BACKGROUND: Postoperative pulmonary complications (PPCs) are major adverse events in neurosurgical patients. This study aimed to develop and validate machine learning models predicting PPCs after neurosurgery. METHODS: PPCs were defined according to the European Perioperative Clinical Outcome standards as occurring within 7 postoperative days. Data of cases meeting inclusion/exclusion criteria were extracted from the anesthesia information management system to create three datasets: The development (data of Huashan Hospital, Fudan University from 2018 to 2020), temporal validation (data of Huashan Hospital, Fudan University in 2021) and external validation (data of other three hospitals in 2023) datasets. Machine learning models of six algorithms were trained using either 35 retrievable and plausible features or the 11 features selected by Lasso regression. Temporal validation was conducted for all models and the 11-feature models were also externally validated. Independent risk factors were identified and feature importance in top models was analyzed. RESULTS: PPCs occurred in 712 of 7533 (9.5%), 258 of 2824 (9.1%), and 207 of 2300 (9.0%) patients in the development, temporal validation and external validation datasets, respectively. During cross-validation training, all models except Bayes demonstrated good discrimination with an area under the receiver operating characteristic curve (AUC) of 0.840. In temporal validation of full-feature models, deep neural network (DNN) performed the best with an AUC of 0.835 (95% confidence interval [CI]: 0.805-0.858) and a Brier score of 0.069, followed by Logistic regression (LR), random forest and XGBoost. The 11-feature models performed comparable to full-feature models with very close but statistically significantly lower AUCs, with the top models of DNN and LR in temporal and external validations. An 11-feature nomogram was drawn based on the LR algorithm and it outperformed the minimally modified Assess respiratory RIsk in Surgical patients in CATalonia (ARISCAT) and Laparoscopic Surgery Video Educational Guidelines (LAS VEGAS) scores with a higher AUC (LR: 0.824, ARISCAT: 0.672, LAS: 0.663). Independent risk factors based on multivariate LR mostly overlapped with Lasso-selected features, but lacked consistency with the important features using the Shapley additive explanation (SHAP) method of the LR model. CONCLUSIONS: The developed models, especially the DNN model and the nomogram, had good discrimination and calibration, and could be used for predicting PPCs in neurosurgical patients. The establishment of machine learning models and the ascertainment of risk factors might assist clinical decision support for improving surgical outcomes. TRIAL REGISTRATION ChiCTR 2100047474; https://www.chictr.org.cn/showproj.html?proj=128279 .
Adult ; Aged ; Female ; Humans ; Male ; Middle Aged ; Algorithms ; Lung Diseases/etiology* ; Machine Learning ; Neurosurgical Procedures/adverse effects* ; Postoperative Complications/diagnosis* ; Risk Factors ; ROC Curve

Objective:To investigate the efficacy and prognosis of different surgical approaches in sporadic medullary thyroid carcinoma.Methods:A retrospective analysis was conducted on 101 patients with sporadic medullary thyroid carcinoma (MTC) who underwent surgical treatment at the Department of Thyroid Surgery, China-Japan Union Hospital of Jilin University, from Feb. 2009 to Nov. 2023. The patients included 36 males and 75 females, with a male-to-female ratio of 1:2.1. The median age of the patients was 47 years old, with an age range of 21 to 72 years old. The study divided participants into two groups based on their surgical methods: an observation group (78 cases) and a control group (23 cases). The observation group received surgical methods in accordance with expert consensus, while the control group did not. The study compared the efficacy and prognosis of the two groups.Results:Statistical differences were found between the two groups in terms of stage II and III in TNM staging, intraoperative frozen pathological findings, number of lymph node resections in the central group, number of lymph node metastases in the central group, number of lymph node resections in the lateral cervical region, postoperative follow-up time, and five-year postoperative serum procalcitonin (Ctn) levels ( P<0.05) .Both groups of patients obtained a significant decrease in Ctn after surgical treatment. In the observation group, Ctn was at the remission level in 57 cases (73.1%), at the stable level in 13 cases (16.7%), and at the progression level in 8 cases (10.2%), while in the control group, Ctn was at the remission level in 20 cases (86.9%), at the progression level in 3 cases (13.1%), and there were no patients at the stable level after the operation.One patient (1.3 per cent) in the observation group had a recurrence after surgery; Two patients (8.7 per cent) in the control group had a recurrence. Conclusions:Standardised and thorough surgery can maximise the clearance of metastatic lymph nodes, effectively reduce the recurrence rate, achieve better efficacy, and improve the long-term prognosis of patients without increasing the risk of surgery and postoperative complications.

Objective:To investigate the value of an MRI and digital pathology images based omics nomogram for the prediction of recurrence risk in soft tissue sarcoma (STS).Methods:This was a retrospective cohort study. From January 2016 to March 2021, 192 patients with STS confirmed by pathology in the Affiliated Hospital of Qingdao University were enrolled, among which 112 patients in the Laoshan campus were enrolled as training set, and 80 patients in the Shinan campus were enrolled as validation set. The patients were divided into recurrence group ( n=87) and no recurrence group ( n=105) during follow-up. The clinical and MRI features of patients were collected. The radiomics features based on fat saturated T 2WI images and pathomics features based on digital pathology images of the lesions were extracted respectively. The clinical model, radiomics model, pathomics model, radiomics-pathomics combined model, and omics nomogram which combined the optimal prediction model and the clinical model were established by multivariate Cox regression analysis. The concordance index (C index) and time-dependent area under the receiver operating characteristic curve (t-AUC) were used to evaluate the performance of each model in predicting STS postoperative recurrence. The DeLong test was used for comparison of t-AUC between every two models. The X-tile software was used to determine the cut-off value of the omics nomogram, then the patients were divided into low risk ( n=106), medium risk ( n=64), and high risk ( n=22) groups. Three groups′ cumulative recurrence-free survival (RFS) rates were calculated and compared by the Kaplan-Meier survival curve and log-rank test. Results:The performance of the radiomics-pathomics combined model was superior to the radiomics model and pathomics model, with C index of 0.727 (95% CI 0.632-0.823) and medium t-AUC value of 0.737 (95% CI0.584-0.891) in the validation set. The omics nomogram was established by combining the clinical model and the radiomics-pathomics combined model, with C index of 0.763 (95% CI 0.685-0.842) and medium t-AUC value of 0.783 (95% CI0.639-0.927) in the validation set. The t-AUC value of omics nomogram was significantly higher than that of clinical model, TNM model, radiomics model, and pathomics model in the validation set ( Z=3.33, 2.18, 2.08, 2.72, P=0.001, 0.029, 0.037, 0.007). There was no statistical difference in t-AUC between the omics nomogram and radiomics-pathomics combined model ( Z=0.70, P=0.487). In the validation set, the 1-year RFS rates of STS patients in the low, medium, and high recurrence risk groups were 92.0% (95% CI 81.5%-100%), 55.9% (95% CI 40.8%-76.6%), and 37.5% (95% CI 15.3%-91.7%). In the training and validation sets, there were statistically significant in cumulative RFS rates among the low, medium, and high groups of STS patients (training set χ2=73.90, P<0.001; validation set χ2=18.70, P<0.001). Conclusion:The omics nomogram based on MRI and digital pathology images has favorable performance for the prediction of STS recurrence risk.

Objective To explore the influencing factors of type 2 diabetes mellitus(T2DM)complicated with metabolic syndrome(MS)and investigate the correlation between the level of 25(OH)D3 and T2DM combined with MS.Methods 592 in patients with T2DM admitted to the Department of Endocrinology of Shenzhen Second People's Hospital were selected from January to December 2020.They were divided into simple T2DM group(T2DM,n=194)and T2DM combined with MS group(MS,n=398).Results Compared with the T2DM group,the MS group had lower 25(OH)D3 levels[26.30(20.50,32.39)vs 24.20(20.16,29.47),P<0.05].Spearman correlation analysis showed that 25(OH)D3 was negatively correlated with MS,FPG,TG,LDL-C,and 24 hUAlb(P<0.05 or P<0.01).Logistic regression analysis showed that 25(OH)D3 was a protective factor for T2DM combined with MS.Conclusions Patients with T2DM and MS have lower 25(OH)D3 levels.25(OH)D3 is a protective factor for T2DM combined with MS.

Objective To explore the correlations between self-esteem,social support and mental health status of patients with deep bums at special sites at different stages of the disease course.Methods A total of 36 inpatients who were admitted to Department of Burn Surgery of The First Affiliated Hospital of Naval Medical University(Second Military Medical University)between Jan.2020 and Sep.2023 were enrolled.The patients were assessed with self-rating anxiety scale(SAS),self-rating depression scale(SDS),post-traumatic stress disorder(PTSD)checklist-civilian version(PCL-C),Rosenberg self-esteem scale(RSES),and perceived social support scale(PSSS)within 7 d of burns(early stage of disease),at wound closure(early rehabilitation stage),and 3 months after wound closure(late rehabilitation stage).The data were collected and invalid data were excluded for statistical analysis.Results A total of 36 patients effectively completed all the scales.There were anxiety,depression and PTSD in patients with deep bums at special sites at different stages of the disease course,and the number of burn patients with anxiety,depression and PTSD showed a downward trend with the course of disease.The RSES score at the early rehabilitation stage was positively correlated with SAS score(rs=0.412,P=0.013),SDS score(rs=0.347,P=0.038)and PCL-C score(rs=0.447,P=0.006)at the early stage of disease,but not with SAS,SDS,or PCL-C scores at the early and late rehabilitation stages(all P＞0.05).There were no correlations between PSSS score at the early rehabilitation stage and SAS,SDS,or PCL-C scores at the early stage of disease or SAS or PCL-C scores at the early stage of rehabilitation(all P＞0.05),but there were negative correlations between PSSS score at the early rehabilitation stage and SDS score at the early stage of rehabilitation(r=-0.430,P=0.009)and SAS score(r=-0.467,P=0.004),SDS score(r=-0.483,P=0.003),and PCL-C score(rs=-0.351,P=0.036)at the late stage of rehabilitation.Conclusion Anxiety,depression,and PTSD are observed in patients with deep burns in special areas at different stages of the disease.A high level of self-esteem is associated with an increased risk of mental problems at early stage of burns.Conversely,a high level of social support is associated with a reduced likelihood of mental problems at late stage of rehabilitation.

ObjectiveTo evaluate the effect of Shengmaisan granules on myocardial fibrosis in chronic heart failure patients with Qi-Yin deficiency syndrome by cardiac magnetic resonance （CMR） imaging and serological indicators. MethodSixty-six chronic heart failure patients with Qi-Yin deficiency syndrome who visited the Affiliated Hospital of Integrated Traditional Chinese and Western Medicine， Nanjing University of Chinese Medicine from October 2021 to January 2023 were selected. The patients were assigned into a control group （33 cases） and an observation group （33 cases） by the minimization random method. Both groups received standardized Western medicine treatment for heart failure. In addition， the control group was treated with placebo granules， and the observation group with Shengmaisan granules for a course of 6 months. The baseline data， clinical efficacy， TCM symptom scores， serological indicators ［high-sensitivity C-reactive protein （hs-CRP）， soluble growth stimulation expressed gene 2 protein （sST2）， pro-collagen Ⅲ N-terminal peptide （PⅢNP）， interleukin （IL）-6， IL-11， transforming growth factor-β₁ （TGF-β₁）］， echocardiography ［Left atrial diameter （LAD）， left ventricular end systolic diameter （LVEDs）， left ventricular end diastolic diameter （LVEDd）］ and CMR indicators ［left ventricular ejection fraction （LVEF）， myocardial extracellular volume fraction （ECV）， and longitudinal relaxation time （T1）］ were compared between the two groups. ResultFinally， 31 patients in the control group and 30 patients in the observation group were included. There was no significant difference in baseline data or indicators between the two groups before treatment. Compared with those before treatment， the scores of TCM symptoms （shortness of breath， fatigue， palpitations， spontaneous or night sweats， thirst/dry throat， feverish feeling in palms and soles， and edema in lower limbs）， total score of TCM symptoms， ECV， T1， inflammation/fibrosis indicators （hs-CRP， sST2， PⅢNP， IL-6， IL-11， and TGF-β₁） in observation group decreased （P<0.05， P<0.01）， and the scores of TCM symptoms （except feverish feeling in palms and soles）， T1， and inflammation/fibrosis indicators in the control group decreased （P<0.05， P<0.01）. After treatment， the observation group had lower scores of TCM symptoms （except feverish feeling in palms and soles and edema in lower limbs）， ECV， T1， and inflammation/fibrosis indicators than the control group （P<0.05， P<0.01）. After treatment， the total response rate in the observation group was 93.33% （28/30）， which was higher than that （80.65%， 25/31） in the control group （Z=2.976， P<0.01）. There was no significant difference in adverse reactions between the two groups during treatment. ConclusionFor patients with chronic heart failure with Qi-Yin deficiency syndrome， Shengmaisan Granules can alleviate the TCM symptoms， reduce inflammation， and inhibit myocardial fibrosis by regulating the TGF-β₁/IL-11 signaling axis.

In recent years, clinical applications of robotic thyroid surgery have been gradually promoted with the continuous improvement of the da Vinci robotic surgical system. Unlike traditional open surgery, robotic thyroid surgery mainly adopts remote access, which has many advantages, such as magnified high-definition 3D view and hand vibration stabilization. The rates and causes of postoperative complications differ due to different approaches, view angles, and operation sequences. This paper presents the literature on both transoral and bilateral areolar axillary approaches in robotic thyroid surgery, focusing on five common complications under both approaches, including laryngeal recurrent nerve injury and hypoparathyroidism, to provide theoretical support for the standardization of robotic thyroid surgery.

Thyroid cancer is the most common malignant tumor of the endocrine system, and its incidence is increasing year by year showing younger trend. The pathological types of thyroid cancer are papillary carcinoma, follicular carcinoma, medullary carcinoma and undifferentiated carcinoma. Medullary thyroid carcinoma (MTC) and papillary thyroid carcinoma (PTC) are the two common types of thyroid cancer. Since MTC and PTC have different biological origins, invasiveness and prognosis. Therefore, the occurrence of both medullary carcinoma and papillary carcinoma is very rare and rarely reported in China and abroad and the treatment is challenging. In this paper, we review the pathogenesis, ancillary tests, diagnosis and treatment of this disease, with the aim of providing reference for clinical treatment of patients with medullary thyroid carcinoma complicated by papillary carcinoma.

Objective:To explore the efficacy of digital and 3D printing technologies on design of superficial iliac circumflex artery flap for coverage the donor site of anterolateral thigh flap(ALTF).Methods:Clinical data of 8 patients were studied retrospectively for treatment of soft tissue defects of hand in the Department of Hand Surgery, Wuxi NO.9 People's Hospital Affiliated to Soochow University, from April 2017 to October 2021. The patients were 6 males and 2 females, aged from 29 to 59 years(mean, 45.8 years). Cause of injury: 3 patients were crushed, 2 by hot pressing, and 3 by machine strangulation. Site of injury included: 5 cases were dorsal hand defects and 3 cases were palm defects. All the wounds were contaminated to varying degrees with soft tissue defects. The areas of soft tissue defect ranged from 11 cm×10 cm to 22 cm×14 cm. Four patients had combined injuries of open fracture of metacarpals and phalanges and 3 with tendon defects. All wounds were repaired by free ALTF transplantation. And the donor sites in the thigh were repaired by superficial iliac circumflex artery flaps. The secondary wounds caused by flap harvesting on abdominal wall were closed directly. The targeted perforator vessels were detected preoperatively by CTA combined with CDU. 3D printed models of the affected hand were obtained before operation for individualised repairs according to the shape and area of the wounds. After the operation, all patients entered scheduled follow-ups at the outpatient clinic and via internet by observing the flap shape and testing the recovery of sensory and movement of adjacent joint.Results:The shapes and sizes of the wounds and the flaps were found basically in accordance with those in the preoperative simulative designs. All flaps in 8 patients survived and the wounds healed completely. All patients entered follow-ups for 8 to 24(average, 17.5) months. The donor thighs presented good appearance and colour, pliability without bloating. The range of motion of the hips and knees was not affected. Only linear scars remained in the abdominal donor sites, with natural colour and appearance.Conclusion:Digital and 3D printing technologies in preoperative design of flaps can help to locate the perforator vessels intraoperatively and guide the individualised design of the flaps with improved operation efficiency and satisfactory appearance of the flaps.