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

Diabetic nephropathy(DN)is a significant causative factor of end-stage renal disease globally,and its pathogenesis involves dysregulation of multiple cellular and hormonal pathways.Podocytes play crucial roles in the process of DN,with the extent of podocyte injury closely associated with key pathological manifestations of renal damage,such as proteinuria,glomerular filtration rate,and glomerulosclerosis.However,due to the complexity and interplay of mechanisms contributing to podocyte injury,such as oxidative stress,abnormal lipid metabolism,and mitochondrial damage,the precise mechanisms underlying podocyte injury remain incompletely understood.This review integrated the latest research findings from both domestic and international studies on the core mechanisms of podocyte injury in DN.Furthermore,this article summarized the implications of these mechanisms for DN treatment,particularly focusing on potential therapeutic targets and the development of related pharmacological interventions derived from targeting podocyte injury pathways,so as to provide a theoretical foundation for the development of clinical therapeutic strategies for DN.

Objective:To investigate the treatment regimens, therapeutic effects, and adverse events of immune checkpoint inhibitors (ICI) in the treatment of progressive multifocal leukoencephalopathy (PML).Methods:A retrospective analysis was performed on patients with PML who received ICI treatment at the Department of Neurology of Peking Union Medical College Hospital from October 2020 to September 2024. The patients′ demographic characteristics, baseline immune status, clinical manifestations, laboratory tests, treatment regimens, and clinical outcomes were analyzed.Results:A total of 2 male patients with PML, aged 40 and 59 years, received ICI treatment. One patient had underlying combined immunodeficiency, while the other had acute myeloid leukemia subtype M2 and had previously undergone umbilical cord blood stem cell transplantation. Both patients were treated with pembrolizumab (dosage range: 2-3 mg/kg, administered every 3-4 weeks), receiving a total of 2-4 courses of treatment. In terms of therapeutic effects, both patients showed significant improvement. Regarding adverse events, 1 patient experienced immune-related adverse event (irAE) of immune-related pneumonia combined with immune-related hypophysitis.Conclusions:ICI may be an effective treatment option for PML. However, the use of ICI may be accompanied by the occurrence of irAE, necessitating close monitoring during treatment.

Objective:To evaluate the clinical predictive value of SPECT myocardial perfusion imaging (MPI) in the occurrence of cardiac death in patients with chronic kidney disease (CKD).Methods:A retrospective follow-up was performed for 160 patients (109 males, 51 females; age: 68.5(61.0, 74.0) years) who underwent MPI in Beijing Anzhen Hospital, Capital Medical University between June 2017 and March 2024. The 17-segment 5-point method was used for image analysis to obtain the left ventricular myocardial perfusion and functional parameters. The patients were followed up for cardiac death, and divided into death group and survival group. Clinical data of those 2 groups were compare by χ2 test, the independent-sample t test or Mann-Whitney U test. Cox proportional hazards regression analysis was used to analyze the predictors related to cardiac death. The ROC curve was used to analyze the performance of predictors. Survival curves were obtained by the Kaplan-Meier method, and log-rank test was performed to compare the difference between 2 groups. Results:The follow-up time of 160 patients with CKD was 26.0(10.0, 46.5) months. Of 160 patients, 17 died and 143 survived. There were statistically significant differences in body mass index (BMI), previous myocardial infarction, previous revascularization, hypersensitive C-reactive protein (hs-CRP), positive MPI, left ventricular end-diastolic volume (EDV), end-systolic volume (ESV), ejection fraction (EF), summed stress score (SSS), summed rest score (SRS) and summed difference score (SDS) between the death group and the survival group ( χ2 values: 4.58-16.13, t values: -2.34, -3.97, Z values: from -2.81 to 5.02, all P<0.05). Multivariate Cox regression analysis showed that SSS (hazard ratio ( HR)=1.153, 95% CI: 1.062-1.252, P=0.001) and hs-CRP ( HR=1.031, 95% CI: 1.004-1.058, P=0.023) were independent risk factors for cardiac death in patients with CKD. The optimal cut-off value of SSS for predicting cardiac death in those patients was determined to be 8 with the AUC of 0.815, and the incidence of cardiac death in the SSS ≥8 group was significantly higher than that in the SSS<8 group (33.3%(12/36) vs 4.0%(5/124); χ2 = 25.44, P<0.001). Conclusion:MPI is an important imaging method for the evaluation of cardiac death in patients with CKD, SSS and hs-CRP are important risk factors in predicting cardiac death in those patients.

Objective:To evaluate the clinical predictive value of SPECT myocardial perfusion imaging (MPI) in the occurrence of cardiac death in patients with chronic kidney disease (CKD).Methods:A retrospective follow-up was performed for 160 patients (109 males, 51 females; age: 68.5(61.0, 74.0) years) who underwent MPI in Beijing Anzhen Hospital, Capital Medical University between June 2017 and March 2024. The 17-segment 5-point method was used for image analysis to obtain the left ventricular myocardial perfusion and functional parameters. The patients were followed up for cardiac death, and divided into death group and survival group. Clinical data of those 2 groups were compare by χ2 test, the independent-sample t test or Mann-Whitney U test. Cox proportional hazards regression analysis was used to analyze the predictors related to cardiac death. The ROC curve was used to analyze the performance of predictors. Survival curves were obtained by the Kaplan-Meier method, and log-rank test was performed to compare the difference between 2 groups. Results:The follow-up time of 160 patients with CKD was 26.0(10.0, 46.5) months. Of 160 patients, 17 died and 143 survived. There were statistically significant differences in body mass index (BMI), previous myocardial infarction, previous revascularization, hypersensitive C-reactive protein (hs-CRP), positive MPI, left ventricular end-diastolic volume (EDV), end-systolic volume (ESV), ejection fraction (EF), summed stress score (SSS), summed rest score (SRS) and summed difference score (SDS) between the death group and the survival group ( χ2 values: 4.58-16.13, t values: -2.34, -3.97, Z values: from -2.81 to 5.02, all P<0.05). Multivariate Cox regression analysis showed that SSS (hazard ratio ( HR)=1.153, 95% CI: 1.062-1.252, P=0.001) and hs-CRP ( HR=1.031, 95% CI: 1.004-1.058, P=0.023) were independent risk factors for cardiac death in patients with CKD. The optimal cut-off value of SSS for predicting cardiac death in those patients was determined to be 8 with the AUC of 0.815, and the incidence of cardiac death in the SSS ≥8 group was significantly higher than that in the SSS<8 group (33.3%(12/36) vs 4.0%(5/124); χ2 = 25.44, P<0.001). Conclusion:MPI is an important imaging method for the evaluation of cardiac death in patients with CKD, SSS and hs-CRP are important risk factors in predicting cardiac death in those patients.

Objective:To investigate the treatment regimens, therapeutic effects, and adverse events of immune checkpoint inhibitors (ICI) in the treatment of progressive multifocal leukoencephalopathy (PML).Methods:A retrospective analysis was performed on patients with PML who received ICI treatment at the Department of Neurology of Peking Union Medical College Hospital from October 2020 to September 2024. The patients′ demographic characteristics, baseline immune status, clinical manifestations, laboratory tests, treatment regimens, and clinical outcomes were analyzed.Results:A total of 2 male patients with PML, aged 40 and 59 years, received ICI treatment. One patient had underlying combined immunodeficiency, while the other had acute myeloid leukemia subtype M2 and had previously undergone umbilical cord blood stem cell transplantation. Both patients were treated with pembrolizumab (dosage range: 2-3 mg/kg, administered every 3-4 weeks), receiving a total of 2-4 courses of treatment. In terms of therapeutic effects, both patients showed significant improvement. Regarding adverse events, 1 patient experienced immune-related adverse event (irAE) of immune-related pneumonia combined with immune-related hypophysitis.Conclusions:ICI may be an effective treatment option for PML. However, the use of ICI may be accompanied by the occurrence of irAE, necessitating close monitoring during treatment.

Objective To observe the value of semi-quantitative parameters related to gated myocardial perfusion imaging(G-MPI)for predicting occurrence of major adverse cardiovascular events(MACE)in patients with chronic kidney disease(CKD).Methods Totally 148 CKD patients who underwent rest G-MPI(R-GMPI)(R-GMPI group,n=95)or stress/rest G-MPI(S/R-GMPI)(S/R-GMPI group,n=53)were retrospectively included.The patients were categorized into MACE subgroup and non-MACE subgroup according to MACE occurred or not during follow-up.Clinical data and G-MPI parameters were compared between subgroups,and independent predictors of MACE in CKD patients were obtained using multivariate Cox proportional hazards regression analysis.Receiver operating characteristic(ROC)curve was drawn,the area under the curve(AUC)was calculated to assess the efficacy of each independent predictor for predicting MACE.Among patients who underwent only R-GMPI,the optimal cut-off value of each parameter for predicting MACE was obtained by ROC curve analysis,and the risk of MACE was stratified,then Kaplan-Meier curves were drawn and compared with log-rank test.Results Among 95 patients who underwent only R-GMPI,compared with non-MACE subgroup,those in MACE subgroup had smaller body mass index(BMI)and higher proportion of previous myocardial infarction and hemodialysis,as well as higher R-GMPI left ventricle end-diastolic volume(R-LVEDV),left ventricle end-systolic volume(R-LVESV),sum rest score(R-SRS)but lower left ventricle ejection fraction(R-LVEF)(all P＜0.05),while R-SRS(HR=1.068,95％CI[1.027,1.110])and R-LVESV(HR=1.011,95％CI[1.005,1.017])were both independent predictors for MACE(both P＜0.05).Among 53 patients who underwent S/R-GMPI,compared with non-MACE subgroup,those in MACE subgroup had with higher blood creatinine and lower estimated glomerular filtration rate(eGFR),higher S-LVESV,R-LVEDV,sum stress score(SSS),SRS and sum difference score(SDS)(all P＜0.05),and SDS(HR=1.454,95％CI[1.063,1.989])was an independent predictor for MACE(P＜0.05).Among 95 CKD patients who underwent only R-GMPI,AUC of R-SRS and R-LVESV alone for predicting MACE was 0.659 and 0.694,respectively,and higher incidence of MACE was found in those w ith R-SRS ≥8 points,also in those with R-LVESV ≥91 ml(both P＜0.05).Conclusion G-MPI could be used to evaluate myocardial perfusion and function in CKD patients.For CKD patients just underwent only R-GMPI,R-SRS and R-LVESV were independent predictors for MACE,whereas SDS might be utilized to predict MACE in CKD patients who could undergo S/R-GMPI.

Objective:To evaluate the predictive value of stress+ rest gated myocardial perfusion imaging (G-MPI) in assessing all-cause mortality risk in patients with familial hypercholesterolemia (FH).Methods:From June 2010 to March 2022, 72 patients (39 males, 33 females; age (21.1±12.3) years) who diagnosed with FH clinically and genetically and underwent stress+ rest G-MPI in Beijing Anzhen Hospital, Capital Medical University were retrospectively followed up. Image analysis was performed using the 17-segment 5-point method to obtain left ventricular myocardial perfusion and functional parameters. Patients were followed for all-cause mortality events, and predictors associated with the risk of all-cause mortality were analyzed using Cox regression. The efficiencies of predictors were evaluated by ROC curve analysis, and the Kaplan-Meier method and log-rank test were used to compare the differences in the incidence of all-cause mortality in different groups of patients with FH. Independent-sample t test or Mann-Whitney U test was used to analyze the data. Results:The follow-up time of 72 patients was 7(4, 10) years, and all-cause death occurred in 16(22.2%) patients during the follow-up period. There were statistically significant differences in total cholesterol (TC), low density lipoprotein cholesterol (LDLC), summed stress score (SSS), summed rest score (SRS), summed difference score (SDS), stress end-systolic volume (SESV), stress ejection fraction (SEF), rest end-diastolic volume (REDV), rest end-systolic volume (RESV) and rest ejection fraction (REF) between the death group and the survival group ( t values: from -2.65 to 4.47, z values: from -3.43 to -1.98, all P<0.05). Cox regression analysis showed that SDS (hazard ratio ( HR)=1.337, 95% CI: 1.114-1.604, P=0.002), SESV ( HR=1.019, 95% CI: 1.008-1.030, P<0.001) and LDLC ( HR=1.355, 95% CI: 1.049-1.749, P=0.020) were independent predictors associated with the risk of all-cause mortality in patients with FH. The optimal cut-off value of SESV for predicting mortality in patients with FH determined by ROC curve analysis was 35.5 ml, with the AUC of 0.701 (95% CI: 0.517-0.885). The incidence of all-cause mortality in the group with SESV≥35.5 ml was significantly higher than that in the group with SESV<35.5 ml (28.6% vs 6.9%; χ2=5.15, P=0.023). Conclusion:Stress+ rest G-MPI is an important imaging method for all-cause mortality risk assessment in patients with FH, and SDS, SESV and LDLC are important factors in predicting mortality in patients with FH.

Objective:To compare the feasibility and efficacy of translocator protein (TSPO) molecular probes N, N-diethyl-2-(2-(4- 18F-fluorophenyl)-5, 7-dimethylpyrazolo[1, 5-a]pyrimidin-3-yl)acetamide ( 18F-FDPA) and 18F-(R)-( N-sec-butyl)-3-fluoromethyl- N-methyl-4-phenylquinoline-2-carboxamide (LW223) for the detection of abdominal vulnerable atherosclerotic plaques (VAP) in rabbit models. Methods:Nine healthy New Zealand white rabbits were divided into group A (control group, n=3), group B (VAP group, n=3) and group C (VAP treatment group, n=3) using completely randomized design. Animals were injected with 18F-FDPA and 18F-LW223 at the end of 12, 16 and 24 weeks. PET/CT and CT angiography (CTA) was performed 40-50 min post injection. All rabbits were sacrificed at the end of 24 weeks after imaging studies. All abdominal aortas were collected for pathological and immunofluorescence examination. Repeated measures analysis of variance (Bonferroni test) and paired t-test were used to analyze the data. Results:Target-to-background ratio (TBR; abdominal aortic lesion/left ventricular blood pool) values of 18F-FDPA in 3 groups at the end of 12, 16 and 24 weeks were significantly different ( F values: 68.09-144.88, all P<0.001). At the end of 12 weeks, there was no increased uptake of 18F-FDPA in the abdominal aorta region in 3 groups. The local 18F-FDPA uptake of the abdominal aorta in group B was significantly higher than the uptake in group C and that in group A at the end of 16 and 24 weeks( P<0.05 or P<0.001), and there were significant differences between group C and group A, with higher uptake in group C (both P<0.01). In 3 groups, there was no significant 18F-LW223 uptake in the abdominal aorta region at 3 time points of PET/CTA imaging. At the end of 12, 16 and 24 weeks, TBR values of 18F-FDPA and 18F-LW223 in 3 groups exhibited statistical differences ( t values: 2.88-36.79, all P<0.05). HE, immunofluorescent CD68 and TSPO staining showed more macrophage infiltration in group B than group C. Conclusion:18F-FDPA can be used to detect VAP in rabbits′ abdominal arteries at early time compared to 18F-LW223, and to evaluate the changes in the stability of vulnerable plaque after lipid-lowering drug intervention.

Objective:To establish the normal reference value of left ventricular function parameters by cadmium-zinc-tellurium (CZT) SPECT stress gated myocardial perfusion imaging (G-MPI) in low-likelihood of stable coronary artery disease (SCAD).Methods:From March 2022 to August 2022, 348 consecutive SCAD patients (146 males, 202 females, age (58±10) years) who underwent exercise or pharmacological stress G-MPI (CZT SPECT) in Beijing Anzhen Hospital, Capital Medical University were retrospectively recruited. Left ventricular end-diastolic volume (EDV), end-systolic volume (ESV), and left ventricular ejection fraction (LVEF) were acquired using quantitative gated SPECT (QGS) analysis. EDV and ESV were corrected by body surface area (BSA) to obtain EDV index (EDVI) and ESV index (ESVI), respectively. Independent-sample t test, one-way analysis of variance and Mann-Whitney U test were used for data analysis. The influences of EDV, ESV, EDVI, ESVI and LVEF were analyzed by multiple regressions for linear models. Results:There were 314 patients with low-likelihood of SCAD (128 males, 186 females, age (58±10) years) and 34 normal controls (18 males, 16 females, age (55±10) years). There were no significant differences of basic clinical characteristics and left ventricular function parameters in different genders between 2 groups ( z values: from -1.74 to -0.02, t values: from -1.16 to 1.17, all P>0.05). Using the 95% CI as the cut-off value for left ventricular function parameters in patients with a low-likelihood of SCAD, the upper limits of EDV, ESV, EDVI and ESVI in females and males were 84 and 111 ml, 30 and 44 ml, 47 and 54 ml/m 2, 17 and 21 ml/m 2, respectively, and the lower limit of LVEF in females and males were 58% and 55%, respectively. In the low-likelihood of SCAD group, the EDV ((58±13) vs (77±17) ml) and ESV ((16±7) vs (26±9) ml) of females were smaller than those of males ( t values: 10.65, 10.35, both P<0.001), while LVEF of females was higher than that of males ((72±7)% vs (67±6)%; t=-6.23, P<0.001). However, there were no significant differences in left ventricular function parameters among different age groups with the same gender ( F values: 0.12-2.19, all P>0.05). Based on multiple regression for linear models, the primary predictors of EDV, ESV and LVEF were gender and weight ( β values: from -0.380 to 0.358, all P<0.05). Conclusions:Normal reference values of left ventricular function parameters are established by CZT SPECT stress G-MPI in low-likelihood of SCAD patients. Left ventricular EDV and ESV of females are smaller than those of males, while LVEF of females is higher than that of males. The influence of gender on left ventricular function parameters should be considered in clinical practice.