Conventional and machine learning-based risk scores for patients with early-stage hepatocellular carcinoma
1
조회
0
다운로드
2
인용
0
참고문헌
키워드
초록
Background/Aims: The performance of machine learning (ML) in predicting the outcomes of patients with hepatocellular carcinoma (HCC) remains uncertain. We aimed to develop risk scores using conventional methods and ML to categorize early-stage HCC patients into distinct prognostic groups. Methods: The study retrospectively enrolled 1,411 consecutive treatment-naïve patients with the Barcelona Clinic Liver Cancer (BCLC) stage 0 to A HCC from 2012 to 2021. The patients were randomly divided into a training cohort (n=988) and validation cohort (n=423). Two risk scores (CATS-IF and CATS-INF) were developed to predict overall survival (OS) in the training cohort using the conventional methods (Cox proportional hazards model) and ML-based methods (LASSO Cox regression), respectively. They were then validated and compared in the validation cohort. Results: In the training cohort, factors for the CATS-IF score were selected by the conventional method, including age, curative treatment, single large HCC, serum creatinine and alpha-fetoprotein levels, fibrosis-4 score, lymphocyte-to-monocyte ratio, and albumin-bilirubin grade. The CATS-INF score, determined by ML-based methods, included the above factors and two additional ones (aspartate aminotransferase and prognostic nutritional index). In the validation cohort, both CATS-IF score and CATS-INF score outperformed other modern prognostic scores in predicting OS, with the CATS-INF score having the lowest Akaike information criterion value. A calibration plot exhibited good correlation between predicted and observed outcomes for both scores. Conclusions: Both the conventional Cox-based CATS-IF score and ML-based CATS-INF score effectively stratified patients with early-stage HCC into distinct prognostic groups, with the CATS-INF score showing slightly superior performance.
Abstract
Background/Aims: The performance of machine learning (ML) in predicting the outcomes of patients with hepatocellular carcinoma (HCC) remains uncertain. We aimed to develop risk scores using conventional methods and ML to categorize early-stage HCC patients into distinct prognostic groups. Methods: The study retrospectively enrolled 1,411 consecutive treatment-naïve patients with the Barcelona Clinic Liver Cancer (BCLC) stage 0 to A HCC from 2012 to 2021. The patients were randomly divided into a training cohort (n=988) and validation cohort (n=423). Two risk scores (CATS-IF and CATS-INF) were developed to predict overall survival (OS) in the training cohort using the conventional methods (Cox proportional hazards model) and ML-based methods (LASSO Cox regression), respectively. They were then validated and compared in the validation cohort. Results: In the training cohort, factors for the CATS-IF score were selected by the conventional method, including age, curative treatment, single large HCC, serum creatinine and alpha-fetoprotein levels, fibrosis-4 score, lymphocyte-to-monocyte ratio, and albumin-bilirubin grade. The CATS-INF score, determined by ML-based methods, included the above factors and two additional ones (aspartate aminotransferase and prognostic nutritional index). In the validation cohort, both CATS-IF score and CATS-INF score outperformed other modern prognostic scores in predicting OS, with the CATS-INF score having the lowest Akaike information criterion value. A calibration plot exhibited good correlation between predicted and observed outcomes for both scores. Conclusions: Both the conventional Cox-based CATS-IF score and ML-based CATS-INF score effectively stratified patients with early-stage HCC into distinct prognostic groups, with the CATS-INF score showing slightly superior performance.
참고문헌 (49)
- Bray F, "Global cancer statistics 2018 : GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries", CA Cancer J Clin, 68, pp.394~424 (2018)
- Singal AG, "Epidemiology and surveillance for hepatocellular carcinoma : New trends", J Hepatol, 72, pp.250~261 (2020)
- Rinella ME, "A multisociety Delphi consensus statement on new fatty liver disease nomenclature", Hepatology, 78, pp.1966~1986 (2023)
- Ho SY, "Evolution of etiology, presentation, management and prognostic tool in hepatocellular carcinoma", Sci Rep, 10, pp.3925~ (2020)
- Hui VW, "Increasing antiviral treatment uptake improves survival in patients with HBV-related HCC", JHEP Rep, 2, pp.100152~ (2020)
- Dang H, "Cure with interferon-free direct-acting antiviral is associated with increased survival in patients with hepatitis C virus-related hepatocellular carcinoma from both East and West", Hepatology, 71, pp.1910~1922 (2020)
- Siegel RL, "Cancer statistics, 2015", CA Cancer J Clin, 65, pp.5~29 (2015)
- Reig M, "BCLC strategy for prognosis prediction and treatment recommendation : The 2022 update", J Hepatol, 76, pp.681~693 (2022)
- Fang KC, "The prognosis of single large hepatocellular carcinoma was distinct from Barcelona clinic liver cancer stage A or B : The role of albumin-bilirubin grade", Liver Cancer, 7, pp.335~358 (2018)
- Roayaie S, "The role of hepatic resection in the treatment of hepatocellular cancer", Hepatology, 62, pp.440~451 (2015)
- Chang CY, "The role of albumin-bilirubin grade in determining the outcomes of patients with very early-stage hepatocellular carcinoma", J Chin Med Assoc, 84, pp.136~143 (2021)
- Deo RC, "Machine learning in medicine", Circulation, 132, pp.1920~1930 (2015)
- Campagnini S, "Machine learning methods for functional recovery prediction and prognosis in post-stroke rehabilitation : a systematic review", J Neuroeng Rehabil, 19, pp.54~ (2022)
- Chen W, "Using machine learning techniques predicts prognosis of patients with Ewing sarcoma", J Orthop Res, 39, pp.2519~2527 (2021)
- Qu Y, "Machine learning models for prognosis prediction in endodontic microsurgery", J Dent, 118, pp.103947~ (2022)
- Zhao Z, "Necroptosisrelated lncRNAs : Predicting prognosis and the distinction between the cold and hot tumors in gastric cancer", J Oncol, 2021, pp.6718443~ (2021)
- Hsieh WY, "The impact of esophagogastric varices on the prognosis of patients with hepatocellular carcinoma", Sci Rep, 7, pp.42577~ (2017)
- Su CW, "Association between esophagogastric varices in hepatocellular carcinoma and poor prognosis after transarterial chemoembolization : A propensity score matching analysis", J Formos Med Assoc, 119, pp.610~620 (2020)
- Liao CY, "Differential prognoses among male and female patients with hepatocellular carcinoma", J Chin Med Assoc, 85, pp.554~565 (2022)
- Bruix J, "Management of hepatocellular carcinoma : an update", Hepatology, 53, pp.1020~1022 (2011)
- Teng W, "Tertiary prevention of HCC in chronic hepatitis B or C infected patients", Cancers(Basel), 13, pp.1729~ (2021)
- Su CW, "Impact of steatosis on prognosis of patients with early-stage hepatocellular carcinoma after hepatic resection", Ann Surg Oncol, 22, pp.2253~2261 (2015)
- Lee PC, "Liver stiffness measured by acoustic radiation force impulse elastography predicted prognoses of hepatocellular carcinoma after radiofrequency ablation", Sci Rep, 10, pp.2006~ (2020)
- Kao WY, "Hepatocellular carcinoma : Nomograms based on the albuminbilirubin grade to assess the outcomes of radiofrequency ablation", Radiology, 285, pp.670~680 (2017)
- Mantovani A, "Cancer-related inflammation", Nature, 454, pp.436~444 (2008)
- Yang YM, "Inflammation and liver cancer : Molecular mechanisms and therapeutic targets", Semin Liver Dis, 39, pp.26~42 (2019)
- Wu SJ, "Lymphocyte to monocyte ratio and prognostic nutritional index predict survival outcomes of hepatitis B virus-associated hepatocellular carcinoma patients after curative hepatectomy", J Surg Oncol, 114, pp.202~210 (2016)
- Yang YT, "The lymphocyte-to-monocyte ratio is a superior predictor of overall survival compared to established biomarkers in HCC patients undergoing liver resection", Sci Rep, 8, pp.2535~ (2018)
- Olingy CE, "Monocyte heterogeneity and functions in cancer", J Leukoc Biol, 106, pp.309~322 (2019)
- Lin S, "Clinicopathological and prognostic value of preoperative lymphocyte to monocyte ratio for hepatocellular carcinoma following curative resection : A meta-analysis including 4, 092 patients", Medicine(Baltimore), 100, pp.e24153~ (2021)
- Mano Y, "Lymphocyte-to-monocyte ratio is a predictor of survival after liver transplantation for hepatocellular carcinoma", Liver Transpl, 24, pp.1603~1611 (2018)
- Sakurai T, "Molecular link between liver fibrosis and hepatocellular carcinoma", Liver Cancer, 2, pp.365~366 (2013)
- Sterling RK, "Development of a simple noninvasive index to predict significant fibrosis in patients with HIV", HCV coinfection, 2006, pp.43, 1317~1325
- Kawaguchi T, "Enhanced liver fibrosis score as a predictive marker for hepatocellular carcinoma development after hepatitis C virus eradication", Mol Clin Oncol, 15, pp.215~ (2021)
- Tamaki N, "Change in fibrosis 4 index as predictor of high risk of incident hepatocellular carcinoma after eradication of hepatitis C virus", Clin Infect Dis, 73, pp.e3349~e3354 (2021)
- Okadome K, "Prognostic nutritional index, tumor-infiltrating lymphocytes, and prognosis in patients with esophageal cancer", Ann Surg, 271, pp.693~700 (2020)
- Lei K, "PNI-based nomograms to predict tumor progression and survival for patients with unresectable hepatocellular carcinoma undergoing transcatheter arterial chemoembolization", J Clin Med, 12, pp.486~ (2023)
- Chen W, "Prognostic nutritional index and neutrophil", lymphocyte ratio can serve as independent predictors of the prognosis of hepatocellular carcinoma patients receiving targeted therapy, 2022, pp.2022, 1389049~
- Wang D, "Prognostic nutritional index and systemic immune-inflammation index predict the prognosis of patients with HCC", J Gastrointest Surg, 25, pp.421~427 (2021)
- Johnson PJ, "Assessment of liver function in patients with hepatocellular carcinoma : a new evidence-based approachthe ALBI grade", J Clin Oncol, 33, pp.550~558 (2015)
- Chan AW, "Integration of albumin-bilirubin(ALBI)score into Barcelona Clinic Liver Cancer(BCLC)system for hepatocellular carcinoma", J Gastroenterol Hepatol, 31, pp.1300~1306 (2016)
- Jung YK, "BCLC stage B is a better designation for single large hepatocellular carcinoma than BCLC stage A", J Gastroenterol Hepatol, 31, pp.467~474 (2016)
- Cho Y, "Survival analysis of single large(>5 cm)hepatocellular carcinoma patients : BCLC A versus B", PLoS One, 11, pp.e0165722~ (2016)
- Zhong JH, "Optimizing stage of single large hepatocellular carcinoma:A study with subgroup analysis by tumor diameter", Medicine(Baltimore), 96, pp.e6608~ (2017)
- Pinato DJ, "A novel, externally validated inflammation-based prognostic algorithm in hepatocellular carcinoma : the prognostic nutritional index(PNI)", Br J Cancer, 106, pp.1439~1445 (2012)
- Zhang Z, "Time-varying covariates and coefficients in Cox regression models", Ann Transl Med, 6, pp.121~ (2018)
- Chan AWH, "Development of pre and post-operative models to predict early recurrence of hepatocellular carcinoma after surgical resection", J Hepatol, 69, pp.1284~1293 (2018)
- Su CW, "The effect of age on the long-term prognosis of patients with hepatocellular carcinoma after resection surgery : a propensity score matching analysis", Arch Surg, 147, pp.137~144 (2012)
- Fu CC, "The outcomes and prognostic factors of patients with hepatocellular carcinoma and normal serum alpha fetoprotein levels", J Formos Med Assoc, 122, pp.593~602 (2023)