Search

CN-122025050-A - Medical service quality big data analysis system

CN122025050ACN 122025050 ACN122025050 ACN 122025050ACN-122025050-A

Abstract

The invention discloses a medical service quality big data analysis system, which relates to the technical field of medical management and comprises a data collection module, a data processing module, a data analysis module and a user interface, wherein the data collection module is used for collecting basic information, operation records, medication records, diagnosis information and postoperative recovery information of patients in hospitals and storing the basic information, the operation records, the medication records, the diagnosis information and the postoperative recovery information by a storage module, the data processing module is used for cleaning and finishing the collected data, the data analysis module is used for adjusting model parameters through an optimization algorithm so that the model predicts postoperative recovery time and medication conditions, and the user interface is used for inquiring analysis results. By knowing the deviation of the actual recovery time and the predicted time, the hospital can more reasonably allocate medical resources, by analyzing the error of the recovery time, the hospital can identify risk factors possibly causing recovery delay, take measures to reduce the risks, and more accurate recovery time prediction can help doctors to make more personalized postoperative care and recovery plans for patients.

Inventors

  • WANG YANMING

Assignees

  • 河南慧云信息科技有限公司

Dates

Publication Date
20260512
Application Date
20260128

Claims (9)

  1. 1. A medical quality of service big data analysis system, the analysis system comprising: the data collection module is used for collecting basic information, operation records, medication records, diagnosis information and postoperative recovery information of patients in hospitals and storing the basic information, the operation records, the medication records, the diagnosis information and the postoperative recovery information by the storage module; The data processing module is used for cleaning and arranging the collected data, processing missing values and abnormal values, ensuring the accuracy and the integrity of the data, carrying out standardization or normalization processing on the data so as to eliminate the dimensional influence among different features, selecting the features related to the postoperative recovery time from the basic information and the operation record of a patient, selecting the features related to the medication condition from the diagnosis information and the medication information, and realizing the statistical analysis, wherein the data are used as the input of a model, and the selected features are used as the input variables of the model; the data analysis module is used for selecting a machine learning algorithm to construct a prediction model, wherein the algorithm is linear regression, training the model by using historical data, adjusting model parameters by an optimization algorithm, enabling the model to predict post-operation recovery time and medication condition, evaluating the trained model by using test data, and calculating the accuracy, precision and recall index of the model to evaluate the prediction capability of the model; and the user interface is used for inquiring the analysis result.
  2. 2. The medical service quality big data analysis system of claim 1, wherein the patient basic information in the data collection module comprises age, sex, weight and height data, the operation records comprise operation type, operation time, anesthesia mode and intra-operation medication information, the medication records comprise medication names, doses, medication frequency and medication routes, the diagnosis information comprises disease names and severity, and the postoperative recovery information comprises discharge time, review time and complications record.
  3. 3. The medical service quality big data analysis system of claim 1, wherein the data processing module comprises a missing value processing unit, an abnormal value detecting unit, a data standardization unit, a characteristic engineering unit and a data discretization unit; The missing value processing unit is used for processing the missing value in a deleting, filling or interpolation method mode; The abnormal value detection unit is used for identifying abnormal values by using a statistical method and correcting or deleting the detected abnormal values; the data standardization unit is used for carrying out standardization treatment on data with different dimensions so as to enable the data to have the same dimensions, wherein the standardization method is minimum-maximum standardization; the characteristic engineering unit extracts characteristics from the original data, including basic characteristics of a patient, disease types and medicine types, creates new characteristics, and converts type variables into numerical variable; the data discretization unit discretizes the continuous variable into the classified variable according to the requirement.
  4. 4. The medical service quality big data analysis system of claim 1, wherein the data analysis module comprises a postoperative recovery period analysis system, and the postoperative recovery period analysis system comprises a data acquisition unit, a data processing unit, a model training unit and a result output unit; The data acquisition unit acquires basic information of a patient, operation records and postoperative recovery information from the storage module; the data processing unit is used for carrying out standardization or normalization processing on the numerical value type characteristics to create new characteristics, wherein the characteristics are combination or interaction items of the existing characteristics, and the characteristics related to the postoperative recovery time are selected; the model training unit is used for training a model by using historical data and predicting the postoperative recovery time; the result output unit compares the predicted postoperative recovery time with the actual recovery time, calculates an error rate, and the error rate mathematical formula is as follows: the prediction error rate= (prediction recovery time-actual recovery time)/actual recovery time×100%.
  5. 5. The medical quality of service big data analysis system of claim 4, wherein the data set division is used to divide the data set into a training set, a validation set and a test set, training is performed with 80% of the data, 10% of the data is used for validation, and 10% of the data is used for testing; The training set is used for training the model, the verification set is used for adjusting the model parameters and preventing overfitting, and the test set is used for evaluating the performance of the model; The feature selection is used for selecting features related to the postoperative recovery time from the original data; tag encoding is used to classify variables.
  6. 6. The medical service quality big data analysis system of claim 4, wherein the training step of the model training unit is as follows: selecting and training a regression model for prediction, wherein the model is linear regression, and the linear regression aims at finding the best fit straight line so as to minimize the error between a predicted value and an actual value; Defining a loss function to measure the difference between the predicted value and the actual value, and finding the optimal model parameter, wherein the loss function is mean square error; After training the model, evaluating the performance of the model on a test set, wherein evaluation indexes comprise R2 fraction and root mean square error; Model deployment, namely saving the trained model, developing an API interface, allowing a user to input new patient data and acquiring a predicted value of postoperative recovery time.
  7. 7. The medical service quality big data analysis system according to claim 1, wherein the postoperative recovery period analysis system comprises a time-reason analysis system, wherein the time-reason analysis system comprises a data collection and arrangement unit, a feature selection and preprocessing unit, an analysis model establishment unit, a model training and verification unit and a reason analysis unit; the data collecting and arranging unit is used for collecting operation records and medication record information; The characteristic selection and preprocessing unit extracts key characteristics from the operation record and the medication record, cleans and standardizes the data, and ensures the consistency and accuracy of the data; The analysis model building unit is used for analyzing by utilizing a logistic regression model and judging whether the analysis model is caused by operation; The model training and verifying unit is used for training the model by using historical data, evaluating the performance of the model by a cross verifying method, adjusting model parameters and optimizing the prediction capability of the model; The reason analysis unit inputs the patient data with longer actual recovery time into a trained model, analyzes the result output by the model, and judges whether the patient data is a problem caused by operation or medication according to the prediction result of the model and the combination of the operation record and the medication record.
  8. 8. The medical service quality big data analysis system of claim 1, wherein the data analysis module comprises a medication condition comparison analysis system, and the medication condition comparison analysis system comprises a data collection unit, a data processing unit, a model training unit and a monitoring and evaluation unit; the data collection unit is used for obtaining basic information of a patient, diagnosis information and medication information from the storage module, wherein the diagnosis information comprises disease names and severity, and the medication information comprises medication names, doses and medication frequency; the data processing unit is responsible for cleaning and converting the acquired data; The model training unit is used for training a classification model by using historical data, wherein the model is a random forest so as to predict the drug dosage; the monitoring and evaluating unit compares the actual medication condition with the recommended medication dosage, calculates the medication accuracy, and the medication accuracy= (correct medication times/total medication times) multiplied by 100%.
  9. 9. The medical service quality big data analysis system of claim 8, wherein the model training steps in the medication condition comparison analysis system are as follows: Step one, acquiring data including disease name, severity, age, weight, sex, current medication and target variable; feature coding, namely converting all features into a numerical form in an SVM model; Training an SVM model by using a historical data set, wherein the data set comprises characteristic vectors of a plurality of patients and corresponding medicine doses, and the SVM model learns how to predict the medicine doses according to the input characteristics; And step four, model evaluation and prediction, namely, predicting the drug dosage by using data of a new patient after the model is trained, and substituting the characteristics into the trained SVM model to obtain the predicted drug dosage.

Description

Medical service quality big data analysis system Technical Field The invention relates to the technical field related to medical management, in particular to a medical service quality big data analysis system. Background With the continuous progress of medical technology and the deep advancement of medical system reform, the demands of medical institutions for fine management of service quality are becoming urgent. At present, massive patient-related data including basic patient information, operation records, medication records, diagnosis information, postoperative recovery information and the like are generated in the medical service process, and the data contains key information closely related to medical service quality and patient recovery effect, so that the data is an important resource for optimizing medical service and improving diagnosis and treatment level. However, there are still a number of deficiencies in the processing and utilization of such medical data by existing medical institutions. In the data management level, medical data of a plurality of medical institutions are stored in different business systems in a scattered mode, the data formats are not uniform and weak in relevance, a data island is formed, and therefore the data are difficult to integrate in a centralized mode and analyze comprehensively. Meanwhile, medical data has diversity and complexity characteristics, and has the problems of missing values, abnormal values and the like, the existing data processing mode lacks systematic cleaning, standardization and characteristic engineering means, the data accuracy and the integrity are difficult to guarantee, and reliable support cannot be provided for subsequent analysis. Therefore, it is necessary to provide a medical service quality big data analysis system to solve the above problems. Disclosure of Invention Aiming at the situation, in order to overcome the defects of the prior art, the invention provides a medical service quality big data analysis system, which solves the problems that most medical institutions lack of data format non-uniformity and weak relevance to form a 'data island', so that centralized integration and comprehensive analysis of data are difficult. In order to achieve the above purpose, the technical scheme adopted by the invention is as follows: a medical quality of service big data analysis system, the analysis system comprising: the data collection module is used for collecting basic information, operation records, medication records, diagnosis information and postoperative recovery information of patients in hospitals and storing the basic information, the operation records, the medication records, the diagnosis information and the postoperative recovery information by the storage module; The data processing module is used for cleaning and arranging the collected data, processing missing values and abnormal values, ensuring the accuracy and the integrity of the data, carrying out standardization or normalization processing on the data so as to eliminate the dimensional influence among different features, selecting the features related to the postoperative recovery time from the basic information and the operation record of a patient, selecting the features related to the medication condition from the diagnosis information and the medication information, and realizing the statistical analysis, wherein the data are used as the input of a model, and the selected features are used as the input variables of the model; the data analysis module is used for selecting a machine learning algorithm to construct a prediction model, wherein the algorithm is linear regression, training the model by using historical data, adjusting model parameters by an optimization algorithm, enabling the model to predict post-operation recovery time and medication condition, evaluating the trained model by using test data, and calculating the accuracy, precision and recall index of the model to evaluate the prediction capability of the model; and the user interface is used for inquiring the analysis result. Preferably, the patient basic information in the data collection module comprises age, sex, weight and height data, the operation records comprise operation type, operation time, anesthesia mode and intra-operation medication information, the medication records comprise medication names, doses, medication frequency and medication routes, the diagnosis information comprises disease names and severity, and the postoperative recovery information comprises discharge time, review time and complications records. Preferably, the data processing module comprises a missing value processing unit, an abnormal value detecting unit, a data normalizing unit, a characteristic engineering unit and a data discretizing unit; The missing value processing unit is used for processing the missing value in a deleting, filling or interpolation method mode; The abnormal value detection unit is used f