A novel machine learning algorithm to predict disease free survival after resection of hepatocellular carcinoma

Schoenberg, Markus Bo; Bucher, Julian Nikolaus; Koch, Dominik; Börner, N.; Hesse, Sebastian; Toni, Enrico N. De; Seidensticker, Max; Angele, Martin K.; Klein, Christoph; Bazhin, Alexandr V.; Werner, Jens; Guba, Markus

doi:10.21037/atm.2020.04.16

Cited by 25 publications

(19 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Until now mostly retrospective studies offered clinical prediction, which could not be confirmed in independent test cohorts [4,7]. Besides novel statistical techniques, some groups of variables show great promise for preoperative prediction of disease-free survival after resection [8]. Increasingly, the antitumor immune response in the cancerous tissue (tumor infiltrating leukocytes; TILs) has been studied as a relevant predictor for survival after HCC resection and transplantation [9][10][11].…”

Section: Introductionmentioning

confidence: 99%

Highly differential count of circulating and tumor infiltrating immune cells in patients with non-HCV/non-HBV hepatocellular carcinoma

Schoenberg

Zhu

Hao

et al. 2021

Cancer Immunol Immunother

Self Cite

View full text Add to dashboard Cite

Background Liver transplantation and liver resection are curative options for early hepatocellular carcinoma (HCC). The outcome is in part depended on the immunological response to the malignancy. In this study, we aimed to identify immunological profiles of non-HCV/non-HBV HCC patients. Methods Thirty-nine immune cell subsets were measured with multicolor flow cytometry. This immunophenotyping was performed in peripheral blood (PB) and tumor specimens of 10 HCC resection patients and 10 healthy donors. The signatures of the highly differential leukocyte count (hDIF) were analyzed using multidimensional techniques. Functional capability was measured using intracellular IFN-γ staining (Trial Registration DRKS00013567). Results The hDIF showed activation (subsets of T-, B-, NK- and dendritic cells) and suppression (subsets of myeloid-derived suppressor cells and T- and B-regulatory cells) of the antitumor response. Principal component analysis of PB and tumor infiltrating leukocytes (TIL) illustrated an antitumor activating gradient. TILs showed functional capability by secreting IFN-γ but did not kill HCC cells. Conclusions In conclusion, the measurement of the hDIF shows distinct differences in immune reactions against non-HBV/non-HCV HCC and illustrates an immunosuppressive gradient toward peripheral blood. Trial Registration DRKS00013567

show abstract

Section: Introductionmentioning

confidence: 99%

Highly differential count of circulating and tumor infiltrating immune cells in patients with non-HCV/non-HBV hepatocellular carcinoma

Schoenberg

Zhu

Hao

et al. 2021

Cancer Immunol Immunother

Self Cite

View full text Add to dashboard Cite

show abstract

“…The predictive variables within the BN model are based on the clinician's experience and knowledge, and the associated relationship between variables and outcome is not always clear; therefore, the performance of the BN model is generally confusing. Unlike ANN and BN, RF and SVM can be used to either select variables or develop models [48][49][50][51][52][53][54]. Wang et al [52] used the RF algorithm to select 30 radiomic features from 3144 MR texture features and developed a predictive RSF model for the 5-year survival of HCC following surgical resection with an area under curve (AUC) of 0.980.…”

Section: Surgical Resectionmentioning

confidence: 99%

Current updates in machine learning in the prediction of therapeutic outcome of hepatocellular carcinoma: what should we know?

et al. 2021

View full text Add to dashboard Cite

With the development of machine learning (ML) algorithms, a growing number of predictive models have been established for predicting the therapeutic outcome of patients with hepatocellular carcinoma (HCC) after various treatment modalities. By using the different combinations of clinical and radiological variables, ML algorithms can simulate human learning to detect hidden patterns within the data and play a critical role in artificial intelligence techniques. Compared to traditional statistical methods, ML methods have greater predictive effects. ML algorithms are widely applied in nearly all steps of model establishment, such as imaging feature extraction, predictive factor classification, and model development. Therefore, this review presents the literature pertaining to ML algorithms and aims to summarize the strengths and limitations of ML, as well as its potential value in prognostic prediction, after various treatment modalities for HCC.

show abstract

“…Due to organ shortage, liver transplantation in HCC patients can only be offered as an adjunct to other curative treatments, such as SR. An ML algorithm has also been applied to extract candidates who can be adequately treated by SR. Schoenberg et al . developed an RF model using preoperatively available routine laboratory values along with existing scores, such as the Glasgow Prognostic Score, Kings Score, and Model for End‐Stage Liver Disease 48 . The developed model showed an AUC of 0.788 for predicting early disease‐free survival (within 24 months after SR).…”

Section: Machine Learning Approach For Predicting the Response To Trementioning

confidence: 99%

Artificial intelligence in the diagnosis and management of hepatocellular carcinoma

Sato

Tateishi

Yatomi

et al. 2021

J of Gastro and Hepatol

View full text Add to dashboard Cite

Despite recent improvements in therapeutic interventions, hepatocellular carcinoma is still associated with a poor prognosis in patients with an advanced disease at diagnosis. Recently, significant progress has been made in image recognition through advances in the field of artificial intelligence (AI) (or machine learning), especially deep learning. AI is a multidisciplinary field that draws on the fields of computer science and mathematics for developing and implementing computer algorithms capable of maximizing the predictive accuracy from static or dynamic data sources using analytic or probabilistic models. Because of the multifactorial and complex nature of liver diseases, the machine learning approach to integrate multiple factors would appear to be an advantageous approach to improve the likelihood of making a precise diagnosis and predicting the response of treatment and prognosis of liver diseases. In this review, we attempted to summarize the potential use of AI in the diagnosis and management of liver diseases, especially hepatocellular carcinoma.

show abstract

A novel machine learning algorithm to predict disease free survival after resection of hepatocellular carcinoma

Cited by 25 publications

References 37 publications

Highly differential count of circulating and tumor infiltrating immune cells in patients with non-HCV/non-HBV hepatocellular carcinoma

Highly differential count of circulating and tumor infiltrating immune cells in patients with non-HCV/non-HBV hepatocellular carcinoma

Current updates in machine learning in the prediction of therapeutic outcome of hepatocellular carcinoma: what should we know?

Artificial intelligence in the diagnosis and management of hepatocellular carcinoma

Contact Info

Product

Resources

About