RESUMO
With the aging of the human body and the reduction in its physiological capacities, falls have become a huge threat to individuals' physical and mental health, leading to serious bodily damage to the elderly and financial pressure on their families. As a result, it is vital to design a fall detection algorithm that monitors the state of human activity. This work designs a human fall detection algorithm based on hierarchical decision making. First, this work proposes a dimensionality reduction approach based on feature importance analysis (FIA), which optimizes the feature space via feature importance. This procedure reduces the dimension of features greatly and reduces the time spent by the model in the training phase. Second, this work proposes a hierarchical decision-making algorithm with an XGBoost model. The algorithm is divided into three levels. The first level uses the threshold approach to make a preliminary assessment of the data and only transfers the fall type data to the next level. The second level is an XGBoost-based classification algorithm to analyze again the type of data which remained from the first level. The third level employs a comparison method to determine the direction of the falling. Finally, the fall detection algorithm proposed in this paper has an accuracy of 98.19%, a sensitivity of 97.50%, and a specificity of 98.63%. The classification accuracy of the fall direction reaches 93.44%, and the algorithm can efficiently determine the fall direction.
Assuntos
Algoritmos , Monitorização Ambulatorial , Humanos , Idoso , Monitorização Ambulatorial/métodosRESUMO
The hospital information structure, which is made up of various medical business systems, is suffering from the problems of the "information isolated island". Medical business systems in the hospital are mutually isomerous and difficult to become a whole. How to realize the internal barrier-free interaction of the patients effective medical information in the hospital and further to complete the area sharing of patients longitudinal diagnosis and treatment information has become a question having to be solved urgently in the process of healthcare informatization. Based on the HL7 standard, this paper refers to the IHE technical framework, expounds the overall structure of the interaction in the hospital internal and area sharing of medical information with the medical information exchange platform. The paper also gives the details of the whole process of the complete display of the discrete patient health information using Portal technology, which is saved in the business systems in different hospitals. It interacts internally through the information exchange platform and at last stores the information in the regional clinical data repository (CDR).
Assuntos
Disseminação de Informação/métodos , Informática Médica/organização & administração , Registro Médico Coordenado , HumanosRESUMO
As a common malignant tumor, breast cancer has seriously affected women's physical and psychological health even threatened their lives. Breast cancer has even begun to show a gradual trend of high incidence in some places in the world. As a kind of common pathological assist diagnosis technique, immunohistochemical technique plays an important role in the diagnosis of breast cancer. Usually, Pathologists isolate positive cells from the stained specimen which were processed by immunohistochemical technique and calculate the ratio of positive cells which is a core indicator of breast cancer in diagnosis. In this paper, we present a new algorithm which was based on modified watershed algorithm and concavity points searching to identify the positive cells and segment the clustered cells automatically, and then realize automatic counting. By comparison of the results of our experiments with those of other methods, our method can exactly segment the clustered cells without losing any geometrical cell features and give the exact number of separating cells.
Assuntos
Algoritmos , Neoplasias da Mama/patologia , Separação Celular , Células Epiteliais/química , Células Epiteliais/patologia , Feminino , Humanos , Processamento de Imagem Assistida por Computador , Imuno-Histoquímica/métodosRESUMO
Hospitalisation risks for chronic obstructive pulmonary disease (COPD) have been attributed to ambient air pollution worldwide. However, a rise in COPD hospitalisations may indicate a considerable increase in fatality rate in public health. The current study focuses on the association between consecutive ambient air pollution (CAAP) and COPD hospitalisation to offer predictable early guidance towards estimates of COPD hospital admissions in the event of consecutive exposure to air pollution. Big data analytics were collected from 3-year time series recordings (from 2015 to 2017) of both air data and COPD hospitalisation data in the Chengdu region in China. Based on the combined effects of CAAP and unit increase in air pollutant concentrations, a quasi-Poisson regression model was established, which revealed the association between CAAP and estimated COPD admissions. The results show the dynamics and outbreaks in the variations in COPD admissions in response to CAAP. Cross-validation and mean squared error (MSE) are applied to validate the goodness of fit. In both short-term and long-term air pollution exposures, Z test outcomes show that the COPD hospitalisation risk is greater for men than for women; similarly, the occurrence of COPD hospital admissions in the group of elderly people (> 65 years old) is significantly larger than that in lower age groups. The time lag between the air quality and COPD hospitalisation is also investigated, and a peak of COPD hospitalisation risk is found to lag 2 days for air quality index (AQI) and PM10, and 1 day for PM2.5. The big data-based predictive paradigm would be a measure for the early detection of a public health event in post-COVID-19. The study findings can also provide guidance for COPD admissions in the event of consecutive exposure to air pollution in the Chengdu region.
RESUMO
OBJECTIVE: To study the effect of Xuebijing on inflammatory response and prognosis in patients with septic shock. METHODS: A prospective randomized controlled study was conducted. Eighty septic shock patients admitted to department of critical care medicine of the First Affiliated Hospital of Zhengzhou University from January to December in 2019 were enrolled. The enrolled patients were divided into Xuebijing group and control group by randomized number table method, with 40 cases in each group. Both groups were strictly followed the guidelines for the diagnosis and treatment of septic shock to take comprehensive treatment measures against sepsis. On this basis, Xuebijing group received intravenous 100 mL Xuebijing injection twice a day for 7 days. Baseline data of enrolled patients were recorded. The levels of interleukin-6 (IL-6), procalcitonin (PCT), C-reactive protein (CRP) and heparin binding protein (HBP) were measured before treatment and 3, 7 and 10 days after treatment. Mechanical ventilation time, the length of intensive care unit (ICU) stay, total hospitalization time and 28-day mortality were recorded. The differences of every indicator between the two groups were compared. Independent risk factors affecting patient prognosis were analyzed by binary Logistic regression. RESULTS: (1) There was no significant difference in baseline data such as gender, age, infection site, acute physiology and chronic health evaluation II (APACHE II) and sequential organ failure score (SOFA) between the two groups. (2) The levels of serum inflammatory factors in both groups showed a decreasing trend after treatment. Compared with the control group, IL-6 and HBP in the Xuebijing group significantly decreased on day 7 [IL-6 (ng/L): 66.20 (16.34, 163.71) vs. 79.81 (23.95, 178.64), HBP (ng/L): 95.59 (45.23, 157.37) vs. 132.98 (73.90, 162.05), both P < 0.05]; on day 10, PCT, CRP, IL-6 and HBP significantly decreased [PCT (µg/L): 1.14 (0.20, 3.39) vs. 1.31 (0.68, 4.21), CRP (mg/L): 66.32 (19.46, 115.81) vs. 89.16 (20.52, 143.76), IL-6 (ng/L): 31.90 (13.23, 138.74) vs. 166.30 (42.75, 288.10), HBP (ng/L): 62.45 (29.17, 96.51) vs. 112.33 (58.70, 143.96), all P < 0.05]. (3) Compared with the control group, mechanical ventilation time and the length of ICU stay were significantly shortened and the total hospitalization expenses were significantly reduced in Xuebijing group [mechanical ventilation time (hours): 57.0 (0, 163.5) vs. 168.0 (24.0, 282.0), the length of ICU stay (days): 8.80±4.15 vs. 17.13±7.05, the total hospitalization expenses (ten thousand yuan): 14.55±7.31 vs. 20.01±9.86, all P < 0.05]. There was no significant difference in 28-day mortality and the total hospitalization time [28-day mortality: 37.5% vs. 35.0%, the total hospitalization time (days): 13.05±8.44 vs. 18.30±9.59, both P > 0.05]. (4) Patients were divided into death and survival groups according to the prognosis, and univariate analysis showed that white blood cell (WBC), neutrophil percentage (NEU%), CRP, lactic acid (Lac), APACHE II score, IL-6, HBP were the factors influencing the prognosis of patients. The above indicators were further analyzed by Logistic regression, which showed that CRP, IL-6, and APACHE II score were independent risk factors for prognosis [odds ratio (OR) was 1.007, 1.828, 1.229, all P < 0.05]. CONCLUSIONS: Combined with Xuebijing to treat septic shock can reduce the body's inflammatory response to a certain extent, thereby reducing the time of mechanical ventilation, shortening the stay of ICU and reducing the total cost of hospitalization. But it cannot reduce the 28-day mortality of patients with septic shock.
Assuntos
Medicamentos de Ervas Chinesas/uso terapêutico , Choque Séptico , APACHE , Humanos , Unidades de Terapia Intensiva , Prognóstico , Estudos Prospectivos , Estudos Retrospectivos , Choque Séptico/tratamento farmacológicoRESUMO
OBJECTIVE: To investigate the effect of recombinant human thrombogenin (rhTPO) on sepsis-associated thrombocytopenia. METHODS: A prospective randomized controlled study was conducted. One hundred patients with sepsis-associated thrombocytopenia admitted to the department of critical care medicine of the First Affiliated Hospital of Zhengzhou University from August 2019 to October 2020 were enrolled. The enrolled patients were divided into rhTPO-using group (TPO group) and routine group (control group) by random number table method, with 50 cases in each group. Both groups were treated according to the guideline of Sepsis-3. In addition, TPO group received rhTPO 15 000 U, once daily for 7 days. Geneal information and acute physiology and chronic health evaluation II (APACHE II) were recorded. The levels of platelet count (PLT), blood coagulation function [prothrombin time (PT) and prothrombin activity (PTA)], myocardial enzyme indexes [troponin (Tn) and creatine kinase (CK)], liver and kidney function [aspartate aminotransferase (AST), total bilirubin (TBil) and creatinine (Cr)] and inflammatory biomarkers [procalcitonin (PCT) and C-reactive protein (CRP)] were recorded before treatment and 1, 3, 5 and 7 days after treatment. The infusion volume of blood components, duration of mechanical ventilation, length of stay in ICU, total length of hospitalization, total cost of hospitalization and 28-day outcome were recorded. According to whether the PLT was lower than 50×109/L, the patients in TPO group were divided into the TPO A group (PLT ≥ 50×109/L, 16 cases) and TPO B group (PLT < 50×109/L, 34 cases), and the absolute value of PLT increase, duration of mechanical ventilation, length of stay in ICU, total length of hospitalization, total cost of hospitalization and 28-day outcome of the two groups were compared. RESULTS: (1) In TPO and control groups, there were no statistically significant differences in gender, age, proportion of patients with primary infection site, APACHEII score, PLT, coagulation function, myocardial enzymes, liver and kidney function and inflammation indexes before treatment (all P > 0.05). (2) The PLT levels of the TPO group were significantly higher than those of the control group on the 5th and 7th day after treatment (×109/L: day 5, 63.94±44.01 vs. 49.85±29.26, day 7, 125.85±112.31 vs. 76.81±50.87, both P < 0.05), and there were no statistically significant differences in PT, PTA, Tn, CK, AST, TBil, Cr, PCT or CRP before and on the 1, 3, 5, 7 days after treatment between TPO and control groups (all P > 0.05). (3) The amount of platelet transfusion in the TPO group was lower than that in the control group [treatment amount: 0 (0, 0) vs 0 (0, 2.00), P = 0.001]. (4) There were no statistically significant differences in mechanical ventilation time, length of stay in ICU, total length of hospitalization, total cost of hospitalization or 28-day outcome between TPO and control groups (all P > 0.05). The mechanical ventilation time, ICU stay time and total hospitalization time of TPO A group were longer than those in TPO B group, but the differences were not statistically significant [mechanical ventilation time (hours): 131.00 (0, 311.00) vs. 50.00 (0, 192.00), ICU stay time (days): 14.44±8.57 vs. 11.73±9.24, total hospitalization time (days): 15.00 (6.00, 23.50) vs. 18.00 (8.00, 31.00), all P > 0.05]. The absolute value of PLT increase in TPO A group was higher than that of TPO B group, but the difference was not statistically significant [×109/L: 65.00 (16.50, 131.50) vs. 36.00 (18.00, 130.00), P > 0.05]. CONCLUSIONS: RhTPO can significantly increase the PLT of patients with sepsis-related thrombocytopenia, thereby reduce the amount of platelet transfusion, but it cannot shorten the length of ICU stay time and total hospitalization time, and it cannot reduce 28-day mortality.