Objective To explore the application value of three mainstream large language models in the diagnosis, differential diagnosis, and treatment decision support of the primary diseases related to pediatric liver transplantation. Methods Seventy-nine cases of pediatric liver transplantation-related diseases diagnosed through pathological or clinical follow-up data were collected from Renji Hospital, Shanghai Jiao Tong University School of Medicine or published high-quality case reports. These cases covered 25 types of primary diseases such as cholestatic liver disease, metabolic diseases, and tumors. Standardized prompts were used to input the case information into the DeepSeek-R1, ChatGPT-4o and Grok-3 models, and the accuracy of their preliminary diagnosis and differential diagnosis based on basic clinical data was evaluated. The final diagnosis accuracy and the response time after supplementary examination were also assessed, as well as the completeness and rationality of their analysis of disease treatment principles. Results In the initial diagnosis and differential diagnosis stage, the comprehensive accuracy of DeepSeek-R1 was the highest [72.1%, 95% confidence interval (CI) 61.4% - 80.8%], and there was a statistically significant difference in the comprehensive accuracy of the three models for initial diagnosis (P = 0.008). After adding further examination information, the final diagnosis accuracy of the three models increased, with DeepSeek-R1 at 88.6% (95% CI 79.7% - 93.9%), ChatGPT-4o at 87.3% (95% CI 78.2% - 93.0%), and Grok-3 at 78.5% (95% CI 68.2% - 86.1%). There was no statistically significant difference among the three models (P = 0.05). The scores given by experts for the treatment principles showed good consistency (Kappa = 0.769). In addition, the response time of ChatGPT-4o is shorter than that of the other two models [(24 ± 7) s]. Conclusions Large language models demonstrate good efficacy in the diagnosis and treatment decision-making process of various pediatric liver diseases, have a good application prospect for auxiliary diagnosis and decision support, and are expected to help improve the accuracy and efficiency of clinical diagnosis and treatment of pediatric liver transplantation-related primary diseases.

Oral squamous cell carcinoma (OSCC) is a common head and neck malignancy. Approximately 50% to 60% of patients with OSCC are diagnosed at a locally advanced stage (clinical staging III-IVa). Even with comprehensive and sequential treatment primarily based on surgery, the 5-year overall survival rate remains below 50%, and patients often suffer from postoperative functional impairments such as difficulties with speaking and swallowing. Programmed death receptor-1 (PD-1) inhibitors are increasingly used in the neoadjuvant treatment of locally advanced OSCC and have shown encouraging efficacy. However, clinical practice still faces key challenges, including the definition of indications, optimization of combination regimens, and standards for efficacy evaluation. Based on the latest research advances worldwide and the clinical experience of the expert group, this expert consensus systematically evaluates the application of PD-1 inhibitors in the neoadjuvant treatment of locally advanced OSCC, covering combination strategies, treatment cycles and surgical timing, efficacy assessment, use of biomarkers, management of special populations and immune related adverse events, principles for immunotherapy rechallenge, and function preservation strategies. After multiple rounds of panel discussion and through anonymous voting using the Delphi method, the following consensus statements have been formulated: 1) Neoadjuvant therapy with PD-1 inhibitors can be used preoperatively in patients with locally advanced OSCC. The preferred regimen is a PD-1 inhibitor combined with platinum based chemotherapy, administered for 2-3 cycles. 2) During the efficacy evaluation of neoadjuvant therapy, radiographic assessment should follow the dual criteria of Response Evaluation Criteria in Solid Tumors (RECIST) version 1.1 and immune RECIST (iRECIST). After surgery, systematic pathological evaluation of both the primary lesion and regional lymph nodes is required. For combination chemotherapy regimens, PD-L1 expression and combined positive score need not be used as mandatory inclusion or exclusion criteria. 3) For special populations such as the elderly (≥ 70 years), individuals with stable HIV viral load, and carriers of chronic HBV/HCV, PD-1 inhibitors may be used cautiously under the guidance of a multidisciplinary team (MDT), with close monitoring for adverse events. 4) For patients with a poor response to neoadjuvant therapy, continuation of the original treatment regimen is not recommended; the subsequent treatment plan should be adjusted promptly after MDT assessment. Organ transplant recipients and patients with active autoimmune diseases are not recommended to receive neoadjuvant PD-1 inhibitor therapy due to the high risk of immune related activation. Rechallenge is generally not advised for patients who have experienced high risk immune related adverse events such as immune mediated myocarditis, neurotoxicity, or pneumonitis. 5) For patients with a good pathological response, individualized de escalation surgery and function preservation strategies can be explored. This consensus aims to promote the standardized, safe, and precise application of neoadjuvant PD-1 inhibitor strategies in the management of locally advanced OSCC patients.

With the continuous deepening of the concept of precision diagnosis and treatment for lung cancer, how to achieve higher efficiency and accuracy in the screening, diagnosis, and treatment pathways in clinical practice has become an important issue that urgently needs to be overcome. The current clinical difficulty lies in the fact that despite continuous advancements in imaging and molecular diagnostic technologies, there are still limitations in manual efficiency and subjective experience when it comes to massive data analysis and multi-scale feature extraction. Artificial intelligence (AI), especially algorithm systems based on deep learning, is an innovative technology capable of deeply empowering medical big data. This method utilizes algorithms such as convolutional neural networks, combined with radiomics, pathomics, and multi-modal data fusion analysis, demonstrating immense potential in early precise detection and benign-malignant differentiation of pulmonary nodules, digital pathological subtype recognition and non-invasive prediction of driver genes, precise 3D surgical planning and automatic delineation of radiotherapy target volumes, as well as dynamic risk warning during follow-up. This innovative technology provides a brand-new solution for realizing intelligent and individualized lung cancer diagnosis and treatment models. This consensus, based on the latest evidence from evidence-based medicine and combined with the development trends in the AI field and real-world clinical needs, was ultimately formed by gathering the consensus opinions of multidisciplinary experts in radiology, pathology, thoracic surgery, and other fields. The main content covers the application specifications of AI in the three core scenarios of lung cancer screening, diagnosis, and treatment, the technical standards for data collection and algorithm validation, as well as the ethical and regulatory challenges faced at the current stage. It aims to clarify the applicable boundaries of AI as a clinical auxiliary decision support tool, providing scientific guidance and standardized exploration directions for peers currently engaged in or planning to carry out AI-assisted clinical diagnosis, treatment, and translation of lung cancer.

ObjectiveTo investigate the expression patterns of key steroidogenic enzymes （CYP11A1， HSD3B1， and CYP19A1） in placental tissues from preeclampsia （PE） patients and evaluate​ their potential as biomarkers for PE. MethodsA case-control study was conducted using placental tissues from PE patients （PE group， n=3） and normotensive pregnant women （control group， n=3）. RNA sequencing was performed to identify differentially expressed genes （DEGs）， followed by validation of target gene expression using Western blot， qRT-PCR， and immunohistochemistry. Steroid hormone levels in placental tissues and serum were measured by ELISA. Spearman correlation analysis was used to assess associations between protein expression and clinical parameters， and receiver operating characteristic （ROC） curve analysis was performed to evaluate the predictive value of target genes for PE. ResultsThe results showed that 501 DEGs （P<0.05 and |Log₂Fold Change| >1） were identified in PE placental tissues， with KEGG enrichment analysis revealing significant involvement in steroid hormone biosynthesis pathways. Compared with the control group， PE placental tissues exhibited significantly decreased protein and mRNA expression of HSD3B1 and CYP19A1 （P<0.01）， while CYP11A1 expression was upregulated （P<0.05）. Serum estradiol （E2） and progesterone （P4） levels were significantly reduced in the PE group （P<0.01）， whereas testosterone （T） levels were elevated （P<0.05）. Correlation analysis demonstrated that CYP11A1 expression was positively associated with systolic blood pressure （SBP）， diastolic blood pressure （DBP）， and soluble fms-like tyrosine kinase-1 （sFlt-1） （P<0.01）， but negatively correlated with placental growth factor （PLGF） （P<0.01）. Conversely， HSD3B1 and CYP19A1 expression showed inverse correlations with these clinical parameters （P<0.01）. ROC analysis revealed that CYP11A1， HSD3B1， and CYP19A1 each had an area under the curve （AUC） of 0.778 for predicting PE， with 95%CI ranging from 0.614 to 0.942 （P=0.004）. The sensitivity was 94.4%， and the specificity was 66.7%. ConclusionThese findings suggest that dysregulated expression of steroidogenic enzymes in PE placental tissues contributes to hormonal imbalance， thereby playing a role in PE pathogenesis. Furthermore， CYP11A1， HSD3B1， and CYP19A1 may serve as potential diagnostic biomarkers for PE.

With the widespread adoption of low-dose CT screening and the extensive application of high-resolution CT, the detection rate of sub-centimeter lung nodules has significantly increased. How to scientifically manage these nodules while avoiding overtreatment and diagnostic delays has become an important clinical issue. Among them, lung nodules with a consolidation tumor ratio less than 0.25, dominated by ground-glass shadows, are particularly worthy of attention. The therapeutic challenge for this group is how to achieve precise and complete resection of nodules during surgery while maximizing the preservation of the patient's lung function. The "watershed topography map" is a new technology based on big data and artificial intelligence algorithms. This method uses Dicom data from conventional dose CT scans, combined with microscopic (22-24 levels) capillary network anatomical watershed features, to generate high-precision simulated natural segmentation planes of lung sub-segments through specific textures and forms. This technology forms fluorescent watershed boundaries on the lung surface, which highly fit the actual lung anatomical structure. By analyzing the adjacent relationship between the nodule and the watershed boundary, real-time, visually accurate positioning of the nodule can be achieved. This innovative technology provides a new solution for the intraoperative positioning and resection of lung nodules. This consensus was led by four major domestic societies, jointly with expert teams in related fields, oriented to clinical practical needs, referring to domestic and foreign guidelines and consensus, and finally formed after multiple rounds of consultation, discussion, and voting. The main content covers the theoretical basis of the "watershed topography map" technology, indications, operation procedures, surgical planning details, and postoperative evaluation standards, aiming to provide scientific guidance and exploration directions for clinical peers who are currently or plan to carry out lung nodule resection using the fluorescent microscope watershed analysis method.

Nonobstructive azoospermia (NOA), one of the most severe types of male infertility, etiology often remains unclear in most cases. Therefore, this study aimed to detect four biallelic detrimental variants (0.5%) in the minichromosome maintenance domain containing 2 ( MCMDC2 ) genes in 768 NOA patients by whole-exome sequencing (WES). Hematoxylin and eosin (H&E) demonstrated that MCMDC2 deleterious variants caused meiotic arrest in three patients (c.1360G>T, c.1956G>T, and c.685C>T) and hypospermatogenesis in one patient (c.94G>T), as further confirmed through immunofluorescence (IF) staining. The single-cell RNA sequencing data indicated that MCMDC2 was substantially expressed during spermatogenesis. The variants were confirmed as deleterious and responsible for patient infertility through bioinformatics and in vitro experimental analyses. The results revealed four MCMDC2 variants related to NOA, which contributes to the current perception of the function of MCMDC2 in male fertility and presents new perspectives on the genetic etiology of NOA.
Humans ; Male ; Azoospermia/genetics* ; Meiosis/genetics* ; Spermatogenesis/genetics* ; Adult ; Exome Sequencing ; Microtubule-Associated Proteins/genetics* ; Alleles ; Infertility, Male/genetics*

OBJECTIVES: To investigate the clinical sub-phenotype (SP) of pediatric acute kidney injury (AKI) and their association with clinical outcomes. METHODS: General status and initial values of laboratory markers within 24 hours after admission to the pediatric intensive care unit (PICU) were recorded for children with AKI in the derivation cohort (n=650) and the validation cohort (n=177). In the derivation cohort, a least absolute shrinkage and selection operator (LASSO) regression analysis was used to identify death-related indicators, and a two-step cluster analysis was employed to obtain the clinical SP of AKI. A logistic regression analysis was used to develop a parsimonious classifier model with simplified metrics, and the area under the curve (AUC) was used to assess the value of this model. This model was then applied to the validation cohort and the combined derivation and validation cohort. The association between SPs and clinical outcomes was analyzed with all children with AKI as subjects. RESULTS: In the derivation cohort, two clinical SPs of AKI (SP1 and SP2) were identified by the two-step cluster analysis using the 20 variables screened by LASSO regression, namely SP_d1 group (n=536) and SP_d2 group (n=114). The simplified classifier model containing eight variables (P<0.05) had an AUC of 0.965 in identifying the two clinical SPs of AKI (P<0.001). The validation cohort was clustered into SP_v1 group (n=156) and SP_v2 group (n=21), and the combined derivation and validation cohort was clustered into SP1 group (n=694) and SP2 group (n=133). After adjustment for confounding factors, compared with the SP1 group, the SP2 group had significantly higher incidence rates of multiple organ dysfunction syndrome and death during the PICU stay (P<0.001), and SP2 was significantly associated with the risk of death within 28 days after admission to the PICU (P<0.001). CONCLUSIONS This study establishes a parsimonious classifier model and identifies two clinical SPs of AKI with different clinical features and outcomes.The SP2 group has more severe disease and worse clinical prognosis.
Humans ; Acute Kidney Injury/diagnosis* ; Prognosis ; Male ; Female ; Child ; Child, Preschool ; Phenotype ; Infant ; Logistic Models ; Adolescent

Objective:To investigate the association between pre- and post-treatment gene mutation profiles and clinical outcomes (treatment response and prognosis) in patients with myelodysplastic syndromes with excess blasts (MDS-EB) receiving hypomethylating agent (HMA) monotherapy.Methods:The clinical characteristics, treatment efficacy, and survival outcomes of 69 treatment-naive patients with MDS-EB who underwent next-generation sequencing (NGS) before treatment and completed at least 4 cycles of HMA monotherapy at the Institute of Hematology & Blood Diseases Hospital, CAMS & PUMC, between June 2016 and September 2023, were retrospectively analyzed.Results:① The cohort comprised 47 males and 22 females with a median age of 62 years (range: 41-80). Thirty-nine patients were classified as MDS-EB1 and 30 as MDS-EB2. The median number of treatment cycles was 6 (range: 4-35). The median follow-up duration was 22 months (range: 5-72), and the median overall survival (OS) was 32 months (95% CI: 27-43). ② The presence of DTA (DNMT3A, TET2, or ASXL1) mutations, signaling pathway mutations, transcription factor mutations, or splicing factor mutations before HMA treatment showed no significant association with the best response within 4 treatment cycles, duration of response (DOR), or OS. TP53 mutation status was significantly associated with DOR and shorter OS. The median DOR was 3 months (95% CI: 1-10) for patients with biallelic TP53 mutations, 10 months (95% CI: 3-34) for those with monoallelic TP53 mutations, and 16 months (95% CI: 8-27) in patients without TP53 mutations ( P=0.032). The median OS was 16 months (95% CI: 7-38), 15 months (95% CI: 6-40), and 35 months (95% CI: 14-91), respectively ( P<0.001). ③ Neither the Revised International Prognostic Scoring System (IPSS-R) nor the Molecular International Prognostic Scoring System (IPSS-M) could predict the best response within 4 treatment cycles or DOR in patients receiving HMA therapy. ④ Among patients without TP53 mutations, the median OS was 55 months (95% CI: 9-106) for the major clone significant clearance group ( n=14) and 31 months (95% CI: 16-184) for the major clone non-significant clearance group ( n=10) ( P=0.013). For patients who responded to HMA treatment and had significant major clone clearance, the 3-year OS rate reached (77.8±13.9) %. Conclusion:For MDS-EB patients receiving HMA monotherapy, single gene mutations, IPSS-R, and IPSS-M could not effectively predict treatment outcomes before therapy. However, for patients without TP53 mutations, monitoring the degree of major clone clearance by NGS during treatment may predict the long-term efficacy in MDS patients receiving HMA therapy.

Objective:To identify the prognostic value of the Revised 15-item Myelodysplastic Syndrome-specific frailty scale (FS-15) in Chinese patients with myelodysplastic syndromes (MDS) .Methods:This retrospective study analyzed 812 patients with newly diagnosed MDS admitted to the Institute of Hematology and Blood Diseases Hospital, Chinese Academy of Medical Sciences, and Peking Union Medical College from August 2016 to June 2023. Patients were assessed using the FS-15 and subsequently categorized into frail and non-frail groups. Clinical and laboratory characteristics, as well as overall survival (OS), were compared between these groups.Results:① The median patient age was 55 years ( IQR 45–64), with a median follow-up of 22.5 months (95% CI: 20.2–24.9) and a median OS of 43.3 months (95% CI: 36.8–49.8). The median FS-15 score was 0.42, with a cutoff value of 0.44. Male patients demonstrated higher median FS-15 scores than female patients (0.42 vs 0.38, P=0.006). In both the Revised International Prognostic Scoring System (IPSS-R; P=0.001) and Molecular International Prognostic Scoring System (IPSS-M; P=0.014) stratifications, FS-15 scores were significantly higher in the very high-risk group compared with the very low-risk group. ② The median OS was 54.7 months (95% CI: 47.5–NA) and 31.5 months (95% CI: 22.9–41.0) in the nonfrail ( n=452) and frail groups ( n=360), respectively ( P<0.001). The 3-year OS rates were (63.2 ± 3.2) % and (46.4 ± 3.6) % for the non-frail and frail groups, with 5-year OS rates of (49.9 ± 4.7) % and (32.0 ± 4.3) %, respectively ( P<0.001). ③Subgroup analysis revealed that nonfrail patients demonstrated significantly higher 3-year OS rates than frail patients in both the IPSS-M low-risk and very high-risk groups (all P<0.05). Similarly, nonfrail patients demonstrated superior 3-year OS rates compared with frail patients in the IPSS-R very low-risk, low-risk, and high-risk groups (all P<0.05). ④Among patients receiving hypomethylating agent therapy, the overall response rate was significantly higher in the non-frail group than in the frail group (86.7% vs 64.6%, P=0.007). Moreover, the frail group experienced higher rates of treatment-related adverse events, including febrile neutropenia (67.1% vs 47.4%, P=0.016) and liver function abnormalities (30.0% vs 14.5%, P=0.023), compared with the non-frail group. Conclusion:The FS-15 frailty score is a feasible and effective tool for assessing frailty in patients newly diagnosed with MDS in China and serves as a valuable prognostic indicator.

Objective:To compare the clinical characteristics of monogenic and non-monogenic early-onset inflammatory bowel disease (EO-IBD) in children and to explore the necessity of genetic analysis in EO-IBD research.Methods:A retrospective analysis of clinical data was conducted on 73 children diagnosed with EO-IBD at the Children's Hospital affiliated with Capital Institute of Pediatrics between January 2017 and December 2023. Genetic analysis was performed utilizing next-generation sequencing technology, with patients stratified into monogenic and non-monogenic groups based on the presence or absence of pathogenic mutations. Subsequently, a comparative analysis of clinical characteristics was conducted between these two cohorts of EO-IBD patients.Results:Among the 73 EO-IBD cases, 27 (37%) were diagnosed as monogenic IBD, and 46 (63%) as non-monogenic IBD. Compared to the non-monogenic group, the monogenic group had an earlier age of onset [1 (0.2, 3.0) months vs. 15 (4.1, 51.3) months, P < 0.001], with a higher incidence within the first month of life (70.4% vs. 13.0%, P < 0.001). Monogenic IBD cases were more likely to present with Crohn's disease (CD) phenotypes (88.9% vs. 52.2%, P = 0.003) and colonic involvement (L2) (91.7% vs. 62.5%, P < 0.001), but were less likely to present with non-penetrating, non-stricturing (B1) disease (87.5% vs. 95.8%, P = 0.019). Children in the monogenic group were more prone to severe malnutrition (74.1% vs. 21.3%, P < 0.001), perianal abscesses (40.7% vs. 8.7%, P < 0.001), perianal tags (22.2% vs. 0%, P = 0.004), fever (74.1% vs. 23.9%, P < 0.001), oral ulcers (44.4% vs. 6.5%, P < 0.001), and skin lesions (33.3% vs. 2.2%, P < 0.001). Regarding treatment, the monogenic group had higher usage of thalidomide (88.9% vs. 54.3%, P = 0.002) and hematopoietic stem cell transplantation (HSCT) (37.0% vs. 0, P < 0.001) and a higher mortality rate (22.2% vs. 2.2%, P = 0.017) . Conclusions:For children with IBD presenting at an early age, especially within the first month of life, and showing symptoms like fever, oral ulcers, skin lesions, severe malnutrition, and perianal disease, monogenic IBD should be considered. Genetic testing results can aid in guiding treatment decisions.