1.Screening of diagnostic markers for endothelial cell Senescence in mice with radiation-induced heart disease and analysis of immune infiltration
Jiaming LAI ; Yuling SONG ; Zixi CHEN ; Jinghuan WEI ; Hao CAI ; Guoquan LI
Chinese Journal of Tissue Engineering Research 2026;30(6):1450-1463
BACKGROUND:Radiotherapy significantly improves survival rates in patients with various malignant tumors.However,with prolonged post-treatment survival,many patients face the risk of radiation-related cardiac toxicity.This is especially true after chest radiotherapy,where the risk of radiation-induced heart disease significantly increases,becoming one of the most severe complications affecting prognosis survival.OBJECTIVE:To identify diagnostic markers of endothelial cellular senescence in radiation-induced heart disease through systematic transcriptomic analysis.METHODS:Firstly,genes associated with cellular senescence were screened from the CellAge database and intersected with the transcriptomic training dataset of a mouse model of radiation-induced heart disease to identify differentially expressed senescence-related genes.Secondly,weighted gene co-expression network analysis and machine learning were used to identify key hub genes that play critical roles in radiation-induced heart disease.The expression of these genes was validated using a dataset of radiation-induced endothelial injury.Additionally,the quanTlseq method was employed to assess the immune infiltration status related to radiation-induced heart disease.The expression levels of key genes and their association with survival in esophageal squamous cell carcinoma patients receiving chest radiotherapy were explored through the analysis of The Cancer Genome Atlas database.RESULTS AND CONCLUSION:(1)Systematic transcriptomic analysis identified CCND1 as the core gene of endothelial cellular senescence in radiation-induced heart disease,and this finding was validated in the mouse model of radiation-induced heart disease.(2)The diagnostic model constructed from these data indicated that CCND1 had high specificity and sensitivity for diagnosing radiation-induced heart disease.(3)Immune infiltration analysis revealed significant immune response dysregulation in the mouse model of radiation-induced heart disease,and CCND1 was closely related to various immune cells.(4)Kaplan-Meier survival analysis showed that CCND1 was associated with poorer disease-specific survival in esophageal squamous cell carcinoma patients receiving chest radiotherapy.This study systematically uncovers,for the first time,the pivotal role of CCND1 in endothelial cell senescence associated with radiation-induced heart disease.CCND1,a gene integral to cell cycle regulation,can induce cellular senescence when abnormally expressed.Furthermore,the findings highlight its potential as an early diagnostic marker.
2.Screening of diagnostic markers for endothelial cell Senescence in mice with radiation-induced heart disease and analysis of immune infiltration
Jiaming LAI ; Yuling SONG ; Zixi CHEN ; Jinghuan WEI ; Hao CAI ; Guoquan LI
Chinese Journal of Tissue Engineering Research 2026;30(6):1450-1463
BACKGROUND:Radiotherapy significantly improves survival rates in patients with various malignant tumors.However,with prolonged post-treatment survival,many patients face the risk of radiation-related cardiac toxicity.This is especially true after chest radiotherapy,where the risk of radiation-induced heart disease significantly increases,becoming one of the most severe complications affecting prognosis survival.OBJECTIVE:To identify diagnostic markers of endothelial cellular senescence in radiation-induced heart disease through systematic transcriptomic analysis.METHODS:Firstly,genes associated with cellular senescence were screened from the CellAge database and intersected with the transcriptomic training dataset of a mouse model of radiation-induced heart disease to identify differentially expressed senescence-related genes.Secondly,weighted gene co-expression network analysis and machine learning were used to identify key hub genes that play critical roles in radiation-induced heart disease.The expression of these genes was validated using a dataset of radiation-induced endothelial injury.Additionally,the quanTlseq method was employed to assess the immune infiltration status related to radiation-induced heart disease.The expression levels of key genes and their association with survival in esophageal squamous cell carcinoma patients receiving chest radiotherapy were explored through the analysis of The Cancer Genome Atlas database.RESULTS AND CONCLUSION:(1)Systematic transcriptomic analysis identified CCND1 as the core gene of endothelial cellular senescence in radiation-induced heart disease,and this finding was validated in the mouse model of radiation-induced heart disease.(2)The diagnostic model constructed from these data indicated that CCND1 had high specificity and sensitivity for diagnosing radiation-induced heart disease.(3)Immune infiltration analysis revealed significant immune response dysregulation in the mouse model of radiation-induced heart disease,and CCND1 was closely related to various immune cells.(4)Kaplan-Meier survival analysis showed that CCND1 was associated with poorer disease-specific survival in esophageal squamous cell carcinoma patients receiving chest radiotherapy.This study systematically uncovers,for the first time,the pivotal role of CCND1 in endothelial cell senescence associated with radiation-induced heart disease.CCND1,a gene integral to cell cycle regulation,can induce cellular senescence when abnormally expressed.Furthermore,the findings highlight its potential as an early diagnostic marker.
3.Quantitative analysis and distribution comparison of salidroside and its liposomes in mouse serum,bronchoalveolar lavage fluid,and lung tissue
Rong WANG ; Ni ZHAO ; Guoquan LI ; Yafeng WANG ; Shen’ao LI ; Jiaming LAI ; Hao CAI
China Pharmacy 2026;37(15):1998-2002
OBJECTIVE Establish a quantitative analysis method for salidroside (Sal) in mouse serum, bronchoalveolar lavage fluid (BALF), and lung tissue, and compare the distribution differences of Sal and its liposomes. METHODS Using high-performance liquid chromatography(HPLC), Welch Xtimate C18 was used as the chromatographic column, with methanol-formic acid aqueous solution (formic acid volume fraction: 0.1% for serum and BALF detection, 0.2% for lung tissue detection) as the mobile phase, flow rate of 1.0 mL/min, detection wavelength of 275 nm, column temperature of 30 ℃, and injection volume of 10 μL. Serum, BALF, and lung tissue homogenate samples were precipitated with methanol for protein analysis. Twelve mice were randomly divided into Sal group and Sal liposome group, and the concentrations of Sal in serum, BALF, and lung tissue were detected after intragastric administration corresponding liquid medicine at a dose of 300 mg/kg (calculated as Sal) for 0.5 h. RESULTS The linear ranges of Sal in serum, BALF, and lung tissue were 1.56-200.00 μg/mL, 1.56-100.00 μg/mL, and 6.24-400.00 μg/g, respectively (all r=0.999 9), with intra-day RSD of 1.35%-3.87%, 1.10%-2.75%, and 1.90%-3.86%, respectively; the inter-day RSD of 3.38%-5.11%, 2.22%- 4.36%, and 2.41%-4.73%, respectively. The relative accuracies were 97.95%-101.61%, 98.29%-101.82%, and 97.41%- 106.94%, respectively. The stability RSDs were all less than 6%. Compared with the Sal group, the Sal liposome group significantly increased the concentration of Sal in BALF of mice (P<0.05), and significantly decreased the concentration of Sal in serum and lung tissue (P<0.05). CONCLUSIONS The HPLC method established in this study is suitable for quantitative analysis of Sal in mouse serum, BALF, and lung tissue. Sal liposomes have a tendency to distribute towards the alveolar cavity during early administration.
4.Pharmacokinetic study of 3 blood-absorbed components of Xiangshao sanjie oral liquid in rats with hyperplasia of mammary gland
Yu ZHANG ; Jiaming LI ; Dan PENG ; Ruoqiu FU ; Yue MING ; Zhengbi LIU ; Jingjing WANG ; Shiqi CHENG ; Hongjun XIE ; Yao LIU
China Pharmacy 2025;36(6):680-685
OBJECTIVE To explore the pharmacokinetic characteristics of 3 blood-absorbed components of Xiangshao sanjie oral liquid in rats with hyperplasia of mammary gland (HMG). METHODS Female SD rats were divided into control group and HMG group according to body weight, with 6 rats in each group. The HMG group was given estrogen+progesterone to construct HMG model. After modeling, two groups were given 1.485 g/kg of Xiangshao sanjie oral liquid (calculated by crude drug) intragastrically, once a day, for 7 consecutive days. Blood samples were collected before the first administration (0 h), and at 5, 15, 30 minutes and 1, 2, 4, 8, 12, 24 hours after the last administration, respectively. Using chlorzoxazone as the internal standard, the plasma concentrations of ferulic acid, paeoniflorin and rosmarinic acid in rats were detected by UPLC-Q/TOF-MS. The pharmacokinetic parameters [area under the drug time curve (AUC0-24 h, AUC0-∞), mean residence time (MRT0-∞), half-life (t1/2), peak time (tmax), peak concentration (cmax)] were calculated by the non-atrioventricular model using Phoenix WinNonlin 8.1 software. RESULTS Compared with the control group, the AUC0-24 h, AUC0-∞ and cmax of ferulic acid in the HMG group were significantly increased (P<0.05); the AUC0-24 h, AUC0-∞ , MRT0-∞ , t1/2 and cmax of paeoniflorin increased, but there was no significant difference between 2 groups (P>0.05); the AUC0-24 h and MRT0-∞ of rosmarinic acid were significantly increased or prolonged (P<0.05). C ONCLUSIONS In HMG model rats, the exposure of ferulic acid, paeoniflorin and rosmarinic acid in Xiangshao sanjie oral liquid all increase, and the retention time of rosmarinic acid is significantly prolonged.
5.Effects of Toxoplasma gondii type I/II rhoptry protein 16 on the polarization and inflammatory response of mouse alveolar macrophages
Jiaming LI ; Tiantian DANG ; Zhijun ZHAO
Chinese Journal of Schistosomiasis Control 2025;37(2):127-135
Objective To investigate the effects of Toxoplasma gondii type Iand IIrhoptry protein 16 (ROP16) on the polarization and inflammatory response of mouse alveolar macrophages, so as to provide the scientific evidence for unveiling the immunoregulatory mechanisms following T. gondii infection in host cells and the clinical diagnosis and treatment of pulmonary toxoplasmosis. MethodsMouse alveolar macrophages served as blank controls, and mouse alveolar macrophages transfected with the empty lentiviral expression vector served as negative controls, and mouse alveolar macrophages transfected with lentiviral vectors overexpressing T. gondii type I and II ROP16 served as the type I and II ROP16 overexpression groups. Following puromycin selection, stably transfected cells that overexpressed type Iand IIROP16 were generated, observed for green fluorescence expression under a fluorescence microscope and verified using PCR, Western blotting and real-time quantitative reverse transcription PCR (RT-qPCR) assays. The expression of ROP16, inducible nitric oxide synthase (iNOS), arginase (Arg)-1, mannose receptor (CD206), cluster of differentiation 86 (CD86), NOD-like receptor thermal protein domain associated protein 3 (NLRP3), caspase-1, apoptosis-associated speck-like protein containing a CARD (ASC), and interleukin (IL)-1β proteins was determined in mouse alveolar macrophages using Western blotting assay, and the mRNA levels of ROP16, iNOS, IL-1β, IL-4, IL-12, IL-18, Arg-1, IL-10, IL-6, tumor necrosis factor (TNF)-α and transforming growth factor (TGF)-β were detected in mouse alveolar macrophages using RT-qPCR assay. Results Fluorescence microscopy showed 90% of mouse alveolar macrophages producing green fluorescent signals in the type Iand II ROP16 overexpression groups and the negative control group. The relative ROP16 protein expression was 1.000 ± 0.000, 1.003 ± 0.020, 1.349 ± 0.055, and 1.376 ± 0.080 in mouse alveolar macrophages in the blank control group, negative control group, and type Iand IIROP16 overexpression groups (F = 35.30, P < 0.01), and the relative ROP16 mRNA expression was 1.007 ± 0.172, 2.030 ± 0.356, 1 409.579 ± 75.960, and 1 413.581 ± 27.712 in the blank control group, negative control group, and type Iand II ROP16 overexpression groups (F = 811.00, P < 0.01). The ROP16 expression was significantly higher in the type Iand IIROP16 overexpression groups than in the blank control group at both protein and mRNA levels (all P value < 0.01). Western blotting assay detected significant differences among the four groups in terms of iNOS, Arg-1, CD86, CD206, NLRP3, caspase-1, ASC, and IL-1β protein expression (F = 124.70, 82.40, 79.82, 919.40, 84.74, 39.85, 2 354.00 and 65.96, all P values < 0.05), and the expression of Arg-1, CD206, NLRP3, caspase-1, ASC, and IL-1β proteins was significantly higher in the type I ROP16 overexpression group than in the blank control group (all P values < 0.001), while the expression of iNOS, CD86, NLRP3, caspase-1, ASC, and IL-1β proteins was significantly higher in the type II ROP16 overexpression group than in the blank control group (all P values < 0.01). RT-qPCR assay detected significant differences among the four groups in terms of iNOS, IL-1β, IL-4, IL-12, IL-18, Arg-1, IL-10, IL-6, TNF-α, and TGF-β mRNA expression (F = 407.00, 1 528.00, 833.10, 267.90, 989.80, 161.80, 461.10, 5 529.00, 849.60 and 8 836.00, all P values < 0.05), and the Arg-1, IL-4, IL-10, and TGF-β mRNA expression was significantly higher in the type I ROP16 overexpression group than in the blank control group (all P values < 0.001), while the iNOS, IL-1β, IL-12, IL-18, IL-6, and TNF-α mRNA expression was significantly higher in the type II ROP16 overexpression group than in the blank control group (all P values < 0.001). Conclusions T. gondii type IROP16 may induce M2-dominant phenotypes of mouse alveolar macrophages, and type II ROP16 may induce M1-dominant phenotypes of mouse alveolar macrophages. Both T. gondii type I and II ROP16 may activate NLRP3, and mediate the activation of ASC, caspase-1 and IL-1β to promote inflammatory responses.
6.Application and mechanisms of targeting BRD4 in osteosarcoma.
Ding CHEN ; Jiaming TIAN ; Yihe DONG ; Zi LI ; Jun HUANG
Journal of Central South University(Medical Sciences) 2025;50(3):416-429
OBJECTIVES:
Metastasis is the primary cause of death in osteosarcoma, and current clinical treatments remain limited. BRD4, a key epigenetic regulator, has shown therapeutic promise in various cancers through its inhibition. However, the mechanistic role of BRD4 in osteosarcoma remains poorly understood. This study aims to elucidate the molecular mechanisms by which BRD4 regulate osteosarcoma progression and to explore novel therapeutic strategies.
METHODS:
Immunofluorescence was used to assess BRD4 expression levels in a tissue microarray containing 80 osteosarcoma samples from different patients. The Gene Expression Omnibus (GEO) dataset (GSE42352, containing survival data from 88 osteosarcoma patients) was downloaded to perform Kaplan-Meier survival analysis based on BRD4 gene expression levels. In vivo, an orthotopic intramedullary osteosarcoma model was established using HOS cells in C57 mice, followed by treatment with varying doses of the BRD4 inhibitor (+)-JQ1. Micro-CT, 3D reconstruction of bone tissue, and HE staining were employed to evaluate pathological changes in bone and intestinal lymph nodes. In vitro, cell viability was measured using the methyl thiazolyl tetrazolium (MTT) assay, while colony formation and Transwell assays assessed proliferative and invasive capacities. Chromatin-bound BRD4 was analyzed via co-immunoprecipitation combined with mass spectrometry (Co-IP/MS), and O-GlcNAc glycosylation sites and glycan chains of BRD4 were identified using Co-IP with Nano-LC MS/MS. Real-time PCR and Western blotting were used to analyze the relative mRNA and protein expression levels of target genes, respectively.
RESULTS:
BRD4 was positively expressed in 61.25% (49/80) of osteosarcoma tissues. Patients with high BRD4 expression exhibited significantly shorter survival times (P<0.05). In the orthotopic mouse model, intervention with (+)-JQ1, a potent and commonly used BETi, significantly inhibited tumor growth in vivo and reduced bone destruction (P<0.05). (+)-JQ1 treatment significantly suppressed the proliferation (P<0.001), invasion (P<0.001), and migration (P<0.05) of HOS cells. In osteosarcoma cells, BRD4 exhibited O-GlcNAc modifications at both N- and C- C-termini, particularly at Thr73, which is essential for protein stability. This modification also contributed to the activation of the EGFR tyrosine kinase inhibitor resistance pathway (KEGG Pathway: hsa01521). (+)-JQ1 treatment displaced BRD4 from enhancers and downregulated the transcription of pathway-related genes, such as EGFR and PDGFC, thereby suppressing the malignant behavior of osteosarcoma cells.
CONCLUSIONS
BRD4 promotes osteosarcoma progression via O-GlcNAc modification at Thr73 and plays a crucial role in tumor growth and metastasis.
Osteosarcoma/drug therapy*
;
Humans
;
Transcription Factors/metabolism*
;
Animals
;
Cell Cycle Proteins
;
Mice
;
Bone Neoplasms/drug therapy*
;
Azepines/pharmacology*
;
Cell Line, Tumor
;
Cell Proliferation/drug effects*
;
Triazoles/pharmacology*
;
Mice, Inbred C57BL
;
Nuclear Proteins/metabolism*
;
Gene Expression Regulation, Neoplastic
;
Male
;
Bromodomain Containing Proteins
7.Unmet needs of patients with intravascular large B-cell lymphoma: three case reports and a literature review.
Xian LI ; Ru LUO ; Jiaming XU ; Xueli JIN ; Weiqin WANG ; Xibin XIAO ; Wenbin QIAN
Journal of Zhejiang University. Science. B 2025;26(5):493-502
Intravascular large B-cell lymphoma (IVLBCL), a rare subtype of non-Hodgkin lymphoma, is classified as an independent subtype of extranodal diffuse large B-cell lymphoma (DLBCL) in the 2008 World Health Organization (WHO) Classification (Turner et al., 2010). The 5th edition of the World Health Organization (WHO 2022) classification of hematolymphoid tumors retains this subtype (Alaggio et al., 2022). IVLBCL, which is characterized by neoplastic lymphocyte proliferation within the lumen of small blood vessels, tends to invade organs, such as the nervous system, skin, bone marrow (BM), and lung (D'Angelo et al., 2019; Satoh et al., 2019; Vásquez et al., 2019; Fukami et al., 2020).
Humans
;
Antineoplastic Combined Chemotherapy Protocols/therapeutic use*
;
Lymphoma, Large B-Cell, Diffuse/drug therapy*
;
Vascular Neoplasms/therapy*
8.The Effects of Tai Chi Training on Bone Density,Bone Turnover Markers,and Heart Rate Variability in High-Risk Osteoporosis Population
Jiaming LIN ; Chao LI ; Wei ZHAO ; Jun ZHOU ; Xiaoying CHEN ; Xiangyu XI ; Haijun HE ; Baohong MI ; Yuefeng CHEN ; Weiheng CHEN
Journal of Traditional Chinese Medicine 2025;66(15):1566-1571
ObjectiveTo explore the effects of the Tai Chi training on bone density, bone turnover markers, and heart rate variability for people with high-risk osteoporosis, and to provide evidence for the prevention of osteoporosis at early stage. MethodsSixty-six cases of people with high risk of osteoporosis were included, and they were divided into 33 cases each in the intervention group and the control group using the random number table method. The control group received osteoporosis health education three times a week, and the intervention group received Tai Chi training under the guidance of a trainer three times a week for 40 mins each time on the basis of the control group, and both groups were intervened for 12 weeks. Dual-energy X-ray absorptiometry was used to measure the bone density of L1~L4 vertebrae, bilateral femoral necks and bilateral total hips in the two groups before and after the intervention; enzyme-linked immunosorbent assay was used to determine bone turnover markers before and after the intervention, including pro-collagen type Ⅰ pro-amino-terminal prepropyl peptide (P1NP) and β-collagen type Ⅰ cross-linking carboxy-terminal peptide (β-CTX). Seven cases with good compliance in the intervention group were selected. After wearing the heart rate sensor, they successively performed Tai Chi training and walking activities recommended by the guideline for 20 mins each, and the heart rate variability (HRV) during exercise was collected, including time-domain indexes such as standard deviation of normal sinus intervals (SDNN), root-mean-square of the difference between adjacent RR intervals (RMSSD), frequency-domain metrics such as low-frequency power (LF), high-frequency power (HF), and low-frequency/high-frequency power ratio (LF/HF), as well as nonlinear metrics such as approximate entropy (ApEn), sample entropy (SampEn). ResultsFinally, 63 cases were included in the outcome analysis, including 30 cases in the intervention group and 33 cases in the control group. After the intervention, the differences of L1~L4 vertebrae, bone density of bilateral femoral neck and bilateral total hip in the intervention group were not statistically significant when compared with those before intervention (P>0.05), while the bone density of all parts of the control group decreased significantly compared with that before intervention (P<0.05), and the difference in the bone density of the L1~L4 vertebrae, bilateral femoral neck, and the right total hip before and after the intervention of the intervention group was smaller than that of the control group (P<0.05). The differences in P1NP and β-CTX between groups before and after intervention was not statistically significant (P>0.05). Compared with walking exercise, LF decreased, HF increased and LF/HF decreased during Tai Chi exercise (P<0.05); the time domain indexes and non-linear indexes between groups had no statistically significant difference (P>0.05). ConclusionTai Chi exercise can maintain lumbar, hip, and femoral bone density and improve sympathetic/parasympathetic balance in people at high risk for osteoporosis, but cannot significantly improve bone turnover markers.
9.CTO inhibits the in situ growth of glioblastoma in mice and regulates the metabolism and inflammatory phenotype of glioma-associated microglia
Yunfan LI ; Jiaming ZOU ; Yucheng WANG ; Rui JU ; Lei GUO
Basic & Clinical Medicine 2025;45(4):478-485
Objective To investigate the effects and regulatory mechanisms of carboxyamidotriazole orotate(CTO)on the metabolism and inflammatory mediators of glioma-associated microglia(GAM).Methods Tumor volume was regularly monitored by in vivo imaging,and histological examination was performed to detect the extent of tumor in-filtration;non-targeted metabolomics analysis was used to detect the level of tricarboxylic acid cycle metabolites in cells;seahorse cell energy measurement method was used to detect the oxygen consumption rate(OCR)and extra-cellular acidification rate(ECAR)of cells;immunofluorescence was used to detect the degree of hypoxia in cells;quantitative PCR was used to detect the mRNA level of pro-cancer mediators M1/M2 in cells;Western blot was used to detect the protein level of hypoxia-inducible factor-1α(HIF-1α)and programmed death receptor-ligand 1(PD-L1).Results CTO inhibited the tumor progression in mice,and down-regulated the oxidative phosphorylation level and improved cell hypoxia in vitro(P<0.01).It also downregulated the expression of pro-oncogenic mediators iNos,Arg-1,Il-10,and Irf4 in GAM(P<0.01).When combined with lactate dehydrogenase inhibitor stiripentol(STP),CTO-induced enhancement of glycolysis and upregulation of PD-L1 expression in GAM was attenuated(P<0.01),and the expressions of Arg-1 and Il-10 was further downregulated(P<0.000 1).Conclusions CTO down-regulates the expression of several oncogenic genes in GAM and inhibits tumor progression in mice.Combined use of lactate dehydrogenase inhibitors can weaken the adverse effect of CTO and reduce the transcriptional level of GAM oncogenic mediators.
10.Prediction of ischemic stroke incidence based on CNN-LSTM-Attention model
Jiaming Liu ; Xiao Zhou ; Fuyin Wang ; Xiao Sun ; Xiaoshuang Xia ; Xin Li
Acta Universitatis Medicinalis Anhui 2025;60(12):2353-2362
Objective:
To construct a deep learning model based on convolutional neural network(CNN)-long short term memory network(LSTM)-Attention to explore the correlation between meteorological and clinical factors and the incidence of ischemic stroke.
Methods:
A fusion model CNN-LSTM-Attention based on CNN, LSTM, and Attention was constructed by incorporating clinical data and meteorological data of ischemic stroke inpatients. The predictive performance of the model was evaluated by maximum prediction error and root mean square error(RMSE). The impact of different lag days on prediction performance was investigated by selecting lag periods ranging from 1 to 7 days.
Results:
In both short-term and long-term predictions, the CNN-LSTM-Attention fusion model(short-term: 1.5 and 0.6; long-term: 8.3 and 2.5) showed superior maximum prediction bias and RMSE compared to the LSTM model(short-term: 2.8 and 1.2; long-term: 19.5 and 5.5) and the CNN-LSTM model(short-term: 2.0 and 0.8; long-term: 11.2 and 3.3). After incorporating lag days, the maximum prediction deviation and RMSE for lags of 3 days(short-term: 0.7 and 0.4; long-term: 5.5 and 1.9) and 5 days(short-term: 0.8 and 0.3; long-term: 6.5 and 2.0) in both short-term and long-term forecasts were smaller than lags of 0 days(short-term: 1.5 and 0.6; long-term: 8.3 and 2.5). The maximum prediction deviation and RMSE in the short-term forecast were greater than lag 0 days for both lag 1 days(1.5 and 0.8) and lag 7 days(1.9 and 0.9). In the long-term forecast, the two indicators for lag 1 days(6.8 and 2.4) were lower than those for lag 0 days but higher than those for lag 3 days and 5 days. The maximum prediction deviation for lag 7 days(7.5) was lower than that for lag 0 days, but the RMSE(2.7) is higher than that for lag 0 days.
Conclusion
The established CNN-LSTM-Attention model demonstrates significant predictive value for the onset of ischemic stroke and can provide reference for the rational allocation of medical resources.


Result Analysis
Print
Save
E-mail