PMID- 35389097
OWN - NLM
STAT- MEDLINE
DCOM- 20220627
LR  - 20220627
IS  - 1432-2307 (Electronic)
IS  - 0945-6317 (Linking)
VI  - 481
IP  - 1
DP  - 2022 Jul
TI  - Subtyping of hepatocellular adenoma: a machine learning-based approach.
PG  - 49-61
LID - 10.1007/s00428-022-03311-w [doi]
AB  - Subtyping of hepatocellular adenoma (HCA) is an important task in practice as 
      different subtypes may have different clinical outcomes and management 
      algorithms. Definitive subtyping is currently dependent on immunohistochemical 
      and molecular testing. The association between some morphologic/clinical features 
      and HCA subtypes has been reported; however, the predictive performance of these 
      features has been controversial. In this study, we attempted machine learning 
      based methods to select an efficient and parsimonious set of morphologic/clinical 
      features for differentiating a HCA subtype from the others, and then assessed the 
      performance of the selected features in identifying the correct subtypes. We 
      first examined 50 liver HCA resection specimens collected at the University of 
      Washington and Kobe University/Kings College London, including HNF1alpha-mutated HCA 
      (H-HCA) (n = 16), inflammatory HCA (I-HCA) (n = 20), beta-catenin activated HCA 
      (beta-HCA) (n = 8), and unclassified HCA (U-HCA) (n = 6). Twenty-six 
      morphologic/clinical features were assessed. We used LASSO (least absolute 
      shrinkage and selection operator) to select key features that could differentiate 
      a subtype from the others. We further performed SVM (support vector machine) 
      analysis to assess the performance (sensitivity, specificity, positive predictive 
      value (PPV), negative predictive value (NPV), and accuracy) of the selected 
      features in HCA subtyping in an independent cohort of liver resection samples 
      (n = 20) collected at the University of Wisconsin-Madison. With some overlap, 
      different combinations of morphologic/clinical features were selected for each 
      subtype. Based on SVM analysis, the selected features classified HCA into correct 
      subtypes with an overall accuracy of at least 80%. Our findings are useful for 
      initial diagnosis and subtyping of HCA, especially in clinical settings without 
      access to immunohistochemical and molecular assays.
CI  - (c) 2022. The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, 
      part of Springer Nature.
FAU - Liu, Yongjun
AU  - Liu Y
AD  - Department of Pathology and Laboratory Medicine, University of Wisconsin School 
      of Medicine and Public Health, Madison, WI, USA.
FAU - Liu, Yao-Zhong
AU  - Liu YZ
AD  - Department of Biostatistics and Data Science, Tulane University School of Public 
      Health and Tropical Medicine, New Orleans, LA, USA.
FAU - Sun, Lifu
AU  - Sun L
AD  - Department of Biostatistics and Data Science, Tulane University School of Public 
      Health and Tropical Medicine, New Orleans, LA, USA.
FAU - Zen, Yoh
AU  - Zen Y
AD  - Department of Diagnostic Pathology, Kobe University Graduate School of Medicine, 
      Kobe, Japan.
AD  - Institute of Liver Studies, King's College Hospital & King's College London, 
      London, UK.
FAU - Inomoto, Chie
AU  - Inomoto C
AD  - Department of Pathology, Tokai University, Isehara, Japan.
FAU - Yeh, Matthew M
AU  - Yeh MM
AD  - Department of Laboratory Medicine and Pathology, University of Washington School 
      of Medicine, 1959 NE Pacific Street, NE140D, Seattle, WA, 98195-6100, USA. 
      myeh@uw.edu.
AD  - Department of Medicine, University of Washington School of Medicine, Seattle, WA, 
      USA. myeh@uw.edu.
LA  - eng
PT  - Journal Article
DEP - 20220407
PL  - Germany
TA  - Virchows Arch
JT  - Virchows Archiv : an international journal of pathology
JID - 9423843
SB  - IM
MH  - *Adenoma, Liver Cell/diagnosis
MH  - *Carcinoma, Hepatocellular
MH  - Humans
MH  - *Liver Neoplasms/chemistry/diagnosis
MH  - Machine Learning
OTO - NOTNLM
OT  - Feature selection
OT  - Hepatocellular adenoma (HCA)
OT  - LASSO
OT  - Machine learning
OT  - Support vector machine (SVM)
EDAT- 2022/04/08 06:00
MHDA- 2022/06/28 06:00
CRDT- 2022/04/07 12:03
PHST- 2021/10/31 00:00 [received]
PHST- 2022/03/13 00:00 [accepted]
PHST- 2022/03/08 00:00 [revised]
PHST- 2022/04/08 06:00 [pubmed]
PHST- 2022/06/28 06:00 [medline]
PHST- 2022/04/07 12:03 [entrez]
AID - 10.1007/s00428-022-03311-w [pii]
AID - 10.1007/s00428-022-03311-w [doi]
PST - ppublish
SO  - Virchows Arch. 2022 Jul;481(1):49-61. doi: 10.1007/s00428-022-03311-w. Epub 2022 
      Apr 7.