Category Ranking
98%
Total Visits
921
Avg Visit Duration
2 minutes
Citations
20
Article Abstract
Background: Multiple artificial intelligence (AI) systems have been approved to risk-stratify thyroid nodules through sonographic characterization. We sought to validate the ability of one such AI system, Koios DS (Koios Medical, Chicago, IL), to aid in improving risk stratification of indeterminate thyroid nodules.
Methods: A retrospective single-institution dataset was compiled of 28 cytologically indeterminate thyroid nodules having undergone molecular testing and surgical resection, with surgical pathology categorized as malignant or benign. Nodules were retrospectively evaluated with Koios DS. After nodule selection, automated and AI-adapter-derived Thyroid Imaging Reporting and Data System (TI-RADS) levels were recorded, and agreement with radiologist-derived levels was assessed using Cohen's κ statistic. The performance of malignancy classification was compared between the radiologist and AI-adapter. Biopsy thresholds were re-evaluated using the AI-adapter.
Results: In this cohort, 7 (25%) nodules were malignant on surgical pathology. The median nodule size was 2.4 cm (interquartile range: 1.8-2.9 cm). Median radiologist and automated TI-RADS levels were both 4, with κ 0.25 ("fair agreement"). Malignancy classification by the radiologist provided sensitivity 100%, specificity 33.3%, positive predictive value (PPV) 33.3%, and negative predictive value (NPV) 100%, compared with the AI-adapter's performance with sensitivity 85.7%, specificity 76.2%, PPV 54.5%, and NPV 94.1%. Using the AI-adapter, 14 of 28 biopsies would have been deferred, 13 of which were surgically benign.
Conclusion: Koios automated and radiologist-derived TI-RADS levels were in consistent agreement for indeterminate thyroid nodules. Malignancy reclassification with the AI-adapter improved PPV at minimal cost to NPV. Risk stratification with the addition of the AI-adapter may allow for more accurate patient counseling and the avoidance of biopsies in select cases that would otherwise be cytologically indeterminate.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1016/j.surg.2024.07.074 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
The role of artificial intelligence in surgeon-performed ultrasonographic evaluation of cytologically indeterminate thyroid nodules.
Am J Surg
September 2025
Department of Surgery, Queen Mary Hospital, the University of Hong Kong, Hong Kong. Electronic address:
Introduction: Evaluating indeterminate thyroid nodules(ITN) is challenging, especially without molecular tests. This study examines whether artificial intelligence (AI) assistance can improve ITN diagnostic accuracy and bridge expertise gaps in surgeon-performed ultrasound.
Methods: 134 ultrasound clips from 67 patients with ITN were reviewed by doctors of four levels: endocrine-surgery specialist, senior residents, junior residents, and medical student.
Diagnosis and management of thyroid nodule.
Curr Opin Endocrinol Diabetes Obes
October 2025
Department of Surgery, American Mission Hospital, Manama, Bahrain.
Purpose Of Review: To review the current medical evidence in the diagnosis and management of thyroid nodules.
Recent Findings: The widespread use of imaging modalities in recent years has led to frequent discovery of incidental thyroid nodules. These nodules are mostly benign (over 90%), hence precise insight in evaluating nodules of concern and following up other nodules is important to avoid unnecessary surgeries and its complications.
Cytologic atypia is predictive of increased risk of malignancy and BRAF mutations in thyroid follicular neoplasms (Bethesda category IV).
J Am Soc Cytopathol
July 2025
Department of Pathology, Dartmouth-Hitchcock Medical Center, Lebanon, New Hampshire.
Introduction: Molecular testing on thyroid fine needle aspirations with indeterminate cytology is integral to patient management. The aim of this study was to investigate the risk of malignancy in nodules diagnosed as Bethesda category IV, follicular neoplasm (FN), with and without cytologic atypia.
Methods: A total of 186 thyroid fine needle aspirations classified as Bethesda category IV (FN) were identified, and were categorized as FN with cytologic atypia or without cytologic atypia.
Circulating Biomarkers in Medullary Thyroid Carcinoma: Bridging Laboratory Complexities and Clinical Application Through Algorithm Design.
J Clin Med
August 2025
Department of Oncology and Nuclear Medicine, University Hospital Center Sestre Milosrdnice, 10000 Zagreb, Croatia.
Medullary thyroid carcinoma (MTC) is a rare (~2-5% of all thyroid cancers) neuroendocrine thyroid malignancy originating from parafollicular C-cells of the thyroid gland with variable biological behavior and potential for early metastasis. Diagnosis, staging, and surveillance are heavily reliant on circulating biomarkers. We aimed to provide a comprehensive overview of circulating biomarkers in the management of MTC and propose an integrated, evidence-based algorithm to guide clinical decision-making using both established and emerging biomarkers.
View Article and Find Full Text PDFMolecular Testing in Thyroid Nodules: How Much Does It Change Clinical Practice?
Biomedicines
August 2025
Department of Surgery, University of Alabama at Birmingham, Birmingham, AL 35233, USA.
Molecular testing is most commonly performed in evaluation of thyroid nodules with indeterminate Fine Needle Aspiration Biopsy (FNAB) results. However, in clinical practice, thyroidectomy may still be pursued in patients who present with clear clinical indications despite a benign molecular test result. The aim of this study is to identify clinical factors that influence the decision to proceed with surgery in the presence of a benign molecular test result.
View Article and Find Full Text PDF