1.Development and multicenter validation of machine learning models for predicting postoperative pulmonary complications after neurosurgery.
Ming XU ; Wenhao ZHU ; Siyu HOU ; Hongzhi XU ; Jingwen XIA ; Liyu LIN ; Hao FU ; Mingyu YOU ; Jiafeng WANG ; Zhi XIE ; Xiaohong WEN ; Yingwei WANG
Chinese Medical Journal 2025;138(17):2170-2179
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
2.Study on the treatment of chronic nonbacterial prostatitis caused by dampness-heat stasis with Oxalis Formula combined with transacupuncture.
Qiang LOU ; Ming-Wei ZHAN ; Yu-Qi LAI ; Xu-Xin ZHAN ; You-Ping XIAO ; Xue-Jun SHANG
National Journal of Andrology 2025;31(2):165-171
OBJECTIVE:
The aim of this study is to evaluate the clinical efficacy of Oxalicao Formula combined with transacupuncture in the treatment of chronic nonbacterial prostatitis (CNP)characterized by dampness-heat stasis.
METHODS:
A total of 70 patients diagnosed with CNP and characterized by dampness-heat stasis were randomly divided into control group and treatment group, with 35 cases in each group. The patients in control group received Qianlie Beixi capsules. While the patients in treatment group were administered with oxalis decoction in conjunction with acupuncture therapy which lasted for 8 weeks. Pre- and post-treatment evaluations for NIH-Chronic Prostatitis Symptom Index (NIH-CPSI), Traditional Chinese Medicine (TCM) symptom scores, urodynamic parameters, immune cell subsets and inflammatory factors were performed.
RESULTS:
Ultimately, 65 patients completed the study with 33 in the treatment group and 32 in the control group. After 8 weeks of intervention, The patients in both of groups demonstrated significant improvements (P<0.05). Specifically, remarkable reductions in the NIH-CPSI total score including pain score, urination score, quality of life impact score, TCM symptom score and inflammatory cytokine levels were observed. Additionally, there were upward trend in maximum and average urinary flow rates as well as the CD4+/CD8+ ratio of immune cells(P<0.05). Compared to the control group, the treatment group exhibited superior outcomes in reducing the NIH-CPSI total score, pain score, urination score, quality of life impact score, TCM symptom score, and inflammatory cytokine levels, and increasing in CD4+/CD8+ ratios, maximum and average urine flow rates(P<0.05).
CONCLUSION
The combination of Oxalicao Formula and transacupuncture for treating CNP characterized by dampness-heat stasis demonstrates significant therapeutic benefits, which has considerable clinical application value.
Humans
;
Male
;
Prostatitis/therapy*
;
Drugs, Chinese Herbal/therapeutic use*
;
Acupuncture Therapy
;
Medicine, Chinese Traditional
;
Chronic Disease
;
Treatment Outcome
;
Adult
3.Mechanism of salvianolic acid B protecting H9C2 from OGD/R injury based on mitochondrial fission and fusion
Zi-xin LIU ; Gao-jie XIN ; Yue YOU ; Yuan-yuan CHEN ; Jia-ming GAO ; Ling-mei LI ; Hong-xu MENG ; Xiao HAN ; Lei LI ; Ye-hao ZHANG ; Jian-hua FU ; Jian-xun LIU
Acta Pharmaceutica Sinica 2024;59(2):374-381
This study aims to investigate the effect of salvianolic acid B (Sal B), the active ingredient of Salvia miltiorrhiza, on H9C2 cardiomyocytes injured by oxygen and glucose deprivation/reperfusion (OGD/R) through regulating mitochondrial fission and fusion. The process of myocardial ischemia-reperfusion injury was simulated by establishing OGD/R model. The cell proliferation and cytotoxicity detection kit (cell counting kit-8, CCK-8) was used to detect cell viability; the kit method was used to detect intracellular reactive oxygen species (ROS), total glutathione (t-GSH), nitric oxide (NO) content, protein expression levels of mitochondrial fission and fusion, apoptosis-related detection by Western blot. Mitochondrial permeability transition pore (MPTP) detection kit and Hoechst 33342 fluorescence was used to observe the opening level of MPTP, and molecular docking technology was used to determine the molecular target of Sal B. The results showed that relative to control group, OGD/R injury reduced cell viability, increased the content of ROS, decreased the content of t-GSH and NO. Furthermore, OGD/R injury increased the protein expression levels of dynamin-related protein 1 (Drp1), mitofusions 2 (Mfn2), Bcl-2 associated X protein (Bax) and cysteinyl aspartate specific proteinase 3 (caspase 3), and decreased the protein expression levels of Mfn1, increased MPTP opening level. Compared with the OGD/R group, it was observed that Sal B had a protective effect at concentrations ranging from 6.25 to 100 μmol·L-1. Sal B decreased the content of ROS, increased the content of t-GSH and NO, and Western blot showed that Sal B decreased the protein expression levels of Drp1, Mfn2, Bax and caspase 3, increased the protein expression level of Mfn1, and decreased the opening level of MPTP. In summary, Sal B may inhibit the opening of MPTP, reduce cell apoptosis and reduce OGD/R damage in H9C2 cells by regulating the balance of oxidation and anti-oxidation, mitochondrial fission and fusion, thereby providing a scientific basis for the use of Sal B in the treatment of myocardial ischemia reperfusion injury.
4.Toxicokinetics of MDMA and Its Metabolite MDA in Rats
Wei-Guang YU ; Qiang HE ; Zheng-Di WANG ; Cheng-Jun TIAN ; Jin-Kai WANG ; Qian ZHENG ; Fei REN ; Chao ZHANG ; You-Mei WANG ; Peng XU ; Zhi-Wen WEI ; Ke-Ming YUN
Journal of Forensic Medicine 2024;40(1):37-42
Objective To investigate the toxicokinetic differences of 3,4-methylenedioxy-N-methylamphetamine(MDMA)and its metabolite 4,5-methylene dioxy amphetamine(MDA)in rats af-ter single and continuous administration of MDMA,providing reference data for the forensic identifica-tion of MDMA.Methods A total of 24 rats in the single administration group were randomly divided into 5,10 and 20 mg/kg experimental groups and the control group,with 6 rats in each group.The ex-perimental group was given intraperitoneal injection of MDMA,and the control group was given intraperi-toneal injection of the same volume of normal saline as the experimental group.The amount of 0.5 mL blood was collected from the medial canthus 5 min,30 min,1 h,1.5 h,2 h,4 h,6 h,8 h,10 h,12 h after administration.In the continuous administration group,24 rats were randomly divided into the experi-mental group(18 rats)and the control group(6 rats).The experimental group was given MDMA 7 d by continuous intraperitoneal injection in increments of 5,7,9,11,13,15,17 mg/kg per day,respectively,while the control group was given the same volume of normal saline as the experimental group by in-traperitoneal injection.On the eighth day,the experimental rats were randomly divided into 5,10 and 20 mg/kg dose groups,with 6 rats in each group.MDMA was injected intraperitoneally,and the con-trol group was injected intraperitoneally with the same volume of normal saline as the experimental group.On the eighth day,0.5 mL of blood was taken from the medial canthus 5 min,30 min,1 h,1.5 h,2 h,4 h,6 h,8 h,10 h,12 h after administration.Liquid chromatography-triple quadrupole tandem mass spectrometry was used to detect MDMA and MDA levels,and statistical software was employed for data analysis.Results In the single-administration group,peak concentrations of MDMA and MDA were reached at 5 min and 1 h after administration,respectively,with the largest detection time limit of 12 h.In the continuous administration group,peak concentrations were reached at 30 min and 1.5 h af-ter administration,respectively,with the largest detection time limit of 10 h.Nonlinear fitting equations for the concentration ratio of MDMA and MDA in plasma and administration time in the single-administration group and continuous administration group were as follows:T=10.362C-1.183,R2=0.974 6;T=7.397 3C-0.694,R2=0.961 5(T:injection time;C:concentration ratio of MDMA to MDA in plasma).Conclusions The toxicokinetic data of MDMA and its metabolite MDA in rats,obtained through single and continuous administration,including peak concentration,peak time,detection time limit,and the relationship between concentration ratio and administration time,provide a theoretical and data foundation for relevant forensic identification.
5.Cloning,Subcellular Localization and Expression Analysis of AaCPS from Artemisia argyi
Xiang CHENG ; Yue MING ; Jingmao YOU ; Zhaohua SHI ; Bo WANG ; Dingrong WAN ; Xianming LIN ; Ran XU
World Science and Technology-Modernization of Traditional Chinese Medicine 2024;26(5):1223-1232
Objective To clone the full-length sequence,subcellular localization,and analyze the expression patterns of the β-caryophyllene synthase gene(AaCPS)of Artemisia argyi,in order to lay a foundation for the gene function analysis of sesquiterpene biosynthesis pathway in A.argyi.Methods The genes annotated as CPS were selected from the transcriptome data of A.argyi.The full-length cDNA sequence of the target gene was obtained by PCR,and the coding region was analyzed using bioinformatics.A prokaryotic expression vector was constructed and transformed into Escherichia coli competent cells to express recombinant protein.A green fluorescent protein(GFP)fused expression vector was constructed,and the subcellular localization of AaCPS was observed using Agrobacterium tumefaciens transient expression method in tobacco.Real-time quantitative PCR(qRT-PCR)was used to analyze the expression patterns of the AaCPS at different harvest times(April,May,June,July).Determination of β-caryophyllene by HS-SPME-GC-MS and correlation analysis.Results The AaCPS gene was cloned from A.argyi.The full-length open reading frame(ORF)was 1647 bp,encoding 548 amino acids.The molecular weight was 63 667 Da with a theoretical pI of 5.94.AaCPS contained conserved Terpen_synth and Terpen_synth_C domains.Phylogenetic analysis indicated that AaCPS was closely related to the CPS protein of Artemisia annua.SDS-PAGE showed the presence of target protein bands between 75 000-120 000 Da(containing 28 132 Da of the labeled protein),indicating successful expression of the AaCPS protein.The protein was found to be localized in the cytoplasm.As shown by qRT-PCR,the expression of AaCPS gene showed an upward trend,reaching the highest in July.The results of HS-SPME-GC-MS showed that the content of β-caryophyllene increased gradually from April to the highest in June.It is consistent with the trend of AaCPS gene expression from April to June.Conclusion Through the cloning and analysis of AaCPS gene,a foundation has been laid for further study of the functional identification of the AaCPS gene in the sesquiterpenes biosynthesis pathway in A.argyi.
6.Expert consensus on ethical requirements for artificial intelligence (AI) processing medical data.
Cong LI ; Xiao-Yan ZHANG ; Yun-Hong WU ; Xiao-Lei YANG ; Hua-Rong YU ; Hong-Bo JIN ; Ying-Bo LI ; Zhao-Hui ZHU ; Rui LIU ; Na LIU ; Yi XIE ; Lin-Li LYU ; Xin-Hong ZHU ; Hong TANG ; Hong-Fang LI ; Hong-Li LI ; Xiang-Jun ZENG ; Zai-Xing CHEN ; Xiao-Fang FAN ; Yan WANG ; Zhi-Juan WU ; Zun-Qiu WU ; Ya-Qun GUAN ; Ming-Ming XUE ; Bin LUO ; Ai-Mei WANG ; Xin-Wang YANG ; Ying YING ; Xiu-Hong YANG ; Xin-Zhong HUANG ; Ming-Fei LANG ; Shi-Min CHEN ; Huan-Huan ZHANG ; Zhong ZHANG ; Wu HUANG ; Guo-Biao XU ; Jia-Qi LIU ; Tao SONG ; Jing XIAO ; Yun-Long XIA ; You-Fei GUAN ; Liang ZHU
Acta Physiologica Sinica 2024;76(6):937-942
As artificial intelligence technology rapidly advances, its deployment within the medical sector presents substantial ethical challenges. Consequently, it becomes crucial to create a standardized, transparent, and secure framework for processing medical data. This includes setting the ethical boundaries for medical artificial intelligence and safeguarding both patient rights and data integrity. This consensus governs every facet of medical data handling through artificial intelligence, encompassing data gathering, processing, storage, transmission, utilization, and sharing. Its purpose is to ensure the management of medical data adheres to ethical standards and legal requirements, while safeguarding patient privacy and data security. Concurrently, the principles of compliance with the law, patient privacy respect, patient interest protection, and safety and reliability are underscored. Key issues such as informed consent, data usage, intellectual property protection, conflict of interest, and benefit sharing are examined in depth. The enactment of this expert consensus is intended to foster the profound integration and sustainable advancement of artificial intelligence within the medical domain, while simultaneously ensuring that artificial intelligence adheres strictly to the relevant ethical norms and legal frameworks during the processing of medical data.
Artificial Intelligence/legislation & jurisprudence*
;
Humans
;
Consensus
;
Computer Security/standards*
;
Confidentiality/ethics*
;
Informed Consent/ethics*
7.Pyridine pigments from functional Monascus rice
Bing-yu LIU ; Xiao-ming ZHENG ; An-an LIU ; Fei XU ; Qian WEI ; You-cai HU
Acta Pharmaceutica Sinica 2023;58(8):2442-2447
The trace chemical components in functional
8.Research progress of brain-computer interface application paradigms based on rapid serial visual presentation.
Jingmin SUN ; Jiayuan MENG ; Jia YOU ; Mingming YANG ; Jing JIANG ; Minpeng XU ; Dong MING
Journal of Biomedical Engineering 2023;40(6):1235-1241
Rapid serial visual presentation (RSVP) is a type of psychological visual stimulation experimental paradigm that requires participants to identify target stimuli presented continuously in a stream of stimuli composed of numbers, letters, words, images, and so on at the same spatial location, allowing them to discern a large amount of information in a short period of time. The RSVP-based brain-computer interface (BCI) can not only be widely used in scenarios such as assistive interaction and information reading, but also has the advantages of stability and high efficiency, which has become one of the common techniques for human-machine intelligence fusion. In recent years, brain-controlled spellers, image recognition and mind games are the most popular fields of RSVP-BCI research. Therefore, aiming to provide reference and new ideas for RSVP-BCI related research, this paper reviewed the paradigm design and system performance optimization of RSVP-BCI in these three fields. It also looks ahead to its potential applications in cutting-edge fields such as entertainment, clinical medicine, and special military operations.
Humans
;
Brain-Computer Interfaces
;
Electroencephalography/methods*
;
Brain/physiology*
;
Artificial Intelligence
;
Photic Stimulation/methods*
9.Chinese Guideline on the Management of Polypoidal Choroidal Vasculopathy (2022).
You-Xin CHEN ; Yu-Qing ZHANG ; Chang-Zheng CHEN ; Hong DAI ; Su-Yan LI ; Xiang MA ; Xiao-Dong SUN ; Shi-Bo TANG ; Yu-Sheng WANG ; Wen-Bin WEI ; Feng WEN ; Ge-Zhi XU ; Wei-Hong YU ; Mei-Xia ZHANG ; Ming-Wei ZHAO ; Yang ZHANG ; Fang QI ; Xun XU ; Xiao-Xin LI
Chinese Medical Sciences Journal 2023;38(2):77-93
Background In mainland China, patients with neovascular age-related macular degeneration (nAMD) have approximately an 40% prevalence of polypoidal choroidal vasculopathy (PCV). This disease leads to recurrent retinal pigment epithelium detachment (PED), extensive subretinal or vitreous hemorrhages, and severe vision loss. China has introduced various treatment modalities in the past years and gained comprehensive experience in treating PCV.Methods A total of 14 retinal specialists nationwide with expertise in PCV were empaneled to prioritize six questions and address their corresponding outcomes, regarding opinions on inactive PCV, choices of anti-vascular endothelial growth factor (anti-VEGF) monotherapy, photodynamic therapy (PDT) monotherapy or combined therapy, patients with persistent subretinal fluid (SRF) or intraretinal fluid (IRF) after loading dose anti-VEGF, and patients with massive subretinal hemorrhage. An evidence synthesis team conducted systematic reviews, which informed the recommendations that address these questions. This guideline used the GRADE (Grading of Recommendations, Assessment, Development, and Evaluation) approach to assess the certainty of evidence and grade the strengths of recommendations. Results The panel proposed the following six conditional recommendations regarding treatment choices. (1) For patients with inactive PCV, we suggest observation over treatment. (2) For treatment-na?ve PCV patients, we suggest either anti-VEGF monotherapy or combined anti-VEGF and PDT rather than PDT monotherapy. (3) For patients with PCV who plan to initiate combined anti-VEGF and PDT treatment, we suggest later/rescue PDT over initiate PDT. (4) For PCV patients who plan to initiate anti-VEGF monotherapy, we suggest the treat and extend (T&E) regimen rather than the pro re nata (PRN) regimen following three monthly loading doses. (5) For patients with persistent SRF or IRF on optical coherence tomography (OCT) after three monthly anti-VEGF treatments, we suggest proceeding with anti-VEGF treatment rather than observation. (6) For PCV patients with massive subretinal hemorrhage (equal to or more than four optic disc areas) involving the central macula, we suggest surgery (vitrectomy in combination with tissue-plasminogen activator (tPA) intraocular injection and gas tamponade) rather than anti-VEGF monotherapy. Conclusions Six evidence-based recommendations support optimal care for PCV patients' management.
10.Safety and efficacy of the early administration of levosimendan in patients with acute non-ST-segment elevation myocardial infarction and elevated NT-proBNP levels: An Early Management Strategy of Acute Heart Failure (EMS-AHF).
Feng XU ; Yuan BIAN ; Guo Qiang ZHANG ; Lu Yao GAO ; Yu Fa LIU ; Tong Xiang LIU ; Gang LI ; Rui Xue SONG ; Li Jun SU ; Yan Ju ZHOU ; Jia Yu CUI ; Xian Liang YAN ; Fang Ming GUO ; Huan Yi ZHANG ; Qing Hui LI ; Min ZHAO ; Li Kun MA ; Bei An YOU ; Ge WANG ; Li KONG ; Jian Liang MA ; Xin Fu ZHOU ; Ze Long CHANG ; Zhen Yu TANG ; Dan Yu YU ; Kai CHENG ; Li XUE ; Xiao LI ; Jiao Jiao PANG ; Jia Li WANG ; Hai Tao ZHANG ; Xue Zhong YU ; Yu Guo CHEN
Chinese Journal of Internal Medicine 2023;62(4):374-383
Objectives: To investigated the safety and efficacy of treating patients with acute non-ST-segment elevation myocardial infarction (NSTEMI) and elevated levels of N-terminal pro-hormone B-type natriuretic peptide (NT-proBNP) with levosimendan within 24 hours of first medical contact (FMC). Methods: This multicenter, open-label, block-randomized controlled trial (NCT03189901) investigated the safety and efficacy of levosimendan as an early management strategy of acute heart failure (EMS-AHF) for patients with NSTEMI and high NT-proBNP levels. This study included 255 patients with NSTEMI and elevated NT-proBNP levels, including 142 males and 113 females with a median age of 65 (58-70) years, and were admitted in the emergency or outpatient departments at 14 medical centers in China between October 2017 and October 2021. The patients were randomly divided into a levosimendan group (n=129) and a control group (n=126). The primary outcome measure was NT-proBNP levels on day 3 of treatment and changes in the NT-proBNP levels from baseline on day 5 after randomization. The secondary outcome measures included the proportion of patients with more than 30% reduction in NT-proBNP levels from baseline, major adverse cardiovascular events (MACE) during hospitalization and at 6 months after hospitalization, safety during the treatment, and health economics indices. The measurement data parameters between groups were compared using the t-test or the non-parametric test. The count data parameters were compared between groups using the χ² test. Results: On day 3, the NT-proBNP levels in the levosimendan group were lower than the control group but were statistically insignificant [866 (455, 1 960) vs. 1 118 (459, 2 417) ng/L, Z=-1.25,P=0.21]. However, on day 5, changes in the NT-proBNP levels from baseline in the levosimendan group were significantly higher than the control group [67.6% (33.8%,82.5%)vs.54.8% (7.3%,77.9%), Z=-2.14, P=0.03]. There were no significant differences in the proportion of patients with more than 30% reduction in the NT-proBNP levels on day 5 between the levosimendan and the control groups [77.5% (100/129) vs. 69.0% (87/126), χ²=2.34, P=0.13]. Furthermore, incidences of MACE did not show any significant differences between the two groups during hospitalization [4.7% (6/129) vs. 7.1% (9/126), χ²=0.72, P=0.40] and at 6 months [14.7% (19/129) vs. 12.7% (16/126), χ²=0.22, P=0.64]. Four cardiac deaths were reported in the control group during hospitalization [0 (0/129) vs. 3.2% (4/126), P=0.06]. However, 6-month survival rates were comparable between the two groups (log-rank test, P=0.18). Moreover, adverse events or serious adverse events such as shock, ventricular fibrillation, and ventricular tachycardia were not reported in both the groups during levosimendan treatment (days 0-1). The total cost of hospitalization [34 591.00(15 527.46,59 324.80) vs. 37 144.65(16 066.90,63 919.00)yuan, Z=-0.26, P=0.80] and the total length of hospitalization [9 (8, 12) vs. 10 (7, 13) days, Z=0.72, P=0.72] were lower for patients in the levosimendan group compared to those in the control group, but did not show statistically significant differences. Conclusions: Early administration of levosimendan reduced NT-proBNP levels in NSTEMI patients with elevated NT-proBNP and did not increase the total cost and length of hospitalization, but did not significantly improve MACE during hospitalization or at 6 months.
Male
;
Female
;
Humans
;
Aged
;
Natriuretic Peptide, Brain
;
Simendan/therapeutic use*
;
Non-ST Elevated Myocardial Infarction
;
Heart Failure/drug therapy*
;
Peptide Fragments
;
Arrhythmias, Cardiac
;
Biomarkers
;
Prognosis

Result Analysis
Print
Save
E-mail