Endocrine surgery — encompassing operations on the thyroid, parathyroid, adrenal glands, and neuroendocrine tumours — sits at the crossroads of complex biochemistry, high-resolution imaging, and precision oncology. Despite its technically demanding nature and the far-reaching metabolic consequences of surgical decisions, the field has only recently begun to engage systematically with artificial intelligence (AI) and machine learning (ML). Traditional risk models, guideline thresholds, and surgeon experience, while indispensable, are insufficiently granular for the heterogeneous clinical presentations encountered in contemporary practice. Meanwhile, advances in deep learning-based imaging analysis, multi-omic biomarker discovery, intra-operative guidance systems, and natural language processing are generating a rapidly growing body of evidence at the interface of AI and operative endocrinology. A dedicated, peer-reviewed platform to consolidate and critically appraise this emerging field is currently absent from the literature.
This Research Topic aims to establish a definitive cross-disciplinary collection at the intersection of AI and endocrine surgery. It will bring together original research, systematic reviews, and technology reports spanning the full surgical continuum: from AI-assisted pre-operative risk stratification and biomarker-guided patient selection, through intra-operative intelligent decision support, to post-operative recurrence prediction and dynamic re-stratification. The Topic seeks to identify methodological best practices for developing and validating AI tools in the endocrine surgical context, address the translational gap between proof-of-concept models and clinical implementation, and foster rigorous evaluation of explainability, fairness, and regulatory readiness. By uniting endocrine surgeons, computational scientists, endocrinologists, translational researchers, and bioethicists, the collection aspires to accelerate the responsible integration of AI into surgical endocrinology and ultimately improve patient outcomes.
We welcome submissions of original research articles, systematic reviews, meta-analyses, prospective validation studies, and technology reports. Case series employing AI-assisted methodology and interdisciplinary translational studies are particularly encouraged. Purely computational studies using public datasets must include appropriate clinical validation. Submissions should address one or more of the following sub-themes (not limited to):
• AI-assisted pre-operative workup: imaging analysis, nodule characterisation, and malignancy risk scoring in thyroid, parathyroid, adrenal, and neuroendocrine tumours
• Machine learning models for surgical risk prediction, complication forecasting, cure probability, and patient selection
• Digital, molecular, and liquid biopsy biomarkers guiding extent of resection and intra-operative decision-making
• Real-time intra-operative AI guidance: tissue identification, nerve/vessel protection, and augmented-reality surgical navigation
• AI-driven post-operative surveillance: biochemical response modelling, recurrence detection, and dynamic risk re-stratification
• Large language model and NLP applications in endocrine surgical documentation and shared decision-making
• Explainability, bias mitigation, and regulatory/ethical frameworks for AI tools in operative endocrinology
• Translational validation studies bridging AI-derived biomarkers from bench to bedside
Keywords: Artificial intelligence, Endocrine surgery, Precision medicine, Risk prediction, Biomarkers
Important note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.
