An electrocardiogram interactive learning system for nursing students

Abstract

The application discloses an electrocardiogram interactive learning system for nursing students, which comprises a student portrait construction module, an electrocardiogram digital twin case generation module, an interactive learning engine and an intelligent evaluation module. The student portrait construction module constructs and dynamically updates the student knowledge portrait according to the basic knowledge test results and historical learning data of the student; the digital twin case generation module matches or parameterizes the corresponding digital twin electrocardiogram case from the case database according to the student knowledge portrait; the interactive learning engine presents the case to the student and guides the completion of electrocardiogram interpretation and nursing decision-making, and provides instant feedback; the intelligent evaluation module comprehensively scores according to the interpretation result and the nursing decision, updates the student portrait and dynamically adjusts the difficulty of the subsequent cases. The application realizes precise electrocardiogram teaching for nursing students by combining digital twin technology with personalized learning paths, and effectively improves the learning efficiency and clinical decision-making ability.

Description

Technical Field

[0001] This invention relates to the field of medical teaching equipment technology, specifically to an interactive electrocardiogram learning system for nursing students. Background Technology

[0002] Electrocardiogram (ECG) interpretation is one of the core clinical skills that nursing students must master. Traditional ECG teaching methods mainly rely on static pattern recognition and classroom lectures, which have the following shortcomings: (1) Static patterns are disconnected from clinical practice, making it difficult for students to apply theoretical knowledge to real clinical scenarios; (2) Students lack sufficient practical opportunities and have difficulty accessing diverse pathological ECG patterns; (3) Teaching feedback is delayed, and students cannot promptly understand their interpretation errors; (4) The existing teaching system lacks a specific design for nursing students and fails to effectively combine ECG interpretation with nursing clinical decision-making. Summary of the Invention

[0003] To address the aforementioned problems in existing technologies, this invention provides an interactive electrocardiogram (ECG) learning system for nursing trainees. It aims to achieve personalized ECG teaching for nursing trainees through a closed-loop mechanism involving trainee knowledge profiling, dynamic generation of digital twin cases, interactive learning, and intelligent assessment. This solves the problems of existing ECG teaching systems, such as lack of personalized matching, disconnect from clinical nursing decision-making, and delayed feedback.

[0004] The technical solution of this invention is as follows:

[0005] An interactive electrocardiogram learning system for nursing trainees includes:

[0006] The student profile building module is used to build and dynamically update student knowledge profiles based on students' basic knowledge assessment results and historical learning data.

[0007] Preferably, the student profile construction module includes at least the following dimensions: waveform recognition ability, rhythm judgment ability, lead recognition ability, distribution of common error types, and learning progress. Specifically, upon first login, students complete a basic electrocardiogram knowledge assessment, covering three dimensions: waveform recognition, rhythm judgment, and lead recognition. The system also records the student's historical learning data, including learning duration, accuracy rate for each dimension, error type distribution, and learning progress. The student profile is represented using vectorization, and the values ​​for each dimension are dynamically adjusted as the student's learning performance updates.

[0008] The ECG digital twin case generation module is used to match or parameterize the corresponding digital twin ECG cases from the ECG case database based on the trainee's knowledge profile. Each digital twin ECG case includes at least twelve-lead ECG waveform data, a clinical scenario description, and standard interpretation results.

[0009] Preferably, the ECG digital twin case generation module further includes a parameterized waveform generation submodule. This submodule generates a synthetic ECG waveform by adjusting one or more parameters, including heart rate, PR interval, QRS duration, and ST segment. Specifically, based on a normal ECG waveform template, the submodule generates various variant waveforms such as sinus tachycardia, sinus bradycardia, atrioventricular block, and myocardial ischemia by adjusting parameters such as heart rate (adjusted within the range of 60-100 beats / min), PR interval (normal value 0.12-0.20 seconds), QRS duration (normal value 0.06-0.10 seconds), and ST segment (whether it is elevated or depressed). Parameter adjustment can be automatically triggered by the system based on the weak dimensions in the student's profile, or it can be manually set by the teacher.

[0010] An interactive learning engine is used to present the digital twin electrocardiogram (ECG) case to trainees, guide them in interpreting the ECG and making nursing decisions, and provide immediate feedback.

[0011] Preferably, the interactive learning engine includes a nursing decision-making simulation submodule. This submodule has a built-in mapping rule library between ECG interpretation results and nursing interventions, used to evaluate the rationality of the nursing interventions selected by the learner based on their interpretation results. Specifically, the mapping rule library stores multiple nursing decision-making rules. For example, when the interpretation result is "acute myocardial infarction," the corresponding rational nursing interventions include "immediately notify the doctor," "administer oxygen," and "establish intravenous access." When the interpretation result is "sinus bradycardia," the corresponding rational nursing interventions include "monitor vital signs" and "assess symptoms." After completing the ECG interpretation, the learner needs to select a rational nursing plan from several nursing intervention options. The system evaluates the rationality of the learner's selection based on the mapping rule library and provides feedback.

[0012] The intelligent assessment module is used to comprehensively score based on the trainee's interpretation results and nursing decisions, update the trainee's knowledge profile, and dynamically adjust the difficulty of subsequent cases.

[0013] Preferably, the intelligent assessment module includes an error pattern recognition submodule. This submodule has a pre-set database of ECG interpretation error patterns for nursing trainees, used to identify the types of interpretation errors made by trainees and provide targeted corrective training. The error pattern database includes common ECG interpretation error types made by nursing trainees, including but not limited to: lead confusion errors, rhythm misjudgment errors, duration measurement errors, and amplitude interpretation errors.

[0014] Preferably, the system further includes an electrocardiogram (ECG) evolution simulation module, used to generate multiple ECG waveforms at different time points for the same case, simulating the disease progression and training trainees' dynamic observation skills. Specifically, the ECG evolution simulation module starts with the ECG waveform of a basic case, and through a parameterized waveform generation submodule, adjusts parameters such as heart rate and ST segment according to the time sequence to generate ECG waveforms of the case at different time points such as 0 hours, 2 hours, 6 hours, and 24 hours after the onset of the disease, and displays them in the form of a time axis. Trainees need to observe the changing trends of the waveforms at each time point to judge the progression of the disease.

[0015] Preferably, the system further includes a multi-person collaborative learning module, which supports multiple learners to interpret the same digital twin electrocardiogram case simultaneously and generates a comparative analysis report of the interpretation results of each learner.

[0016] Preferably, the system adopts a client-server architecture, with the student profile construction module, electrocardiogram digital twin case generation module, and intelligent assessment module deployed on the server side, and the interactive learning engine deployed on the client side. The client and server side are connected via wireless network communication.

[0017] The advantages of this invention are:

[0018] (1) Personalized case matching is achieved through student knowledge profiles, which overcomes the "one-size-fits-all" defect of traditional electrocardiogram teaching. It can accurately push training content to each student's knowledge weaknesses and improve learning efficiency.

[0019] (2) Digital twin cases combine electrocardiogram interpretation with nursing clinical decision-making. Through the nursing decision simulation sub-module, trainees’ comprehensive judgment ability in real clinical scenarios is trained, which is more in line with the actual work needs of nursing trainees.

[0020] (3) The instant feedback and error pattern recognition mechanism can quickly locate the type of error in the student's judgment and push targeted correction training to help the student correct the wrong cognition in time and avoid the error from becoming entrenched.

[0021] (4) The ECG evolution simulation module trains students’ dynamic observation ability and disease judgment ability by displaying the waveform changes of cases at different time points, making up for the shortcomings of traditional static atlas teaching that cannot display the evolution of disease.

[0022] (5) The multi-person collaborative learning module supports collaborative interpretation and comparative analysis among students, which cultivates students' teamwork ability and clinical communication ability and enriches the teaching form. Attached Figure Description

[0023] Figure 1 This is a block diagram of the system structure of the present invention.

[0024] In the diagram: 100 - Interactive ECG learning system for nursing trainees, 110 - Server-side, 111 - Trainee profile building module, 112 - ECG digital twin case generation module, 113 - Intelligent assessment module, 114 - ECG case database, 120 - Client-side, 121 - Interactive learning engine, 122 - ECG evolution simulation module, 123 - Multi-person collaborative learning module. Detailed Implementation

[0025] The specific embodiments of the present invention will be further described below with reference to the accompanying drawings. It should be noted that these descriptions are for the purpose of aiding understanding the present invention, but do not constitute a limitation thereof. Furthermore, the technical features involved in the various embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0026] like Figure 1 As shown, this invention provides an interactive electrocardiogram (ECG) learning system 100 for nursing trainees. The system adopts a client-server architecture, including a server 110 and a client 120. The server 110 includes a trainee profile construction module 111, an ECG digital twin case generation module 112, an intelligent assessment module 113, and an ECG case database 114. The client 120 includes an interactive learning engine 121, an ECG evolution simulation module 122, and a multi-user collaborative learning module 123. The client 120 and the server 110 are connected via a wireless network to enable the distribution of digital twin cases and the transmission of trainee learning data.

[0027] The student profile building module 111 is used to construct and dynamically update student knowledge profiles based on students' basic knowledge assessment results and historical learning data. When students log in to the system for the first time, they need to complete a basic electrocardiogram (ECG) knowledge assessment, which includes three dimensions: waveform recognition (such as the morphology recognition of P waves, QRS complexes, and T waves), rhythm judgment (such as the differentiation of sinus rhythm, atrial rhythm, and ventricular rhythm), and lead recognition (such as the location and corresponding waveform characteristics of limb leads and precordial leads). The system calculates the initial ability values ​​for each dimension based on the assessment results.

[0028] During ECG interpretation practice, the system continuously records learner data, including accuracy rates for each dimension, time taken per case interpretation, error type distribution (e.g., lead confusion, rhythm misjudgment), and learning progress (number of completed cases and difficulty level). The learner profile is represented using vectorization; for example, a learner profile vector can be represented as {waveform recognition ability value, rhythm judgment ability value, lead recognition ability value, common error type distribution vector, and learning progress value}. After each student completes a digital twin case practice, the system updates the values ​​for each dimension of the profile using a moving average algorithm based on the student's performance in that practice.

[0029] The ECG digital twin case generation module 112 is used to generate corresponding digital twin ECG cases by matching or parameterizing the corresponding cases from the ECG case database 114, based on the student profile construction module 111. The ECG case database 114 stores a large amount of labeled ECG case data, classified according to difficulty level and pathology type, including at least a normal ECG library, an arrhythmia library, a myocardial ischemia library, and other abnormal ECG libraries.

[0030] Each case study includes 12-lead electrocardiogram (ECG) waveform data, a corresponding clinical scenario description, standard interpretation results, and nursing decision recommendations. The case matching engine retrieves cases from database 114 that match the trainee's skill level based on the trainee's weakest dimensions in their profile. For example, if a trainee's "rhythm judgment ability" score is low, the system prioritizes matching cases of moderate difficulty from the arrhythmia database. When existing cases in the database cannot accurately match the trainee's training needs, the parameterized waveform generation submodule comes into play. This submodule uses a normal ECG waveform template of sinus rhythm as a base and generates a synthetic ECG waveform by adjusting one or more parameters, including heart rate (adjusting upwards or downwards within the range of 60-100 beats / min can generate waveforms of sinus tachycardia or sinus bradycardia), PR interval (prolongation within the normal range of 0.12-0.20 seconds can simulate first-degree atrioventricular block), QRS duration (greater than 0.12 seconds can simulate bundle branch block), and ST segment (elevation or depression can simulate myocardial ischemia or myocardial infarction).

[0031] The adjustment range of each parameter is automatically determined by the system based on the corresponding weakness in the student's profile, or it can be manually set by the teacher through the teacher's portal. Each generated digital twin ECG case includes at least twelve-lead ECG waveform data, a clinical scenario description (including patient's chief complaint, vital signs, and nursing background information), and standard interpretation results (including diagnostic conclusion, interpretation basis, and recommended nursing measures).

[0032] The interactive learning engine 121 is used to present digital twin electrocardiogram (ECG) cases generated by the digital twin case generation module 112 to trainees, guide trainees to complete ECG interpretation and nursing decisions, and provide immediate feedback.

[0033] The interactive learning engine 121 is deployed on client 120 and interacts with students through a graphical user interface. Students first read the clinical scenario description presented in the case presentation submodule (e.g., "A 65-year-old male patient was admitted to the hospital due to chest pain and profuse sweating for 30 minutes, with a blood pressure of 110 / 70 mmHg and a heart rate of 92 beats / min"), and then view the corresponding twelve-lead electrocardiogram waveform. The guided interpretation submodule guides students to complete the electrocardiogram interpretation through step-by-step questioning: (1) calculate the heart rate; (2) analyze whether the rhythm is regular; (3) determine the morphology and location of the P wave; (4) measure the PR interval and QRS duration; (5) observe ST segment and T wave changes; (6) make a comprehensive diagnosis. In each step, students need to select the correct answer from multiple options.

[0034] After the trainee completes the interpretation, the nursing decision-making simulation submodule is activated. This submodule has a built-in mapping rule library that stores multiple mapping rules between ECG interpretation results and nursing interventions. For example, rule 1, when the interpretation result is "acute ST-segment elevation myocardial infarction," corresponds to appropriate nursing interventions including "immediately notify the doctor," "administer oxygen," "establish intravenous access," and "ECG monitoring." Rule 2, when the interpretation result is "sinus bradycardia (heart rate <50 beats / min)," corresponds to appropriate nursing interventions including "monitor vital signs," "assess for symptoms," and "prepare atropine."

[0035] Trainees select appropriate nursing plans from several nursing intervention candidates. The system evaluates the completeness (whether key interventions are covered) and priority (whether the intervention order is reasonable) of their selections based on a mapping rule base. The instant feedback submodule displays the correctness judgment immediately after the trainee submits their answer at each step, and displays the complete judgment basis and knowledge point explanations after the entire process is completed.

[0036] The intelligent assessment module 113 is used to give a comprehensive score based on the student's interpretation results and nursing decisions in the interactive learning engine 121, update the student knowledge profile in the student profile building module 111, and dynamically adjust the difficulty of subsequent cases.

[0037] The automatic scoring engine comprehensively evaluates trainees' performance across four dimensions: accuracy of interpretation (40%), completeness of interpretation (20%), rationality of nursing decisions (30%), and time efficiency (10%). The comprehensive score is out of 100: below 60 points indicates "needs improvement," 60-79 points is "passable," 80-89 points is "good," and above 90 points is "excellent." The error pattern recognition submodule has a pre-set database of ECG interpretation error patterns for nursing trainees, including common ECG interpretation errors encountered during the learning process. These errors include lead confusion (e.g., confusing chest leads V1 and V2), rhythm misjudgment (e.g., misjudging atrial fibrillation as sinus arrhythmia), duration measurement errors (e.g., inaccurate QRS duration measurement), and amplitude interpretation errors (e.g., misjudging ST segment elevation). This submodule identifies the types of errors by comparing the trainee's interpretation results with the standard answers and records them in the "Common Error Type Distribution" dimension of the trainee profile.

[0038] Based on the comprehensive score and error type identification results, the intelligent assessment module 113 performs dynamic difficulty adjustment: for students with a comprehensive score above 80 and no obvious error type, the next case is increased by one level in difficulty; for students with a comprehensive score below 60 or with serious error type, the next case maintains the current difficulty or decreases by one level, and pushes the corresponding correction training case for the error type.

[0039] The ECG evolution simulation module 122 is used to generate multiple ECG waveforms at different time points for the same case, simulating the disease progression. Specifically, the module starts with the ECG waveform of a basic case (such as acute inferior myocardial infarction) and automatically adjusts key parameters according to the time sequence through the parameterized waveform generation submodule: at 0 hours after onset, the ST segment is elevated with a convex upward curve; after 2 hours, the ST segment elevation becomes more pronounced, and pathological Q waves appear; after 6 hours, the ST segment begins to decline, and the T wave begins to invert; after 24 hours, the ST segment has basically recovered, and the T wave is deeply inverted. The module continuously displays the ECG waveforms at each time point in a time-axis manner. Trainees need to observe the changing trends of the waveforms at each time point to determine whether the condition is improving or worsening, and adjust nursing decisions accordingly.

[0040] The multi-user collaborative learning module 123 supports 2-6 learners simultaneously interpreting the same digital twin electrocardiogram (ECG) case. Each learner logs into the system through their respective client 120 and joins the same collaborative session. Each learner independently completes the case interpretation and nursing decision-making before submitting their results. The collaborative session management submodule summarizes the interpretation results of all learners, and the comparative analysis report generation submodule generates a comparative report containing the following: comparison of interpretation accuracy among learners, comparison of nursing decision choices among learners, comparison of error types among learners, and an overall ranking. This report supports peer review and discussion among learners, fostering teamwork skills.

[0041] The overall system workflow is as follows: Students log in to the system through client 120. The student profile building module 111 loads the student's existing knowledge profile. If the student is new, they are first guided to complete a basic knowledge assessment to generate an initial profile. The ECG digital twin case generation module 112 matches corresponding digital twin ECG cases from the ECG case database 114 or generates them through the parameterized waveform generation submodule, based on the weak dimensions and current difficulty level in the student's knowledge profile. The interactive learning engine 121 presents the digital twin ECG cases to the student and guides them step-by-step through the guided interpretation submodule to complete the ECG interpretation. The nursing decision-making simulation submodule guides trainees to make nursing decisions; if dynamic observation of changes in the patient's condition is required, trainees can call the electrocardiogram evolution simulation module 122; in the collaborative learning mode, the multi-person collaborative learning module 123 synchronously coordinates the interpretation process of each trainee; the intelligent assessment module 113 gives a comprehensive score based on the trainee's interpretation results and nursing decisions, and the error pattern recognition submodule identifies and records the trainee's error type; the intelligent assessment module 113 updates the trainee knowledge profile in the trainee profile construction module 111 based on the score results and error type, and dynamically adjusts the difficulty level of subsequent cases based on the updated profile, forming a closed-loop feedback.

[0042] The embodiments of the present invention have been described in detail above with reference to the accompanying drawings, but the present invention is not limited to the described embodiments. For those skilled in the art, various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principles and spirit of the present invention, and these variations still fall within the protection scope of the present invention.

Claims

1. An interactive electrocardiogram learning system for nursing trainees, characterized in that, include: The student profile building module is used to build and dynamically update student knowledge profiles based on students' basic knowledge assessment results and historical learning data. The ECG digital twin case generation module is used to match or parameterize the corresponding digital twin ECG case from the ECG case database based on the trainee's knowledge profile. Each digital twin ECG case includes at least twelve-lead ECG waveform data, clinical scenario description, and standard interpretation results. An interactive learning engine is used to present the digital twin electrocardiogram (ECG) case to trainees, guide them in interpreting the ECG and making nursing decisions, and provide immediate feedback. The intelligent assessment module is used to comprehensively score based on the trainee's interpretation results and nursing decisions, update the trainee's knowledge profile, and dynamically adjust the difficulty of subsequent cases.

2. The interactive electrocardiogram learning system for nursing trainees according to claim 1, characterized in that: The electrocardiogram digital twin case generation module also includes a parameterized waveform generation submodule, which generates a synthetic electrocardiogram waveform by adjusting one or more parameters among heart rate, PR interval, QRS duration, and ST segment.

3. The interactive electrocardiogram learning system for nursing trainees according to claim 1, characterized in that: The student profile construction module includes at least the following dimensions: waveform recognition ability, rhythm judgment ability, lead recognition ability, distribution of common error types, and learning progress.

4. The interactive electrocardiogram learning system for nursing trainees according to claim 1, characterized in that: The interactive learning engine includes a nursing decision simulation submodule, which has a built-in mapping rule library between electrocardiogram interpretation results and nursing measures, used to evaluate the rationality of the nursing measures selected by the learner based on the interpretation results.

5. The interactive electrocardiogram learning system for nursing trainees according to claim 1, characterized in that: It also includes an electrocardiogram evolution simulation module, which is used to generate multiple electrocardiogram waveforms at different time points for the same case, simulate the evolution of the disease, and train trainees' dynamic observation ability.

6. The interactive electrocardiogram learning system for nursing trainees according to claim 1, characterized in that: It also includes a multi-person collaborative learning module, which supports multiple learners to interpret the same digital twin electrocardiogram case at the same time and generate a comparative analysis report of each learner's interpretation results.

7. The interactive electrocardiogram learning system for nursing trainees according to claim 1, characterized in that, The intelligent assessment module includes an error pattern recognition submodule, which has a pre-set database of error patterns in ECG interpretation for nursing trainees. This database is used to identify the types of interpretation errors made by trainees and to push targeted corrective training.

8. The interactive electrocardiogram learning system for nursing trainees according to any one of claims 1 to 7, characterized in that, The system adopts a client-server architecture. The student profile construction module, the electrocardiogram digital twin case generation module, and the intelligent assessment module are deployed on the server side, while the interactive learning engine is deployed on the client side. The client and the server side are connected via wireless network communication.

Images