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

Identification of Hurthle cell cancers by non-operative fine-needle aspiration biopsy (FNAB) of thyroid nodulesis challenging. Resultingly, non-cancerous Hurthle lesions were conventionally distinguished from Hurthle 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 Hurthle cells in many FNAB. We 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 Hurthle 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 classifiersto sequentially triage Hurthle cell-containing FNAB, including: 1. presence of Hurthle cells, 2. presence of neoplastic Hurthle cells, and 3. presence of benign Hurthle cells. The final Hurthle cell Index utilizes 1048 nuclear and mitochondrial genes; and Hurthle 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. The accurate algorithmic depiction of this complex biological system among Hurthle subtypes results in a dramatic improvement of classification performance; specificity among Hurthle cell neoplasms increases from 11.8% with the GEC to 58.8% with the GSC, while maintaining the same sensitivity of 89%.