Analytical Verification Performance of Afirma Genomic Sequencing Classifier in the Diagnosis of Cytologically Indeterminate Thyroid Nodules

Artificial intelligence assisted diagnosis of early tc markers and its application

Thyroid cancer (TC) is a common endocrine malignancy with an increasing incidence worldwide. Early diagnosis is particularly important for TC patients, because it allows patients to receive treatment as early as possible. Artificial intelligence (AI) provides great advantages for complex healthcare systems by analyzing big data based on machine learning. Nowadays, AI is widely used in the early diagnosis of cancer such as TC. Ultrasound detection and fine needle aspiration biopsy are the main methods for early diagnosis of TC. AI has been widely used in the detection of malignancy in thyroid nodules by ultrasound images, cytopathology images and molecular markers. It shows great potential in auxiliary medical diagnosis. The latest clinical trial has shown that the performance of AI models matches with the diagnostic efficiency of experienced clinicians, and more efficient AI tools will be developed in the future. Therefore, in this review, we summarized the recent advances in the application of AI algorithms in assessing the risk of malignancy in thyroid nodules. The objective of this review was to provide a data base for the clinical use of AI-assisted diagnosis in TC, as well as to provide new ideas for the next generation of AI-assisted diagnosis in TC.

An old friend, a new insight: Calcitonin measurement in serum and aspiration needle washout fluids significantly increases the early and accurate detection of medullary thyroid cancer

BACKGROUND

The sensitivity of cytological (CY) evaluation after fine-needle aspiration (FNA) for detecting medullary thyroid carcinoma (MTC) is a subject of controversy. The routine use of serum calcitonin (CT) in patients with thyroid nodules is not universally adopted. The authors conducted CT screening of FNA washout fluid (FNA-CT) to address the diagnostic challenges. The objective was to assess the contributions of serum CT, FNA cytology (FNA-CY), and FNA-CT to the diagnosis.

METHODS

Between February 2019 and June 2022 (group 1), the authors prospectively screened the CT of patients with thyroid nodules. Both FNA-CY and FNA-CT were performed for patients with persistently elevated CT values. The sensitivity of FNA-CY, serum CT, and FNA-CT for accurate diagnosis was evaluated. Additionally, the authors retrospectively examined data from patients with thyroid nodules before CT screening (2008-2019) (group 2). They compared the characteristics of MTC patients in groups 1 and 2.

RESULTS

MTC was identified in 30 patients (0.25%) in group 1 and 19 (0.07%) in group 2. A FNA-CT cutoff value of 4085.5 pg/mL detected MTC with a sensitivity of 96.8%, and a serum CT cutoff value of 28.3 pg/mL detected MTC with a sensitivity of 86.7%. In contrast, FNA-CY detected MTC with a sensitivity of 42.4%. In group 1, 18 patients (60%) with MTC were diagnosed with microcarcinoma, whereas only two patients (10.5%) in group 2 had microcarcinoma.

CONCLUSIONS

This study detected MTC earlier by routinely measuring serum CT in all patients with nodular thyroid disease and performing FNA-CT in those with elevated values. FNA-CT and serum CT sensitivities were significantly higher than those of FNA-CY. This study revealed different FNA-CT cutoff values compared to other studies, emphasizing the need for determining clinic-specific cutoff values.

Combined Afirma Genomic Sequencing Classifier and TERT promoter mutation detection in molecular assessment of Bethesda III-VI thyroid nodules

Molecular analysis of thyroid nodules can provide diagnostic and prognostic information as well as indicate opportunities for targeted therapy. Whole RNA exome analysis offers information that can be leveraged to predict tumor behavior.

Risk stratification of cytologically indeterminate thyroid nodules with nondiagnostic or benign cytology on repeat FNA: Implications for molecular testing and surveillance

BACKGROUND

Evidence guiding the management of cytologically indeterminate thyroid nodules with nondiagnostic (ND) or benign cytology on repeat fine-needle aspiration (FNA) is limited. This study evaluates the utility of molecular testing and estimates the risk of noninvasive follicular thyroid neoplasm with papillary-like nuclear features (NIFTP) and cancer among such nodules.

METHODS

This was a retrospective single-institution review of thyroid nodules from adults that were classified as atypia of undetermined significance (AUS) or follicular neoplasm (FN) on initial FNA and underwent repeat FNA for cytology and Afirma testing (June 2013-July 2021). The association between repeat FNA cytology and RNA yield for Afirma was determined. Histologic outcomes were integrated with Afirma results to define end points for each nodule.

RESULTS

A total of 691 AUS and FN nodules underwent repeat FNA and Afirma testing. Diagnostic Afirma results were obtained in 98% of cases overall and in 91% of nodules with ND cytology on repeat FNA. Using combined molecular and histologic end points, the NIFTP and/or cancer prevalence for nodules with ND cytology on repeat FNA was 9% (95% confidence interval [CI], 0.042-0.182), falling between those nodules classified as benign (5%; 95% CI, 0.029-0.094) and those classified as AUS or FN (18%; 95% CI, 0.140-0.218) on repeat FNA, although not reaching statistical significance from either subgroup (p = .38 and .10, respectively).

CONCLUSIONS

AUS and FN nodules that are ND on repeat FNA have low but nonnegligible risk of NIFTP and/or cancer and may benefit from molecular testing, given the low test failure rate in this subgroup. Conversely, AUS and FN nodules reclassified as benign on repeat FNA have a very low risk of NIFTP and/or cancer and are unlikely to benefit from molecular testing.

Risk assessment of cytologically indeterminate thyroid nodules with integrated molecular testing and repeat biopsy: a surgical decision-oriented tool

BACKGROUND

The preoperative diagnosis of cytologically indeterminate thyroid nodules (ITNs) is very challenging. In this study, we aim to provide an integrated risk assessment for thyroid nodules with indeterminate cytology to guide surgical decision-making, which includes results of blood tests, molecular tests, and repeat fine-needle aspiration biopsy (FNAB).

METHODS

The study retrospectively included 265 ITNs between June 2019 and April 2022. According to our integrated risk assessment process that starts with blood testing, followed by supplementary DNA mutation detection on the first FNAB, and finally repeat FNAB, we divided the ITNs into high-risk and low-risk groups. Performance was evaluated with sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), area under the receiver operating characteristic curve (AUC), and the consistency between the risk evaluation and histological results.

RESULTS

Of the 265 ITNs, 87 were included in the risk assessment process. The risk assessment had a sensitivity of 84.1%, specificity of 83.3%, PPV of 95.1%, NPV of 57.7%, and AUC of 0.837. The nodules with consistent results between the risk groups and histological outcomes, which included malignant cases in the high-risk group and benign cases in the low-risk group, accounted for 83.9% of all risk-assessed nodules.

CONCLUSIONS

These data suggest that the integrated risk assessment might provide proper information for surgical decision-making in patients with ITNs.

Maximizing Small Biopsy Patient Samples: Unified RNA-Seq Platform Assessment of over 120,000 Patient Biopsies

Despite its wide-ranging benefits, whole-transcriptome or RNA exome profiling is challenging to implement in a clinical diagnostic setting. The Unified Assay is a comprehensive workflow wherein exome-enriched RNA-sequencing (RNA-Seq) assays are performed on clinical samples and analyzed by a series of advanced machine learning-based classifiers. Gene expression signatures and rare and/or novel genomic events, including fusions, mitochondrial variants, and loss of heterozygosity were assessed using RNA-Seq data generated from 120,313 clinical samples across three clinical indications (thyroid cancer, lung cancer, and interstitial lung disease). Since its implementation, the data derived from the Unified Assay have allowed significantly more patients to avoid unnecessary diagnostic surgery and have played an important role in guiding follow-up decisions regarding treatment. Collectively, data from the Unified Assay show the utility of RNA-Seq and RNA expression signatures in the clinical laboratory, and their importance to the future of precision medicine.

Preoperative Identification of Medullary Thyroid Carcinoma (MTC): Clinical Validation of the Afirma MTC RNA-Sequencing Classifier

Background: Cytopathological evaluation of thyroid fine-needle aspiration biopsy (FNAB) specimens can fail to raise preoperative suspicion of medullary thyroid carcinoma (MTC). The Afirma RNA-sequencing MTC classifier identifies MTC among FNA samples that are cytologically indeterminate, suspicious, or malignant (Bethesda categories III-VI). In this study we report the development and clinical performance of this MTC classifier. Methods: Algorithm training was performed with a set of 483 FNAB specimens (21 MTC and 462 non-MTC). A support vector machine classifier was developed using 108 differentially expressed genes, which includes the 5 genes in the prior Afirma microarray-based MTC cassette. Results: The final MTC classifier was blindly tested on 211 preoperative FNAB specimens with subsequent surgical pathology, including 21 MTC and 190 non-MTC specimens from benign and malignant thyroid nodules independent from those used in training. The classifier had 100% sensitivity (21/21 MTC FNAB specimens correctly called positive; 95% confidence interval [CI] = 83.9-100%) and 100% specificity (190/190 non-MTC FNAs correctly called negative; CI = 98.1-100%). All positive samples had pathological confirmation of MTC, while all negative samples were negative for MTC on surgical pathology. Conclusions: The RNA-sequencing MTC classifier accurately identified MTC from preoperative thyroid nodule FNAB specimens in an independent validation cohort. This identification may facilitate an MTC-specific preoperative evaluation and resulting treatment.

T cell subtype profiling measures exhaustion and predicts anti-PD-1 response

Anti-PD-1 therapy can provide long, durable benefit to a fraction of patients. The on-label PD-L1 test, however, does not accurately predict response. To build a better biomarker, we created a method called T Cell Subtype Profiling (TCSP) that characterizes the abundance of T cell subtypes (TCSs) in FFPE specimens using five RNA models. These TCS RNA models are created using functional methods, and robustly discriminate between naïve, activated, exhausted, effector memory, and central memory TCSs, without the reliance on non-specific, classical markers. TCSP is analytically valid and corroborates associations between TCSs and clinical outcomes. Multianalyte biomarkers based on TCS estimates predicted response to anti-PD-1 therapy in three different cancers and outperformed the indicated PD-L1 test, as well as Tumor Mutational Burden. Given the utility of TCSP, we investigated the abundance of TCSs in TCGA cancers and created a portal to enable researchers to discover other TCSP-based biomarkers.

Risk of malignancy in cytologically indeterminate thyroid nodules harboring thyroid stimulating hormone receptor mutations

OBJECTIVES

To evaluate the frequency and risk of malignancy of TSHRpI568T mutations discovered in indeterminate thyroid nodules (ITN) within the Veracyte CLIA laboratory undergoing Afirma^® Genomic Sequencing Classifier (GSC) testing, and to evaluate a broader cohort of TSHR variants and their categorization as Afirma GSC benign (GSC-B) or suspicious (GSC-S). Finally, we seek to assess the risk of malignancy (ROM) of this group of TSHR mutated ITN in the GSC-S category.

METHODS

ITN submitted to Veracyte for Afirma GSC testing between October 2017 and February 2022 were analyzed for TSHR variants and rates of GSC-B and GSC-S were calculated based upon BIII or IV cytology, by TSHR variant codon amino acid (AA) substitution, age, and gender. For GSC-S samples, surgical pathology reports were requested, and the rate of malignancy was calculated.

RESULTS

Five percent of the ITN samples harbored an isolated TSHR variant and 5% of those were classified as GSC-S. Among TSHRpI568T samples, 96% were GSC-B and of the GSC-S samples, 21% were malignant. Among an unselected group of TSHR, absent TSHRpI568T mutations, 16.3% of GSC-S samples were malignant, all but one with codon mutations in the transmembrane subdomains of the TSHR. This prompted a dedicated evaluation of transmembrane codons which revealed a malignancy rate of 10.7% among GSC-S nodules. In total, 13/85 (15.3%) TSHR mutated ITN with Afirma GSC-S results were found to be malignant.

CONCLUSIONS

TSHR variants are rare in ITN, and most are categorized as benign under Afirma GSC testing which carries a < 4% risk of malignancy. For GSC-S ITN with TSHR mutations, the risk of malignancy is ≥= 15%, which is clinically meaningful and may alter treatment or monitoring recommendations for patients.

Afirma Genomic Sequencing Classifier and Xpression Atlas Molecular Findings in Consecutive Bethesda III-VI Thyroid Nodules

CONTEXT

Broad genomic analyses among thyroid histologies have been described from relatively small cohorts.

OBJECTIVE

Investigate the molecular findings across a large, real-world cohort of thyroid fine-needle aspiration (FNA) samples.

DESIGN

Retrospective analysis of RNA sequencing data files.

SETTING

Clinical Laboratory Improvement Amendments laboratory performing Afirma Genomic Sequencing Classifier (GSC) and Xpression Atlas (XA) testing.

PARTICIPANTS

A total of 50 644 consecutive Bethesda III-VI nodules.

INTERVENTION

None.

MAIN OUTCOME MEASURES

Molecular test results.

RESULTS

Of 48 952 Bethesda III/IV FNAs studied, 66% were benign by Afirma GSC. The prevalence of BRAF V600E was 2% among all Bethesda III/IV FNAs and 76% among Bethesda VI FNAs. Fusions involving NTRK, RET, BRAF, and ALK were most prevalent in Bethesda V (10%), and 130 different gene partners were identified. Among small consecutive Bethesda III/IV sample cohorts with one of these fusions and available surgical pathology excision data, the positive predictive value of an NTRK or RET fusion for carcinoma or noninvasive follicular thyroid neoplasm with papillary-like nuclear features was >95%, whereas for BRAF and ALK fusions it was 81% and 67%, respectively. At least 1 genomic alteration was identified by the expanded Afirma XA panel in 70% of medullary thyroid carcinoma classifier-positive FNAs, 44% of Bethesda III or IV Afirma GSC suspicious FNAs, 64% of Bethesda V FNAs, and 87% of Bethesda VI FNAs.

CONCLUSIONS

This large study demonstrates that almost one-half of Bethesda III/IV Afirma GSC suspicious and most Bethesda V/VI nodules had at least 1 genomic variant or fusion identified, which may optimize personalized treatment decisions.

Effectiveness of Molecular Testing Techniques for Diagnosis of Indeterminate Thyroid Nodules: A Randomized Clinical Trial

Importance

Approximately 20% of thyroid nodules display indeterminate cytology. Molecular testing can refine the risk of malignancy and reduce the need for diagnostic hemithyroidectomy.

Objective

To compare the diagnostic performance between an RNA test (Afirma genomic sequencing classifier) and DNA-RNA test (ThyroSeq v3 multigene genomic classifier).

Design, Setting, and Participants

This parallel randomized clinical trial of monthly block randomization included patients in the UCLA Health system who underwent thyroid biopsy from August 2017 to January 2020 with indeterminate cytology (Bethesda System for Reporting Thyroid Cytopathology category III or IV).

Interventions

Molecular testing with the RNA test or DNA-RNA test.

Main Outcomes and Measures

Diagnostic test performance of the RNA test compared with the DNA-RNA test. The secondary outcome was comparison of test performance with prior versions of the molecular tests.

Results

Of 2368 patients, 397 were eligible for inclusion based on indeterminate cytology, and 346 (median [interquartile range] age, 55 [44-67] years; 266 [76.9%] women) were randomized to 1 of the 2 tests. In the total cohort assessed for eligibility, 3140 thyroid nodules were assessed, and 427 (13.6%) nodules were cytologically indeterminate. The prevalence of malignancy was 20% among indeterminate nodules. The benign call rate was 53% (95% CI, 47%-61%) for the RNA test and 61% (95% CI, 53%-68%) for the DNA-RNA test. The specificities of the RNA test and DNA-RNA test were 80% (95% CI, 72%-86%) and 85% (95% CI, 77%-91%), respectively (P = .33); the positive predictive values (PPV) of the RNA test and DNA-RNA test were 53% (95% CI, 40%-67%) and 63% (95% CI, 48%-77%), respectively (P = .33). The RNA test exhibited a higher PPV compared with the prior test version (Afirma gene expression classifier) (54% [95% CI, 40%-67%] vs 38% [95% CI, 27%-48%]; P = .01). The DNA-RNA test had no statistically significant difference in PPV compared with its prior version (ThyroSeq v2 next-generation sequencing) (63% [95% CI, 48%-77%] vs 58% [95% CI, 43%-73%]; P = .75). Diagnostic thyroidectomy was avoided in 87 (51%) patients tested with the RNA test and 83 (49%) patients tested with the DNA-RNA test. Surveillance ultrasonography was available for 90 nodules, of which 85 (94%) remained stable over a median of 12 months follow-up.

Conclusions and Relevance

Both the RNA test and DNA-RNA test displayed high specificity and allowed 49% of patients with indeterminate nodules to avoid diagnostic surgery. Although previous trials demonstrated that the prior version of the DNA-RNA test was more specific than the prior version of the RNA test, the current molecular test techniques have no statistically significant difference in performance.

Trial Registration

ClinicalTrials.gov Identifier: NCT02681328.

Limitations of preoperative cytology for medullary thyroid cancer: Proposal for improved preoperative diagnosis for optimal initial medullary thyroid carcinoma specific surgery

BACKGROUND

Preoperative diagnosis of medullary thyroid carcinoma (MTC) is often difficult, given the poor sensitivity of fine-needle aspiration (FNA) cytology for MTC. This study investigates this issue and presents recommendations for improving preoperative diagnostic paradigms in MTC cases.

DESIGN/METHOD

Histopathologically confirmed MTC patients with preoperative cytologic assessment of index nodules were enrolled. FNA diagnosis, final pathology, and surgery details were collected.

RESULTS

Out of 71 patients, 49 (69%) were diagnosed by FNA as either definitive MTC (35, 49%) or suspected MTC (14, 20%) and 22 (31%) patients had no indication of MTC on FNA.

CONCLUSION

In a tertiary-care setting, one-third of subjects had an FNA interpretation that did not suggest the possibility of MTC. The limitations of preoperative diagnosis are especially problematic for MTC as they can cause delayed or incomplete treatment. Additional testing is proposed to improve preoperative diagnosis and surgical care of MTC patients.

Use of artificial intelligence and machine learning for estimating malignancy risk of thyroid nodules

PURPOSE OF REVIEW

Current methods for thyroid nodule risk stratification are subjective, and artificial intelligence algorithms have been used to overcome this shortcoming. In this review, we summarize recent developments in the application of artificial intelligence algorithms for estimating the risks of malignancy in a thyroid nodule.

RECENT FINDINGS

Artificial intelligence have been used to predict malignancy in thyroid nodules using ultrasound images, cytopathology images, and molecular markers. Recent clinical trials have shown that artificial intelligence model's performance matched that of experienced radiologists and pathologists. Explainable artificial intelligence models are being developed to avoid the black box problem. Risk stratification algorithms using artificial intelligence for thyroid nodules are now commercially available in many countries.

SUMMARY

Artificial intelligence models could become a useful tool in a thyroidolgist's armamentarium as a decision support tool. Increased adoption of this emerging technology will depend upon increased awareness of the potential benefits and pitfalls in using artificial intelligence.

Quality of Life Following Molecular Marker Testing for Indeterminate Thyroid Nodules

OBJECTIVE

Thyroid cancer has a disproportionately negative effect on the quality of life (QOL) compared to malignancies with a worse prognosis. The QOL of patients with indeterminate thyroid nodules has not been previously evaluated. We aimed to assess the impact of molecular test results on the QOL of patients with indeterminate thyroid nodules.

METHODS

A short version of the Thyroid-Related Patient-Reported Outcome (ThyPro-39) was used to assess the QOL of patients who underwent thyroid fine needle aspiration (FNA) biopsy throughout UCLA Health from May, 2016, to June, 2017. All patients with indeterminate biopsy results underwent molecular testing with either Afirma Gene Expression Classifier or ThyroSeq v2 at the time of the initial biopsy. The QOL associated with symptoms of goiter, anxiety, depression, and impaired daily life were analyzed.

RESULTS

Of 825 consented patients, 366 completed the assessment (44.4% response rate). FNA results included 76% benign, 7% malignant, and 17% indeterminate. There were no differences in QOL between patients with a benign FNA and patients with an indeterminate result with benign molecular testing. In patients with an indeterminate FNA, symptoms of goiter (20.5 versus 10.4; P = .033) and depression (33.3 versus 21.0; P = .026) were worse for patients with suspicious versus benign molecular test results; however, no significant differences were observed in anxiety or impaired daily life.

CONCLUSION

A benign molecular test result may provide reassurance for patients with indeterminate thyroid nodules that the risk of malignancy is low. Long-term follow-up is necessary to determine if benign molecular test results maintain improved QOL.

The Afirma Xpression Atlas for thyroid nodules and thyroid cancer metastases: Insights to inform clinical decision-making from a fine-needle aspiration sample

Recent analytical and clinical validation of the Afirma Xpression Atlas (XA) demonstrates test reliability and the identification of genomic alterations that may inform patient management. The updated Afirma Genomic Sequencing Classifier and XA reports aim to optimize the understanding of these contributions, including decisions about observation versus surgery, the need for disease‐specific preoperative testing, associated neoplasm types, prognostics, the identification of molecular targets for systemic therapy, and the recognition of potential hereditary syndromes.

Testing for Afirma in Thyroid Nodules with High-Risk Indeterminate Cytology (TIR3B): First Italian Experience

A percentage of 15 to 30% of thyroid fine-needle aspiration (FNA) is indeterminate, i.e., TIR3A and TIR3B according to the Italian consensus for thyroid cytology. Afirma, a molecular analysis of thyroid FNA specimens, has recently gained popularity as an adjunct to microscopic cytological evaluation, in order to avoid diagnostic surgery in patients with indeterminate thyroid cytology. We described the first Italian experience with Afirma tests in a single Italian institution and assessed the performance of the Afirma test in TIR3B. Moreover, this is a preliminary study to assess the patient response to the offer of Afirma testing. The Afirma test was proposed to 67 patients with thyroid nodules that had yielded TIR3B cytology. Fifty-one patients (76.1%) chose the Afirma test, 25/51 underwent the test but the remaining 26 did not because of cost. A total of 41/67 (61.2%) patients underwent surgery, and 22/41 (53.7%) nodules were carcinomas. Of the 25 tested by Afirma, 9 (36%) were classified as Afirma-suspicious (Afirma-S); seven of them underwent surgery, and in 6/7 (85.7%), a cancer was proven at histology. Afirma is the procedure that many Italian patients with TIR3B lesions would choose. However, its routine clinical application in Italy is currently limited by high costs for the patient. When Afirma is performed in this setting of patients, the cancer risk of suspicious result is higher than that expected in all the series of TIR3B. Therefore, testing for Afirma in these nodules may be useful for managing patients and tailoring their surgical approach.