Home
|
About Us
|
Editorial Board
|
|
Subscribe
|
Messages Board
|
Contact Us
|
中文
Chinese Journal Of Hospital Statistics
Office Online
Online Submission
Peer Review
Office Work
Journal Online
Forthcoming Articles
Current Issue
Archive
Read Articles
Download Articles
Email Alert
2022 Vol. 29, No. 4
Published: 2022-08-25
241
Establishing a statistical data center to facilitate the refined management of hospitals
Zhou Hongzhen, Liang Shengkun, Wu Yunhong
DOI: 10.3969/j.issn.1006-5253.2022.04.001
Objective
To establish a high-quality statistical data management center, realize the open query and display output of hospital statistical data.
Methods
Data of hospitals and departments were sorted to focus on index meanings, data sources, calculation formulas and value methods, and to develop data dictionaries, establish databases, develop statistical data management platform based on Hospital Management Information System (HIS), import checked data, assign access rights and open the platform for use.
Results
A hospital statistica data management center has been formed, including 175 indicators in 29 subcategories of 8 dimensions involving basic statistics data, service efficiency, service quality, patient safety, cost structure, DRGs indicators, satisfaction, major diseases and surgery. It realized the unified management and shared use of the statistical indicator data of the whole hospital.
Conclusion
The establishment of statistical data management platform based on HIS system has improved the work efficiency of statisticians, promoted the sharing and utilization of crossbusiness and crossdepartment data, and provided accurate data support for the hospital's refined management and scientific decisionmaking.
2022 Vol. 29 (4): 241-245 [
Abstract
] (
38
)
HTML
(1 KB)
PDF
(2969 KB) (
163
)
246
Analysis of clinical features and prognostic factors of small cell lung-cancer-in different age groups
Wang Rong，Shen Huanhuan，Xie Shuyang，Zhao Zhenjun
DOI: 10.3969/j.issn.1006-5253.2022.04.002
Objective
To analyze the clinical characteristics and prognostic factors of patients with small cell lung-cancer- in different age groups, and to provide reference for improving the prognostic status of patients.
Methods
In the SEER database, qualified small cell lung cancer patients were selected and divided into groups using X-tile software to find out the age cutoff value and group them according to age. Chi-square test and rank-sum test were used for the comparison of clinical characteristics between groups, time series test was used for the difference of survival curve, multivariate Cox proportional hazard model was used to analyze the influencing factors, and the forest plot was used to visualize the statistically significant factors.
Results
Totally 23 358 eligible small-cell lung cancer patients were included. According to the age analysis results of X-Tile software, they were divided into three groups: ≤65 years old, 66-years old and ≥80 years old. There were statistically significant differences in gender, AJCC cancer stage, surgery, radiotherapy and chemotherapy, bone metastasis, brain metastasis, lung metastasis and tumor size among patients of different age groups (P<0.05). Demographic characteristics (race, gender, family income, insurance, and marital status), AJCC stage, treatment (surgery, radiotherapy, and chemotherapy), metastasis (bone, brain, liver and lung metastasis), and tumor size had statistically significant difference in prognosis for those below 80 years old (P<0.05).AJCC stage, treatment (surgery, radiotherapy, and chemotherapy), metastasis (brain metastasis and liver metastasis), and tumor size had statistically significant difference in prognosis for those 80 years old and above (P<0.05), while demographic characteristics (race, gender, family income, and marital status) had no significant difference in prognosis (P>0.05).
Conclusion
The clinical characteristics of small cell lung cancer patients in different age groups are not all the same, and the prognostic factors are also different. Demographic characteristics, AJCC staging, treatment, metastasis and tumor size are the main influence factors of prognosis for relatively young patients; demographic characteristics are no longer the main factors that affect the prognosis for older patients. It is suggested that different measures should be taken to improve the prognosis of patients of different ages according to the main influencing factors.
2022 Vol. 29 (4): 246-252 [
Abstract
] (
41
)
HTML
(1 KB)
PDF
(5098 KB) (
172
)
253
Analysis of nosocomial infection in a general hospital from 2016 to 2021
Jiang Xuejin, Lü Min, Sun Jihua
DOI: 10.3969/j.issn.1006-5253.2022.04.003
Objective
To investigate the situation of nosocomial infection, the use of antibiotics and the submission of pathogens culture in a general hospital, so as to provide data support for the prevention and control of nosocomial infection.
Methods
A cross-sectional survey of nosocomial infection was conducted in all inpatients on the survey days of each year from 2016 to 2021. Excel 2016 and SPSS 26.0 software were used for data collation and statistical analysis. Descriptive analysis, chi-square test and Fisher's exact probability were used for statistical analysis.
Results
From 2016 to 2021, the prevalence rate of nosocomial infection was 1.89%-2.31%, and there was no statistical difference between years (χ
2
=1.133, P=0.951). The departments with the highest prevalence of nosocomial infection were mainly the Iintensive Care Unit, Department of Hematology, Department of Cardiac Surgery, Department of Rehabilitation Medicine, Department of Thoracic Surgery, etc. Except for 2018, the proportion of respiratory system in other years was more than 50%, and the proportion of Gram-negative bacteria was more than 70%. From 2016 to 2021, the utilization rate of antibiotics was 25.26%-37.45%, showing a downward trend, and the difference between years was statistically significant (χ
2
=150.784, P<0.001). The submission rate of pathogens culture for therapeutic use of antibiotics was 46.20%-56.75%, showing an overall upward trend, and there was a statistical difference between years (χ
2
=15.853, P=0.007).
Conclusion
The prevalence rate of nosocomial infection is low. At the same time, the reasonable use of antibiotics and the standardized submission of pathogen culture are developing well. However, the prevention and control of highrisk departments and places of nosocomial infection still need to be strengthened.
2022 Vol. 29 (4): 253-256 [
Abstract
] (
56
)
HTML
(1 KB)
PDF
(2544 KB) (
161
)
257
Effect of empowerment ability on hypoglycemia fear behavior in type 2 diabetic patients
Zhuge Xiaohe, Chen Ru, Yi Aizhen
DOI: 10.3969/j.issn.1006-5253.2022.04.004
Objective
To investigate the status quo of empowerment ability and hypoglycemia fear behavior in patients with type 2 diabetes, and to analyze the effect of empowerment on hypoglycemia fear behavior in type 2 diabetic patients, so as to provide theoretical basis for the formulation of intervention measures.
Methods
The convenience sampling method was used to select 284 patients with type 2 diabetes admitted to our hospital from January 2020 to June 2021 as the research objects. The general data questionnaire, Diabetes Empowerment Scaleshort Form and Hypoglycemia Fear Survey-Behaviour Scale were used for questionnaire investigation.
Results
The scores of empowerment ability and hypoglycemia fear behavior were 30.72±5.84 and 46.15±8.42 respectively in type 2 diabetic patients. There were statistically significant differences in the scores of hypoglycemic fear behavior among type 2 diabetes patients with different genders, educational levels, marital status, family per capita monthly income, complications, diabetes-related education, and the frequency of hypoglycemia in recent half year (P<0.05). Pearson correlation analysis showed that the empowerment score of type 2 diabetes patients was negatively correlated with the total score of hypoglycemic fear behavior and the scores of all dimensions (P<0.01). The results of multiple linear regression analysis showed that gender, diabetes-related education, and empowerment ability were the main influencing factors of fear behavior of hypoglycemia in type 2 diabetes patients (P<0.01), which could explain 41.8% of the total variation.
Conclusion
The fear behavior of hypoglycemia in patients with type 2 diabetes is affected by their gender, diabetesrelated education and empowerment ability. Therefore, targeted intervention measures should be taken according to the different conditions of patients to improve their empowerment ability and reduce their fear behavior of hypoglycemia.
2022 Vol. 29 (4): 257-261 [
Abstract
] (
43
)
HTML
(1 KB)
PDF
(2912 KB) (
95
)
262
Study on dietary compliance with phosphorus control in hemodialysis patients and its correlation with disease perception
Jin Yingying, Hu Qinjie, Huang Peipei, Hu Danxiang
DOI: 10.3969/j.issn.1006-5253.2022.04.005
Objective
To study the compliance of phosphorus control diet and its correlation with disease perception in elderly maintenance hemodialysis patients, and provide guidance for clinical intervention.
Methods
Elderly patients with end-stage renal disease who received maintenance hemodialysis in a hospital from November 2019 to march 2022 were selected as study objects. The Maintenance Hemodialysis-Related Dietary Compliance Scale and the Brief Illness Perception Questionnaire (BIPQ) in patients with endstage renal disease were used to analyze the patients′ compliance with phosphorus control diet and disease perception status. The Pearson correlation analysis method was used to analyze the correlation between phosphorus control diet compliance and disease perception in maintenance hemodialysis patients.
Results
The total score of dietary compliance with phosphorus control in 284 elderly patients with end-stage renal disease who underwent maintenance hemodialysis was (48.45±2.16) points, of which 71 cases (25.00%) had high compliance with phosphorus control diet, 111 cases (39.08%) had moderate compliance, and 102 cases (35.92%) had low compliance. The total score of disease perception BIPQ scale of elderly patients on maintenance hemodialysis was（47.49±14.64）points; the Pearson correlation analysis showed that the adherence to phosphorus control diet was significantly negatively correlated with disease perception in elderly patients on maintenance hemodialysis (r=-0.879, P＜0.001).
Conclusion
The overall compliance of phosphorus control diet in elderly patients on maintenance hemodialysis is at a moderate level, and the compliance of phosphorus control diet is negatively correlated with disease perception.
2022 Vol. 29 (4): 262-265 [
Abstract
] (
38
)
HTML
(1 KB)
PDF
(2303 KB) (
421
)
266
Epidemiological analysis of the emergency department of adult internal medicine in a prefecture-level tertiary hospital in Shandong
Luan Chunye, Guo Lisha, Zhang Bing, Su Pengtao, Li Weihua, Zhang Jinying
DOI: 10.3969/j.issn.1006-5253.2022.04.006
Objective
To analyze the epidemiological characteristics and disease spectrum of adult emergency patients in a prefecture-level tertiary hospital in Shandong Province, find out the regularity and clinical characteristics of medical treatment, and provide data support for clarifying the priorities of emergency treatment and optimizing emergency procedures.
Methods
Clinical data of pre-triage patients in the emergency department from January to December 2019 including gender, age, pre-triage grade, diagnosis, visit time and other information were collected from the triage information system of a tertiary hospital in Shandong Province for retrospective analysis.
Results
Totally 28 428 adult internal medicine patients were admitted to the emergency department throughout the year, with a male to female ratio of 0.937∶1; the 30 year-old group accounted for the most (25.38%), the 45 year-old group accounted for 23.36%, and the 60-74 year-old group accounted for 23.77%. The peak of all-day visits was from 19：00 to 19：59 (accounting for 36.67% of the total number of visits), with a clear circadian rhythm. The pre-examination and triage levels of the patients were mainly grade 4 sub-acute or non-acute. In adult patients, the proportion of patients with grade 1 acute and grade 2 acute increased with age. Nervous system, digestive system, circulatory system, and respiratory system diseases were the main disease spectrum of adult medical emergency.
Conclusion
The emergency treatment has obvious circadian rhythm and disease spectrum characteristics. It is necessary to strengthen the arrangement of emergency personnel at night, strengthen the training and learning of the diagnosis and treatment of major diseases, improve the efficiency of treatment, and ensure the safety of patients in seeking medical treatment.
2022 Vol. 29 (4): 266-269 [
Abstract
] (
49
)
HTML
(1 KB)
PDF
(2552 KB) (
126
)
270
Retrospective analysis of 265 cases with adverse reactions to psychotropic drugs in a tertiary psychiatric hospital
Wu Xuqi, Sun Ting
DOI: 10.3969/j.issn.1006-5253.2022.04.007
Objective
To analyze the characteristics, influencing factors and potential risks of adverse drug reactions (ADR) in a tertiary psychiatric hospital, so as to provide reference for clinical prevention and disposal of adverse drug reactions of psychotropic drugs.
Methods
A retrospective analysis was conducted on 265 ADR case reports due to the use of psychotropic drugs reported by a psychiatric hospital from October 2019 to October 2021.
Results
Among the 265 reported cases with ADR, 88 were males and 177 were females, with a higher incidence among females. The average age of the patients was (42.23±17.54) years old, with the majority being young and middle-aged. Forty drugs were involved in ADRs reports, of which the number of adverse reaction reports of antipsychotics was the largest, accounting for 66.42%, followed by antidepressants, accounting for 20.38%. The top three drugs in the cumulative number of reported ADR cases were Olanzapine, Quetiapine and Risperidone respectively. The system most affected by ADRs was the digestive system, with 105 cases reported, accounting for 37.23%, followed by the nervous system, with 88 cases reported, accounting for 31.21%.
Conclusion
The forms of adverse reactions caused by psychiatric drugs are various, and it is difficult to identify them. Clinicians should strengthen the monitoring of the use of psychiatric drugs and use the psychiatric drugs reasonably to ensure the medication safety.
2022 Vol. 29 (4): 270-274 [
Abstract
] (
40
)
HTML
(1 KB)
PDF
(2777 KB) (
437
)
275
Analysis on the composition and changes of inpatient costs in a hospital from 2016 to 2021
Wang Jian, Chu Zhijie, Lu Wenqiao, Pang Jing, Wang Jingyi
DOI: 10.3969/j.issn.1006-5253.2022.04.008
Objective
To understand the internal composition and changes of average inpatient costs in a hospital from 2016 to 2021, so as to provide empirical basis for reducing the inpatient burden and promoting the high-quality development of traditional Chinese medicine.
Methods
The grey correlation analysis and the structure variation analysis were used for statistical analysis.
Results
From 2016 to 2021, inpatient costs increased with an average annual growth rate of 3.46%. From the perspective of grey correlation, the diagnostic cost was the item with the greatest correlation. The structure variation of inpatient costs was 32.77% from 2016 to 2021. Causing the change of cost structure mainly included three major items: Western medicine costs, consumable costs and diagnostic costs with the cumulative contribution rate of 73.97%.
Conclusion
In controlling the cost of western medicine, the hospital had achieved remarkable results, but the growth rate of per inpatient cost needs to be further reduced, and the diagnostic costs and consumable costs are the key to control the cost of inpatients. It is necessary to further increase the proportion of traditional Chinese medicine costs, promote the balance between herbal medicine costs and western medicine costs, and highlight the advantages of traditional Chinese medicine. It is necessary to further increase the proportion of the cost reflecting the service value of medical staff.
2022 Vol. 29 (4): 275-278 [
Abstract
] (
42
)
HTML
(1 KB)
PDF
(2355 KB) (
139
)
279
Prediction of ARIMA model based on R language on average length of stay
Guo Zaijin，Zhou Luojing
DOI: 10.3969/j.issn.1006-5253.2022.04.009
Objective
To establish a differential autoregressive integrated moving average ( ARIMA ) model to predict the average length of stay in a tertiary hospital in Jiangsu Province and provide scientific reference for the allocation of medical resources.
Methods
Based on the average hospital stay data of a tertiary hospital in Jiangsu Province from January 2013 to June 2021, the ARIMA model was constructed by using R software to predict the average hospital stay in the hospital from July 2021 to May 2022, and to compare with the actual value to evaluate the prediction effect of the ARIMA model.
Results
The average length of stay of the hospital has been decreasing year by year since January 2013, and has certain seasonal characteristics. The best fitted ARIMA model is ARIMA ( 0, 1, 1 ) ( 0, 1, 1 ) 12 , with MAPE of 1.78% and RMSE of 0.24. In the prediction of ARIMA model, RMSE is 1.49, MAPE is 7.78%, and the prediction results are ideal.
Conclusion
ARIMA model has good prediction effect on the average length of stay in the hospital, and can be used for the shortterm prediction of the average length of stay in the hospital.
2022 Vol. 29 (4): 279-282 [
Abstract
] (
43
)
HTML
(1 KB)
PDF
(2705 KB) (
128
)
283
Inpatients with malignant tumors in a tertiary traditional Chinese medicine hospital in Shandong Province
Song Rong
DOI: 10.3969/j.issn.1006-5253.2022.04.010
Objective
analyze the cases of malignant tumors in a tertiary traditional Chinese medicine hospital in Shandong Province, so as to provide reference for the prevention and treatment of malignant tumors in the hospital and the local area.
Methods
Data were collected from the first page of medical records of malignant tumor patients from January 2018 to June 2022, and the age and gender distribution of the inpatients were analyzed, as well as the composition and ranking changes of the top 10 malignant tumor diseases in different years, genders and age groups.
Results
There were 76 714 patients with malignant tumors, including 35 189 males and 41 525 females, and the male to female ratio was 0.85∶1. The patients were mainly aged-over-50, with 67 997 patients, accounting for 88.64%. The number of hospitalized patients with malignant tumors increased year by year from 2018 to 2022. The top five malignant tumors were lung cancer, stomach cancer, colorectal cancer, liver cancer and kidney cancer in males, and breast cancer, lung cancer, cervical cancer, colorectal cancer and stomach cancer in females. The top three diseases of patients over 50 years old were lung cancer, breast cancer and colorectal cancer in the 50- years old group, lung cancer, breast cancer and stomach cancer in the 60- years old group, and lung cancer, stomach cancer and colorectal cancer in the group over 70 years old.
Conclusion
The hospital authorities should further strengthen scientific management, optimize the allocation of medical resources within the hospital, and authorities in the relevant competent departments should formulate comprehensive prevention and treatment measures for local population with malignant tumors over 50 years old.
2022 Vol. 29 (4): 283-286 [
Abstract
] (
41
)
HTML
(1 KB)
PDF
(2350 KB) (
98
)
287
Analysis on the proportion of drugs in a dermatology hospital and the influencing factors
Lin Jinxiong，Yu Yao，Liao Yuehua，An Ningbo
DOI: 10.3969/j.issn.1006-5253.2022.04.011
Objective
To explore the influencing factors of the drug proportion in hospitals specializing in dermatology and the relationship paths, so as to provide theoretical basis for scientific control of drug proportion, alleviation of patients′ disease economic burden and hospital management practice.
Methods
Path analysis was performed on the first page of medical records of 15 315 inpatients in a large tertiary dermatology hospital in Guangdong Province in recent 5 years.
Results
The average drug proportion of patients was 21.45%, and the median drug proportion was 19.27%. Variables such as gender, marital status, medical insurance, surgery, readmission within a month, use of antibiotics, clinical path, and hospitalization days directly affected the drug proportion, with statistical significance (P<0.05); Bootstrap test showed that surgery, hospitalization days, medical insurance, marital status, readmission within a month, clinical path, use of antibiotics, gender, case type, age, nosocomial infection and complications could indirectly affect the proportion of drugs through the effects on hospitalization days (P<0.05).
Conclusion
In order to rationalize the drug proportion control, it is necessary to strengthen the grasp of controllable factors such as hospitalization days and surgery, take reasonable measures to transform uncontrollable factors such as gender, age, marital status into controllable factors, and accurately implement policies to achieve the effect of comprehensive management of the drug proportion and keep them in a reasonable range, so as to reduce the economic burden of patients and improve the quality of medical services and people′s livelihood.
2022 Vol. 29 (4): 287-291 [
Abstract
] (
45
)
HTML
(1 KB)
PDF
(3788 KB) (
96
)
292
Analysis of irrational medical orders in pharmacy intravenous admixture services of a tertiary hospital
Liu Xiyu，Xiao Ming，Luo Yongchuan，Li Yuchen，Lü Jiantao
DOI: 10.3969/j.issn.1006-5253.2022.04.012
Objective
To classify and analyze irrational drug use in pharmacy intravenous admixture services (PIVAS) of a tertiary hospital, and to provide a reference for improving the rational use of drugs and ensuring the drug use safety of patients.
Methods
A retrospective survey method was used to sort out the long-term medical orders of a hospital from January 2018 to August 2021, classify irrational medical orders, and analyze the situation of irrational drug use.
Results
Among the 490 269 long-term medical orders, there were 2 739 irrational medication orders, of which the number of irrational long-term medical orders in 2019 was the largest. Among the types of long-term medical orders for irrational drug use, the top 3 errors in issuing-medical- orders were that drugs and solvents were not grouped together (8.21%), the number of changes made by physicians (1.79%), and the repeated issuing of medical orders (0.33%). The top three errors without prescriptions of doctors were irrational selection of solvent types (32.06%), irrational selection of solvent dosage (19.46%) and inappropriate drug dose (16.43%).
Conclusion
Prescription pharmacists use professional pharmaceutical knowledge, relevant laws and regulations and medication system software to carefully review the contents of prescriptions or medical orders, timely intervene and find unreasonable drug use, so as to reduce the occurrence of adverse drug reactions and improve the safety and effectiveness of drugs.
2022 Vol. 29 (4): 292-296 [
Abstract
] (
50
)
HTML
(1 KB)
PDF
(2938 KB) (
110
)
297
Practice and effect analysis of performance appraisal for management position of the clinical research center
Liu Jiajing， Jiang Xiaoying，Zhu Zhengfei
DOI: 10.3969/j.issn.1006-5253.2022.04.013
Objective
To explore the construction of the performance appraisal system for management positions in clinical research centers, further improve the level of clinical research management in hospitals, realize the efficient operation of research projects, and provide ideas for the performance appraisal of clinical research managers.
Methods
Through the analysis of the management positions of the clinical research center, the performance appraisal system based on workload was implemented, and the labor value of three-level factors was used to quantify the newly started projects, including the satisfaction and penalty-items. The t test was used to analyze the key data before and after the implementation.
Results
The t-test results showed that some workload indicators, satisfaction and personnel income in creased significantly. There were significant differences in the number of newly launched projects (t=2.24, P=0.037), the number of projects under research (t=9.71, P<0.01), the number of clinical trial drugs (t=9.42, P<0.01), satisfaction (t=4.83, P<0.01) and per capita income (t=5.55, P<0.01).
Conclusion
The workload-based assessment system changed from the quota-based, can decompose and quantify the workload, difficulty and risk, stimulate the enthusiasm of staff with management positions in clinical research centers, achieve a win-win situation between hospitals and staff, and provide ideas for improving the compensation incentive mechanism for relevant positions.
2022 Vol. 29 (4): 297-300 [
Abstract
] (
33
)
HTML
(1 KB)
PDF
(2417 KB) (
314
)
301
Impact of strengthening assessment and evaluation management on Internet hospital operation based on interrupted time-series analysis
Xu Yanjie, Dong Henglei
DOI: 10.3969/j.issn.1006-5253.2022.04.014
Objective
To study the intervention effect of strengthening assessment and evaluation management on Internet medical service quantity.
Methods
Interrupted time-series (ITS) method was used to analyze the amount of Internet diagnosis and treatment services before and after strengthening the assessment management of a specialized hospital in Tianjin.
Results
The number of Internet diagnosis and treatment services increased significantly (t=3.670, P<0.05), with an increase of 215 visits per month compared with that before the strengthening of assessment and evaluation management.
Conclusion
Strengthening assessment and evaluation management can significantly improve the quantity of Internet diagnosis and treatment services.
2022 Vol. 29 (4): 301-303 [
Abstract
] (
33
)
HTML
(1 KB)
PDF
(2656 KB) (
90
)
304
Simulation study on linear regression analysis strategy under extreme value conditions
Hu Weiwei, Li Yemian, Yan Hong, Chen Fangyao
DOI: 10.3969/j.issn.1006-5253.2022.04.015
Objective
To compare the actual effects of four commonly used extreme value processing strategies in multi-factor regression analysis under different extreme value conditions, and to provide a reference for formulating extreme value processing strategies in multi-factor regression analysis.
Methods
Monte Carlo algorithm was used to simulate the extreme data under different conditions, and the extreme value processing strategy of multivariate regression analysis under different extreme conditions was simulated. Type I error probability-α, type II error probability-β, root mean square error of model coefficient estimation, model R
2
and adjustment R
2
were used as evaluation indexes.
Results
The method of directly deleting extreme values performs well when the proportion of extreme values and the number of observation points containing extreme values are small, but with the increasing proportion and number of extreme values, the performance becomes worse and worse. Robust regression analysis has a very good performance under various extreme conditions of large sample size, except that the performance is not very good when the sample size is small. The method of converting extreme values into missing values and then performing multiple interpolation only has acceptable performance when the sample size is small and the proportion of extreme values is low. The processing method of data conversion is very poor in all extreme conditions.
Conclusion
Robust regression analysis is best used when the sample size is large, but it should be used with caution when the sample size is small. The method of converting extreme values into missing values and then multiple interpolation is suitable for data sets with small proportion of extreme values. The method of directly deleting extreme values is only suitable for data sets with small number of observation points and small proportion, while the method of data conversion is not suitable for most extreme values.
2022 Vol. 29 (4): 304-311 [
Abstract
] (
35
)
HTML
(1 KB)
PDF
(4906 KB) (
124
)
312
Comparison of the effects of discretization methods of continuous explanatory variables based on logistic regression
He Xianying
DOI: 10.3969/j.issn.1006-5253.2022.04.016
Objective
To explore the advantages and disadvantages of different data discretization methods when the continuous independent variable and logit-π-do not satisfy the linear relationship, and to provide reference for the continuous independent variable discretization in logistic regression analysis.
Methods
A casecontrol study was used to generate simulated data from the three perspectives of effect size, number of independent variables, and sample size with R software. The continuous independent variables were further processed by different discretization to fit logistic regression models, and the fitting effects of different methods were compared.
Results
The results of different simulation data sets showed that when the four continuous variable processing methods were used to fit the logistic regression model, "maximum OR values method" could better screen out meaningful influencing factors. At the same time, its model fitting effect was also the best, which was shown as the smallest-AIC, the largest Nagelkerke R
2
, and the higher correct total rate.
Conclusion
It is recommended to use "maximum-OR-values method" to discrete continuous variables if the relationship between these variables and logit
π
is non-monotonic.
2022 Vol. 29 (4): 312-317 [
Abstract
] (
46
)
HTML
(1 KB)
PDF
(3617 KB) (
265
)
318
Statistical method of eliminating "nucleic acid test times" from the total number of outpatient patients based on HIS system
Jiang Guojian, Huang Yuqing, He Guobin, Jiang Yufei, Xu Minhui, Guo Jiayi
DOI: 10.3969/j.issn.1006-5253.2022.04.017
Objective
To optimize the statistical caliber of the total number of outpatient visits.
Methods
Through analyzing the characteristics of three ways of billing for COVID-19 nucleic acid testing in outpatient and emergency departments of hospitals, namely self-service machine, mobile APP and doctor billing, the module of "accompanying COVID-19 testing" was added to the outpatient and emergency prescription system, the value of special labeled fields was added, the screening logic and calculation formula were clarified, information was obtained from HIS system and program statements were edited. Accurate statistics of the number of COVID-19 nucleic acid tests was achieved, as well as the total number of outpatient visits after eliminating the number of nucleic acid tests.
Results
The statistical module based on process combing and information program design of the HIS system can efficiently and accurately achieve the latest statistical caliber requirements and reflect the actual medical visits more accurately.
Conclusion
It can strengthen the objectivity of data comparison in different periods and provide more valuable data for hospital outpatient operation and management to accurately extract the nucleic acid test persontimes and calculate the total out-patient visits after the exclusion.
2022 Vol. 29 (4): 318-320 [
Abstract
] (
40
)
HTML
(1 KB)
PDF
(1766 KB) (
100
)
Copyright © Editorial Board of journal1
Supported by:
Beijing Magtech
