CN118471454B - Method and system for assisting in statistics of working efficiency of outpatient service according to triage system - Google Patents
Method and system for assisting in statistics of working efficiency of outpatient service according to triage system Download PDFInfo
- Publication number
- CN118471454B CN118471454B CN202410925309.5A CN202410925309A CN118471454B CN 118471454 B CN118471454 B CN 118471454B CN 202410925309 A CN202410925309 A CN 202410925309A CN 118471454 B CN118471454 B CN 118471454B
- Authority
- CN
- China
- Prior art keywords
- data
- diagnosis
- doctor
- working efficiency
- patient
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 24
- 238000012549 training Methods 0.000 claims abstract description 21
- 238000011002 quantification Methods 0.000 claims abstract description 20
- 238000007781 pre-processing Methods 0.000 claims abstract description 19
- 238000013210 evaluation model Methods 0.000 claims abstract description 13
- 238000012545 processing Methods 0.000 claims abstract description 13
- 238000003745 diagnosis Methods 0.000 claims description 189
- 238000006243 chemical reaction Methods 0.000 claims description 99
- 238000011282 treatment Methods 0.000 claims description 48
- 230000009466 transformation Effects 0.000 claims description 24
- 238000010276 construction Methods 0.000 claims description 12
- 238000007476 Maximum Likelihood Methods 0.000 claims description 6
- 238000013139 quantization Methods 0.000 claims description 6
- 230000009286 beneficial effect Effects 0.000 abstract description 4
- 230000000007 visual effect Effects 0.000 abstract description 3
- 230000008569 process Effects 0.000 description 3
- 238000007619 statistical method Methods 0.000 description 3
- 230000001131 transforming effect Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 208000025174 PANDAS Diseases 0.000 description 1
- 208000021155 Paediatric autoimmune neuropsychiatric disorders associated with streptococcal infection Diseases 0.000 description 1
- 240000000220 Panda oleosa Species 0.000 description 1
- 235000016496 Panda oleosa Nutrition 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000013479 data entry Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000001303 quality assessment method Methods 0.000 description 1
- 238000012552 review Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
- G16H40/20—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the management or administration of healthcare resources or facilities, e.g. managing hospital staff or surgery rooms
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06398—Performance of employee with respect to a job function
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Biomedical Technology (AREA)
- Medical Informatics (AREA)
- General Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Public Health (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Primary Health Care (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Entrepreneurship & Innovation (AREA)
- Bioinformatics & Computational Biology (AREA)
- Strategic Management (AREA)
- Evolutionary Biology (AREA)
- General Health & Medical Sciences (AREA)
- Epidemiology (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Marketing (AREA)
- Databases & Information Systems (AREA)
- Pathology (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention belongs to the technical field of medical data processing, and relates to a method and a system for assisting in counting working efficiency of an outpatient service according to a triage system. The method comprises the following steps: acquiring basic business data of a hospital; the triage system is used for counting triage data; preprocessing data and extracting characteristic data; constructing a sample data set; constructing a layered linear model of the working efficiency of a doctor; training to obtain a working efficiency evaluation model of a doctor; obtaining the current doctor working efficiency quantification index. The invention can improve the accuracy of statistics of the working efficiency of doctors, and is beneficial to making more reasonable medical decisions according to the working efficiency of doctors; the invention provides visual understanding of the influence degree of each characteristic data on the working efficiency of doctors through a layered linear model.
Description
Technical Field
The invention belongs to the technical field of medical data processing, and particularly relates to a method and a system for assisting in counting working efficiency of an outpatient service according to a triage system.
Background
Work efficiency in the medical field generally refers to the efficiency of a doctor in providing medical services, including quality of diagnosis, time management, resource utilization, and the like. The general assessment of physician work efficiency typically involves a number of metrics such as patient satisfaction, time of diagnosis, quality of diagnosis and resource utilization. The proportion of the working time of the doctor is conventionally calculated by a workload statistics method (statistics of the number of times of the patients of the clinic, etc.), the diagnosis and treatment quality of the doctor is statistically calculated using a case quality assessment method, etc.
The existing method for calculating the working efficiency of the outpatient doctor by using the registration times of the outpatient doctor and the visit times of the doctor on the same day in the HIS system and then using a workload statistical method has the following defects:
(1) The workload statistical method is more visual and easy to understand, but the method mainly depends on two data points of registration and visit, the accuracy of evaluation is limited by a data source, other important aspects in the doctor work, such as factors of case complexity, consultation time, patient satisfaction and the like, are ignored, and the evaluation of the working efficiency is not comprehensive enough;
(2) The accuracy of the calculation result is directly affected by the data quality and the integrity of the HIS system, and errors of the calculation result can be directly caused by data entry errors or information missing;
(3) The complexity of the condition and the time required for the doctor are different for different patients, and simple consultation and treatment of complex diseases cannot be equally regarded as such as review or report, etc., and the method does not consider the difference of the complexity of the cases;
(4) Doctors also need to participate in administrative management, conferences and the like, and these tasks also occupy the working time of the doctors, but are often ignored in workload statistics.
Therefore, the conventional HIS system does not evaluate the working efficiency of the doctor precisely enough, and if deviation occurs in the data result, the influence on the result is also large, and the accuracy of data statistics is low. There is a need to provide more accurate data by means of triage systems to address these problems.
Disclosure of Invention
In order to solve the technical problems, the invention provides a method and a system for assisting in counting the working efficiency of an outpatient according to a triage system.
In a first aspect, the present invention provides a method for assisting in counting out the working efficiency of an outpatient service according to a triage system, comprising:
acquiring basic business data of a hospital, wherein the basic business data comprise job title information, consulting room information, registration information of doctors and diagnosis and treatment time data of each patient;
The triage system is used for counting triage data; the triage data comprises first-stage triage data, second-stage triage data, third-stage triage data, doctor's data for patient switching and historical doctor's working efficiency quantification indexes; the statistics of the first-stage diagnosis data comprises registration information synchronously acquired from the HIS system as basic data of the first-stage diagnosis; the statistics of the second-stage diagnosis data comprises marking the priority and case difference of the patient by using the diagnosis dividing function of the diagnosis dividing system, and recording corresponding data; counting three-stage diagnosis data comprises counting the time of calling different patients by a doctor by using the number calling function of the diagnosis system; counting the doctor's visit data of the patient switching doctor, including using the second-stage diagnosis dividing function of the diagnosis dividing system, recording the data of other doctors of the patient switching, and marking the patient visit information;
Preprocessing basic business data and triage data of a hospital, and extracting to obtain numeric characteristic data; the characteristic data comprise doctor title data, diagnosis and treatment time data of a patient, conversion rate of primary diagnosis and treatment, conversion rate of secondary diagnosis and conversion rate of tertiary diagnosis and treatment; the quantitative index of the doctor working efficiency is the number of patients in doctor unit time;
constructing a sample data set by utilizing the characteristic data and historical doctor working efficiency quantification indexes;
Taking the characteristic data as factors, setting weight coefficients and intercepts of the factors, taking the preprocessed historical doctor working efficiency quantization index as output, and constructing a layered linear model of the doctor working efficiency;
Training the layered linear model by using a sample data set, and training out a weight coefficient of the factor for each doctor to obtain a doctor working efficiency evaluation model;
Acquiring current hospital basic service data and triage system statistics triage data, preprocessing, encoding and classifying, extracting to obtain characteristic data of a current doctor, and inputting the characteristic data of the current doctor into a doctor working efficiency evaluation model to obtain a current doctor working efficiency quantification index.
In a second aspect, the invention provides a system for assisting in counting the working efficiency of an outpatient service doctor according to a triage system, which comprises an acquisition unit, a statistics unit, a preprocessing unit, a sample data set construction unit, a hierarchical linear model construction unit, a model training unit and a data processing unit;
the acquisition unit is used for acquiring basic business data of a hospital, including job title information, consulting room information, registration information of doctors and diagnosis and treatment time data of each patient;
The statistics unit is used for counting triage data by the triage system; the triage data comprises first-stage triage data, second-stage triage data, third-stage triage data, doctor's data for patient switching and historical doctor's working efficiency quantification indexes; the statistics of the first-stage diagnosis data comprises registration information synchronously acquired from the HIS system as basic data of the first-stage diagnosis; the statistics of the second-stage diagnosis data comprises marking the priority and case difference of the patient by using the diagnosis dividing function of the diagnosis dividing system, and recording corresponding data; counting three-stage diagnosis data comprises counting the time of calling different patients by a doctor by using the number calling function of the diagnosis system; counting the doctor's visit data of the patient switching doctor, including using the second-stage diagnosis dividing function of the diagnosis dividing system, recording the data of other doctors of the patient switching, and marking the patient visit information; the quantitative index of the doctor working efficiency is the number of patients in doctor unit time;
The pretreatment unit is used for preprocessing basic business data and triage data of the hospital and extracting and obtaining numerical characteristic data; the characteristic data comprise doctor title data, diagnosis and treatment time data of a patient, conversion rate of primary diagnosis and treatment, conversion rate of secondary diagnosis and conversion rate of tertiary diagnosis and treatment;
The sample data set construction unit is used for constructing a sample data set by utilizing the characteristic data and the historical doctor working efficiency quantification index;
The hierarchical linear model construction unit is used for taking the characteristic data as factors, setting weight coefficients and intercepts of the factors, taking the preprocessed historical doctor working efficiency quantization index as output, and constructing a hierarchical linear model of the doctor working efficiency;
the model training unit is used for training the layered linear model by utilizing the sample data set, and training out the weight coefficient of the factors for each doctor to obtain a doctor working efficiency evaluation model;
The data processing unit is used for acquiring the basic business data of the current hospital and the statistical triage data of the triage system, carrying out coding and classification after preprocessing, extracting the characteristic data of the current doctor, inputting the characteristic data of the current doctor into the working efficiency evaluation model of the doctor, and obtaining the working efficiency quantification index of the current doctor.
On the basis of the technical scheme, the invention can be improved as follows.
Further, the patient visit information includes the patient visit priority, the patient visit department, the patient intent visit doctor, the doctor who is being switched to visit, and the reason why the doctor is being switched from patient to patient.
Further, the basic business data and triage data of the hospital are preprocessed, classification and coding are carried out, the single-heat coding is carried out on the job title data of doctors, the nonlinear conversion is carried out on the diagnosis and treatment time data of patients, and the standardized processing is carried out on the conversion rate data of triage at each level.
Further, performing the one-time thermal encoding on the job title data of the doctor includes classifying the job title data of the doctor into a plurality of grades, and assigning a value to the job title data of the doctor corresponding to each grade.
Further, non-linearly transforming the patient's time of diagnosis data includes applying a natural logarithmic transformation or a Box-Cox transformation to each patient's time of diagnosis data point; assuming that the diagnosis and treatment time data of the patient is x, the constant is c, and the log is a logarithmic transformation function, the diagnosis and treatment time data of the patient after transformation is; Let λ be the transformation parameter, and confirm the best λ value by maximum likelihood estimation using Box-Cox function in SciPy library of Python.
Further, the data of conversion rate of each stage of triage is standardized by adopting a Z-score mode; setting the conversion rate of the first grade diagnosis asThe conversion rate of the second-stage diagnosis isThe conversion rate of the three-stage diagnosis isN is the total number of samples of conversion rate of each triage,For the conversion rate of the i-th fraction diagnosis,Is the conversion rate of the i-th fraction diagnosisThe value of the j-th sample among the n conversion samples,The mean value of the conversion rate of the i-th fraction diagnosis,Standard deviation of the conversion rate for the i-th fraction diagnosis,Normalized values for conversion of the ith fraction diagnosis, normalized values are used to characterizeAnd mean value ofAnd (b) the difference between (a) and (b) then:
；
；
。
further, a hierarchical linear model was built using the statsmodels library of Python.
Further, a layered linear model of the doctor's working efficiency is constructed, assuming that the doctor's working efficiency is Y,In order to be an intercept term,The coefficients for the job title data of the doctor,Is a coefficient of diagnosis and treatment time data of a patient,Is the coefficient of the conversion rate of the first order diagnosis,Is the coefficient of the conversion rate of the second-stage diagnosis,The physician's job data is the conversion rate of the third-level diagnosisThe diagnosis and treatment time data of the patient are thatThe conversion rate of the first-stage diagnosis isThe conversion rate of the second-stage diagnosis isThe conversion rate of the three-stage diagnosis is，As an error term, then:
。
The beneficial effects of the invention are as follows: the invention can improve the accuracy of the working efficiency of the statistical doctor, builds a layered linear model through careful feature selection and optimizes, improves the accuracy of the model for predicting the working efficiency of the doctor, and is beneficial to making more reasonable medical decisions according to the working efficiency of the doctor; the invention provides visual understanding of the influence degree of each characteristic data on the working efficiency of doctors through a layered linear model.
Drawings
FIG. 1 is a schematic diagram of a method for assisting in counting the working efficiency of an outpatient service according to the diagnosis system provided in embodiment 1 of the present invention;
fig. 2 is a schematic diagram of a system for assisting in counting the working efficiency of an outpatient service according to the diagnosis system according to embodiment 2 of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. The components of the embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations.
Example 1
As an embodiment, as shown in fig. 1, to solve the above technical problem, the present embodiment provides a method for assisting in counting the working efficiency of an outpatient according to a triage system, including:
acquiring basic business data of a hospital, wherein the basic business data comprise job title information, consulting room information, registration information of doctors and diagnosis and treatment time data of each patient;
The triage system is used for counting triage data; the triage data comprises first-stage triage data, second-stage triage data, third-stage triage data, doctor's data for patient switching and historical doctor's working efficiency quantification indexes; the statistics of the first-stage diagnosis data comprises registration information synchronously acquired from the HIS system as basic data of the first-stage diagnosis; the statistics of the second-stage diagnosis data comprises marking the priority and case difference of the patient by using the diagnosis dividing function of the diagnosis dividing system, and recording corresponding data; counting three-stage diagnosis data comprises counting the time of calling different patients by a doctor by using the number calling function of the diagnosis system; counting the doctor's visit data of the patient switching doctor, including using the second-stage diagnosis dividing function of the diagnosis dividing system, recording the data of other doctors of the patient switching, and marking the patient visit information; the quantitative index of the doctor working efficiency is the number of patients in unit time, such as the number of patients in each hour; the historical doctor working efficiency quantification index is the number of patients in doctor unit time;
Preprocessing basic business data and triage data of a hospital, and extracting to obtain numeric characteristic data; the characteristic data comprise doctor title data, diagnosis and treatment time data of a patient, conversion rate of primary diagnosis and treatment, conversion rate of secondary diagnosis and conversion rate of tertiary diagnosis and treatment;
constructing a sample data set by utilizing the characteristic data and historical doctor working efficiency quantification indexes;
Taking the characteristic data as factors, setting weight coefficients and intercepts of the factors, taking the preprocessed historical doctor working efficiency quantization index as output, and constructing a layered linear model of the doctor working efficiency;
Training the layered linear model by using a sample data set, and training out a weight coefficient of the factor for each doctor to obtain a doctor working efficiency evaluation model;
Acquiring current hospital basic service data and triage system statistics triage data, preprocessing, encoding and classifying, extracting to obtain characteristic data of a current doctor, and inputting the characteristic data of the current doctor into a doctor working efficiency evaluation model to obtain a current doctor working efficiency quantification index.
In the actual application process, basic data acquisition is performed from an HIS system (Hospital Information System ), and the specific steps are as follows: the title information of the doctor, the doctor's visit location information, the patient's registration information and the doctor's visit time to the patient are acquired.
Counting and recording by using registration information synchronously acquired from the HIS system as basic data of a first-stage diagnosis; marking and recording the priority and case difference of the patient by using the triage function of the triage system; counting the time of calling different patients by a doctor by using the number calling function of the triage system, and recording; using the second-stage triage function of the triage system, patient-switching data of other doctors is recorded, and patient-related information is marked, such as: patient priority, patient department, patient intent doctor, doctor to be switched to doctor, and reasons for patient switch to doctor (e.g. reasons for doctor job title difference, excessive waiting number and urgent report etc.).
Optionally, the patient visit information includes patient visit priority, patient visit department, patient intent visit doctor, doctor being switched to visit, and reason for patient to switch doctor.
Optionally, preprocessing basic business data and triage data of the hospital, classifying and encoding, including single-hot encoding job title data of doctors, nonlinear conversion of diagnosis and treatment time data of patients, and standardized processing of conversion rate data of triage at each level.
Optionally, performing the one-time thermal encoding on the job title data of the doctor includes classifying the job title data of the doctor into a plurality of grades, and assigning a value to the job title data of the doctor corresponding to each grade.
The assignment of the doctor's title is performed, e.g. assignment of 1 to the assistant physician, assignment of 2 to the physician, assignment of 3 to the secondary physician and assignment of 4 to the primary physician. For an assistant physician a feature column is created that has a value of 1 when the physician is an assistant physician, and 0 otherwise. Similarly, a feature column is created separately for other job titles. The original job title data is converted by using a single-hot encoding function (such as get_ dummies function of pandas library in Python) in the data processing tool, a corresponding single-hot encoding vector is generated for each doctor, and after conversion, the original single "doctor job title" column is replaced by four new columns, which respectively represent different job title levels.
Optionally, non-linearly transforming the patient's time of diagnosis data includes applying a natural logarithmic transformation or a Box-Cox transformation to each patient's time of diagnosis data point; assuming that the diagnosis and treatment time data of the patient is x, the constant is c, and the log is a logarithmic transformation function, the diagnosis and treatment time data of the patient after transformation is; Let λ be the transformation parameter, and confirm the best λ value by maximum likelihood estimation using Box-Cox function in SciPy library of Python.
For diagnosis and treatment time data of patients containing extreme values or not obeying the positive too-distributed, the distribution is more approximate to the distribution by using logarithmic transformation or Box-Cox transformation, and the influence of the extreme values is reduced. Or confirming the optimal lambda value by a maximum likelihood estimation mode so that the transformed data is closest to normal distribution. Maximum Likelihood Estimation (MLE) is a statistical method for estimating the values of model parameters that are able to maximally interpret or generate observed data. The basic principle of MLE is to find those model parameter values that can produce observation data with the highest probability.
The best lambda value is automatically found using a specialized library and function (e.g., boxcox function in the SciPy library of Python), and the data of 0 or negative values in the data is processed, e.g., a constant is added, so that all data values are positive, and the transformed data is used for training of the hierarchical linear model, before the transformation function is used.
Optionally, the conversion rate data of each grade of diagnosis is standardized by adopting a Z-score mode; setting the conversion rate of the first grade diagnosis asThe conversion rate of the second-stage diagnosis isThe conversion rate of the three-stage diagnosis isN is the total number of samples of conversion rate of each triage,For the conversion rate of the i-th fraction diagnosis,Is the conversion rate of the i-th fraction diagnosisThe value of the j-th sample among the n conversion samples,The mean value of the conversion rate of the i-th fraction diagnosis,Standard deviation of the conversion rate for the i-th fraction diagnosis,Normalized values for conversion of the ith fraction diagnosis, normalized values are used to characterizeAnd mean value ofAnd (b) the difference between (a) and (b) then:
；
；
。
The conversion rate of the first grade diagnosis is the proportion of patients who go from the first grade diagnosis to the actual diagnosis, the conversion rate of the second grade diagnosis is the proportion of patients who go from the second grade diagnosis to the actual diagnosis, and the conversion rate of the third grade diagnosis is the proportion of patients who go from the third grade diagnosis to the actual diagnosis.
The mean is used to measure the center position of the data, and the standard deviation is used to measure the degree of dispersion of the data. Using the normalized values obtainedThe corresponding values in the original data are replaced to train and analyze the model. The mean value of the data after Z-score standardization is 0, and the standard deviation is 1, so that the convergence rate in the layered linear model training process is improved, and the generalization capability of the model is improved.
Alternatively, a hierarchical linear model is built using the statsmodels library of Python.
Optionally, constructing a layered linear model of the doctor's working efficiency, setting the doctor's working efficiency as Y,In order to be an intercept term,The coefficients for the job title data of the doctor,Is a coefficient of diagnosis and treatment time data of a patient,Is the coefficient of the conversion rate of the first order diagnosis,Is the coefficient of the conversion rate of the second-stage diagnosis,The physician's job data is the conversion rate of the third-level diagnosisThe diagnosis and treatment time data of the patient are thatThe conversion rate of the first-stage diagnosis isThe conversion rate of the second-stage diagnosis isThe conversion rate of the three-stage diagnosis is，As an error term, then:
。
In the practical application process, the intercept term represents the baseline working efficiency when all input features are 0, and the coefficient of each feature data represents the change amount of the working efficiency of doctors when each unit is changed. The error term represents other factors that affect the efficiency of the physician in addition to the characteristic data.
Simplifying or adding random effect structures enables hierarchical linear model parameter adjustments, such as adding random slopes or adjusting random intercepts for only a portion of the variables.
The invention can improve the accuracy of the working efficiency of the statistical doctor, builds a layered linear model through careful feature selection and optimizes, improves the accuracy of the model for predicting the working efficiency of the doctor, and is beneficial to making more reasonable medical decisions according to the working efficiency of the doctor.
The invention provides an intuitive understanding of the extent to which each feature data affects the target variable (i.e., the physician's work efficiency) through a hierarchical linear model. For example, it is clear how factors such as job title, time of diagnosis and treatment of patients, and conversion rate of individual diagnosis affect the efficiency of doctor's work.
Example 2
Based on the same principle as the method described in embodiment 1, as shown in fig. 2, the present embodiment provides a system for assisting in counting the working efficiency of an outpatient service according to a triage system, which comprises an acquisition unit, a statistics unit, a preprocessing unit, a sample data set construction unit, a hierarchical linear model construction unit, a model training unit and a data processing unit;
the acquisition unit is used for acquiring basic business data of a hospital, including job title information, consulting room information, registration information of doctors and diagnosis and treatment time data of each patient;
The statistics unit is used for counting triage data by the triage system; the triage data comprises first-stage triage data, second-stage triage data, third-stage triage data, doctor's data for patient switching and historical doctor's working efficiency quantification indexes; the statistics of the first-stage diagnosis data comprises registration information synchronously acquired from the HIS system as basic data of the first-stage diagnosis; the statistics of the second-stage diagnosis data comprises marking the priority and case difference of the patient by using the diagnosis dividing function of the diagnosis dividing system, and recording corresponding data; counting three-stage diagnosis data comprises counting the time of calling different patients by a doctor by using the number calling function of the diagnosis system; counting the doctor's visit data of the patient switching doctor, including using the second-stage diagnosis dividing function of the diagnosis dividing system, recording the data of other doctors of the patient switching, and marking the patient visit information; the quantitative index of the doctor working efficiency is the number of patients in doctor unit time;
The pretreatment unit is used for preprocessing basic business data and triage data of the hospital and extracting and obtaining numerical characteristic data; the characteristic data comprise doctor title data, diagnosis and treatment time data of a patient, conversion rate of primary diagnosis and treatment, conversion rate of secondary diagnosis and conversion rate of tertiary diagnosis and treatment;
The sample data set construction unit is used for constructing a sample data set by utilizing the characteristic data and the historical doctor working efficiency quantification index;
The hierarchical linear model construction unit is used for taking the characteristic data as factors, setting weight coefficients and intercepts of the factors, taking the preprocessed historical doctor working efficiency quantization index as output, and constructing a hierarchical linear model of the doctor working efficiency;
the model training unit is used for training the layered linear model by utilizing the sample data set, and training out the weight coefficient of the factors for each doctor to obtain a doctor working efficiency evaluation model;
The data processing unit is used for acquiring the basic business data of the current hospital and the statistical triage data of the triage system, carrying out coding and classification after preprocessing, extracting the characteristic data of the current doctor, inputting the characteristic data of the current doctor into the working efficiency evaluation model of the doctor, and obtaining the working efficiency quantification index of the current doctor.
Optionally, the patient visit information includes patient visit priority, patient visit department, patient intent visit doctor, doctor being switched to visit, and reason for patient to switch doctor.
Optionally, preprocessing basic business data and triage data of the hospital, classifying and encoding, including single-hot encoding job title data of doctors, nonlinear conversion of diagnosis and treatment time data of patients, and standardized processing of conversion rate data of triage at each level.
Optionally, performing the one-time thermal encoding on the job title data of the doctor includes classifying the job title data of the doctor into a plurality of grades, and assigning a value to the job title data of the doctor corresponding to each grade.
Optionally, non-linearly transforming the patient's time of diagnosis data includes applying a natural logarithmic transformation or a Box-Cox transformation to each patient's time of diagnosis data point; assuming that the diagnosis and treatment time data of the patient is x, the constant is c, and the log is a logarithmic transformation function, the diagnosis and treatment time data of the patient after transformation is; Let λ be the transformation parameter, and confirm the best λ value by maximum likelihood estimation using Box-Cox function in SciPy library of Python.
Optionally, the conversion rate data of each grade of diagnosis is standardized by adopting a Z-score mode; setting the conversion rate of the first grade diagnosis asThe conversion rate of the second-stage diagnosis isThe conversion rate of the three-stage diagnosis isN is the total number of samples of conversion rate of each triage,For the conversion rate of the i-th fraction diagnosis,Is the conversion rate of the i-th fraction diagnosisThe value of the j-th sample among the n conversion samples,The mean value of the conversion rate of the i-th fraction diagnosis,Standard deviation of the conversion rate for the i-th fraction diagnosis,Normalized values for conversion of the ith fraction diagnosis, normalized values are used to characterizeAnd mean value ofAnd (b) the difference between (a) and (b) then:
；
；
。
alternatively, a hierarchical linear model is built using the statsmodels library of Python.
Optionally, constructing a layered linear model of the doctor's working efficiency, setting the doctor's working efficiency as Y,In order to be an intercept term,The coefficients for the job title data of the doctor,Is a coefficient of diagnosis and treatment time data of a patient,Is the coefficient of the conversion rate of the first order diagnosis,Is the coefficient of the conversion rate of the second-stage diagnosis,The physician's job data is the conversion rate of the third-level diagnosisThe diagnosis and treatment time data of the patient are thatThe conversion rate of the first-stage diagnosis isThe conversion rate of the second-stage diagnosis isThe conversion rate of the three-stage diagnosis is，As an error term, then:
。
The above is only a preferred embodiment of the present invention, and is not intended to limit the present invention, but various modifications and variations can be made to the present invention by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (8)
1. The method for assisting in counting the working efficiency of the outpatient according to the triage system is characterized by comprising the following steps:
acquiring basic business data of a hospital, wherein the basic business data comprise job title information, consulting room information, registration information of doctors and diagnosis and treatment time data of each patient;
The triage system is used for counting triage data; the triage data comprises first-stage triage data, second-stage triage data, third-stage triage data, doctor's data for patient switching and historical doctor's working efficiency quantification indexes; the statistics of the first-stage diagnosis data comprises registration information synchronously acquired from the HIS system as basic data of the first-stage diagnosis; the statistics of the second-stage diagnosis data comprises marking the priority and case difference of the patient by using the diagnosis dividing function of the diagnosis dividing system, and recording corresponding data; counting three-stage diagnosis data comprises counting the time of calling different patients by a doctor by using the number calling function of the diagnosis system; counting the doctor's visit data of the patient switching doctor, including using the second-stage diagnosis dividing function of the diagnosis dividing system, recording the data of other doctors of the patient switching, and marking the patient visit information; the quantitative index of the doctor working efficiency is the number of patients in doctor unit time; the patient visit information comprises patient visit priority, patient visit departments, patient intention visit doctors, doctors who are switched to visit and reasons for switching doctors between patients;
Preprocessing basic business data and triage data of a hospital, and extracting to obtain numeric characteristic data; the characteristic data comprise doctor title data, diagnosis and treatment time data of a patient, conversion rate of primary diagnosis and treatment, conversion rate of secondary diagnosis and conversion rate of tertiary diagnosis and treatment;
constructing a sample data set by utilizing the characteristic data and historical doctor working efficiency quantification indexes;
Taking the characteristic data as factors, setting weight coefficients and intercepts of the factors, taking the preprocessed historical doctor working efficiency quantization index as output, and constructing a layered linear model of the doctor working efficiency;
Training the layered linear model by using a sample data set, and training out a weight coefficient of the factor for each doctor to obtain a doctor working efficiency evaluation model;
Acquiring current hospital basic service data and triage system statistics triage data, preprocessing, encoding and classifying, extracting to obtain characteristic data of a current doctor, and inputting the characteristic data of the current doctor into a doctor working efficiency evaluation model to obtain a current doctor working efficiency quantification index.
2. The method for assisting in counting the working efficiency of an outpatient service according to the triage system according to claim 1, wherein the preprocessing of basic business data and triage data of a hospital is performed for classification and coding, including single-hot coding of job title data of a doctor, nonlinear conversion of diagnosis and treatment time data of a patient, and standardized processing of data of triage conversion rate.
3. The method of assisting in the statistics of the working efficiency of an outpatient service according to the triage system according to claim 2, wherein the step of performing the single-hot encoding of the job title data of the doctor includes dividing the job title data of the doctor into a plurality of grades, and assigning a value to the job title data of the doctor corresponding to each grade.
4. The method of assisting in the statistics of the working efficiency of an outpatient service according to claim 2, wherein the nonlinear transformation of the patient's time of diagnosis data includes applying a natural logarithmic transformation or a Box-Cox transformation to each patient's time of diagnosis data point; assuming that the diagnosis and treatment time data of the patient is x, the constant is c, and the log is a logarithmic transformation function, the diagnosis and treatment time data of the patient after transformation is; Let λ be the transformation parameter, and confirm the best λ value by maximum likelihood estimation using Box-Cox function in SciPy library of Python.
5. The method for assisting in counting the working efficiency of an outpatient service according to the triage system according to claim 2, wherein the data of the conversion rate of each triage is standardized by adopting a Z-score mode; setting the conversion rate of the first grade diagnosis asThe conversion rate of the second-stage diagnosis isThe conversion rate of the three-stage diagnosis isN is the total number of samples of conversion rate of each triage,For the conversion rate of the i-th fraction diagnosis,Is the conversion rate of the i-th fraction diagnosisThe value of the j-th sample among the n conversion samples,The mean value of the conversion rate of the i-th fraction diagnosis,Standard deviation of the conversion rate for the i-th fraction diagnosis,Normalized values for conversion of the ith fraction diagnosis, normalized values are used to characterizeAnd mean value ofAnd (b) the difference between (a) and (b) then:
；
；
。
6. The method of assisting in the statistics of the operating efficiency of an outpatient service according to claim 1, wherein the hierarchical linear model is built using a statsmodels library of Python.
7. The method for assisting in counting the working efficiency of an outpatient service according to claim 1, wherein a hierarchical linear model of the working efficiency of the doctor is constructed, the working efficiency of the doctor is set to be Y,In order to be an intercept term,The coefficients for the job title data of the doctor,Is a coefficient of diagnosis and treatment time data of a patient,Is the coefficient of the conversion rate of the first order diagnosis,Is the coefficient of the conversion rate of the second-stage diagnosis,The physician's job data is the conversion rate of the third-level diagnosisThe diagnosis and treatment time data of the patient are thatThe conversion rate of the first-stage diagnosis isThe conversion rate of the second-stage diagnosis isThe conversion rate of the three-stage diagnosis is，As an error term, then:
。
8. The system for assisting in counting the working efficiency of the outpatient service doctor by the triage system is characterized by comprising an acquisition unit, a counting unit, a preprocessing unit, a sample data set construction unit, a layered linear model construction unit, a model training unit and a data processing unit;
the acquisition unit is used for acquiring basic business data of a hospital, including job title information, consulting room information, registration information of doctors and diagnosis and treatment time data of each patient;
The statistics unit is used for counting triage data by the triage system; the triage data comprises first-stage triage data, second-stage triage data, third-stage triage data, doctor's data for patient switching and historical doctor's working efficiency quantification indexes; the statistics of the first-stage diagnosis data comprises registration information synchronously acquired from the HIS system as basic data of the first-stage diagnosis; the statistics of the second-stage diagnosis data comprises marking the priority and case difference of the patient by using the diagnosis dividing function of the diagnosis dividing system, and recording corresponding data; counting three-stage diagnosis data comprises counting the time of calling different patients by a doctor by using the number calling function of the diagnosis system; counting the doctor's visit data of the patient switching doctor, including using the second-stage diagnosis dividing function of the diagnosis dividing system, recording the data of other doctors of the patient switching, and marking the patient visit information; the quantitative index of the doctor working efficiency is the number of patients in doctor unit time; the patient visit information comprises patient visit priority, patient visit departments, patient intention visit doctors, doctors who are switched to visit and reasons for switching doctors between patients;
The pretreatment unit is used for preprocessing basic business data and triage data of the hospital and extracting and obtaining numerical characteristic data; the characteristic data comprise doctor title data, diagnosis and treatment time data of a patient, conversion rate of primary diagnosis and treatment, conversion rate of secondary diagnosis and conversion rate of tertiary diagnosis and treatment;
The sample data set construction unit is used for constructing a sample data set by utilizing the characteristic data and the historical doctor working efficiency quantification index;
The hierarchical linear model construction unit is used for taking the characteristic data as factors, setting weight coefficients and intercepts of the factors, taking the preprocessed historical doctor working efficiency quantization index as output, and constructing a hierarchical linear model of the doctor working efficiency;
the model training unit is used for training the layered linear model by utilizing the sample data set, and training out the weight coefficient of the factors for each doctor to obtain a doctor working efficiency evaluation model;
The data processing unit is used for acquiring the basic business data of the current hospital and the statistical triage data of the triage system, carrying out coding and classification after preprocessing, extracting the characteristic data of the current doctor, inputting the characteristic data of the current doctor into the working efficiency evaluation model of the doctor, and obtaining the working efficiency quantification index of the current doctor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410925309.5A CN118471454B (en) | 2024-07-11 | 2024-07-11 | Method and system for assisting in statistics of working efficiency of outpatient service according to triage system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410925309.5A CN118471454B (en) | 2024-07-11 | 2024-07-11 | Method and system for assisting in statistics of working efficiency of outpatient service according to triage system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118471454A CN118471454A (en) | 2024-08-09 |
| CN118471454B true CN118471454B (en) | 2024-09-03 |
Family
ID=92166995
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410925309.5A Active CN118471454B (en) | 2024-07-11 | 2024-07-11 | Method and system for assisting in statistics of working efficiency of outpatient service according to triage system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118471454B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN119168162A (en) * | 2024-11-11 | 2024-12-20 | 四川互慧软件有限公司 | Multi-target task-based outpatient resource prediction method and system |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113571167A (en) * | 2021-07-28 | 2021-10-29 | 重庆橡树信息科技有限公司 | Rapid triage system based on configured scoring knowledge model |
| CN114550889A (en) * | 2022-02-21 | 2022-05-27 | 南通市妇幼保健院（南通市儿童医院） | Method and system for improving efficiency of consultation and inquiry of pediatricians |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021178731A1 (en) * | 2020-03-04 | 2021-09-10 | Karl Denninghoff | Neurological movement detection to rapidly draw user attention to search results |
-
2024
- 2024-07-11 CN CN202410925309.5A patent/CN118471454B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113571167A (en) * | 2021-07-28 | 2021-10-29 | 重庆橡树信息科技有限公司 | Rapid triage system based on configured scoring knowledge model |
| CN114550889A (en) * | 2022-02-21 | 2022-05-27 | 南通市妇幼保健院（南通市儿童医院） | Method and system for improving efficiency of consultation and inquiry of pediatricians |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118471454A (en) | 2024-08-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US7925603B1 (en) | System for measuring and improving patient flow in health care systems | |
| CN110148440B (en) | A medical information query method | |
| Alfiero et al. | Intellectual capital-based performance improvement: a study in healthcare sector | |
| Ghanes et al. | A comprehensive simulation modeling of an emergency department: A case study for simulation optimization of staffing levels | |
| CN109754886A (en) | Therapeutic scheme intelligent generating system, method and readable storage medium storing program for executing, electronic equipment | |
| CN110119432B (en) | Data processing method for medical platform | |
| US20160328439A1 (en) | Computer-assisted method for adaptive, risk-based monitoring of clinical studies | |
| CN111695836B (en) | Clinical trial online operation management and control integrated system | |
| CN118471454B (en) | Method and system for assisting in statistics of working efficiency of outpatient service according to triage system | |
| Huang et al. | Using six sigma, lean, and simulation to improve the phlebotomy process | |
| Muhsin et al. | Hospital performance improvement through the hospital information system design | |
| Yawe | Hospital performance evaluation in Uganda: a super-efficiency data envelope analysis model | |
| CN118411069A (en) | Scientific and technological innovation quantitative evaluation method | |
| CN118692643A (en) | A blood management decision-making support system | |
| CN113449971A (en) | Inspection task assignment method based on clinical test index data analysis result | |
| Soorapanth et al. | Towards a framework for evaluating the costs and benefits of simulation modelling in healthcare | |
| Yadav | Machine Learning for Predicting Healthcare Policy Outcomes: Utilizing Machine Learning to Forecast the Outcomes of Proposed Healthcare Policies on Population Health and Economic Indicators | |
| CN111815487A (en) | Health education assessment method, device and medium based on deep learning | |
| CN113919891B (en) | A standard cost accounting system and method for medical service items based on time-based activity-based costing | |
| CN113642669B (en) | Feature analysis-based fraud prevention detection method, device, equipment and storage medium | |
| Battu et al. | Patient flow optimization in an emergency department using simpy-based simulation modeling and analysis: a case study | |
| CN115798697A (en) | County-area health community diagnosis and treatment equipment management system based on artificial intelligence algorithm | |
| WO2002052278A1 (en) | Clinical examination precision guarantee system | |
| CN114066207A (en) | Performance assessment method and system based on subjective and objective combination | |
| CN117423475B (en) | Department infection risk identification method and system applied to hospital scene |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |