Construction method of AIS patient pre-hospital delay risk prediction model

Abstract

The invention discloses a construction method of an AIS patient pre-hospital delay risk prediction model, and relates to the field of medicine. Comprising the following steps: data acquisition: acquiring data through a hospital electronic medical record system and telephone return visit, and performing anonymization processing on the data after approval by an ethical committee; model construction: performing inter-group comparison by using SPSS 29.0, then screening independent risk factors of pre-hospital delay by using binary Logistic regression, and finally constructing a column diagram prediction model by using an rms packet of R 3.6.3 software; and verifying the model, and evaluating the distinction degree through the area AUC under the working characteristic curve of the subject. The pre-hospital delay prediction model for the first-onset AIS patient, constructed by the method, has good distinction degree and accuracy, provides a basis for identifying the pre-hospital delay of the first-onset AIS patient, effectively shortens the arrival time of the patient for the first-onset AIS patient, and has important public health significance and clinical value.

Description

Technical Field

[0001] This invention relates to the medical field, and more particularly to a method for constructing a pre-hospital delay risk prediction model for AIS patients. Background Technology

[0002] Stroke is the second leading cause of death worldwide, accounting for 11.02% of all deaths globally. It is characterized by five major features: high incidence, high disability rate, high mortality rate, high recurrence rate, and high economic burden. It not only seriously threatens patients' lives and health but also imposes a heavy burden on society. In China, more than 2 million new cases of stroke occur annually, making it the leading cause of death among residents. Its incidence remains consistently high and shows a significant trend towards affecting younger people. Acute ischemic stroke (AIS) is the most common type of stroke, accounting for approximately 70% to 80% of all stroke cases. Intravenous thrombolysis is one of the effective treatments for AIS. With the development of reperfusion therapy, the prognosis of AIS patients has significantly improved. However, due to the strict time window, some patients still miss the optimal treatment opportunity. Whether patients can seek medical attention promptly after the onset of symptoms and receive intravenous thrombolysis or endovascular thrombectomy (EVT) is crucial to their prognosis.

[0003] "Pre-hospital delay" refers to the time delay between symptom onset and the patient's arrival at the hospital, and is currently the main cause of treatment delays in acute myocardial insufficiency (AIS). Studies show that the low thrombolysis rate in AIS patients is primarily due to pre-hospital delay, with most AIS patients still unable to reach the hospital within the designated time window. The factors contributing to pre-hospital delay in AIS patients are diverse, including sociodemographic and socioeconomic factors, past medical history, and variables related to the severity of the illness. Due to differences in economic levels, geographical environments, medical conditions, and cultural backgrounds across countries and regions, the occurrence and influencing factors of pre-hospital delay in AIS patients also vary significantly.

[0004] Currently, several studies have investigated and analyzed the influencing factors of pre-hospital delays in AIS patients in the local area. Studies show significant differences in the medical history and healthcare behavior between first-time AIS patients and recurrent AIS patients, with the 24-hour pre-hospital delay rate being higher for first-time patients than for recurrent patients. Considering that first-time patients often lack health education during hospitalization, have weaker ability to recognize stroke symptoms, and lack awareness of the need for timely medical attention, research on pre-hospital delays in first-time AIS patients remains relatively scarce. Therefore, in-depth exploration of the influencing factors of pre-hospital delays in first-time AIS patients, and the development of intervention measures to effectively shorten patient arrival time, has significant public health and clinical value.

[0005] Therefore, this invention proposes a method for constructing a pre-hospital delay risk prediction model for AIS patients. Summary of the Invention

[0006] The purpose of this invention is to address the shortcomings of existing technologies by proposing a method for constructing a pre-hospital delay risk prediction model for AIS patients.

[0007] To achieve the above objectives, the present invention adopts the following technical solution:

[0008] A method for constructing a pre-hospital delay risk prediction model for AIS patients includes the following steps:

[0009] S1: Data collection, data is obtained through the hospital's electronic medical record system and telephone follow-ups, and the data is anonymized after approval by the ethics committee;

[0010] S2: Model building: SPSS 29.0 was used for intergroup comparisons, then binary logistic regression was used to screen for independent risk factors of pre-hospital delay, and finally the rms package of R 3.6.3 software was used to build a nomogram prediction model.

[0011] S3: Model validation. The discrimination of the model is evaluated by the area under the receiver operating characteristic curve (AUC). The goodness of fit of the model is evaluated by the Hosmer-Lemeshow test. At the same time, calibration curves are plotted to verify the accuracy of the model.

[0012] Preferably, in step S1, the collected data includes sociodemographic data, clinical data, situational data, and scale rating data.

[0013] Preferably, the sociodemographic data includes age, gender, ethnicity, education level, occupation, place of residence, and type of medical insurance.

[0014] Preferably, the clinical factor data include NIHSS score, TOAST classification, and history of loss of consciousness / syncope.

[0015] Preferably, the contextual factor data includes patient reactions when symptoms appear, traffic congestion during transport, and bystander information.

[0016] Preferably, the scale rating data is the Perceived Social Support Scale (PSSS).

[0017] Preferably: In step S2, when comparing between groups, the count data is processed through x 2 For quantitative data, a t-test was performed.

[0018] Preferably, in step S2, independent risk factors include PSSS score, transit traffic congestion, NIHSS score, patient response when symptoms occur, and loss of consciousness / syncope.

[0019] The beneficial effects of this invention are as follows:

[0020] 1. The pre-hospital delay prediction model for first-episode AIS patients constructed in this invention has good discrimination and accuracy, providing a basis for identifying pre-hospital delays in first-episode AIS patients. At the same time, it effectively shortens the time to hospital for first-episode AIS patients, which has important public health significance and clinical value. Attached Figure Description

[0021] Figure 1 This is a flowchart illustrating the construction method of a pre-hospital delay risk prediction model for AIS patients proposed in this invention. Detailed Implementation

[0022] The technical solution of the present invention will be further described in detail below with reference to specific embodiments.

[0023] In the description of this invention, it should be noted that, unless otherwise explicitly specified and limited, the terms "installation," "connection," "linking," and "setting" should be interpreted broadly. For example, they can refer to a fixed connection or setting, a detachable connection or setting, or an integral connection or setting. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0024] Example 1:

[0025] Data collection:

[0026] Data collection was rigorously conducted by two trained researchers, primarily using the hospital's electronic medical record system to extract detailed patient information, supplemented by telephone follow-ups. Forty-four risk variables associated with pre-hospital delays in first-episode AIS patients were included, covering sociodemographic, socioeconomic, medical history, and epidemiological contexts. Key variables included age, sex, ethnicity, education level, stable occupation, residential status, place of residence, medical insurance status, Perceived Social Support Scale (PSSS) score, number of children, family history of stroke, self-reported financial difficulties, and medical history. Epidemiological context-related variables included NIHSS score (National Institutes of Health Stroke Scale), TOAST classification, presence of bystanders, the first person to notice symptoms, and initial stroke symptom presentation. To protect the legal rights and privacy of the participants, this study was reviewed by the Ethics Committee of the Second Affiliated Hospital of Chongqing Medical University (ethics approval number: 2024(82)). All sensitive personal health information in the dataset was anonymized.

[0027] Statistical analysis

[0028] Statistical analysis was performed using SPSS 29.0.1.0 and R 3.6.3 software. Count data were expressed as percentages (%), and continuous data as mean ± standard deviation (M ± SD). For comparisons between groups, the chi-square test was used for count data, and the independent samples t-test was used for continuous data. Finally, a binary logistic regression model was used to analyze the risk factors for pre-hospital delay in first-episode AIS patients. In R 3.6.3 software, a nomogram model of pre-hospital delay risk was constructed using the rms package, and its discriminative power was assessed using the area under the receiver operating characteristic curve (ROC) (AUC). The goodness of fit of the model was assessed using the Hosmer-Lemeshow test, and a calibration curve was plotted to further validate the model's accuracy.

[0029] The above description is only a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any equivalent substitutions or modifications made by those skilled in the art within the scope of the technology disclosed in the present invention, based on the technical solution and inventive concept of the present invention, should be covered within the scope of protection of the present invention.

Claims

1. A method for constructing a pre-hospital delay risk prediction model for AIS patients, characterized in that, Includes the following steps: S1: Data collection, data is obtained through the hospital's electronic medical record system and telephone follow-ups, and the data is anonymized after approval by the ethics committee; S2: Model building: SPSS 29.0 was used for intergroup comparisons, then binary logistic regression was used to screen for independent risk factors of pre-hospital delay, and finally the rms package of R 3.6.3 software was used to build a nomogram prediction model. S3: Model validation. The discrimination of the model is evaluated by the area under the receiver operating characteristic curve (AUC). The goodness of fit of the model is evaluated by the Hosmer-Lemeshow test. At the same time, calibration curves are plotted to verify the accuracy of the model.

2. The method for constructing a pre-hospital delay risk prediction model for AIS patients according to claim 1, characterized in that, In step S1, the collected data includes sociodemographic factor data, clinical factor data, situational factor data, and scale scoring data.

3. The method for constructing a pre-hospital delay risk prediction model for AIS patients according to claim 2, characterized in that, The sociodemographic data include age, gender, ethnicity, education level, occupation, place of residence, and type of medical insurance.

4. The method for constructing a pre-hospital delay risk prediction model for AIS patients according to claim 2, characterized in that, The clinical factor data included NIHSS score, TOAST classification, and history of loss of consciousness / syncope.

5. The method for constructing a pre-hospital delay risk prediction model for AIS patients according to claim 2, characterized in that, The contextual factors data include patient reactions when symptoms appear, traffic congestion during transport, and bystander behavior.

6. The method for constructing a pre-hospital delay risk prediction model for AIS patients according to claim 2, characterized in that, The scale rating data is the Perceived Social Support Scale (PSSS).

7. The method for constructing a pre-hospital delay risk prediction model for AIS patients according to claim 1, characterized in that, In step S2, when comparing groups, count data are obtained through x. 2 For quantitative data, a t-test was performed.

8. The method for constructing a pre-hospital delay risk prediction model for AIS patients according to claim 1, characterized in that, In step S2, independent risk factors include PSSS score, transit traffic congestion, NIHSS score, patient response when symptoms occur, and loss of consciousness / syncope.

Images