1.Application of time series and machine learning models in predicting the trend of sickness absenteeism among primary and secondary school students in Shanghai
WANG Zhengzhong, ZHANG Zhe, ZHOU Xinyi, YUAN Linlin, ZHAI Yani, SUN Lijing, LUO Chunyan
Chinese Journal of School Health 2025;46(3):426-430
Objective:
To analyze the temporal variation patterns of sickness absenteeism among primary and secondary school students in Shanghai, so as to explore models suitable for predicting peaks and intensity of absenteeism rates.
Methods:
The seasonal and trend decomposition using loess (STL) method was used to analyze the seasonal and long term trend changes in sickness absenteeism among primary and secondary school students from September 1 in 2010 to June 30 in 2018, in Shanghai. A hierarchical clustering method based on Dynamic Time Warping (DTW) was employed to classify absenteeism symptoms with similar temporal patterns. Based on historical data, the study constructed and evaluated different time series algorithms and machine learning models to optimize the accuracy of predicting the trend of sickness absenteeism.
Results:
During the research period, the average new absenteeism rate due to illness was 16.86 per 10 000 person day for every academic year, and the trend of sickness absenteeism exhibited both seasonality and a long term upward trend, reaching its highest point in the 2017 academic year (22.47 per 10 000 person day). The symptoms of absenteeism were divided into three categories: high incidence in winter and spring (respiratory symptoms, fever and general discomfort, etc.), high incidence in summer (eye symptoms, nosebleeds, etc.) and those without obvious seasonality (skin symptoms, accidental injuries, etc.).The constructed time series models effectively predicted the trend of absenteeism due to illness, although the accuracy of predicting peak intensity was relatively low. Among them, the multi layer perceptron (MLP) model performed the best, with an root mean squared error (RMSE) of 8.96 and an mean absolute error (MAE) of 4.37, reducing 36.51% and 39.02% compared to the baseline model.
Conclusion
Time series models and machine learning algorithms could effectively predict the trend of sickness absenteeism, and corresponding prevention and control measures can be taken for absenteeism caused by different symptoms during peak periods.
2.Activation of Pink1/Parkin pathway alleviates the acute lung injury in exertional heat stroke rats
Zhengzhong SUN ; Liya JIANG ; Ran MENG ; Yunya MA ; Yan GU ; Yuxiang ZHANG ; Jiaxing WANG
Chinese Journal of Emergency Medicine 2024;33(7):983-990
Objective:To investigate the role of Pink1/Parkin-induced mitophagy in acute lung injury of exertional heat stroke rats.Methods:Sixty SD rats were randomly divided into four groups, including normal group (CON group), normal Parkin overexpression group (CON+Parkin group), heat stroke group (EHS group) and heat stroke Parkin overexpression group (EHS+Parkin group), with fifteen rats in each group. The rat model of exertional heat stroke was established and the survival curve was drawn. Pulmonary coefficient and pulmonary capillary permeability were detected. HE staining was used to observe the pathological changes of lung tissue. ELISA was used to detect the contents of IL-6, IL-1β, TNF-α and ROS in lung tissue; immunohistochemistry was used to observe apoptosis in lung tissue; Western blot was used to determine the expression of Pink1, Parkin, P62 and LC3 in rat lung tissue, and the LC3II/LC3I ratio was calculated. Single factor multi-level group comparison was performed by single factor analysis of variance, SNK-q method was used to further pairwise comparison between groups.Results:Compared with the normal group, the survival rate of EHS group was decreased ( P<0.001), lung coefficient and pulmonary vascular permeability were increased [(4.39±0.42), (33.38±8.29) μg/g, P<0.05)], lung tissue was exudative and solid, the levels of inflammatory factors IL-6, IL-1β, TNF-α and ROS were significantly increased[(34.31±5.34) pg/mL, (34.03±4.78) pg/mL, (91.64±8.16) pg/mL, (259.01±89.17) U/mg, P<0.05)], and apoptosis was increased. Western and immunohistochemistry results showed that the expressions of Pink1 and Parkin were decreased, co-location of Pink1and Parkin was attenuated, LC3II/LC3I were decreased, and P62 expression was increased. Compared with the EHS group, the survival rate of EHS+Parkin group was significantly increased ( P<0.05), lung coefficient and pulmonary vascular permeability were decreased [(3.83±0.62), (22.49±7.90) μg/g, P<0.05)], exudation and consolidation and other pathological changes were significantly reduced, and the levels of the above inflammatory factors and ROS were significantly decreased [(14.09±3.24) pg/mL, (26.94±2.11) pg/mL、(63.35±11.62) pg/mL, (161.13±26.31) U/mg, P<0.05]. Lung tissue apoptosis was reduced. The co-location of Pink1and Parkin、Parkin expression and LC3II/LC3I ratio were increased ( P<0.05), P62 expression was decreased( P<0.05), while Pink1 expression was not significant different (q=0.75). There was no difference between normal group and normal Parkin overexpression group (q=0.95). Conclusion:Activation of Pink1/Parkin-induced mitophagy can alleviate the acute lung injury in exertional heat stroke rats.
3.Spatio-temporal distribution of emerging snail-infested sites in different environmental types in Yunnan Province
Junhui HUANG ; Yun ZHANG ; Chunhong DU ; Jing SONG ; Ning XU ; Honglin JIANG ; Zhengzhong WANG ; Ying XIONG ; Yixin TONG ; Jiangfan YIN ; Feng JIANG ; Qingwu JIANG ; Yi DONG ; Yibiao ZHOU
Chinese Journal of Endemiology 2023;42(3):178-184
Objective:To explore the spatial and temporal distribution patterns of emerging snail-infested sites in different environmental types in Yunnan Province.Methods:The data of snail-infested sites in Yunnan Province from 1950 to 2014 (from Yunnan Institute for Endemic Diseases Control and Prevention), were collected and sorted out, a spatial and temporal database on the distribution of emerging snail-infested sites were established, and the changes in the spatial and temporal distribution of emerging snail-infested sites in different environments types (ditches, tangerines, paddy fields, dry land, beaches and other environments) were studied by using spatial autocorrelation analysis and scanning statistics analysis.Results:From 1950 to 2014, the annual number of emerging snail-infested sites in Yunnan Province reached a peak (1 730) in 1955 and then showed a fluctuating downward trend. From 1993 to 2014, the number of emerging snail-infested sites remained below 100, and increased to 160 and 131, respectively, in 2004 and 2013. The longest mean duration of 43.85 years was recorded for the beaches environment for emerging snail-infested sites, followed by the paddy fields environment with a mean duration of 37.01 years, and the shortest mean duration of 20.44 years for the tangerines environment. Spatial autocorrelation analysis showed that there was a positive spatial correlation between the duration of emerging snail-infested sites of different environmental types (global Moran's I ranged from 0.43 to 0.64, P < 0.05). Scanning statistics analysis showed that emerging snail-infested sites of different environmental types had spatial and temporal aggregation ( P < 0.001), with 3- 6 clusters of statistically significant aggregation detected respectively. Conclusion:The emerging snail-infested sites in different environments types in Yunnan Province have spatial and temporal aggregation, and it is necessary to strengthen monitoring and prevention and control of the aggregation areas of different environment types to prevent further spread of the snail.
4.Influencing factors of protein energy wasting in maintenance hemodialysis patients
Jing ZHANG ; Jie TIAN ; Hongling WANG ; Zhengzhong HE
International Journal of Biomedical Engineering 2021;44(4):300-306
Objective:To explore the main risk factors of protein energy expenditure (PEW) in maintenance hemodialysis (MHD) patients.Methods:According to diagnostic criteria, 166 patients with MHD were divided into PEW group and control group. The general clinical data, physical indexes, and physical and chemical analysis results of all patients was collected, and the differences in indexes between the two groups of patients were compared. Logistic analysis was used to find the risk factors of MHD combined with PEW.Results:There were statistically significant differences in blood pressure, protein intake, vitamin intake, and uric acid, creatinine, blood calcium levels between the PEW group and the control group (all P<0.05). Multivariate logistic regression analysis showed that blood pressure, daily sleep time, whether to take vitamins, body mass index (BMI), creatinine and parathyroid hormone (PTH) were the risk factors of MHD combined with PEW. Conclusions:In clinical practice, more attention should be paid to controlling blood pressure, improving sleep, and supplementing vitamins in patients with MHD.
5.Genetic diagnosis of a patient with long-time misdiagnosis of epilepsy.
Linli LIU ; Zhengzhong ZHANG ; Zicen DU ; Chunshui YU
Chinese Journal of Medical Genetics 2019;36(10):1019-1021
OBJECTIVE:
To identify pathogenic mutation of TSC1 and TSC2 genes in a patient with long-time misdiagnosis of epilepsy.
METHODS:
Peripheral blood samples and clinical data of the patient and her 2 parents were collected. Potential mutation of TSC1 and TSC2 genes were detected by direct sequencing.
RESULTS:
The patient had frequent episodes of epilepsy in addition with Shagreen patches for 10 years. A frame-shifting mutation c.2509_2512delAACA was detected in exon 20 of the TSC1 gene. This same mutation was not found in her unaffected parents.
CONCLUSION
The recurrent frame-shifting mutation c.2509_2512delAACA (p.Asn837ValfsX11) of the TSC1 gene probably underlies the disease in this patient.
Diagnostic Errors
;
Epilepsy
;
diagnosis
;
genetics
;
Female
;
Frameshift Mutation
;
Humans
;
Tuberous Sclerosis
;
diagnosis
;
genetics
;
Tuberous Sclerosis Complex 1 Protein
;
genetics
;
Tuberous Sclerosis Complex 2 Protein
;
genetics
6. Genetic diagnosis of a patient with long-time misdiagnosis of epilepsy
Linli LIU ; Zhengzhong ZHANG ; Zicen DU ; Chunshui YU
Chinese Journal of Medical Genetics 2019;36(10):1019-1021
Objective:
To identify pathogenic mutation of
7.Verification and evaluation of the prognostic models for extranodal natural killer / T-cell lymphoma, nasal type
Zhenle FEI ; Zhengzhong TANG ; Zongtao HU ; Fan ZHANG ; Hongwei SI
Journal of Leukemia & Lymphoma 2018;27(10):600-603,608
Objective To verify and evaluate the prognostic models for extranodal natural killer/T-cell lymphoma, nasal type (ENKL). Methods ENKL patients in the 105th Hospital of PLA from January 1990 to December 2015 were retrospectively analyzed, and patients were followed to the August 2016 through telephone and medical records. The models were evaluated by C-index, and the prognostic ability of each factor was assessed by survival curves. Results A total of 76 patients met the inclusion criteria, with a median age of 41.9 years old (range, 14-74 years old), all patients received chemotherapy, and 49 received radiation therapy. During the median observation time (37.0 months), 37 patients died in a median of 28.4 months. The prognostic factors of Eastern Cooperative Oncology Group performance status (ECOG PS) score, level of lactate dehydrogenase (LDH) and Ann Arbor staging were the influencing factors of overall survival in the univariate survival analysis (all P<0.05), and only ECOG PS score was significant in the multivariate Cox regression (OR: 4.231, 95 % CI 2.172-8.240, P= 0.000). C-index of international prognostic index (IPI) was 0.541 (95 % CI 0.534- 0.555), and those of model with ECOG PS score, Ann Arbor staging, primary lesion invasion, LDH and age as the indicators and model with ECOG PS core, Ann Arbor staging, primary lesion invasion, LDH and hemoglobin as the indicators were both 0.726 (95 % CI 0.626-0.826). Conclusion Both model with ECOG PS score, Ann Arbor staging, primary lesion invasion, LDH and age as the indicators and model with ECOG PS core, Ann Arbor staging, primary lesion invasion, LDH and hemoglobin as the indicators can accurately predict the prognosis of patients with ENKL and are significantly better than the IPI model.
8.Correlations of a disintegrin and metalloproteinase with thrombospondin type 1 motifs gene polymorphisms with vulnerability of carotid plaque and lipid-loweringing efficacy of atorvastatin in patients with cerebral infarction
Chenling LYU ; Chao CHEN ; Zhengzhong ZHANG ; Zhou ZHENG ; Xiaoping JIN
Chinese Journal of Neuromedicine 2018;17(10):997-1002
Objective To investigate the associations ofa disintegrin and metalloproteinase with thrombospondin type 1 motifs (ADAMTS1) gene single nucleotide polymorphism (SNPs) with vulnerability of carotid plaque formation and atorvastatin lipid-efficacy in patients with cerebral infarction.Methods Seven hundred and seventy-eight patients with anterior circulation infarction,admitted to our hospital from June 2010 to June 2015,were divided into the following 3 groups according to their carotid ultrasound examination results:vulnerable plaque group (n=291),stable plaque group (n=286) and no plaque group (n=201).Atorvastatin was given in patients from the 3 groups and the low density lipoprotein cholesterin (LDL-C) level was detected to evaluate the atorvastatin lipid-efficacy in 151 patients from vulnerable plaque group 4 weeks after treatment.The SNPs of rs402007 (G/C) in ADAMTS1 gene of all patients were detected by PCR amplification and DNA sequencing.Results There were statistically significant differences in age,fibrinogen (FIB) level,homocysteine (HCY) level and percentage of patients having diabetes among the three groups (P<0.05).The frequencies of GC+CC genotype and C allele in rs402007 (G/C) ofADAMTS1 gene in the vulnerable plaque group were significantly higher as compared with those in the no plaque and vulnerable plaque groups (P<0.05).After adjusting risk factors (age,FIB,HCY and diabetes),GC+CC genotype was the independent risk factor of vulnerable plaque (OR=1.559,P=0.015,95%CI:1.089-2.232).There were no significant differences in LDL-C levels before and after atorvastatin treatment among the GG,GC,and CC genotypes in vulnerable plaque group (P>0.05).Conclusion C allele in ADAMTS1 gene might increase the risk of plaque's instability;no correlation exists between A DAMTS1 gene polymorphisms and LDL-C lowing efficacy to atorvastatin.
9.Analysis of SLC39A4 gene mutation in a patient with acrodermatitis enteropathica.
Yunzhu MU ; Zhengzhong ZHANG ; Ping YANG ; Hao YANG ; Yiping LIU ; Linli LIU ; Xing CHEN
Chinese Journal of Medical Genetics 2017;34(3):387-389
OBJECTIVETo detect pathogenic mutation of the SLC39A4 gene in a male patient with acrodermatitis enteropathica (AE).
METHODSPeripheral venous blood sample and clinical data from the patient and his parents were collected. One hundred unrelated healthy individuals were recruited as controls. All coding exons and flanking exon-intron sequences of the SLC39A4 gene were analyzed by PCR and direct sequencing.
RESULTSThe results revealed that the patient and his mother have both carried a novel frame-shift mutation c.1110InsG (p.Gly370GlyfsX47 to TGA) in exon 6. A novel nonsense mutation c.958C to T (p.Q320X) in exon 5 was also detected in the patient and his father and grandmother. This novel mutation was not detected in the unaffected family members and 100 unrelated healthy controls.
CONCLUSIONThe novel frame-shift mutation c.1110InsG (p.Gly370GlyfsX47 to TGA) derived from the mother and nonsense mutation c.958C to T (p.Q320X) of the SLC39A4 gene derived from the father may underlie the disease in the patient.
Acrodermatitis ; genetics ; Adolescent ; Base Sequence ; Cation Transport Proteins ; genetics ; Exons ; Homozygote ; Humans ; Male ; Molecular Sequence Data ; Mutation ; Pedigree ; Zinc ; deficiency
10.Analysis of TSC gene mutations in five patients with tuberous sclerosis complex.
Linli LIU ; Zhengzhong ZHANG ; Yunzhu MU ; Fen XIONG ; Hao YANG ; Ping YANG ; Yiping LIU ; Xing CHEN ; Weichi SUI
Chinese Journal of Medical Genetics 2017;34(2):164-168
OBJECTIVETo identify pathogenic mutations of TSC1 and TSC2 genes in two familial and one sporadic cases with tuberous sclerosis complex (TSC).
METHODSFor five patients and their family members, potential mutations of the TSC1 and TSC2 genes were detected by direct sequencing.
RESULTSFor one family, a novel missense mutation c.1964C>T (p.S655F) was detected in the exon 19 of the TSC2 gene. For the sporadic patient, a repeat substitution with deletion mutation c.5238-5255delCATCAAGCGGCTCCGCCA (p.His1746GlnfsX56) was detected in the exon 40 of the TSC2 gene, which led to a stop codon TGA after the 56th amino acids. No mutation was found in another family.
CONCLUSIONThe missense mutation c.1964C>T(P.S655F) and the substitution with deletion mutation 5238-5255delCATCAAGCGGCTCCGCCA(p.His1746GlnfsX56) of the TSC2 gene probably underlie the disease in the first family and the sporadic case.
Adolescent ; Adult ; Base Sequence ; Child, Preschool ; DNA Mutational Analysis ; Female ; Humans ; Male ; Mutation, Missense ; Pedigree ; Phenotype ; Tuberous Sclerosis ; genetics ; Tumor Suppressor Proteins ; genetics


Result Analysis
Print
Save
E-mail