Gland surgery最新文献

{"title":"Development and internal validation of a multivariable MRI-based radiomics prediction model for preoperative cervical lymph node metastasis in thyroid cancer.","authors":"Shuo Shen, Mingrui Zhang, Fuling Huang, Chunyi Zhou, Yajing Liang, Yimin Liang, Huimei Yang, Ruilin Xiang, HaoJun Tang, Fu Li","doi":"10.21037/gs-2026-0259","DOIUrl":"10.21037/gs-2026-0259","url":null,"abstract":"<p><strong>Background: </strong>Accurate preoperative assessment of cervical lymph node metastasis (LNM) is crucial for surgical planning in thyroid cancer (TC), yet conventional ultrasound and computed tomography have limited sensitivity. This study aimed to develop and internally validate a magnetic resonance imaging (MRI)-based radiomics prediction model for preoperative LNM status in patients with TC.</p><p><strong>Methods: </strong>We prospectively enrolled 97 consecutive patients with pathologically confirmed TC who underwent preoperative MRI and cervical lymph node dissection at The First Affiliated Hospital of Guangxi Medical University from April 2017 to January 2019. The reference standard was histopathology. Patients were randomly divided into training and validation sets at a 7:3 ratio. A total of 1,691 radiomics features were extracted from T2-weighted imaging (T2WI) and T1-weighted heterogeneous contrast-enhanced imaging (T1C+), respectively. Using the Boruta algorithm, we selected a subset of optimized features for the radiomics signature, and a random forest algorithm was used to construct the radiomics model. Subsequently, the ability of this model to predict the status of lymph nodes of patients with TC was evaluated through receiver operating characteristic (ROC) curve analysis.</p><p><strong>Results: </strong>The combined model had better diagnostic performance than did models based on T2WI and T1C+ alone. Of the 97 patients, 61 (62.9%) were LNM-positive. In the training set, the area under the curve (AUC) values for the T2WI, T1C+, and combined models were 0.914, 0.959, and 0.963, respectively; the corresponding AUC values in the validation set were 0.853, 0.881, and 0.900, respectively. In the validation set, the combined model achieved an AUC of 0.900, with a sensitivity of 0.944 and specificity of 0.500.</p><p><strong>Conclusions: </strong>The MRI based radiomics model shows promising discriminative ability for preoperative LNM prediction in TC, but its low specificity (0.500) limits standalone clinical utility. External validation in larger cohorts is required before clinical implementation.</p>","PeriodicalId":12760,"journal":{"name":"Gland surgery","volume":"15 7","pages":"198"},"PeriodicalIF":1.9,"publicationDate":"2026-07-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13462804/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148727728","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Perioperative pancreatic ductal adenocarcinoma care in 2025: who needs neoadjuvant?-who needs radiation?","authors":"Runan Sheng, Qiong Wu, Kejia Lan","doi":"10.21037/gs-2026-0177","DOIUrl":"10.21037/gs-2026-0177","url":null,"abstract":"<p><p>Despite advances in multimodal therapy, pancreatic ductal adenocarcinoma (PDAC) remains a highly fatal tumor. For surgically resectable and borderline-resectable PDAC (BR-PDAC), the optimal integration of neoadjuvant chemotherapy and radiotherapy has yet to be established. Recent randomized studies (e.g., ESPAC-5F, NORPACT-1, Alliance A021501, and PREOPANC) and updated guidelines [of the National Comprehensive Cancer Network (NCCN), European Society for Medical Oncology (ESMO), and Japanese Society of Hepato‑Biliary‑Pancreatic Surgery (JASPAC)] now identify which patients are likely to benefit from treatment before surgery. For resectable PDAC, upfront surgery followed by adjuvant chemotherapy (typically modified FOLFIRINOX) remains the standard of care. However, new research (e.g., Prep-02/JSAP05) suggests that some high-risk patients may benefit from neoadjuvant therapy. For BR-PDAC, neoadjuvant multiagent chemotherapy (typically FOLFIRINOX) is widely accepted as the standard approach for increasing the likelihood of margin-negative resection and improving survival. Induction chemotherapy (with or without ablative radiotherapy) is commonly employed to downstage tumors in locally advanced PDAC. Debate continues as to the role of radiotherapy [either conventional chemoradiotherapy or stereotactic body radiotherapy (SBRT)]. PREOPANC reported a slight survival benefit for preoperative gemcitabine-based chemoradiotherapy in resectable PDAC and BR-PDAC, while Alliance A021501 reported no additional benefit from SBRT following FOLFIRINOX in BR-PDAC. Advanced imaging [multiphasic computed tomography/magnetic resonance imaging (CT/MRI) and positron emission tomography/computed tomography (PET/CT)] enhances the precision of staging and response evaluation. Molecular diagnostics, particularly germline/somatic BRCA and KRAS status and circulating tumor DNA (ctDNA) monitoring, are currently informing perioperative decisions and innovative therapeutics. As of 2025, personalized perioperative care guided by resectability status, tumor biology, and patient-specific characteristics has emerged as the key strategy for optimizing the selection of patients for neoadjuvant chemotherapy and/or radiotherapy. This review sought to synthesize the most recent evidence and guidelines on the treatment of resectable, BR, and locally advanced PDAC.</p>","PeriodicalId":12760,"journal":{"name":"Gland surgery","volume":"15 7","pages":"203"},"PeriodicalIF":1.9,"publicationDate":"2026-07-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13462953/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148722090","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A time‑dependent risk prediction model for distant metastasis in early‑stage breast cancer based on explainable ensemble learning: a retrospective cohort study.","authors":"Huijing Wu, Hongliang Ren, Shunxiang Liu, Lin Tang, Xuefeng Xie","doi":"10.21037/gs-2026-0163","DOIUrl":"10.21037/gs-2026-0163","url":null,"abstract":"<p><strong>Background: </strong>Distant metastasis is a leading cause of death in early-stage breast cancer, but current tools are imprecise or costly. This study aimed to develop an SHapley Additive exPlanations (SHAP)‑enhanced ensemble learning model using routine clinicopathological features to predict metastasis risk.</p><p><strong>Methods: </strong>This retrospective cohort study enrolled 351 patients with stage I-III breast cancer diagnosed between 2016 and 2024. The primary endpoint was distant metastasis‑free survival (DMFS). Comprehensive clinicopathological variables were refined using recursive feature elimination with cross‑validation. A stacking ensemble framework was constructed incorporating CoxNet, random survival forest (RSF), gradient boosting survival trees (GBST), and DeepSurv as base learners, with LightGBM as the meta‑learner. Model performance was assessed using the concordance index (C‑index), time‑dependent area under the curve (AUC), integrated Brier score, and calibration curves. SHAP was applied for global and local interpretability.</p><p><strong>Results: </strong>During a median follow‑up of 42 months, 89 distant metastasis events occurred. Eight core predictors were identified. The Stack‑LightGBM model achieved a global C‑index of 0.82 [95% confidence interval (CI): 0.77-0.87] and time‑dependent AUCs of 0.85 (95% CI: 0.80-0.90), 0.82 (95% CI: 0.77-0.87), and 0.79 (95% CI: 0.74-0.84) for 1‑, 3‑, and 5‑year DMFS, respectively, outperforming all single models. SHAP analysis revealed N stage and Ki‑67 as dominant risk drivers, with non‑linear effects and clinically meaningful feature interactions. Kaplan-Meier (KM) analysis yielded 5‑year distant metastasis‑free survival rates of 95.2%, 78.5%, and 51.3% for low‑, intermediate‑, and high‑risk groups, respectively (log‑rank P<0.001). Fine‑Gray competing risk analysis accounting for non‑breast cancer death gave 5‑year cumulative incidence of distant metastasis of 4.8%, 21.5%, and 48.7%, respectively. Decision curve analysis (DCA) confirmed positive net clinical benefit.</p><p><strong>Conclusions: </strong>This SHAP‑enhanced interpretable ensemble model provides accurate, transparent, and individualized prediction of distant metastasis risk using routine clinicopathological data, offering a practical tool to refine risk stratification and guide adjuvant therapy without additional genomic testing.</p>","PeriodicalId":12760,"journal":{"name":"Gland surgery","volume":"15 7","pages":"187"},"PeriodicalIF":1.9,"publicationDate":"2026-07-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13462873/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148721394","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Computed tomography quantitative imaging features for pancreatic ductal adenocarcinoma after neoadjuvant therapy: a narrative review.","authors":"Hushuang Duan, Yan Deng, Yingping Huang, Peijun Tang, Xin Wen, Xinghui Li, Xiaoming Zhang","doi":"10.21037/gs-2026-0239","DOIUrl":"10.21037/gs-2026-0239","url":null,"abstract":"<p><strong>Background and objective: </strong>Pancreatic ductal adenocarcinoma (PDAC) is one of the most lethal solid malignancies. Neoadjuvant therapy (NAT) has been routinely used in borderline resectable and locally advanced cases, now it is also gradually expanding to some resectable cases. Post-NAT assessment on computed tomography (CT) is intrinsically challenging, as therapy-induced stromal remodeling, fibrosis, and inflammation may obscure viable tumor, while size-based criteria correlate poorly with pathological response and survival. This narrative review aims to synthesize CT-based quantitative imaging features for PDAC after NAT and to clarify how these imaging biomarkers may support clinically relevant multidisciplinary decision-making.</p><p><strong>Methods: </strong>A narrative review was conducted using a three-layer literature identification strategy. A primary search of PubMed and Web of Science Core Collection was performed on 7 April 2026 to identify English-language articles published from 2013 to 2026. The search focused on PDAC, NAT, CT, and CT-derived quantitative approaches, including radiomics, perfusion CT, dual-energy/spectral CT, and photon-counting CT (PCCT), together with clinically relevant endpoints such as response, resectability, margin status, survival, recurrence, and prognosis. Targeted supplementary retrieval and manual anchor retrieval were additionally used for key reviews, foundational pathology and tumor microenvironment (TME) references, complementary magnetic resonance imaging (MRI) and positron emission tomography (PET) literature, and methodological framework papers.</p><p><strong>Key content and findings: </strong>Quantitative CT features after NAT can be organized around four multidisciplinary team (MDT) decisions: assessment of tumor-vessel interface resectability and the probability of margin-negative (R0) resection, NAT stewardship, surgical-window timing, and early recurrence risk stratification. The most informative measurement layers include interpretable morphologic and enhancement-based metrics, longitudinal delta features, perfusion-derived functional parameters, iodine- and material-sensitive metrics from energy-resolved CT, and multi-compartment radiomics or habitat analysis.</p><p><strong>Conclusions: </strong>Building on this evidence, we outline a pragmatic, CT-centric measurement ladder that progresses from interpretable enhancement and iodine metrics to interface focused features and habitat-level heterogeneity, aiming to reduce inter-reader variability and improve multicenter reproducibility, with MRI and PET positioned as complementary modalities for future multimodal validation.</p>","PeriodicalId":12760,"journal":{"name":"Gland surgery","volume":"15 7","pages":"201"},"PeriodicalIF":1.9,"publicationDate":"2026-07-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13462682/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148722821","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Development and validation of a predictive nomogram for cervical lymph node metastasis in aspect ratio ≥1 papillary thyroid carcinoma using ultrasonic features and serum calcitonin.","authors":"Yan Liu, Yuchen He, Jianwei He, Zhenhao Zheng, Xichen Yao, Tianxin Liu, Ziyu Liu, Ruyan Zhou, Wen Liu, Jun Li","doi":"10.21037/gs-2026-0193","DOIUrl":"10.21037/gs-2026-0193","url":null,"abstract":"<p><strong>Background: </strong>Preoperative prediction of cervical lymph node metastasis (CLNM) remains challenging in patients with papillary thyroid carcinoma (PTC) exhibiting an aspect ratio ≥1, a subgroup in which ultrasound alone has limited sensitivity (approximately 50%) and no dedicated predictive model currently exists. This study aimed to develop and internally validate a predictive nomogram combining ultrasonic features and serum calcitonin for CLNM in this specific population.</p><p><strong>Methods: </strong>This retrospective study consecutively enrolled 156 patients with aspect ratio ≥1 PTC who underwent thyroidectomy and neck lymph node dissection at a single center (November 2023 to June 2025). The gold standard outcome was pathologically confirmed CLNM. Forty-six candidate predictors (clinical, ultrasonographic, and serological variables) were collected. Predictor selection was performed using least absolute shrinkage and selection operator (LASSO) regression with 10-fold cross-validation, followed by multivariate logistic regression. A nomogram was constructed and internally validated using 1,000 bootstrap resamples. Model performance was assessed by area under the curve (AUC), calibration curve, sensitivity, specificity, and decision curve analysis (DCA).</p><p><strong>Results: </strong>Among 156 patients [116 females, 40 males; median age 52 years, interquartile range (IQR), 45-57 years], CLNM was present in 48 patients (30.8%). Five independent predictors were identified: multifocality [odds ratio (OR) =5.87; 95% confidence interval (CI): 1.85-18.66], maximum diameter ≥1 cm (OR =11.57; 95% CI: 2.26-59.16), ill-defined margin (OR =7.43; 95% CI: 2.06-26.76), microcalcifications (OR =3.43; 95% CI: 1.19-9.93), and serum calcitonin (OR =1.44; 95% CI: 1.08-1.92 per pg/mL). The nomogram achieved an apparent AUC of 0.834 (95% CI: 0.767-0.901) and a bootstrap-corrected AUC of 0.813. At the optimal probability cutoff of 0.264, sensitivity was 81.2% and specificity 75.9%. Calibration showed good agreement (Hosmer-Lemeshow P=0.41), and DCA demonstrated net clinical benefit across a threshold probability range of 5-80%.</p><p><strong>Conclusions: </strong>This nomogram combining five preoperative predictors shows satisfactory discriminative ability for CLNM in patients with aspect ratio ≥1 PTC. However, given the single-center design, modest sample size, and lack of external validation, these findings should be considered preliminary. External validation in independent multicenter cohorts is required before clinical application.</p>","PeriodicalId":12760,"journal":{"name":"Gland surgery","volume":"15 7","pages":"185"},"PeriodicalIF":1.9,"publicationDate":"2026-07-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13462562/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148721760","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Standard imaging-guided chest wall perforator flap reconstruction without intraoperative handheld Doppler for granulomatous lobular mastitis: a simplified approach for resource-limited settings.","authors":"Zi-Ying Wang, Jia-Wei Yin, Yuan-Yuan Li, Wei Liang, Quan-Feng Shao, Jiao Xue, Bei Zhu, Lin Zheng, Wei-Xian Chen","doi":"10.21037/gs-2026-0196","DOIUrl":"10.21037/gs-2026-0196","url":null,"abstract":"<p><strong>Background: </strong>Surgical management of granulomatous lobular mastitis (GLM) requires balancing complete lesion excision with the preservation of breast aesthetics. While the chest wall perforator flap (CWPF) is a valuable volume replacement technique, its clinical adoption may be limited by the need for intraoperative handheld Doppler localization and specialized training. This study aimed to evaluate the efficacy of a simplified CWPF reconstruction approach guided by multimodal preoperative imaging and performed without intraoperative handheld Doppler.</p><p><strong>Methods: </strong>A retrospective analysis was performed on 80 patients diagnosed with GLM between January 2022 and May 2024. Patients were assigned to two groups: Group A (n=43) underwent extended mass resection followed by modified CWPF reconstruction without intraoperative handheld Doppler, while Group B (n=37) received conventional surgical therapy (simple lumpectomy, extended mass resection, or segmental mastectomy without reconstruction). Group A was managed via a multimodal imaging protocol: magnetic resonance imaging (MRI) for source vessel identification, computed tomography (CT) for skeletal landmark referencing, and ultrasound for surface marking, thereby eliminating the need for intraoperative handheld Doppler localization.</p><p><strong>Results: </strong>All CWPF flaps were harvested under preoperative imaging guidance without the use of a handheld Doppler device. Postoperative complication rate was comparable between groups, mainly involving delayed wound healing, positive bacterial culture, subcutaneous fat liquefaction, incision infection, nipple-areola ischemic necrosis, ecchymosis, or hematoma (all P>0.05). Notably, Group A achieved significantly superior cosmetic outcomes compared with Group B (P<0.001). Patients in Group A also reported improved quality of life and higher patient satisfaction (P<0.001).</p><p><strong>Conclusions: </strong>Precise preoperative planning using multimodal imaging (MRI, CT, ultrasound) enables safe and effective CWPF reconstruction without intraoperative handheld Doppler in GLM surgery. This streamlined approach maintains surgical precision and favorable aesthetic outcomes while potentially reducing dependence on additional intraoperative localization devices, and may represent a practical strategy for breast reconstruction in resource-limited settings.</p>","PeriodicalId":12760,"journal":{"name":"Gland surgery","volume":"15 7","pages":"194"},"PeriodicalIF":1.9,"publicationDate":"2026-07-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13462774/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148722789","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Detection of preoperative serum trace elements in thyroid tumors.","authors":"Xiaohong Zhang, Xin Song, Yungang Pu, Yu Liu, Xiangyi Liu","doi":"10.21037/gs-2026-0171","DOIUrl":"10.21037/gs-2026-0171","url":null,"abstract":"<p><strong>Background: </strong>The incidence of thyroid tumors has increased sharply worldwide. Some trace elements (Ca, Mg, Fe, Mn, Co, Cu, Zn, Se) are essential for maintaining the hormonal balance of the thyroid gland, while other toxic elements (Ni, As, Pt, Mo, Cd, Ti, Pb) may cause various thyroid diseases. Our study aims to investigate whether serum trace elements are related to the occurrence of thyroid tumors.</p><p><strong>Methods: </strong>Preoperative serum samples were collected from patients with thyroid tumors, including 54 benign thyroid tumor cases and 76 papillary thyroid carcinoma (PTC) cases. Fifty-one healthy individuals who underwent routine physical examinations were selected as the control group. Serum concentrations of 15 trace elements (Ca, Mg, Fe, Mn, Co, Cu, Zn, Se, Ni, As, Pt, Mo, Cd, Ti, Pb) were measured by inductively coupled plasma-mass spectrometry (ICP-MS). Meanwhile, clinical biochemical and thyroid function indicators were detected. Serum levels among the three groups were compared using SPSS 22.0 software.</p><p><strong>Results: </strong>Among the three groups, there was no significant difference in serum biochemical and thyroid function indicators. Among the 15 trace elements, preoperative serum levels of Ca, Mg, Cu, Zn, Se, and Mo in the benign thyroid tumor and PTC groups were markedly higher than those in the control group (P<0.05). However, no significant difference in these 6 trace elements was observed between the benign thyroid tumor and PTC groups. Regarding the remaining 9 trace elements, there was no significant difference among the three groups. Multivariable analyses indicated that only high serum Cu [odds ratio (OR), 1.004; 95% confidence interval (CI): 1.002-1.008; P=0.02] and high serum Zn (OR, 1.009; 95% CI: 1.005-1.013; P<0.001) levels were independent risk factors for thyroid tumors. The receiver operating characteristic (ROC) curve analysis showed that serum Cu and Zn had an area under the curve (AUC) of 0.720 (sensitivity 63.1% and specificity 76.5%; P<0.001) and 0.781 (sensitivity 63.1% and specificity 88.2%; P<0.001) for distinguishing between thyroid tumors and the control group, respectively. In addition, serum Cu levels in thyroglobulin antibody (TG-Ab)-positive patients were obviously higher compared with those in TG-Ab-negative patients.</p><p><strong>Conclusions: </strong>Our study indicates that the concentrations of preoperative serum trace elements (Ca, Mg, Cu, Zn, Se, and Mo) may be correlated with thyroid tumors, but they were not associated with the benign or malignant nature of thyroid tumors. Serum Zn may serve as a useful adjunct for the diagnosis of thyroid tumors. Additionally, a high serum Cu concentration is positively correlated with the presence of thyroid autoantibodies.</p>","PeriodicalId":12760,"journal":{"name":"Gland surgery","volume":"15 7","pages":"188"},"PeriodicalIF":1.9,"publicationDate":"2026-07-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13462683/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148720938","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Artificial intelligence-based systems as auxiliary tools for thyroid nodule malignancy detection on ultrasound: a systematic review and meta-analysis of diagnostic accuracy.","authors":"Rafael De Cicco, Francisco Araujo Dias, Victor Bandini Vieira, Rafael Souza, Tabata Briaunys Milan","doi":"10.21037/gs-2026-1-0126","DOIUrl":"10.21037/gs-2026-1-0126","url":null,"abstract":"<p><strong>Background: </strong>Artificial intelligence (AI)-based systems are valuable tools in thyroid nodule diagnosis, but clinical controversy remains regarding diagnostic inconsistency and specificity. This meta-analysis evaluated the diagnostic accuracy of AI-assisted ultrasound systems for detecting malignant thyroid nodules compared to radiologists and risk stratification systems.</p><p><strong>Methods: </strong>Guided by the PICOS (Population, Intervention, Comparison, Outcome, Study Design) framework, a systematic search across PubMed, Semantic Scholar, and OpenAlex identified 69 studies using histopathological or cytological reference standards. Quality and Risk of Bias were assessed via an AI-tailored QUADAS-2 tool. Pooled sensitivity, specificity, and area under the receiver operating characteristic curve (AUC) were calculated using bivariate random-effects meta-analysis.</p><p><strong>Results: </strong>The 69 studies evaluated >350,000 nodules. AI-based systems demonstrated high diagnostic accuracy: pooled sensitivity 89% [95% confidence interval (CI): 87-91%], specificity 84% (95% CI: 80-88%), and AUC 0.93 (95% CI: 0.91-0.95). In direct comparisons, AI systems achieved comparable or superior performance to experienced radiologists (AUC 0.90-0.95 <i>vs.</i> 0.76-0.86). AI significantly improved specificity over individual radiologists and systems like ACR TI-RADS. AI-optimized TI-RADS achieved higher specificity (70.2% <i>vs.</i> 49.2%, P<0.001) than standard ACR TI-RADS with similar sensitivity. Consequently, AI-assisted strategies reduced unnecessary fine-needle aspirations (FNAs) by up to 26.7 percentage points. Performance peaked for nodules <20 mm and in externally validated, multicenter settings. AI provided the greatest incremental benefit for less experienced practitioners, markedly improving interobserver agreement.</p><p><strong>Conclusions: </strong>AI systems achieve high diagnostic accuracy for thyroid nodule malignancy, demonstrating performance comparable or superior to radiologists and risk stratification frameworks. As adjunctive tools, they safely reduce unnecessary biopsies and improve diagnostic consistency. Future clinical integration must prioritize multimodal data and radiomics to maximize utility.</p>","PeriodicalId":12760,"journal":{"name":"Gland surgery","volume":"15 7","pages":"186"},"PeriodicalIF":1.9,"publicationDate":"2026-07-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13462842/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148723955","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Development of a nomogram for predicting severe post-parathyroidectomy hypocalcemia in patients with secondary hyperparathyroidism: a retrospective cohort study.","authors":"Suhail Sayed, Doris Goubran, Diana Prince, Norbert Viallet, Ciaran Lane, Paul Kerr","doi":"10.21037/gs-2026-0243","DOIUrl":"10.21037/gs-2026-0243","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background: &lt;/strong&gt;Severe hypocalcemia affects 25-50% of patients with secondary hyperparathyroidism (sHPT) after total parathyroidectomy. It results from acute postoperative hypoparathyroidism and rapid skeletal mineral uptake. Severe hypocalcaemia leads to significant morbidity, prolonged hospital stays, and increased healthcare costs. Few risk assessment prediction tools exist; they lack external validation and exhibit methodological shortcomings. To enable evidence-based risk stratification and personalised perioperative management, we developed and internally validated a nomogram for predicting severe post-parathyroidectomy hypocalcaemia (SPPH) in patients with sHPT who underwent total parathyroidectomy with autotransplantation.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;This retrospective cohort study included 227 patients from two tertiary care institutions with sHPT who underwent total parathyroidectomy with autotransplantation between 2019 and 2024. All subjects had sHPT [parathyroid hormone (PTH) &gt;3× upper limit of normal] in the context of stage 4-5 chronic kidney disease (CKD) or dialysis dependent. Patients with autonomous parathyroid function (calcium-independent PTH elevation) were excluded. Intensive calcium supplementation protocols were administered to all patients. SPPH was defined by: (I) serum calcium &lt;1.9 mmol/L; (II) intravenous calcium requirement beyond postoperative day 3; (III) symptomatic hypocalcemia (tetany, seizures, arrhythmias, or laryngospasm) requiring intravenous calcium and/or urgent cardiac monitoring; or (IV) hospitalization ≥7 days primarily for calcium management. We employed the least absolute shrinkage and selection operator (LASSO) regression for variable selection, followed by multivariable logistic regression. Internal validation utilized 200 bootstrap resamples to derive the optimism-corrected performance estimates.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;The incidence of SPPH was 49.8% (113/227). Among 157 patients with complete predictor data, LASSO identified four optimal predictors: [adjusted odds ratio (OR) 0.87 per year, 95% confidence interval (CI): 0.76-0.99], preoperative phosphate at one month (adjusted OR 1.29 per mmol/L, 95% CI: 0.96-1.71), preoperative alkaline phosphatase (ALP) at one month (adjusted OR 4.11 per 100 U/L, 95% CI: 1.89-8.92), and preoperative PTH at three months (adjusted OR 0.87 per 10 pmol/L, 95% CI: 0.68-1.13). The model demonstrated good discrimination with an apparent c-statistic of 0.751 (optimism-corrected 0.739), good calibration (Hosmer-Lemeshow P=0.657), and positive net benefit across clinically relevant threshold probabilities of 0.1-0.8. Risk stratification yielded three clinically meaningful groups: low-risk (&lt;30% predicted probability, n=25, 8.0% observed SPPH rate), intermediate-risk (30-70%, n=92, 58.7% rate), and high-risk (&gt;70%, n=40, 72.5% rate).&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Conclusions: &lt;/strong&gt;We developed and internally validated a nomogram for preoperative risk strati","PeriodicalId":12760,"journal":{"name":"Gland surgery","volume":"15 7","pages":"192"},"PeriodicalIF":1.9,"publicationDate":"2026-07-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13462921/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148720933","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Development and performance evaluation of a risk assessment model for cervical lymph node metastasis in patients with Hashimoto's thyroiditis coexisting with papillary thyroid carcinoma.","authors":"Yuyu Hua, Caihong Wang, Fei Wang, Ruheng Feng, Qiqi Qin, Jing Wen","doi":"10.21037/gs-2026-0205","DOIUrl":"10.21037/gs-2026-0205","url":null,"abstract":"<p><strong>Background: </strong>The incidence of coexisting Hashimoto's thyroiditis (HT) and papillary thyroid carcinoma (PTC) is rising. The risk of cervical lymph node metastasis (CLNM) in HT-PTC patients remains controversial, and overlapping ultrasonographic features of lymph nodes complicate accurate diagnosis. Therefore, this study aimed to construct a risk assessment model for CLNM in patients with concurrent HT and PTC, and to evaluate its clinical application value.</p><p><strong>Methods: </strong>A total of 261 patients with postoperative pathologically confirmed PTC coexisting with HT who underwent thyroid surgery at the Affiliated Hospital of Guizhou Medical University from January 2018 to December 2023 were retrospectively enrolled. Univariate and multivariate logistic regression analyses were first performed to identify independent predictors of CLNM. Variables with P<0.05 in the multivariate analysis were incorporated into model development. Four models were constructed: based on tumor nodule ultrasound features (TN-US), lymph node ultrasound features (LN-US), their combination (TN-LN-US), and a full-feature model integrating clinical, laboratory, and ultrasound parameters (Clin-US). Receiver operating characteristic (ROC) curves were plotted to evaluate diagnostic performance, and the DeLong test was used to compare the area under the ROC curve (AUC) among the models. Internal validation was conducted using the bootstrap method, and model performance was further assessed using calibration curves, decision curve analysis (DCA), and clinical impact curve (CIC).</p><p><strong>Results: </strong>Among the 261 patients with PTC coexisting with HT, univariate and multivariate logistic regression analyses identified age, alkaline phosphatase, primary tumor microcalcifications, primary tumor vascularity, lymph node morphology, intranodal cortical echogenicity, and lymph node microcalcifications as independent risk factors for CLNM (P<0.05). The Clin-US model demonstrated the best diagnostic performance (AUC =0.842, bootstrap 95% confidence interval: 0.792-0.885). Bootstrap internal validation indicated stable model parameters. Calibration curves showed good model fit, with predicted probabilities closely matching actual incidence. DCA and CIC further confirmed favorable clinical applicability of the model.</p><p><strong>Conclusions: </strong>We developed a Clin-US model that combines clinical data and ultrasound for predicting lymph node metastasis in PTC patients with concurrent HT. The model demonstrated promising diagnostic performance and may assist clinicians in preoperative risk stratification, facilitating individualized treatment decisions for this population.</p>","PeriodicalId":12760,"journal":{"name":"Gland surgery","volume":"15 7","pages":"190"},"PeriodicalIF":1.9,"publicationDate":"2026-07-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13462679/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148720363","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}