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

OBJECTIVES: To investigate the risk factors for the occurrence of cardiopulmonary dysfunction following ligation of hemodynamically significant patent ductus arteriosus (hsPDA) in preterm infants. METHODS: A retrospective collection of clinical data was conducted on preterm infants with a gestational age of <34 weeks who were admitted to the Maternal and Child Health Hospital of Hubei Province, Tongji Medical College, Huazhong University of Science and Technology from January 2018 to August 2024. These infants underwent hsPDA ligation after 1-2 courses of failed ibuprofen treatment. Based on the occurrence of blood pressure changes and oxygenation or ventilation failure postoperatively, the infants were divided into a cardiopulmonary dysfunction group (19 cases) and a non-cardiopulmonary dysfunction group (40 cases). Binary logistic regression analysis was performed to explore risk factors for postoperative cardiopulmonary dysfunction. RESULTS: Binary logistic regression analysis indicated that a faster average weight gain rate preoperatively and low levels of free triiodothyronine (FT₃) within one week before surgery were risk factors for cardiopulmonary dysfunction following hsPDA ligation (P<0.05). Receiver operating characteristic curve analysis showed that an average weight gain rate >11.45 g/(kg·d) and FT₃ levels <2.785 pmol/L within one week before surgery had predictive value for postoperative cardiopulmonary dysfunction (P<0.05). The combination of these two indicators provided the highest predictive value (P<0.05), with an area under the curve of 0.825, a sensitivity of 79%, and a specificity of 75%. CONCLUSIONS An average weight gain rate exceeding 11.45 g/(kg·d) and FT₃ levels below 2.785 pmol/L within one week before surgery are risk factors affecting cardiopulmonary function after hsPDA ligation. Preoperative assessment and intervention should be strengthened to reduce the risk of postoperative complications.
Humans ; Ductus Arteriosus, Patent/physiopathology* ; Risk Factors ; Female ; Infant, Newborn ; Male ; Retrospective Studies ; Infant, Premature ; Ligation/adverse effects* ; Hemodynamics ; Postoperative Complications/etiology* ; Logistic Models ; Lung Diseases/etiology*

Diffuse alveolar hemorrhage (DAH) is a severe complication that can occur post- hematopoietic stem cell transplantation (HSCT). So far, the precise pathogenesis and risk factors of DAH post-HSCT remain elusive, diagnostic criteria have not reached a consensus, and the efficacy of existing therapeutic measures is far from satisfactory. At present, it is believed that the core mechanism of DAH post-HSCT is a vicious cycle initiated by endothelial injury, accompanied by a series of subsequent inflammatory and cellular responses. Treatment primarily focuses on managing inflammation, promoting hemostasis, and improving oxygenation. This paper reviews recent advances in understanding the pathogenesis, risk factors, clinical manifestations, diagnosis, and treatment of DAH following HSCT.
Humans ; Hematopoietic Stem Cell Transplantation/adverse effects* ; Hemorrhage/etiology* ; Pulmonary Alveoli ; Lung Diseases/etiology* ; Risk Factors

OBJECTIVE: To detect the serum level of chemokine CXC motif chemokine 10 (CXCL-10) and Krebs von den lungen-6 (KL-6) in patients with rheumatoid arthritis associated interstitial lung disease (RA-ILD), and to analyze their correlation with RA-ILD, as well as the significance in RA-ILD. METHODS: A total of 169 RA patients were enrolled in the study. According to imaging findings of with and without ILD in high-resolution computed tomography scans of chest, the subjects were divided into RA-ILD group and RA-non-ILD group. According to the inclusion and exclusion criteria, 80 patients in each of the two groups were finally selected. Two groups were matched according to the 1 ∶ 1 ratio using propensity score matching (PSM). The serum CXCL-10 and KL-6 levels were detected by enzyme-linked immunosorbent assay. The clinical features, laboratory data and medications between the two groups were compared after PSM and the correlation between serum levels and clinical parameters were analyzed. Binary Logistic regression was used to analyze the risk factors of ILD in the RA patients, and the predictive value of CXCL-10 and KL-6 in RA-ILD was evaluated. RESULTS: In this study, 49 patients with RA-ILD and 49 patients with RA-non-ILD were selected by PSM. The levels of CXCL-10 and KL-6 in the RA-ILD group [64.36 (34.01, 110.18) ng/L, 360.70 (236.35, 715.05) U/mL] were significantly higher than those in the RA-non-ILD group [29.80 (16.89, 40.55) ng/L, 210.69 (159.98, 255.50) U/mL] (all P < 0.001). The results of correlation analysis showed that the level of serum CXCL-10 was positively correlated with the Warrick score on chest CT (r=0.378, P=0.007) and negatively correlated with the percentage of forced vital capacity to the predicted value (FVC%, r=-0.338, P=0.018). And the level of KL-6 was positively correlated with rheumatoid factor (RF, r=0.296, P=0.039) and negatively correlated with FVC% (r=-0.436, P=0.002) and the percentage of diffusion capacity for carbon monoxide to the predicted value (DLCO%, r=-0.426, P=0.002). Both univariate and multivariate Logistic regression analysis showed that CXCL-10 and KL-6 were positively correlated with ILD, the values of OR were 1.035 and 1.023 in CXCL-10 and those were 1.004 and 1.005 in KL-6 respectively (P < 0.05). The ROC curves were plotted with CXCL-10 and KL-6. The area under the curve (AUC) was 0.770 and 0.752 respectively. The AUC of combined detection increased to 0.800. CONCLUSION Serum levels of CXCL-10 and KL-6 are significantly elevated in patients with RA-ILD and correlated with the severity of ILD. The combined estimate of them helps to improve the effectiveness of diagnosis.
Humans ; Lung Diseases, Interstitial/etiology* ; Arthritis, Rheumatoid/complications* ; Chemokine CXCL10/blood* ; Mucin-1/blood* ; Female ; Male ; Tomography, X-Ray Computed ; Risk Factors ; Middle Aged

Humans ; Lupus Erythematosus, Systemic/diagnosis* ; Hemorrhage/etiology* ; Lung Diseases/etiology* ; Pulmonary Alveoli

The current organ allocation rules prioritize elderly and urgent patients on the lung transplantation (LT) waiting list. A steady increase in the threshold at which age is taken into consideration for LT has been observed. This retrospective cohort study recruited 166 lung transplant recipients aged ≽ 65 years between January 2016 and October 2020 in the largest LT center in China. In the cohort, subgroups of patients aged 65-70 years (111 recipients, group 65-70) and ≽ 70 years (55 recipients, group ≽ 70) were included. Group D restrictive lung disease was the main indication of a lung transplant in recipients over 65 years. A significantly higher percentage of coronary artery stenosis was observed in the group ≽ 70 (30.9% vs. 14.4% in group 65-70, P = 0.014). ECMO bridging to LT was performed in 5.4% (group 65-70) and 7.3% (group ≽ 70) of patients. Kaplan-Meier estimates showed that recipients with cardiac abnormalities had a significantly increased risk of mortality. After adjusting for potential confounders, cardiac abnormality was shown to be independently associated with the increased risk of post-LT mortality (HR 6.37, P = 0.0060). Our result showed that LT can be performed in candidates with an advanced age and can provide life-extending benefits.
Aged ; Humans ; East Asian People ; Heart Diseases/etiology* ; Lung Transplantation/adverse effects* ; Retrospective Studies

Neurocritical care (NCC) is not only generally guided by principles of general intensive care, but also directed by specific goals and methods. This review summarizes the common pulmonary diseases and pathophysiology affecting NCC patients and the progress made in strategies of respiratory support in NCC. This review highlights the possible interactions and pathways that have been revealed between neurological injuries and respiratory diseases, including the catecholamine pathway, systemic inflammatory reactions, adrenergic hypersensitivity, and dopaminergic signaling. Pulmonary complications of neurocritical patients include pneumonia, neurological pulmonary edema, and respiratory distress. Specific aspects of respiratory management include prioritizing the protection of the brain, and the goal of respiratory management is to avoid inappropriate blood gas composition levels and intracranial hypertension. Compared with the traditional mode of protective mechanical ventilation with low tidal volume (Vt), high positive end-expiratory pressure (PEEP), and recruitment maneuvers, low PEEP might yield a potential benefit in closing and protecting the lung tissue. Multimodal neuromonitoring can ensure the safety of respiratory maneuvers in clinical and scientific practice. Future studies are required to develop guidelines for respiratory management in NCC.
Humans ; Lung ; Lung Diseases/etiology* ; Positive-Pressure Respiration/methods* ; Respiration, Artificial/adverse effects* ; Tidal Volume

Objective: The aim of this study was to summarize the clinical and imaging characteristics of post-primary tuberculosis in children, so as to improve the early identification and diagnosis of post-primary tuberculosis. Methods: This was a retrospective study which enrolled children who were admitted to the Department No.2 of Respiratory Medicine, Beijing Children's Hospital Affiliated to Capital Medical University between January 2015 to December 2020 and with a diagnosis of post-primary tuberculosis. Results: A total of 30 patients were enrolled, including 10 males and 20 females. The age on admission were 13.0 (12.0, 13.3) years. Their common symptoms were cough and fever, there were 26 cases (87%) with cough and 23 cases (77%) with fever, but only 4 cases (13%) had other toxic symptoms (night sweat, weakness or weight loss) of tuberculosis other than fever. Blood examination showed that the white blood cell count was (10±3)×10⁹/L, accompanied by elevated proportion of neutrophils (0.69±0.11) and increased level of C-reactive protein (31 (15,81) mg/L). The common radiographic findings of CT were nodular or mass shadow with cavitation (19 cases (63%)), consolidation (13 cases (43%)), bronchogenic spread (12 cases (40%)), hilar or mediastinal lymphadenopathy (5 cases (17%)) in this cohort. The affected locations included the right upper lobe (21 cases (70%)), the left lower lobe (17 cases (57%)) and the right lower lobe (15 cases (50%)). Acid-fast bacillus smears and mycobacterial cultures were attempted for all cases, resulting in 33% (10/30) with smear positivity and 50% (15/30) with culture positivity. Conclusions: Post-primary tuberculosis in children has no specific clinical manifestations. Imaging of chest CT is mainly manifested as nodular shadow with cavitation, consolidation or bronchogenic spread. Accurate identification of post-primary tuberculosis is crucial for preventing the spread and early treatment of tuberculosis.
Child ; Cough/etiology* ; Female ; Humans ; Lung ; Lung Diseases ; Male ; Retrospective Studies ; Tuberculosis/diagnosis*

Occupational and environmental exposure can directly cause specific lung diseases, and can also induce autoimmune diseases that can lead to various types of interstitial lung diseases. In recent years, it was discovered that certain occupational and environmental exposure was related to the increased risk of Idiopathic pulmonary fibrosis (IPF) disease and progression, including metal and mineral dust, wood dust, organic dust, asbestos dust, silica dust, cigarette smoke and air pollution. IPF is a chronic progressive fibrotic lung disease of unknown etiology, with a characteristic imaging and histologic pattern called usual interstitial pneumonia. This article is a review based on the correlation and mechanism of occupational and environmental exposure in the pathogenesis and disease progression of IPF to improve the understanding of the disease and promote the formulation of treatment plans.
Humans ; Idiopathic Pulmonary Fibrosis/etiology* ; Dust ; Environmental Exposure/adverse effects* ; Occupational Exposure/adverse effects* ; Lung Diseases, Interstitial

OBJECTIVE: To construct and validate a nomogram for predicting the risk of secondary peripheral neuropathy in patients with advanced lung cancer. METHODS: The sociodemographic and clinical data of 335 patients with advanced lung cancer admitted to Department of Respiratory, the First Affiliated Hospital of Zhejiang University School of Medicine from May 2020 to May 2021 were retrospectively collected. Pearson correlation analysis, univariate and multivariate logistic regression analyses were used to identify the risk factors of secondary peripheral neuropathy in patients with advanced lung cancer. A nomogram was constructed according to the contribution of each risk factor to secondary peripheral neuropathy, and the receiver operating characteristic (ROC) curve, Calibration curve and clinical decision curve were used to evaluate differentiation, calibration, and the clinical utility of the model. The nomogram was further validated with data from 64 patients with advanced lung cancer admitted between June 2021 and August 2021. RESULTS: The incidences of secondary peripheral neuropathy in two series of patients were 34.93% (117/335) and 40.63% (26/64), respectively. The results showed that drinking history ( OR=3.650, 95% CI: 1.523-8.746), comorbid diabetes ( OR=3.753, 95% CI: 1.396-10.086), chemotherapy ( OR=2.887, 95% CI: 1.046-7.970), targeted therapy ( OR=8.671, 95% CI: 4.107-18.306), immunotherapy ( OR=2.603, 95% CI: 1.337-5.065) and abnormal liver and kidney function ( OR=12.409, 95% CI: 4.739-32.489) were independent risk factors for secondary peripheral neuropathy (all P<0.05). A nomogram was constructed based on the above risk factors. The area under the ROC curve (AUC) of the nomogram for predicting the secondary peripheral neuropathy was 0.913 (95% CI: 0.882-0.944); and sensitivity, specificity, positive and negative predictive values were 85.47%, 81.65%, 71.43% and 91.28%, respectively. The Calibration curve and clinical decision curve showed good calibration and clinical utility. External validation results showed that the AUC was 0.764 (95% CI: 0.638-0.869); and sensitivity, specificity, positive and negative predictive values were 79.28%, 85.79%, 73.25% and 85.82%, respectively. CONCLUSIONS Advanced lung cancer patients have a high risk of secondary peripheral neuropathy after anticancer therapy. Drinking history, comorbid diabetes, chemotherapy, targeted therapy, immunotherapy, abnormal liver and kidney function are independent risk factors. The nomogram prediction model constructed in the study is effective and may be used for the risk assessment of secondary peripheral neuropathy in patients with advanced lung cancer.
Humans ; Nomograms ; Retrospective Studies ; Peripheral Nervous System Diseases/etiology* ; Risk Factors ; Lung Neoplasms/complications*