Hospital stay optimization system, method, and corresponding computer device and storage medium

Abstract

The application discloses a hospitalization day optimization system and method, and corresponding computer equipment and storage medium, wherein the system comprises a data acquisition module for acquiring patient data; a clustering module for clustering patients according to main diagnosis coding and DRG grouping coding; a grouping module for grouping patients according to the attending physicians of the patients for each patient group; an abnormal patient group determination module for determining, for each patient group with the same main diagnosis coding, a patient group with a significant difference between the average hospitalization days as an abnormal patient group; an abnormal patient group determination module for determining, for each abnormal patient group, a patient group with a significant difference in hospitalization days as an abnormal patient group; and a hospitalization day optimization value determination module for calculating, for each abnormal patient group, the average hospitalization days of other patient groups except the abnormal patient group as the hospitalization day optimization value of the corresponding abnormal patient group. The application can improve the turnover efficiency of beds.

Description

Technical Field

[0001] This application relates to the field of electronic digital data processing, and more particularly to a system for optimizing hospital stay duration. This application also relates to a method for optimizing hospital stay duration, as well as corresponding computer equipment and computer-readable storage media. Background Technology

[0002] For hospitals, bed resources are typically a critical medical resource in their operations, especially in first-tier cities. Insufficient bed capacity often restricts hospital service capacity, increases waiting times for critically ill patients, and can even delay timely treatment. Simply reducing the length of hospital stays would lead to a decline in the quality of medical services, an outcome hospitals do not want to see. Therefore, rationally determining the length of stay for different diseases and improving the turnover rate of hospital beds is an important issue in the construction and development of modern hospitals.

[0003] Meanwhile, the recovery curves for different diseases are different. Some diseases require significantly less medical care in the later stages. Driven by DRG (Diagnosis Related Groups) or DIP payment reforms, hospitals are scientifically and rationally reducing the number of bed days for different diseases in order to reduce the consumption of medical resources and increase daily bed revenue. This is also one of the ways for hospitals to expand profits and increase efficiency. Summary of the Invention

[0004] This invention provides a system, method, and corresponding computer equipment and storage medium for optimizing hospital stay duration, which can reasonably optimize the length of hospital stay and improve the turnover efficiency of hospital beds.

[0005] In a first aspect of the present invention, a system for optimizing hospital stay duration is provided, the system comprising:

[0006] The data acquisition module is used to acquire patient data. Each patient's data includes information about the patient, attending physician, primary diagnosis code, DGR group code, and length of hospital stay.

[0007] The grouping module is used to group patients according to their primary diagnosis code and DRG grouping code, with patients having the same primary diagnosis code and DRG grouping code grouped into the same patient group.

[0008] The grouping module is used to group patients according to their attending physicians for each patient group, with patients with the same attending physician being grouped together.

[0009] The abnormal patient group identification module is used to identify patient groups with significant differences in the mean length of hospital stay among various patient groups with the same primary diagnosis code as abnormal patient groups.

[0010] The abnormal patient group identification module is used to identify patient groups with significant differences in length of hospital stay for each abnormal patient group.

[0011] The module for determining the optimal length of hospital stay is used to calculate the average length of hospital stay of other patient groups besides the abnormal patient group for each abnormal patient group as the optimal length of hospital stay for the corresponding abnormal patient group.

[0012] In a second aspect of the present invention, a method for optimizing length of hospital stay is provided, the method comprising:

[0013] Acquire patient data, each patient's data including information about the patient, attending physician, primary diagnosis code, DGR group code, and length of hospital stay;

[0014] Patients are grouped according to their primary diagnosis code and DRG grouping code, with patients having the same primary diagnosis code and DRG grouping code grouped into the same patient group.

[0015] For each patient group, patients are grouped according to their attending physician, with patients with the same attending physician being grouped together.

[0016] For patient groups with the same primary diagnosis code, those groups with significant differences in the mean length of hospital stay are identified as abnormal patient groups.

[0017] For each abnormal patient group, the patient group with a significant difference in length of hospital stay was identified as the abnormal patient group;

[0018] For each abnormal patient group, the average length of hospital stay of other patient groups is calculated as the optimized length of hospital stay for the corresponding abnormal patient group.

[0019] In a third aspect of the invention, a computer device is provided, including a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the functions of a system according to a first aspect of the invention or the steps of a method according to a second aspect of the invention.

[0020] According to a fourth aspect of the present invention, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the functions of a system according to a first aspect of the present invention or the steps of a method according to a second aspect of the present invention.

[0021] According to this invention, by grouping patients with the same primary diagnosis code and DRG grouping code into the same patient group; within each patient group, patients with the same attending physician are grouped into the same patient subgroup; for each patient group with the same primary diagnosis code, patient subgroups with significant differences in the mean length of hospital stay are identified as abnormal patient subgroups; for each abnormal patient subgroup, patient subgroups with significant differences in the length of hospital stay are identified as abnormal patient subgroups; for each abnormal patient subgroup, the mean length of hospital stay of other patient subgroups is calculated as the optimized length of hospital stay value for the corresponding abnormal patient subgroup. This allows identification of which physicians within the abnormal patient group exhibit significant abnormalities in their length of hospital stay, enabling reasonable optimization of the length of hospital stay during the treatment process of these physicians. This determines the reasonable length of hospital stay value for the corresponding disease, providing guidance for future inpatient treatment of this disease, thereby improving bed turnover efficiency and reducing medical resource consumption.

[0022] Other features and advantages of the present invention will become clearer after reading the detailed description of the embodiments of the present invention in conjunction with the accompanying drawings. Attached Figure Description

[0023] Figure 1 This is a block diagram of an embodiment of the system according to the present invention;

[0024] Figure 2 This is a flowchart of an embodiment of the method according to the present invention.

[0025] For clarity, these figures are schematic and simplified, showing only the details necessary for understanding the invention, while omitting other details. Detailed Implementation

[0026] The embodiments and examples of the present invention will now be described in detail with reference to the accompanying drawings.

[0027] The scope of the invention will become apparent from the detailed description given below. However, it should be understood that while the detailed description and specific examples illustrate preferred embodiments of the invention, they are given for illustrative purposes only.

[0028] Figure 1 A block diagram of a preferred embodiment of the hospital stay optimization system according to the present invention is shown.

[0029] The data acquisition module 102 is used to acquire patient data. Through the hospital's medical record system and DRG grouping results data, the treatment records of each patient can be obtained, such as patient number, attending physician number, length of hospital stay, primary diagnosis code, primary surgery code, DRG grouping code, etc.

[0030] The grouping module 104 is used to group patients according to their primary diagnostic code and DRG grouping code. Patients with the same primary diagnostic code and DRG grouping code are grouped into the same patient group. Based on the principles of DRG, patients in each patient group should have the same clinical characteristics and consumption of medical resources.

[0031] For example, the dataset in Table 1 below contains data on nine patients with a primary diagnosis code of I25.103. Based on the primary diagnosis code and DRG grouping code, this data is divided into two patient groups. In this specification, the terms "doctor" and "attending physician" are used interchangeably.

[0032] Table 1

[0033]

[0034] Grouping module 106 is used to group patients according to their attending physicians for each patient group. Patients with the same attending physician are grouped into the same patient group. In the example given in Table 1 above, all patients in patient group 1 have attending physician D, and therefore are divided into only one patient group, namely patient group 1. Similarly, patients in patient group 2 are divided into three patient groups, namely patient groups 2-4, as shown in the table below:

[0035]

[0036]

[0037] The abnormal patient group identification module 108 is used to identify patient groups with significant differences in the mean length of hospital stay among various patient groups with the same primary diagnosis code as abnormal patient groups.

[0038] In this embodiment, the abnormal patient population was identified using analysis of variance (also known as the F-test).

[0039] An F-test was performed on the length of hospital stay data for the patient group. The F-test can be used to determine whether the main factors affecting the length of hospital stay are caused by the subjective characteristics of doctors or by the characteristics of the disease itself.

[0040] For patient groups with the same primary diagnosis code, the F-value for the length of hospital stay for each patient group is first determined, where...

[0041] in:

[0042] Between-group variance =

[0043] ∑Number of cases treated by doctors * (Average length of hospital stay for doctors - Average length of hospital stay for the entire patient population) 2

[0044] Between-group degrees of freedom = number of doctors in the patient group - 1

[0045] Within-group variance = ∑(Patient length of hospital stay - Average length of hospital stay for corresponding physicians) 2

[0046] Intragroup freedom = Number of patients in the patient group – Number of doctors in the patient group

[0047] Then, by consulting the F-test critical table, the significance value Fp corresponding to each F value is determined.

[0048] The significance level (Fp) of the F-test is determined. If Fp < the threshold, then the doctor's subjective factors are considered the determining factor for the corresponding length of hospital stay. Conversely, the characteristics of the disease itself determine the length of hospital stay for the corresponding patient. The Fp threshold can be adjusted according to the actual situation. If only optimization of excessively long hospital stays is needed, it is a one-sided test, and the threshold can be selected as 0.1. If optimization of excessively short hospital stays is also needed, it is a two-sided test, and the threshold can be selected as 0.05. Patients with F significance values ​​below the threshold (e.g., 0.1) are identified as an abnormal patient group.

[0049] For the patient groups shown in Table 1 above, an F-test analysis was performed on each patient group. There are two patient groups, corresponding to two F-values. The significance value Fp of each group can be obtained by looking up the table below:

[0050]

[0051] Analysis of variance (ANOVA) can be used to determine which doctor groups show significant differences in the mean length of hospital stay across different diseases if no further analysis is needed. However, if significant differences exist, it's necessary to analyze which doctor groups show significant differences and which do not. In the example above, for patient groups with a Fp value less than 0.1, doctor subjective behavior significantly impacts the length of hospital stay, allowing for optimization. Patient group 2 has an Fp value less than 0.1, necessitating further analysis, while patient group 1 has an Fp value greater than 0.1, so further analysis is not recommended. It's important to note that in practice, at least seven data points are required for statistical significance for each patient group.

[0052] The abnormal patient group identification module 110 is used to identify the patient group with a significant difference in length of hospital stay as the abnormal patient group for each abnormal patient group.

[0053] In this embodiment, the abnormal patient group was determined using multiple comparison methods, such as the LSD (Least Significant Difference) method. Analysis of variance (ANOVA) can indicate whether the differences between population means are significant; that is, it only shows that the means are not all equal, but it cannot specifically identify which means have significant differences. A t-test can only indicate whether the difference between two means is significant. Comparing m means requires performing (m / 2) = m(m-1) / 2 t-tests individually, which is not only labor-intensive but also prone to error. Multiple comparison methods can overcome these shortcomings. For example, the LSD method is essentially a pairwise t-test, but unlike other methods, it uses the joint variance of all samples to estimate the standard error of the mean difference, rather than comparing the joint variance of two samples, while ensuring homogeneity of variance.

[0054] The LSD-t method uses the basic logic of the t-test. Its core idea is to find a new statistic (i.e., the LSD-t value) to replace the t-statistic (i.e., the t-value) for the t-test while keeping the significance level unchanged. Therefore, it is essentially still a t-test. However, compared with the independent samples t-test, the LSD-t method makes adjustments in terms of the statistic (LSD-t) and degrees of freedom (v). It makes full use of sample information, and is therefore more accurate and reliable.

[0055] The LSD-t value is calculated using the following formula:

[0056] v = v 组内

[0057]

[0058] in, The difference in mean length of hospital stay between the two patient groups participating in the pairwise comparison; represents the standard error of the two patient groups participating in pairwise comparisons; v represents the degrees of freedom of the LSD-t test, and its value is equal to the within-group degrees of freedom v. 组内 =Number of doctors in the patient group - 1; MS 组内 n is the within-group variance; i n j The number of patients in each of the two patient groups participating in the pairwise comparison is represented by i and j, which are the group numbers.

[0059] After obtaining the t-value of LSD, look up the corresponding p-value in the t-distribution critical value table, which is the significance level of the t-test. When p is less than the threshold, for example, 0.1, it is considered that there is a significant difference between the means of the two groups.

[0060] In the list of significance level values for pairwise grouping, count the number of groups that are significantly different from other groups for each group, that is, the number of statistical occurrences where p < 0.1, which represents the number of times the length of hospital stay of this doctor and other doctors shows significant abnormalities. Sort them in descending order according to the number of occurrences, and determine one or more patient groups with the highest number of occurrences as abnormal patient groups. For example, patient groups ranked in the top 20% and with a value greater than 2 can be considered abnormal patient groups (the length of hospital stay of the corresponding doctor is significantly abnormal compared to that of other doctors).

[0061] Continuing with the above example, perform a multiple comparison test on patient group 2. After the multiple comparison method, obtain the significance between each doctor (patient group) under the same patient group. There are only three doctors, A, B, and C (corresponding to patient groups 2 to 4) under patient group 2. The results of the multiple comparison method are shown in the following table:

[0062] A P(A, B) = 0.02 P(A, C) = 0.30 B P(B, A) = 0.02 P(B, C) = 0.01 C P(C, A) = 0.30 P(C, B) = 0.01

[0063] Among them, p(A,B) represents the significance level calculated between group A and group B after the multiple comparison method, and so on.

[0064] When the threshold is 0.1, sort the number of times the significance level value p of the t-test for each group is less than 0.1 from large to small, and count the number:

[0065] Group B: There are 2 groups with significance less than the threshold compared to other groups, namely A and C;

[0066] Group A: There is 1 group with significance less than the threshold compared to other groups, namely B;

[0067] Group C: There is 1 group with significance less than the threshold compared to other groups, namely B.

[0068] The more the number of abnormal groups, the more abnormal the data of this group, which also means that the length of hospital stay of the attending doctor corresponding to this group is relatively abnormal. Therefore, determine this group (here it is group B) as the abnormal patient group.

[0069] The length of hospital stay optimization value determination module 112 is used to calculate the average length of hospital stay of other patient groups except the abnormal patient group as the length of hospital stay optimization value for the corresponding abnormal patient group for each abnormal patient group.

[0070] In other words, after identifying which doctors have abnormal hospital stays, the next step is to exclude these abnormal doctors' records and calculate the average hospital stay for the normal group. This average is the optimal value for reasonable hospital stays. If the hospital stay for the abnormal group is significantly higher than the reasonable value, then communication between the attending physician and other doctors regarding treatment plans should be strengthened to adjust and optimize the treatment plan and reduce the hospital stay for that disease. If the hospital stay for the abnormal group is significantly lower than the reasonable value, then postoperative follow-ups between the attending physician and the patient should be strengthened to monitor the probability of repeat hospitalization. If abnormal data is found, the hospital stay for that disease can be appropriately extended.

[0071] This invention is based on the principle that patients with the same disease and the same DRG grouping results should use relatively similar medical resources. By using historical medical record data and DRG grouping results, patients under each disease are grouped according to their DRG grouping results to ensure that the severity of symptoms is similar within each patient group. Hypothesis testing is performed on these patient groups to determine whether the factors influencing the length of hospital stay are due to physician subjectivity or the characteristics of the disease itself. For diseases where the length of hospital stay is determined by the characteristics of the disease itself, no optimization of hospital stay length is performed. Instead, a more detailed analysis is conducted on diseases where the length of hospital stay is influenced by physician subjectivity, removing significantly abnormal lengths of hospital stay and identifying statistically reasonable lengths of hospital stay, thereby scientifically improving the turnover efficiency of hospital beds.

[0072] Figure 2 A flowchart of a preferred embodiment of the method for optimizing hospital stay days according to the present invention is shown.

[0073] In step S202, patient data is acquired, and each patient data includes information about the patient, attending physician, primary diagnosis code, DGR group code, and length of hospital stay.

[0074] In step S204, patients are grouped according to their primary diagnosis code and DRG grouping code, with patients having the same primary diagnosis code and DRG grouping code grouped into the same patient group.

[0075] In step S206, for each patient group, patients are grouped according to their attending physician, with patients with the same attending physician being grouped into the same patient group.

[0076] In step S208, for each patient group with the same primary diagnosis code, the patient group with a significant difference in the mean length of hospital stay is identified as an abnormal patient group.

[0077] In step S210, for each abnormal patient group, the patient group with a significant difference in length of hospital stay is identified as the abnormal patient group.

[0078] In step S212, for each abnormal patient group, the average length of hospital stay of other patient groups besides the abnormal patient group is calculated as the optimized length of hospital stay value for the corresponding abnormal patient group.

[0079] In another embodiment, the present invention provides a computer-readable storage medium having a computer program stored thereon, the computer program being executed by a processor to achieve [the desired result]. Figure 1 The system embodiments shown or other corresponding system embodiments combine the functions or implementations of these embodiments. Figure 2 The steps of the method embodiments or other corresponding method embodiments shown are not repeated here.

[0080] In another embodiment, the present invention provides a computer device including a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to achieve [a specific action / combination]. Figure 1 The system embodiments shown or other corresponding system embodiments combine the functions or implementations of these embodiments. Figure 2 The steps of the method embodiments or other corresponding method embodiments shown are not repeated here.

[0081] The various embodiments described herein, or their specific features, structures, or characteristics, may be suitably combined in one or more embodiments of the invention. Furthermore, in some cases, the order of steps described in the flowcharts and / or pipeline processes may be modified where appropriate, and they need not be performed in the exact order described. Additionally, various aspects of the invention may be implemented using software, hardware, firmware, or combinations thereof, and / or other computer-implemented modules or devices that perform the described functions. Software implementations of the invention may include executable code stored in a computer-readable medium and executed by one or more processors. Computer-readable media may include computer hard disk drives, ROM, RAM, flash memory, portable computer storage media such as CD-ROM, DVD-ROM, flash drives, and / or other devices having a Universal Serial Bus (USB) interface, and / or any other suitable tangible or non-transitory computer-readable medium or computer memory on which executable code can be stored and executed by a processor. The invention may be used in conjunction with any suitable operating system.

[0082] Unless explicitly stated otherwise, the singular forms “a” and “the” used herein include the plural meaning (i.e., meaning “at least one”). It should be further understood that the terms “having,” “comprising,” and / or “including” as used in the specification indicate the presence of the described features, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, elements, components, and / or combinations thereof. The term “and / or” as used herein includes any and all combinations of one or more of the listed related items.

[0083] The foregoing has described some preferred embodiments of the present invention. However, it should be emphasized that the present invention is not limited to these embodiments, but can be implemented in other ways within the scope of the present invention. Those skilled in the art can make various modifications and variations to the present invention based on the inventive concept and without departing from the scope of the present invention, and such modifications or variations still fall within the protection scope of the present invention.

Claims

1. A system for optimizing hospital stay duration, characterized in that, The system includes: The data acquisition module is used to acquire patient data. Each patient's data includes information about the patient, attending physician, primary diagnosis code, DRG group code, and length of hospital stay. The grouping module is used to group patients according to their primary diagnosis code and DRG grouping code, with patients having the same primary diagnosis code and DRG grouping code grouped into the same patient group. The grouping module is used to group patients according to their attending physicians for each patient group, with patients with the same attending physician being grouped together. The abnormal patient group identification module is used to identify patient groups with significant differences in the mean length of hospital stay among various patient groups with the same primary diagnosis code as abnormal patient groups. The abnormal patient group identification module is used to identify the patient group with significant differences in length of hospital stay for each abnormal patient group. The module for determining the optimal length of hospital stay is used to calculate the average length of hospital stay of other patient groups besides the abnormal patient group for each abnormal patient group as the optimal length of hospital stay for the corresponding abnormal patient group.

2. The system according to claim 1, characterized in that, The abnormal patient group was identified using analysis of variance.

3. The system according to claim 2, characterized in that, The abnormal patient group identification module is used for: For patient groups with the same primary diagnosis code, determine the F-test value for the length of hospital stay for each patient group; Determine the F-significance value corresponding to each F-test value; Patients with F significance values ​​below the first threshold were identified as abnormal patient groups.

4. The system according to claim 3, characterized in that, The first threshold is 0.1 or 0.

05.

5. The system according to claim 1, characterized in that, The abnormal patient group was determined using a multiple comparison method.

6. The system according to claim 5, characterized in that, The abnormal patient group identification module is used for: Determine the significance level of the t-test for each pair of patient groups; Determine the number of times the t-test significance level of each patient group compared to other patient groups is lower than the second threshold; One or more patient groups with the highest frequency were identified as abnormal patient groups.

7. The system according to claim 5, characterized in that, The multiple comparison method is the least significant difference method.

8. A method for optimizing hospital stay duration, characterized in that, The method includes: Acquire patient data, each patient's data including information about the patient, attending physician, primary diagnosis code, DRG group code, and length of hospital stay; Patients are grouped according to their primary diagnosis code and DRG grouping code, with patients having the same primary diagnosis code and DRG grouping code grouped into the same patient group. For each patient group, patients are grouped according to their attending physician, with patients who have the same attending physician being grouped together. For patient groups with the same primary diagnosis code, those groups with significant differences in the mean length of hospital stay are identified as abnormal patient groups. For each abnormal patient group, the patient group with a significant difference in length of hospital stay was identified as the abnormal patient group; For each abnormal patient group, the average length of hospital stay of other patient groups is calculated as the optimized length of hospital stay for the corresponding abnormal patient group.

9. A computer device comprising a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to perform the functions of the system according to any one of claims 1-7 or the steps of the method according to claim 8.

10. A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the functions of the system according to any one of claims 1-7 or the steps of the method according to claim 8.

Images