1.Clinical Efficacy and Mechanism of Bupi Qingfei Prescription in Treating Stable Bronchiectasis
Zi YANG ; Guangsen LI ; Bing WANG ; Bo XU ; Jianxin WANG ; Sheng CAO ; Xinyan CHEN ; Xia SHI ; Qing MIAO
Chinese Journal of Experimental Traditional Medical Formulae 2026;32(2):162-169
ObjectiveTo explore the clinical efficacy and mechanism of Bupi Qingfei prescription (BPQF) in treating stable bronchiectasis in the patients with syndromes of lung-spleen Qi deficiency and phlegm-heat accumulation in the lungs. MethodsA randomized, double-blind, placebo-controlled trial was conducted. Patients were randomized into BPQF and placebo control (PC) groups. On the basis of conventional Western medicine treatment, the BPQF granules and placebo were respectively administered at 10 g each time, twice a day, for a course of 24 weeks. The TCM symptom scores, Quality of Life Questionnaire for Bronchiectasis (QOL-B) scores, lung function indicators, T lymphocyte subsets, level of inflammatory factors in the sputum, level of neutrophil elastase (NE) in the sputum, and occurrence of adverse reactions were observed before and after treatment in the two groups. ResultsA total of 64 patients completed the study, encompassing 32 in the BPQF group and 32 in the PC group. After treatment, the BPQF group showed decreased TCM symptom scores (P<0.01), increased QOL-B scores (P<0.01), and declined levels of tumor necrosis factor (TNF)-α and NE (P<0.05, P<0.01). The PC group showed decreased TCM symptom (except spleen deficiency) scores (P<0.01), increased the QOL-B health cognition and respiratory symptom domain scores (P<0.05, P<0.01), and a declined TNF-α level (P<0.01). Moreover, the BPQF group had lower TCM symptom (except chest tightness) scores (P<0.05, P<0.01), higher QOL-B (except treatment burden) scores (P<0.05, P<0.01), and lower levels of interleukin-6 and TNF-α (P<0.05) than the PC group. Neither group showed serious adverse reactions during the treatment process. ConclusionBPQF can ameliorate the clinical symptoms of stable bronchiectasis patients who have lung-spleen Qi deficiency or phlegm-heat accumulation in the lungs by regulating the immune balance and inhibiting airway inflammatory responses.
2.Herbal Textual Research on Inulae Flos in Famous Classical Formulas
Caixia LIU ; Yue HAN ; Yanzhu MA ; Lei GAO ; Sheng WANG ; Yan YANG ; Wenchuan LUO ; Ling JIN ; Jing SHAO ; Zhijia CUI ; Zhilai ZHAN
Chinese Journal of Experimental Traditional Medical Formulae 2026;32(3):210-221
In this paper, by referring to ancient and modern literature, the textual research of Inulae Flos has been conducted to clarify the name, origin, production area, quality evaluation, harvesting, processing and others, so as to provide reference and basis for the development and utilization of famous classical formulas containing this herb. After textual research, it could be verified that the medicinal use of Inulae Flos was first recorded in Shennong Bencaojing of the Han dynasty. In successive dynasties, Xuanfuhua has been taken as the official name, and it also has other alternative names such as Jinfeicao, Daogeng and Jinqianhua. The period before the Song and Yuan dynasties, the main origin of Inulae Flos was the Asteraceae plant Inula japonica, and from the Ming and Qing dynasties to the present, I. japonica and I. britannica are the primary source. In addition to the dominant basal species, there are also regional species such as I. linariifolia, I. helianthus-aquatili, and I. hupehensis. The earliest recorded production areas in ancient times were Henan, Hubei and other places, and the literature records that it has been distributed throughout the country since modern times. The medicinal part is its flower, the harvesting and processing method recorded in the past dynasties is mainly harvested in the fifth and ninth lunar months, and dried in the sun, and the modern harvesting is mostly harvested in summer and autumn when the flowers bloom, in order to remove impurities, dry in the shade or dry in the sun. In addition, the roots, whole herbs and aerial parts are used as medicinal materials. In ancient times, there were no records about the quality of Inulae Flos, and in modern times, it is generally believed that the quality of complete flower structure, small receptacles, large blooms, yellow petals, long filaments, many fluffs, no fragments, and no branches is better. Ancient processing methods primarily involved cleaning, steaming, and sun-drying, supplemented by techniques such as boiling, roasting, burning, simmering, stir-frying, and honey-processing. Modern processing focuses mainly on cleaning the stems and leaves before use. Regarding the medicinal properties, ancient texts describe it as salty and sweet in taste, slightly warm in nature, and mildly toxic. Modern studies characterize it as bitter, pungent, and salty in taste, with a slightly warm nature. Its therapeutic effects remain consistent across eras, including descending Qi, resolving phlegm, promoting diuresis, and stopping vomiting. Based on the research results, it is recommended that when developing famous classical formulas containing Inulae Flos, either I. japonica or I. britannica should be used as the medicinal source. Processing methods should follow formula requirements, where no processing instructions are specified, the raw products may be used after cleaning.
3.Herbal Textual Research on Inulae Flos in Famous Classical Formulas
Caixia LIU ; Yue HAN ; Yanzhu MA ; Lei GAO ; Sheng WANG ; Yan YANG ; Wenchuan LUO ; Ling JIN ; Jing SHAO ; Zhijia CUI ; Zhilai ZHAN
Chinese Journal of Experimental Traditional Medical Formulae 2026;32(3):210-221
In this paper, by referring to ancient and modern literature, the textual research of Inulae Flos has been conducted to clarify the name, origin, production area, quality evaluation, harvesting, processing and others, so as to provide reference and basis for the development and utilization of famous classical formulas containing this herb. After textual research, it could be verified that the medicinal use of Inulae Flos was first recorded in Shennong Bencaojing of the Han dynasty. In successive dynasties, Xuanfuhua has been taken as the official name, and it also has other alternative names such as Jinfeicao, Daogeng and Jinqianhua. The period before the Song and Yuan dynasties, the main origin of Inulae Flos was the Asteraceae plant Inula japonica, and from the Ming and Qing dynasties to the present, I. japonica and I. britannica are the primary source. In addition to the dominant basal species, there are also regional species such as I. linariifolia, I. helianthus-aquatili, and I. hupehensis. The earliest recorded production areas in ancient times were Henan, Hubei and other places, and the literature records that it has been distributed throughout the country since modern times. The medicinal part is its flower, the harvesting and processing method recorded in the past dynasties is mainly harvested in the fifth and ninth lunar months, and dried in the sun, and the modern harvesting is mostly harvested in summer and autumn when the flowers bloom, in order to remove impurities, dry in the shade or dry in the sun. In addition, the roots, whole herbs and aerial parts are used as medicinal materials. In ancient times, there were no records about the quality of Inulae Flos, and in modern times, it is generally believed that the quality of complete flower structure, small receptacles, large blooms, yellow petals, long filaments, many fluffs, no fragments, and no branches is better. Ancient processing methods primarily involved cleaning, steaming, and sun-drying, supplemented by techniques such as boiling, roasting, burning, simmering, stir-frying, and honey-processing. Modern processing focuses mainly on cleaning the stems and leaves before use. Regarding the medicinal properties, ancient texts describe it as salty and sweet in taste, slightly warm in nature, and mildly toxic. Modern studies characterize it as bitter, pungent, and salty in taste, with a slightly warm nature. Its therapeutic effects remain consistent across eras, including descending Qi, resolving phlegm, promoting diuresis, and stopping vomiting. Based on the research results, it is recommended that when developing famous classical formulas containing Inulae Flos, either I. japonica or I. britannica should be used as the medicinal source. Processing methods should follow formula requirements, where no processing instructions are specified, the raw products may be used after cleaning.
4.Study on the new workflow of PIVAS based on intelligent auxiliary devices
Haiwen DING ; Sheng LIU ; Zhaolin CHEN ; Liqin TANG ; Tong TONG
China Pharmacy 2026;37(1):99-104
OBJECTIVE To build a new workflow of pharmacy intravenous admixture services (PIVAS), effectively connect intelligent equipment, and promote the intelligent development of PIVAS. METHODS Based on intelligent auxiliary equipment, PIVAS workflow was optimized, and a process-oriented model was established. This model integrated intelligent prescription review (automatic prescription review+manual intervention mode), intelligent labeling, intelligent allocation, intelligent sorting, and finished infusion quality inspection system. Furthermore, an assessment was conducted to examine unreasonable medical order rate of intelligent prescription review, the working efficiency and error rate of intelligent labeling machine and intelligent sorting machine, and the dispensing efficiency and accuracy of intelligent dispensing robot. RESULTS Under the intelligent prescription review mode, the rate of unreasonable medical orders decreased from 0.157% to 0.050% (P<0.05); automatic labeling efficiency reached 21.7 sheets/min, surpassing the manual labeling efficiency of 13.8 sheets/min (P<0.05), and the daily labeling error rate decreased from 6.1‰ to 2.5‰ (P<0.05). Simultaneously operating two dispensing robots significantly improved the efficiency of batch dispensing and reduced the residual amount of liquid medicine (P<0.05); additionally, a quality testing system for finished infusion was established, involving appearance, Tyndall effect, insoluble particles, turbidity, absorbance, pH and osmotic pressure, to ensure the quality of finished infusion and reduce the risk of infusion. CONCLUSIONS The new process of PIVAS connected with intelligent devices in our hospital can improve work efficiency, reduce dispensing errors, ensure the quality of finished infusion, and improve the level of pharmaceutical care.
5.Expert consensus on neoadjuvant PD-1 inhibitors for locally advanced oral squamous cell carcinoma (2026)
LI Jinsong ; LIAO Guiqing ; LI Longjiang ; ZHANG Chenping ; SHANG Chenping ; ZHANG Jie ; ZHONG Laiping ; LIU Bing ; CHEN Gang ; WEI Jianhua ; JI Tong ; LI Chunjie ; LIN Lisong ; REN Guoxin ; LI Yi ; SHANG Wei ; HAN Bing ; JIANG Canhua ; ZHANG Sheng ; SONG Ming ; LIU Xuekui ; WANG Anxun ; LIU Shuguang ; CHEN Zhanhong ; WANG Youyuan ; LIN Zhaoyu ; LI Haigang ; DUAN Xiaohui ; YE Ling ; ZHENG Jun ; WANG Jun ; LV Xiaozhi ; ZHU Lijun ; CAO Haotian
Journal of Prevention and Treatment for Stomatological Diseases 2026;34(2):105-118
Oral squamous cell carcinoma (OSCC) is a common head and neck malignancy. Approximately 50% to 60% of patients with OSCC are diagnosed at a locally advanced stage (clinical staging III-IVa). Even with comprehensive and sequential treatment primarily based on surgery, the 5-year overall survival rate remains below 50%, and patients often suffer from postoperative functional impairments such as difficulties with speaking and swallowing. Programmed death receptor-1 (PD-1) inhibitors are increasingly used in the neoadjuvant treatment of locally advanced OSCC and have shown encouraging efficacy. However, clinical practice still faces key challenges, including the definition of indications, optimization of combination regimens, and standards for efficacy evaluation. Based on the latest research advances worldwide and the clinical experience of the expert group, this expert consensus systematically evaluates the application of PD-1 inhibitors in the neoadjuvant treatment of locally advanced OSCC, covering combination strategies, treatment cycles and surgical timing, efficacy assessment, use of biomarkers, management of special populations and immune related adverse events, principles for immunotherapy rechallenge, and function preservation strategies. After multiple rounds of panel discussion and through anonymous voting using the Delphi method, the following consensus statements have been formulated: 1) Neoadjuvant therapy with PD-1 inhibitors can be used preoperatively in patients with locally advanced OSCC. The preferred regimen is a PD-1 inhibitor combined with platinum based chemotherapy, administered for 2-3 cycles. 2) During the efficacy evaluation of neoadjuvant therapy, radiographic assessment should follow the dual criteria of Response Evaluation Criteria in Solid Tumors (RECIST) version 1.1 and immune RECIST (iRECIST). After surgery, systematic pathological evaluation of both the primary lesion and regional lymph nodes is required. For combination chemotherapy regimens, PD-L1 expression and combined positive score need not be used as mandatory inclusion or exclusion criteria. 3) For special populations such as the elderly (≥ 70 years), individuals with stable HIV viral load, and carriers of chronic HBV/HCV, PD-1 inhibitors may be used cautiously under the guidance of a multidisciplinary team (MDT), with close monitoring for adverse events. 4) For patients with a poor response to neoadjuvant therapy, continuation of the original treatment regimen is not recommended; the subsequent treatment plan should be adjusted promptly after MDT assessment. Organ transplant recipients and patients with active autoimmune diseases are not recommended to receive neoadjuvant PD-1 inhibitor therapy due to the high risk of immune related activation. Rechallenge is generally not advised for patients who have experienced high risk immune related adverse events such as immune mediated myocarditis, neurotoxicity, or pneumonitis. 5) For patients with a good pathological response, individualized de escalation surgery and function preservation strategies can be explored. This consensus aims to promote the standardized, safe, and precise application of neoadjuvant PD-1 inhibitor strategies in the management of locally advanced OSCC patients.
6.Gut microbiota and osteoporotic fractures
Wensheng ZHAO ; Xiaolin LI ; Changhua PENG ; Jia DENG ; Hao SHENG ; Hongwei CHEN ; Chaoju ZHANG ; Chuan HE
Chinese Journal of Tissue Engineering Research 2025;29(6):1296-1304
BACKGROUND:Osteoporotic fracture is the most serious complication of osteoporosis.Previous studies have demonstrated that gut microbiota has a regulatory effect on skeletal tissue and that gut microbiota has an important relationship with osteoporotic fracture,but the causal relationship between the two is unclear. OBJECTIVE:To explore the causal relationship between gut microbiota and osteoporotic fractures using Mendelian randomization method. METHODS:The genome-wide association study(GWAS)datasets of gut microbiota and osteoporotic fracture were obtained from the IEU Open GWAS database and the Finnish database R9,respectively.Using gut microbiota as the exposure factor and osteoporotic fracture as the outcome variable,Mendelian randomization analyses with random-effects inverse variance weighted,MR-Egger regression,weighted median,simple model,and weighted model methods were performed to assess whether there is a causal relationship between gut microbiota and osteoporotic fracture.Sensitivity analyses were performed to test the reliability and robustness of the results.Reverse Mendelian randomization analyses were performed to further validate the causal relationship identified in the forward Mendelian randomization analyses. RESULTS AND CONCLUSION:The results of this Mendelian randomization analysis indicated a causal relationship between gut microbiota and osteoporotic fracture.Elevated abundance of Actinomycetales[odds ratio(OR)=1.562,95%confidence interval(CI):1.027-2.375,P=0.037),Actinomycetaceae(OR=1.561,95%CI:1.027-2.374,P=0.037),Actinomyces(OR=1.544,95%CI:1.130-2.110,P=0.006),Butyricicoccus(OR=1.781,95%CI:1.194-2.657,P=0.005),Coprococcus 2(OR=1.550,95%CI:1.068-2.251,P=0.021),Family ⅩⅢ UCG-001(OR=1.473,95%CI:1.001-2.168,P=0.049),Methanobrevibacter(OR=1.274,95%CI:1.001-1.621,P=0.049),and Roseburia(OR=1.429,95%CI:1.015-2.013,P=0.041)would increase the risk of osteoporotic fractures in patients.Elevated abundance of Bacteroidia(OR=0.660,95%CI:0.455-0.959,P=0.029),Bacteroidales(OR=0.660,95%CI:0.455-0.959,P=0.029),Christensenellacea(OR=0.725,95%CI:0.529-0.995,P=0.047),Ruminococcaceae(OR=0.643,95%CI:0.443-0.933,P=0.020),Enterorhabdus(OR=0.558,95%CI:0.395-0.788,P=0.001),Eubacterium rectale group(OR=0.631,95%CI:0.435-0.916,P=0.016),Lachnospiraceae UCG008(OR=0.738,95%CI:0.546-0.998,P=0.048),and Ruminiclostridium 9(OR=0.492,95%CI:0.324-0.746,P=0.001)would reduce the risk of osteoporotic fractures in patients.We identified 16 gut microbiota associated with osteoporotic fracture by the Mendelian randomization method.That is,using gut microbiota as the exposure factor and osteoporotic fracture as the outcome variable,eight gut microbiota showed positive causal associations with osteoporotic fracture and another eight gut microbiota showed negative causal associations with osteoporotic fracture.The results of this study not only identify new biomarkers for the early prediction of osteoporotic fracture and potential therapeutic targets in clinical practice,but also provide an experimental basis and theoretical basis for the study of improving the occurrence and prognosis of osteoporotic fracture through gut microbiota in bone tissue engineering.
7.Cervical lordosis ratio can be used as a decision-making indicator for selection of posterior surgical approach for multi-level cervical spondylotic myelopathy
Jiahang MIAO ; Sheng MA ; Qupeng LI ; Huilin YU ; Tianyu HU ; Xiao GAO ; Hu FENG
Chinese Journal of Tissue Engineering Research 2025;29(9):1796-1802
BACKGROUND:At present,research has only shown that the cervical lordosis ratio can be an important factor in predicting the loss of lordosis curvature after laminoplasty,and no one has studied whether the cervical lordosis ratio,a dynamic level indicator,can be one of the decision-making factors for the selection of posterior cervical surgical procedures. OBJECTIVE:To investigate whether the cervical lordosis ratio,an index of cervical hyperextension and hyperflexion,can be used as a selective index for laminoplasty and laminectomy fusion. METHODS:A retrospective review of 141 patients who had undergone posterior cervical surgery more than one year of follow-up due to multi-level cervical spondylotic myelopathy from December 2015 to March 2020 was performed.Among them,63 patients received laminectomy and fusion(laminectomy and fusion group)and 78 patients received laminoplasty(laminoplasty group).The demographic statistics(gender,age,body mass index,follow-up time),imaging indexes such as C2-7 Cobb angle,C2-7 range of motion,flexion Cobb angle,extension Cobb angle,flexion range of motion and extension range of motion,clinical effect indexes such as Japanese Orthopaedic Association score and visual analog scale score were compared between the two groups.The evaluation index of cervical lordosis alignment change was C2-7 Cobb angle difference before and after operation(ΔCL).Cervical lordosis ratio was equal to 100%×flexion range of motion/C2-7 range of motion.Receiver operating characteristic curve analysis was used to determine the role of cervical lordosis ratio in predicting postoperative severe cervical lordosis loss(ΔCL≤-10°).According to the critical value of cervical lordosis ratio(68.5%),all patients were divided into low cervical lordosis ratio group and high cervical lordosis ratio group.In these two ratio groups,the cervical lordosis alignment index and clinical effect index between the two operation groups were discussed again. RESULTS AND CONCLUSION:(1)Cervical lordosis alignment decreased after laminectomy and fusion and laminoplasty(P=0.039,P=0.002),and cervical lordosis alignment change in laminoplasty group(ΔCL)was greater than that of laminectomy and fusion group,and the difference between the two groups was statistically significant.(2)Based on receiver operating characteristic curve analysis,cervical lordosis ratio in predicting severe cervical lordosis alignment change(ΔCL≤-10°)had good identification ability(area under the curve=0.792).(3)In low cervical lordosis ratio group,there was no significant difference in cervical lordosis alignment change(ΔCL)between laminectomy and fusion group and laminoplasty group(P=0.141).(4)In high cervical lordosis ratio group,the ΔCL of laminoplasty group was greater than that in laminectomy and fusion group(P=0.001),which had a higher probability of postoperative severe cervical lordosis alignment change(ΔCL≤-10°)(43%,29%).(5)It is indicated that cervical lordosis ratio can be used as a decision-making index for the choice of posterior surgery for multi-level cervical spondylotic myelopathy.Laminoplasty can be considered in the low cervical lordosis ratio group,while laminectomy and fusion can be considered in the high cervical lordosis ratio group.
8.Causal relationship between modifiable factors and joint sports injuries
Tingting DONG ; Tianxin CHEN ; Yan LI ; Sheng ZHANG ; Lei ZHANG
Chinese Journal of Tissue Engineering Research 2025;29(9):1953-1962
BACKGROUND:The causal relationship between modifiable factors such as lifestyle,metabolic characteristics,and nutritional intake and joint sports injuries has been increasingly recognized in clinical studies.However,the exact causal relationship between these modifiable factors and joint sports injuries remains unclear. OBJECTIVE:To investigate the causal relationship between modifiable factors and joint sports injuries using Mendelian randomization to provide a basis for sports injury prevention. METHODS:The GWAS dataset of intervening factors and joint sports injuries was obtained from publicly available data.The causal relationships between lifestyle,metabolic characteristics,nutritional intake,and joint sports injuries were explored using the inverse variance weighting method,the MR-Egger method,and the weighted median method.For sensitivity analyses,Cochran's Q test,MR-Egger regression,leave-one-out method,and MR-PRESSO were used to verify the stability and reliability of the results. RESULTS AND CONCLUSION:(1)In terms of lifestyle,coffee(OR=0.29,95%CI:0.10-0.79,P=0.016),and tea consumption(OR=0.41,95%CI=0.19-0.85,P=0.017)were associated with a decreased risk of ankle and foot joint sports injuries,and coffee consumption(OR=3.31,95%CI=1.02-10.73,P=0.046)was potentially causally associated with an increased risk of shoulder joint sports injuries;and never smoking(OR=0.78,95%CI=0.70-0.87,P=1.49×10-5)was significantly causally associated with a decreased risk of ankle and foot joint sports injuries.(2)In terms of metabolic characteristics,calcium levels(OR=0.88,95%CI=0.79-0.98,P=0.017)were potentially causally associated with a decreased risk of wrist and hand joint sports injuries.(3)In terms of nutritional intake,vitamin A intake(OR=1.08,95%CI:1.02-1.13,P=0.007)was potentially causally associated with increased risk of knee joint sports injury.(4)For the sensitivity analysis,Cochran's Q test showed the existence of heterogeneity(P<0.05),so the random effect model was used for the analysis.MR-Egger regression and MR-PRESSO test did not find evidence of pleiotropy(P>0.05),and the leave-one-out method showed that the results were stable after eliminating single nucleotide polymorphisms one by one.(5)This study preliminarily reveals the effects of modifiable factors,such as lifestyle,metabolic characteristics,and nutritional intake,on the risk of joint sports injuries.It provides valuable research evidence and guidance for the prevention of joint sports injuries.
9.Influencing factors and construction of a nomogram predictive model for postoperative anastomotic leak in patients with carcinoma of the esophagus and gastroesophageal junction
Hao PENG ; Siqi SHENG ; Jing CHEN ; Maitiasen MAIRHABA ; Haizhu SONG ; Jun YI
Chinese Journal of Clinical Thoracic and Cardiovascular Surgery 2025;32(02):208-215
Objective To analyze the influencing factors for postoperative anastomotic leak (AL) in carcinoma of the esophagus and gastroesophageal junction and construct a nomogram predictive model. Methods The patients who underwent radical esophagectomy at Jinling Hospital Affiliated to Nanjing University School of Medicine from January 2018 to June 2020 were included in this study. Relevant variables were screened using univariate and multivariate logistic regression analyses. A nomogram was then developed to predict the risk factors associated with postoperative AL. The predictive performance of the nomogram was validated using the receiver operating characteristic (ROC) curve. Results A total of 468 patients with carcinoma of the esophagus and gastroesophageal junction were included in the study, comprising 354 males and 114 females, with a mean age of (62.8±7.2) years. The tumors were predominantly located in the middle or lower esophagus, and 51 (10.90%) patients experienced postoperative AL. Univariate logistic regression analysis indicated that age, body mass index (BMI), tumor location, preoperative albumin levels, diabetes mellitus, anastomosis technique, anastomosis site, and C-reactive protein (CRP) levels were potentially associated with AL (P<0.05). Multivariate logistic regression analysis identified age, BMI, tumor location, diabetes mellitus, anastomosis technique, and CRP levels as independent risk factors for AL (P<0.05). A nomogram was developed based on the findings from the multivariate logistic regression analysis. The area under the receiver operating characteristic (ROC) curve was 0.803, indicating a strong concordance between the actual observations and the predicted outcomes. Furthermore, decision curve analysis demonstrated that the newly established nomogram holds significant value for clinical decision-making. Conclusion The predictive model for postoperative AL in patients with carcinoma of the esophagus and gastroesophageal junction demonstrates strong predictive validity and is essential for guiding clinical monitoring, early detection, and preventive strategies.
10.Application of fractal dimension CONVLSTM model in predicting the number of influenza cases in Hefei City
Sheng ZHANG ; Junjun MAO ; Weiling CHENG
Journal of Public Health and Preventive Medicine 2025;36(1):8-12
Objective To develop a multivariate modeling and prediction approach using the data of influenza incidence, meteorological factors and PM2.5 variables in Hefei City, and to provide new insights into multivariate modeling and prediction methods. Methods PM2.5 data were transformed into fractal dimension data and, along with meteorological data, were incorporated into a ConvLSTM model. The performance of this model was compared with traditional ARIMAX and multivariate LSTM models. Results The ARIMAX model's testing set Mean Absolute Error (MAE) was 95.75, Root Mean Square Error (RMSE) was 176.72, and Index of Agreement (IA) was 0.396642. The multivariate LSTM model's testing set MAE was 22.18, RMSE was 43.06, and IA was 0.974611. For the fractal dimension-based ConvLSTM model, the testing set MAE was 17.37, RMSE was 32.25, and IA was 0.988149. Conclusion The fractal dimension effectively captures the complexity and self-similarity of PM2.5 concentration, providing the model with richer feature information. The fractal dimension-based ConvLSTM model significantly outperforms the traditional ARIMAX model and the multivariate LSTM model in prediction accuracy and can be used for predicting the number of influenza cases.


Result Analysis
Print
Save
E-mail