Alexander, EK,) of undetermined clinical significance,” “follicular neoplasm or lesion suspicious for follicular neoplasm,” or “suspicious cytologic findings” were 95%, 94%, and 85%, respectively. Analysis of 7 aspirates with false negative results revealed that 6 had a paucity of thyroid follicular cells, suggesting insufficient sampling of the nodule. These data suggest consideration of a more conservative approach for most patients with thyroid nodules that are cytologically indeterminate on fine-needle aspiration and benign according to gene-expression classifier results. COMMENT-Currently several organizations are developing “gene classifier systems” for use on thyroid FNA aspirates to help identify a sample as very likely benign, or very likely malignant. When applied to samples classified as “indeterminate”, “suspicious for follicular neoplasm”, or “suspicious cytologic findings” under the Bethesda classification system, this gene classifier system, developed by Veracyte, predicted a benign lesion with 85-92% sensitivity and 49-52% specificity, based on final review of surgical specimens. Seven false negative reports among the histologically malignant lesions were thought probably due to inadequate samples. The method is not appropriate for us on FNA samples classified as benign. However it appears that it could allow avoidance of surgery on many of the 15-30% of nodules now classified as indeterminate on FNA cytology. Since the method can not be expected to achieve 100% accuracy, these patients will deserve continued follow up for any sign of malignancy. Further experience in general practice, and information on other classifier systems currently in use, will define their role in patient care.