters, proved to be a powerful predictor of DFS. These results warrant a prospective study to improve the model for selection of suitable candidates for LR as alternative to transplantation. The predictive model is available online: tiny.cc/hcc_model.
Identifiants
pubmed: 32395478
doi: 10.21037/atm.2020.04.16
pii: atm-08-07-434
pmc: PMC7210189
doi:
Types de publication
Journal Article
Langues
eng
Pagination
434Informations de copyright
2020 Annals of Translational Medicine. All rights reserved.
Déclaration de conflit d'intérêts
Conflicts of Interest: All authors have completed the ICMJE uniform disclosure form (available at http://dx.doi.org/10.21037/atm.2020.04.16). The authors have no conflicts of interest to declare.
Références
Ann Surg Treat Res. 2015 Aug;89(2):81-6
pubmed: 26236697
Surgery. 2015 Dec;158(6):1530-7
pubmed: 26298028
Gastroenterology. 2016 Apr;150(4):835-53
pubmed: 26795574
HPB (Oxford). 2015 Feb;17(2):168-75
pubmed: 25263399
Ann Transl Med. 2018 Aug;6(15):308
pubmed: 30211196
Eur Urol. 2015 Jun;67(6):1142-1151
pubmed: 25572824
Surg Oncol. 2017 Jun;26(2):178-187
pubmed: 28577724
Eur J Gastroenterol Hepatol. 2009 Jul;21(7):730-8
pubmed: 19430302
Neuropharmacology. 2009;56 Suppl 1:3-8
pubmed: 18617195
HPB (Oxford). 2011 Jul;13(7):494-502
pubmed: 21689233
BMJ. 2009 Jun 29;338:b2393
pubmed: 19564179
Liver Int. 2019 Aug;39(8):1478-1489
pubmed: 31131974
J Hepatol. 2018 Jul;69(1):182-236
pubmed: 29628281
Cancer. 2012 Jun 15;118(12):3191-8
pubmed: 22025126
Nat Rev Clin Oncol. 2014 Sep;11(9):525-35
pubmed: 25091611
World J Gastroenterol. 2016 Jan 7;22(1):232-52
pubmed: 26755873
Gastroenterol Res Pract. 2016;2016:4743808
pubmed: 26843858
Hepatology. 1998 Sep;28(3):751-5
pubmed: 9731568
J Surg Oncol. 2018 Mar;117(4):625-633
pubmed: 29165812
Br J Surg. 2012 Sep;99(9):1263-9
pubmed: 22864887
Hepatology. 2001 Feb;33(2):464-70
pubmed: 11172350
Hepatology. 2018 Aug;68(2):723-750
pubmed: 29624699
Dtsch Arztebl Int. 2014 Feb 14;111(7):101-6
pubmed: 24622679
Exp Mol Pathol. 2016 Oct;101(2):165-171
pubmed: 27554417
BMC Bioinformatics. 2011 Mar 17;12:77
pubmed: 21414208
Ann Surg. 2003 Sep;238(3):315-21; discussion 321-3
pubmed: 14501497
Liver Transpl. 2003 May;9(5):513-20
pubmed: 12740796
Surg Oncol. 2018 Dec;27(4):663-673
pubmed: 30449490
Medicine (Baltimore). 2015 Sep;94(36):e1486
pubmed: 26356714
J Cancer. 2018 Jan 1;9(1):148-156
pubmed: 29290780
Twin Res Hum Genet. 2011 Feb;14(1):1-15
pubmed: 21314251
Br J Cancer. 2012 Sep 4;107(6):988-93
pubmed: 22878374
Hepatology. 2018 Jan;67(1):358-380
pubmed: 28130846
Dtsch Arztebl Int. 2017 Aug 7;114(31-32):519-526
pubmed: 28835324
Hepatology. 2015 Jun;61(6):1957-67
pubmed: 25645298
Clin Cancer Res. 2019 Jul 1;25(13):3847-3855
pubmed: 30808773
Epidemiology. 2010 Jan;21(1):128-38
pubmed: 20010215