Affordable Access

Access to the full text

Identification of Hürthle cell cancers: solving a clinical challenge with genomic sequencing and a trio of machine learning algorithms

Authors
  • Hao, Yangyang1
  • Duh, Quan-Yang2
  • Kloos, Richard T.3
  • Babiarz, Joshua1
  • Harrell, R. Mack4, 5, 6
  • Traweek, S. Thomas7
  • Kim, Su Yeon1
  • Fedorowicz, Grazyna1
  • Walsh, P. Sean1
  • Sadow, Peter M.8
  • Huang, Jing1
  • Kennedy, Giulia C.1, 3
  • 1 Veracyte, Inc, Department of Research & Development, 6000 Shoreline Court, Suite 300, South San Francisco, CA, 94080, USA , South San Francisco (United States)
  • 2 Section of Endocrine Surgery, University of California San Francisco, Department of Surgery, San Francisco, CA, USA , San Francisco (United States)
  • 3 Veracyte, Inc, Department of Medical Affairs, South San Francisco, USA , South San Francisco (United States)
  • 4 The Memorial Center for Integrative Endocrine Surgery, Hollywood, FL, USA , Hollywood (United States)
  • 5 The Memorial Center for Integrative Endocrine Surgery, Weston, FL, USA , Weston (United States)
  • 6 The Memorial Center for Integrative Endocrine Surgery, Boca Raton, FL, USA , Boca Raton (United States)
  • 7 Thyroid Cytopathology Partners, Austin, TX, USA , Austin (United States)
  • 8 Head and Neck Pathology Division, Massachusetts General Hospital and Harvard Medical School, Department of Pathology, Boston, MA, USA , Boston (United States)
Type
Published Article
Journal
BMC Systems Biology
Publisher
Springer (Biomed Central Ltd.)
Publication Date
Apr 05, 2019
Volume
13
Issue
Suppl 2
Identifiers
DOI: 10.1186/s12918-019-0693-z
Source
Springer Nature
Keywords
License
Green

Abstract

BackgroundIdentification of Hürthle cell cancers by non-operative fine-needle aspiration biopsy (FNAB) of thyroid nodules is challenging. Resultingly, non-cancerous Hürthle lesions were conventionally distinguished from Hürthle cell cancers by histopathological examination of tissue following surgical resection. Reliance on histopathological evaluation requires patients to undergo surgery to obtain a diagnosis despite most being non-cancerous. It is highly desirable to avoid surgery and to provide accurate classification of benignity versus malignancy from FNAB preoperatively. In our first-generation algorithm, Gene Expression Classifier (GEC), we achieved this goal by using machine learning (ML) on gene expression features. The classifier is sensitive, but not specific due in part to the presence of non-neoplastic benign Hürthle cells in many FNAB.ResultsWe sought to overcome this low-specificity limitation by expanding the feature set for ML using next-generation whole transcriptome RNA sequencing and called the improved algorithm the Genomic Sequencing Classifier (GSC). The Hürthle identification leverages mitochondrial expression and we developed novel feature extraction mechanisms to measure chromosomal and genomic level loss-of-heterozygosity (LOH) for the algorithm. Additionally, we developed a multi-layered system of cascading classifiers to sequentially triage Hürthle cell-containing FNAB, including: 1. presence of Hürthle cells, 2. presence of neoplastic Hürthle cells, and 3. presence of benign Hürthle cells. The final Hürthle cell Index utilizes 1048 nuclear and mitochondrial genes; and Hürthle cell Neoplasm Index leverages LOH features as well as 2041 genes. Both indices are Support Vector Machine (SVM) based. The third classifier, the GSC Benign/Suspicious classifier, utilizes 1115 core genes and is an ensemble classifier incorporating 12 individual models.ConclusionsThe accurate algorithmic depiction of this complex biological system among Hürthle subtypes results in a dramatic improvement of classification performance; specificity among Hürthle cell neoplasms increases from 11.8% with the GEC to 58.8% with the GSC, while maintaining the same sensitivity of 89%.

Report this publication

Statistics

Seen <100 times