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

The surveillance data of new cases of acute myocardial infarction (AMI) from January 1, 2013, to December 31, 2021, in Tengzhou City, Shandong Province, were used to analyze the incidence rate of AMI and its change trend among residents. The age and gender standardized incidence rate was calculated based on the 7th National Population Census 2020. The Cochran-Armitage trend test was used to analyze the trend of onset time and age. From 2013 to 2021, the crude and standardized incidence rate of total AMI in Tengzhou City declined from 130.07/100 000 and 161.12/100 000 to 76.15/100 000 and 72.77/100 000 ( Z=-13.785 and -20.822, both P<0.001). The crude and standardized incidence rates of males were higher than those of females. In 2016, males aged 45-54 years old and females aged 35-64 years old increased by 33.33%, 103.65%, 106.30%, and 95.75% compared to 2015, and the differences were statistically significant ( χ2=6.512, 4.965, 25.115, and 46.004, all P<0.05). The incidence rate of AMI in men aged<35 and 35-44 years old had an upward trend. From 2013 to 2021, the incidence rate of AMI decreased by 55.15% in urban areas and 36.59% in rural areas ( Z=-8.529 and -11.235, both P<0.001).

The surveillance data of new cases of acute myocardial infarction (AMI) from January 1, 2013, to December 31, 2021, in Tengzhou City, Shandong Province, were used to analyze the incidence rate of AMI and its change trend among residents. The age and gender standardized incidence rate was calculated based on the 7th National Population Census 2020. The Cochran-Armitage trend test was used to analyze the trend of onset time and age. From 2013 to 2021, the crude and standardized incidence rate of total AMI in Tengzhou City declined from 130.07/100 000 and 161.12/100 000 to 76.15/100 000 and 72.77/100 000 ( Z=-13.785 and -20.822, both P<0.001). The crude and standardized incidence rates of males were higher than those of females. In 2016, males aged 45-54 years old and females aged 35-64 years old increased by 33.33%, 103.65%, 106.30%, and 95.75% compared to 2015, and the differences were statistically significant ( χ2=6.512, 4.965, 25.115, and 46.004, all P<0.05). The incidence rate of AMI in men aged<35 and 35-44 years old had an upward trend. From 2013 to 2021, the incidence rate of AMI decreased by 55.15% in urban areas and 36.59% in rural areas ( Z=-8.529 and -11.235, both P<0.001).

Objective:To analyze long-term prognosis and influencing factors of recurrence in vocal fold leukoplakia treated by endoscopic cordectomy with CO 2 laser. Methods:A retrospective review was conducted on 599 patients with vocal fold leukoplakia [566 males and 33 females, aged 17-84 years (median age 55 years)], undergoing endoscopic cordectomy by CO 2 laser under general anesthesia at the Department of Otorhinolaryngology Head and Neck Surgery of Beijing Tongren Hospital, Capital Medical University, from January 2000 to December 2023. The study analyzed the clinical features, pathological grade, surgical methods, postoperative voice function, recurrence, malignant changes and analyzed the long-term efficacy and and its influencing factors. The patients were followed up for a duration of 6-249 months postoperatively, with a median follow-up time of 48 months. SPSS 20.0 software was used for statistical analysis. Results:Among the 599 patients, the histopathological grades included simple squamous cell hyperplasia in ( n=264, 44.08%), mild dysplasia ( n=96, 16.03%), moderate dysplasia ( n=74, 12.35%), severe dysplasia( n=43, 7.81%), carcinoma in situ( n=35, 5.84%), and carcinoma in situ with microinvasion( n=87, 14.52%). The 3-year and 5-year overall recurrence rates were 12.91% and 16.00%, respectively. In patients with precancerous lesion, 3.91% of recurrences presented with an upgraded pathologic grade and 2.34% evolved into carcinoma. The risk of recurrence was higher in lesions involving the anterior commissure, larger lesions, significant reduction/absence of mucosal waves, neovascularization/suspected neovascularization, and pathology of dysplasia/carcinoma in situ/carcinoma in situ with microinvasion( F=44.76,21.54,11.55,8.78,23.20,respectively, P<0.05). Additionally, patients with recurrent disease exhibited higher reflux symptom index scores compared to those without recurrence. Exophytic lesion characteristics and the inability to cease smoking postoperatively were identified as independent risk factors for recurrence with an upgraded pathological grade, with odds ratios of 8.675 and 11.380 times greater than those with non-exophytic lesions and successful smoking cessation, respectively. At the 6-months postoperative assessment, patients who underwent subepithelial cordectomy (typeⅠ) demonstrated a statistically significant increase in fundamental frequency ( t=-3.38, P<0.05), and while other voice acoustic parameters were not significantly different.Conversely, those who underwent transmuscular cordectomy (TypeⅢ) exhibited significant alterations in multiple voice acoustic parameters when compared to preoperative values ( P<0.05). Furthermore, postoperative vocal fold adhesions developed in 84 patients with 13 of these individuals requiring surgical intervention for adhesion release. Conclusions:Lesions involving the anterior commissure, larger lesions, pathology of dysplasia/carcinoma in situ/carcinoma in situ with microinfiltration, significant reduction/absence of vocal fold mucosal waves, and neovascularization visible under NBI are indicative of an increased risk of recurrence, whereas exophytic lesions and the inability to cease smoking postoperatively significantly increase the risk of recurrence with elevated pathologic grade. Recovery of postoperative voice quality is procedure-dependent, underscoring the importance of surgical approach selection in the management of vocal fold leukoplakia.

Improving the entire outpatient clinic experience is an important measure in the new era to enhance patients'sense of gain from medical treatment.Beijing Tongren Hospital Affiliated to Capital Medical University explores the establishment of a full-process outpatient service management system based on continuous improvement of medical services.Through the concept of forward service,it focuses on the patient's pre-diagnosis experience;the process is simplified and intelligently guided to optimize the patient's in-diagnosis experience;and continuous diagnosis and treatment Model innovation improves patients'post-diagnosis experience and creates a Chinese-style modern outpatient medical service model to continuously meet the people's growing needs for a better life.

Improving the entire outpatient clinic experience is an important measure in the new era to enhance patients'sense of gain from medical treatment.Beijing Tongren Hospital Affiliated to Capital Medical University explores the establishment of a full-process outpatient service management system based on continuous improvement of medical services.Through the concept of forward service,it focuses on the patient's pre-diagnosis experience;the process is simplified and intelligently guided to optimize the patient's in-diagnosis experience;and continuous diagnosis and treatment Model innovation improves patients'post-diagnosis experience and creates a Chinese-style modern outpatient medical service model to continuously meet the people's growing needs for a better life.

Improving the entire outpatient clinic experience is an important measure in the new era to enhance patients'sense of gain from medical treatment.Beijing Tongren Hospital Affiliated to Capital Medical University explores the establishment of a full-process outpatient service management system based on continuous improvement of medical services.Through the concept of forward service,it focuses on the patient's pre-diagnosis experience;the process is simplified and intelligently guided to optimize the patient's in-diagnosis experience;and continuous diagnosis and treatment Model innovation improves patients'post-diagnosis experience and creates a Chinese-style modern outpatient medical service model to continuously meet the people's growing needs for a better life.

Improving the entire outpatient clinic experience is an important measure in the new era to enhance patients'sense of gain from medical treatment.Beijing Tongren Hospital Affiliated to Capital Medical University explores the establishment of a full-process outpatient service management system based on continuous improvement of medical services.Through the concept of forward service,it focuses on the patient's pre-diagnosis experience;the process is simplified and intelligently guided to optimize the patient's in-diagnosis experience;and continuous diagnosis and treatment Model innovation improves patients'post-diagnosis experience and creates a Chinese-style modern outpatient medical service model to continuously meet the people's growing needs for a better life.

Improving the entire outpatient clinic experience is an important measure in the new era to enhance patients'sense of gain from medical treatment.Beijing Tongren Hospital Affiliated to Capital Medical University explores the establishment of a full-process outpatient service management system based on continuous improvement of medical services.Through the concept of forward service,it focuses on the patient's pre-diagnosis experience;the process is simplified and intelligently guided to optimize the patient's in-diagnosis experience;and continuous diagnosis and treatment Model innovation improves patients'post-diagnosis experience and creates a Chinese-style modern outpatient medical service model to continuously meet the people's growing needs for a better life.

Improving the entire outpatient clinic experience is an important measure in the new era to enhance patients'sense of gain from medical treatment.Beijing Tongren Hospital Affiliated to Capital Medical University explores the establishment of a full-process outpatient service management system based on continuous improvement of medical services.Through the concept of forward service,it focuses on the patient's pre-diagnosis experience;the process is simplified and intelligently guided to optimize the patient's in-diagnosis experience;and continuous diagnosis and treatment Model innovation improves patients'post-diagnosis experience and creates a Chinese-style modern outpatient medical service model to continuously meet the people's growing needs for a better life.