A method and apparatus for patient safety monitoring and feedback for stereotactic radiosurgery

Abstract

The application discloses a patient safety monitoring and feedback method and device for stereotactic radiosurgery treatment, and relates to the technical field of medical equipment. The method comprises the following steps: collecting radiotherapy treatment data, and obtaining an individualized minute-level monitoring reminder scheme based on a pre-trained symptom type prediction model, wherein the individualized minute-level monitoring reminder scheme comprises a predetermined number of time nodes, and each time node corresponds to monitoring reminder content; collecting a patient treatment process record, wherein the patient treatment process record comprises a time-symptom-dose corresponding sequence; and obtaining a comprehensive monitoring report based on multiple core vital signs and control instructions. The application can significantly integrate objective physiological data and subjective feedback information, provide doctors with more comprehensive and more accurate decision support, and avoid misjudgment or reaction lag caused by a single signal.

Description

Technical Field

[0001] This invention relates to the field of medical device technology, and in particular to a method and device for patient safety monitoring and feedback in stereotactic radiosurgery. Background Technology

[0002] Stereotactic radiosurgery (SRS) is a high-precision, non-invasive tumor treatment technique. Systems like the ZAP-X system precisely focus multiple beams of high-energy radiation onto the lesion to destroy diseased tissue. Currently, effective communication between patients and doctors is lacking in actual ZAP-X treatment. The standard practice involves placing a pulse oximeter on the patient's hand. Beyond this, real-time patient information is only available after treatment based on the patient's recollection. Safety feedback during treatment relies entirely on the camera monitoring within the ZAP-X system. However, the patient's face is covered by a head mold during treatment, drastically increasing the difficulty of facial expression recognition. Furthermore, the patient is in a completely isolated state during treatment, increasing their fear and uncertainty, which negatively impacts treatment acceptance. While ZAP-X boasts advantages such as high precision and minimal invasiveness, the treatment process still carries potential risks: Physiological risks: Patients may experience abnormal vital signs during treatment due to stress, treatment reactions, or potential complications (such as changes in intracranial pressure, acute radiation reactions, etc.), including arrhythmias, decreased blood oxygen saturation, blood pressure fluctuations, and discomfort (such as severe headaches, nausea, limb numbness, etc.). Currently, although standard monitors are available in the treatment room, they are mostly standalone devices, not deeply integrated with the treatment system, and lack methods for collecting patient feedback specific to SRS treatment scenarios; Communication barriers: Patients are in a closed treatment pod, physically isolated from the operating room. Traditional communication relies on intercom systems, but when patients experience discomfort, they may be unable to perceive the specific discomfort due to panic or physical limitations, and thus cannot clearly express it. Summary of the Invention

[0003] To address the technical problems of existing technologies, such as patients' inability to promptly report discomfort during treatment, doctors' tendency to overlook abnormal signs, and the inability to detect abnormal treatment states early, this invention provides a method and device for patient safety monitoring and feedback in stereotactic radiosurgery. The technical solution is as follows:

[0004] On the one hand, a method for patient safety monitoring and feedback in stereotactic radiosurgery is provided. This method is implemented by a patient safety monitoring and feedback device for stereotactic radiosurgery, including a radiotherapy data acquisition module, a symptom analysis model module, a symptom early warning module, a real-time data acquisition module, a data fusion module, and a report generation module. Its characteristic is that it includes: Used for collecting radiotherapy treatment data, which includes raw planning data, target area information, organs at risk information, and baseline clinical information; The method is used to obtain a pre-trained symptom type prediction model, which is a set of prediction models based on LSTM neural networks, including a first model for target location prediction and a second model for organ at risk distance prediction. For use in a pre-trained symptom type prediction model, a personalized minute-level monitoring and reminder scheme is obtained. The personalized minute-level monitoring and reminder scheme includes a predetermined number of time nodes and monitoring and reminder content corresponding to each time node. Used to obtain patient treatment process records, which include a time-symptom-dose correspondence sequence; Used to obtain multiple core vital signs and control commands, which are used to adjust or stop treatment to protect patient safety; This is used to obtain a comprehensive monitoring report, which includes post-radiotherapy monitoring data, a summary of symptom occurrence, and an assessment of radiotherapy tolerance.

[0005] Preferably, the radiotherapy data acquisition module includes: The radiotherapy planning parameters are collected to obtain the raw planning data, which include the prescription dose parameters, total irradiation duration, baseline dose rate, and dose rate dynamic change curve. Collect the geometric features of the target area to obtain target area information, wherein the geometric features of the target area include the location and / or volume of the target area; Geometric features of organs at risk are collected, and spatial relationship analysis is performed to obtain information about organs at risk, including spatial relationship data between the target area and the organs at risk. Clinical information is collected to obtain baseline clinical information, which includes age, gender, ECOG score and comorbidities, including hypertension, diabetes and history of cerebrovascular disease. By merging the original planning data, target area information, organ at risk information, and baseline clinical information, radiotherapy treatment data is obtained.

[0006] Preferably, the symptom analysis model module includes: Historical case data of a predetermined number of patients undergoing brain radiotherapy were collected to obtain historical case data. The historical case data included radiotherapy planning parameters, pain scores and physiological change follow-up records, and physiological monitoring equipment record sheets. The radiotherapy planning parameters included dose rate time series and target area location or distance to organs at risk. The physiological monitoring equipment record sheets recorded real-time physiological change data collected during radiotherapy, including blood oxygen saturation, heart rate, and body movement. The pain scores and physiological change follow-up records were post-processed to extract the main symptom sequences, which were then added to the historical case data. The main symptom types included limb numbness / tingling, headache / dizziness, cardiovascular reaction, skin burning, visual abnormalities, or dysphagia. Based on the historical database, radiotherapy data feature vectors are extracted. These radiotherapy data feature vectors include mean dose rate, peak dose rate, slope of change, target volume, target location encoding, or distance to organs at risk. A symptom type prediction model is constructed based on a multi-layer neural network structure. The multi-layer neural network structure includes an input layer, a hidden layer, and an output layer. The input layer is used to receive the feature vector of radiotherapy data. The hidden layer adopts a bidirectional structure with 64 LSTM units. The output layer is used to output the prediction probability matrix of the main symptom type at a preset number of time nodes. The symptom type prediction model is a prediction model group based on LSTM neural network. The prediction model group includes a first model for target area location prediction and a second model for organ at risk distance prediction. Using the radiotherapy data features as input features, a symptom type prediction model is trained to obtain a pre-trained symptom type prediction model.

[0007] Preferably, the symptom warning module includes: Radiotherapy treatment data is input into a pre-trained symptom type prediction model to predict symptoms and obtain the output of symptom types. The output of symptom types includes the prediction of target area location and the prediction of organs at risk. The predicted target area location is combined with a knowledge base for matching analysis to identify N symptoms that may occur or may worsen, resulting in a priority symptom set. The knowledge base includes symptom association rules, symptom evolution paths, or symptom severity mapping tables. The prediction of the organs at risk is combined with a knowledge base for matching analysis to identify N symptoms that are currently occurring or may worsen, thus obtaining a set of secondary symptoms. Priority identifiers are assigned to each symptom in the priority symptom set to generate a priority observation sequence. When there is a gap in the priority observation sequence, symptoms are extracted from the secondary symptom set to supplement it, resulting in patient observation instructions. The patient observation instructions include reminder instructions to guide the patient in observing physical signs and manifestations. The reminder instructions are combined with the corresponding feedback mechanism to obtain a patient observation guidance plan and a doctor's monitoring focus. The patient observation guidance plan includes time point identifiers, monitoring content descriptions, expected symptom information, and / or feedback method descriptions. The feedback mechanism includes a binary yes or no assessment method to confirm discrete symptoms. The doctor's monitoring focus includes physiological parameter monitoring items, subjective feeling assessment items, or physical sign observation items. Based on the set of priority symptoms and the patient observation guidance plan, a personalized minute-level monitoring reminder plan is generated. The personalized minute-level monitoring reminder plan includes a predetermined number of time nodes and monitoring reminder content corresponding to each time node.

[0008] Preferably, the real-time data acquisition module includes: Based on the generated personalized minute-level monitoring and reminder scheme, a multimodal reminder signal is obtained through the timed triggering mechanism during the radiotherapy treatment process. The multimodal reminder signal includes a voice broadcast signal and a vibration feedback signal. An auditory prompting module and a tactile feedback module are used for state guidance to obtain patient feedback. The state guidance includes short and clear verbal instructions and tactile alarms. The system collects real-time feedback from patients through a patient feedback terminal, and obtains feedback content with time nodes, including the presence and severity of symptoms. By using the parameter acquisition module of the radiotherapy equipment, radiotherapy operation data at this time point is collected to obtain the time-symptom-dose correspondence sequence; Based on the time-symptom-dose correspondence sequence, the patient's treatment process record is obtained through data integration and structuring.

[0009] Preferably, the data fusion module includes: During radiotherapy, multiple core vital signs of the patient are monitored to obtain real-time physiological parameters, including blood oxygen saturation, heart rate, and body movement. The patient's treatment process is recorded and then processed to obtain fused data. The fused data processing includes establishing a patient feedback-physiological parameter time correspondence table. The fused data is compared with baseline values ​​to obtain the magnitude of change in physiological parameters. The baseline comparison calculation includes calculating the magnitude of change in physiological parameters relative to the patient's baseline value. A threshold determination module is used to determine safety and obtain control instructions. The safety determination includes providing early warning information when any physiological feature parameter in the received set of physiological feature parameters exceeds its corresponding preset value. The control instructions are used to adjust or stop treatment to protect patient safety.

[0010] Preferably, the report generation module includes: By integrating radiotherapy treatment data, patient treatment process records, multiple core vital signs and control commands, post-radiotherapy monitoring data is obtained. Based on the post-radiotherapy monitoring data, after processing by the symptom statistics module, a summary of symptom occurrence is obtained. The summary of symptom occurrence includes all symptoms actually experienced by the patient during the entire radiotherapy process, the time of occurrence, or the severity. Based on the summary of symptom occurrence and through comprehensive scoring, a radiotherapy tolerance assessment is obtained, which is used to quantify the patient's overall tolerance to this radiotherapy. The post-radiotherapy monitoring data, symptom occurrence summary, and radiotherapy tolerance assessment are combined to obtain a comprehensive monitoring report, which is used to provide data support for subsequent radiotherapy plan adjustments.

[0011] On the other hand, a patient safety monitoring and feedback device for stereotactic radiosurgery is provided, which is applied to a method for patient safety monitoring and feedback in stereotactic radiosurgery. The device includes: Radiotherapy data acquisition module: used to acquire radiotherapy treatment data, including raw planning data, target area information, organs at risk information, and baseline clinical information; Symptom analysis model module: used to obtain a pre-trained symptom type prediction model, which is a prediction model group based on LSTM neural network, including a first model for target area location prediction and a second model for organ at risk distance prediction; Symptom warning module: used to obtain a personalized minute-level monitoring and reminder scheme based on a pre-trained symptom type prediction model. The personalized minute-level monitoring and reminder scheme includes a predetermined number of time nodes and monitoring and reminder content corresponding to each time node. Real-time data acquisition module: used to obtain patient treatment process records, which include time-symptom-dosage correspondence sequences; Data fusion module: used to obtain multiple core vital signs and control commands, which are used to adjust or stop treatment to protect patient safety; Report generation module: used to generate a comprehensive monitoring report, which includes post-radiotherapy monitoring data, a summary of symptom occurrence, and an assessment of radiotherapy tolerance.

[0012] On the other hand, a patient safety monitoring and feedback device for stereotactic radiosurgery is provided, the patient safety monitoring and feedback device for stereotactic radiosurgery comprising: a processor; a memory storing computer-readable instructions, wherein when the computer-readable instructions are executed by the processor, the method described in any one of the above-described methods for patient safety monitoring and feedback for stereotactic radiosurgery is implemented.

[0013] On the other hand, a computer-readable storage medium is provided, characterized in that the computer-readable storage medium stores program code, which can be invoked by a processor to execute the method as described in any one of claims 1 to 7.

[0014] The beneficial effects of the technical solutions provided in the embodiments of the present invention include at least the following: It can monitor multiple core vital signs of patients in real time, continuously and non-invasively, while enabling patients to focus on key physical conditions in any state and convey clear subjective feelings to medical staff. It deeply integrates objective physiological data with subjective feedback information, providing doctors with more comprehensive and accurate decision support and avoiding misjudgment or delayed response that may be caused by a single signal. Attached Figure Description

[0015] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0016] Figure 1 This is a structural diagram of a patient safety monitoring and feedback system for stereotactic radiosurgery provided in an embodiment of the present invention; Figure 2 This is a flowchart of a symptom early warning method provided by an embodiment of the present invention; Figure 3 This is a block diagram of a patient safety monitoring and feedback device for stereotactic radiosurgery provided in an embodiment of the present invention; Figure 4 This is a schematic diagram of a patient safety monitoring and feedback device for stereotactic radiosurgery provided in an embodiment of the present invention.

[0017] Technical terms: LSTM: Long Short-Term Memory, is a special type of recurrent neural network (RNN) that can effectively solve the gradient vanishing or gradient exploding problems in long sequence training. ECOG: Electrocorticography is an invasive neuromonitoring technique that records brain electrical activity using electrodes placed on the surface of the cerebral cortex. ZAP-X is a non-invasive brain tumor treatment device based on stereotactic radiosurgery technology. Detailed Implementation

[0018] The technical solution of the present invention will now be described with reference to the accompanying drawings.

[0019] In embodiments of the present invention, words such as "exemplarily," "for example," etc., are used to indicate that something is an example, illustration, or description. Any embodiment or design described as "exemplary" in the present invention should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of the word "exemplary" is intended to present the concept in a concrete manner. Furthermore, in embodiments of the present invention, the meaning expressed by "and / or" can be both, or either one.

[0020] In the embodiments of this invention, the terms "image" and "picture" may sometimes be used interchangeably. It should be noted that, without emphasizing the distinction between them, they convey the same meaning. Similarly, the terms "of," "corresponding (relevant)," and "corresponding" may sometimes be used interchangeably. It should be noted that, without emphasizing the distinction between them, they convey the same meaning.

[0021] In this embodiment of the invention, sometimes a subscript such as W1 may be written in a non-subscript form such as W1. When the difference is not emphasized, the meaning they express is the same.

[0022] To make the technical problems, technical solutions and advantages of the present invention clearer, a detailed description will be given below in conjunction with the accompanying drawings and specific embodiments.

[0023] This invention provides a method for patient safety monitoring and feedback in stereotactic radiosurgery. This method can be implemented using a patient safety monitoring and feedback device for stereotactic radiosurgery, which can be a terminal or a server. Figure 1 The flowchart shown is for a patient safety monitoring and feedback method used in stereotactic radiosurgery. The process of this method may include the following steps:

[0024] Used for collecting radiotherapy treatment data, which includes raw planning data, target area information, organs at risk information, and baseline clinical information; Preferably, the radiotherapy data acquisition module includes: The radiotherapy planning parameters are collected to obtain the raw planning data, which include the prescription dose parameters, total irradiation duration, baseline dose rate, and dose rate dynamic change curve. Collect the geometric features of the target area to obtain target area information, wherein the geometric features of the target area include the location and / or volume of the target area; Geometric features of organs at risk are collected, and spatial relationship analysis is performed to obtain information about organs at risk, including spatial relationship data between the target area and the organs at risk. Clinical information is collected to obtain baseline clinical information, which includes age, gender, ECOG score and comorbidities, including hypertension, diabetes and history of cerebrovascular disease. By merging the original planning data, target area information, organ at risk information, and baseline clinical information, radiotherapy treatment data is obtained.

[0025] In some embodiments, target volume geometry features are extracted via CT. Raw data is exported in DICOM-RT format through the CT data export interface to ensure data integrity and accuracy. Target volume geometry features are delineated by physicians with clinical experience in radiation oncology.

[0026] It should be noted that the geometric features of organs at risk are typically extracted using distance measurement and overlapping volume calculation methods. The collected data includes characteristic parameters of organs at risk and spatial relationship measurements.

[0027] It should be further explained that the patient's unique identifier (hospitalization number + treatment sequence number) is used as the association key to match the patient information corresponding to each data source.

[0028] The method is used to obtain a pre-trained symptom type prediction model, which is a set of prediction models based on LSTM neural networks, including a first model for target location prediction and a second model for organ at risk distance prediction. Preferably, the symptom analysis model module includes: Historical case data of a predetermined number of patients undergoing brain radiotherapy were collected to obtain historical case data. The historical case data included radiotherapy planning parameters, pain scores and physiological change follow-up records, and physiological monitoring equipment record sheets. The radiotherapy planning parameters included dose rate time series and target area location or distance to organs at risk. The physiological monitoring equipment record sheets recorded real-time physiological change data collected during radiotherapy, including blood oxygen saturation, heart rate, and body movement. The pain scores and physiological change follow-up records were post-processed to extract the main symptom sequences, which were then added to the historical case data. The main symptom types included limb numbness / tingling, headache / dizziness, cardiovascular reaction, skin burning, visual abnormalities, or dysphagia. Based on the historical database, radiotherapy data feature vectors are extracted. These radiotherapy data feature vectors include mean dose rate, peak dose rate, slope of change, target volume, target location encoding, or distance to organs at risk. A symptom type prediction model is constructed based on a multi-layer neural network structure. The multi-layer neural network structure includes an input layer, a hidden layer, and an output layer. The input layer is used to receive the feature vector of radiotherapy data. The hidden layer adopts a bidirectional structure with 64 LSTM units. The output layer is used to output the prediction probability matrix of the main symptom type at a preset number of time nodes. The symptom type prediction model is a prediction model group based on LSTM neural network. The prediction model group includes a first model for target area location prediction and a second model for organ at risk distance prediction. Using the radiotherapy data features as input features, a symptom type prediction model is trained to obtain a pre-trained symptom type prediction model.

[0029] In some embodiments, the preset number is not less than 200 cases.

[0030] It should be noted that the target area was located using a three-dimensional coordinate system of the brain. The brainstem, optic nerve, and hippocampus were selected as the core organs at risk based on their distance from the target area.

[0031] It should be further noted that the pain score was calculated using the Numerical Rating Scale (NRS), with a score range of 0-10. The follow-up time points were set as follows: 1 day before radiotherapy, after the 5th radiotherapy session, after the 10th radiotherapy session, on the day the radiotherapy ended, and 1 month after radiotherapy. In the main example, the pain scores of one patient at each time point were 2, 3, 4, 3, and 2, respectively. The physiological change follow-up record included descriptions of subjective symptoms and physical examination results at each follow-up time point.

[0032] Preferably, real-time monitoring data is exported through physiological monitoring equipment to record physiological changes during radiotherapy (single radiotherapy session duration 4-15 minutes), including blood oxygen saturation (monitoring range 90%-100%, sampling frequency 1Hz), heart rate (monitoring range 60-120 beats / min, sampling frequency 1Hz), and body movement (monitored using an accelerometer, sampling frequency 5Hz, body movement intensity quantified using 0-5 levels).

[0033] Preferably, in the patient's radiotherapy treatment data file, the missing rate of each core data item (prescription dose, target area information, spatial relationship of organs at risk, key clinical information) should be less than 10%, and the missing rate of secondary data items (such as dose rate fluctuation details) should be ≤15%, with missing values ​​replaced by the mean.

[0034] For use in a pre-trained symptom type prediction model, a personalized minute-level monitoring and reminder scheme is obtained. The personalized minute-level monitoring and reminder scheme includes a predetermined number of time nodes and monitoring and reminder content corresponding to each time node. Preferably, the symptom warning module includes: Radiotherapy treatment data is input into a pre-trained symptom type prediction model to predict symptoms and obtain the output of symptom types. The output of symptom types includes the prediction of target area location and the prediction of organs at risk. The predicted target area location is combined with a knowledge base for matching analysis to identify N symptoms that may occur or may worsen, resulting in a priority symptom set. The knowledge base includes symptom association rules, symptom evolution paths, or symptom severity mapping tables. The prediction of the organs at risk is combined with a knowledge base for matching analysis to identify N symptoms that are currently occurring or may worsen, thus obtaining a set of secondary symptoms. Priority identifiers are assigned to each symptom in the priority symptom set to generate a priority observation sequence. When there is a gap in the priority observation sequence, symptoms are extracted from the secondary symptom set to supplement it, resulting in patient observation instructions. The patient observation instructions include reminder instructions to guide the patient in observing physical signs and manifestations. The reminder instructions are combined with the corresponding feedback mechanism to obtain a patient observation guidance plan and a doctor's monitoring focus. The patient observation guidance plan includes time point identifiers, monitoring content descriptions, expected symptom information, and / or feedback method descriptions. The feedback mechanism includes a binary yes or no assessment method to confirm discrete symptoms. The doctor's monitoring focus includes physiological parameter monitoring items, subjective feeling assessment items, or physical sign observation items. Based on the set of priority symptoms and the patient observation guidance plan, a personalized minute-level monitoring reminder plan is generated. The personalized minute-level monitoring reminder plan includes a predetermined number of time nodes and monitoring reminder content corresponding to each time node.

[0035] In some embodiments, the symptom warning module has a built-in knowledge base. The knowledge base data sources include industry guidelines and adverse reaction data of brain radiotherapy, covering symptom association rules (e.g., when the distance between the target area and the brainstem is ≤10mm, the correlation between headache and dizziness symptoms increases by 75%), symptom evolution paths (e.g., the evolution cycle from limb numbness to limb weakness is 3-7 days), and symptom severity mapping tables (pain scores of 0-2 indicate mild, 3-5 indicate moderate, and 6-10 indicate severe). N is set to 3 gradient values ​​to complete the symptom set identification.

[0036] It should be noted that examples of priority symptom set identification include: when the target area is near the hippocampus, the priority symptom set is "drowsiness, headache / dizziness, memory loss"; when the target area is near the brainstem, the priority symptom set is "headache / dizziness, limb numbness".

[0037] It should be further explained that there are two types of feedback mechanisms: symptom feedback mechanism (binary yes / no confirmation, such as "Do you have a headache? Yes / No") and symptom severity feedback mechanism (binary confirmation + severity rating, such as "Headache severity: mild / severe").

[0038] Preferably, the following are examples of reminders: 1 month after radiotherapy: remind to observe dizziness; 2 months after radiotherapy: remind to observe limb numbness (level 2); 3 months after radiotherapy: remind to observe headache and provide feedback on the severity of symptoms; 5 months after radiotherapy: remind to observe headache and provide feedback on the severity of symptoms; 8 months after radiotherapy: remind to observe visual abnormalities and limb numbness.

[0039] Preferably, this feedback mechanism requires only two buttons for the patient to operate, significantly reducing the risk of misoperation. For example: 1. 1 minute after radiotherapy: Reminds the patient to observe dizziness (Level 1), please press the "Yes" or "No" button for feedback; 2. 2 minutes after radiotherapy: Reminds the patient to observe limb numbness (Level 2), please press the "Yes" or "No" button for feedback; 3. 3 minutes after radiotherapy: Reminds the patient to observe headache, pressing "Yes" indicates mild, long press "Yes" indicates moderate, and pressing "Yes" twice consecutively indicates severe. If there is no headache, please press "No"; 4. 5 minutes after radiotherapy: Reminds the patient to observe headache, please provide feedback on symptom severity according to the above button rules; 5. 8 minutes after radiotherapy: Reminds the patient to observe visual abnormalities, please press the "Yes / No" button for feedback; subsequently, reminds the patient to observe limb numbness, please press the "Yes / No" button for feedback.

[0040] Used to obtain patient treatment process records, which include a time-symptom-dose correspondence sequence; Preferably, the real-time data acquisition module includes: Based on the generated personalized minute-level monitoring and reminder scheme, a multimodal reminder signal is obtained through the timed triggering mechanism during the radiotherapy treatment process. The multimodal reminder signal includes a voice broadcast signal and a vibration feedback signal. An auditory prompting module and a tactile feedback module are used for state guidance to obtain patient feedback. The state guidance includes short and clear verbal instructions and tactile alarms. The system collects real-time feedback from patients through a patient feedback terminal, and obtains feedback content with time nodes, including the presence and severity of symptoms. By using the parameter acquisition module of the radiotherapy equipment, radiotherapy operation data at this time point is collected to obtain the time-symptom-dose correspondence sequence; Based on the time-symptom-dose correspondence sequence, the patient's treatment process record is obtained through data integration and structuring.

[0041] Used to obtain multiple core vital signs and control commands, which are used to adjust or stop treatment to protect patient safety; Preferably, the data fusion module includes: During radiotherapy, multiple core vital signs of the patient are monitored to obtain real-time physiological parameters, including blood oxygen saturation, heart rate, and body movement. The patient's treatment process is recorded and then processed to obtain fused data. The fused data processing includes establishing a patient feedback-physiological parameter time correspondence table. The fused data is compared with baseline values ​​to obtain the magnitude of change in physiological parameters. The baseline comparison calculation includes calculating the magnitude of change in physiological parameters relative to the patient's baseline value. A threshold determination module is used to determine safety and obtain control instructions. The safety determination includes providing early warning information when any physiological feature parameter in the received set of physiological feature parameters exceeds its corresponding preset value. The control instructions are used to adjust or stop treatment to protect patient safety.

[0042] In some implementations, the timestamp-physiological parameter-patient key press feedback can be converted into a two-dimensional table, for example: It should be noted that setting preset blood oxygen saturation values ​​can significantly reduce the likelihood of doctors overlooking important vital signs, for example: Preset values ​​for blood oxygen saturation: lenient threshold (low value): ≤93% (warning), ≤90% (emergency stop); Heart rate preset values ​​(based on percentage change from baseline): Standard threshold (intermediate value): ±20% (warning), ±30% (emergency stop); Preset values ​​for physical activity level: Standard threshold (intermediate value): ≥3 (warning), ≥4 (emergency stop).

[0043] This is used to obtain a comprehensive monitoring report, which includes post-radiotherapy monitoring data, a summary of symptom occurrence, and an assessment of radiotherapy tolerance.

[0044] Preferably, the report generation module includes: By integrating radiotherapy treatment data, patient treatment process records, multiple core vital signs and control commands, post-radiotherapy monitoring data is obtained. Based on the post-radiotherapy monitoring data, after processing by the symptom statistics module, a summary of symptom occurrence is obtained. The summary of symptom occurrence includes all symptoms actually experienced by the patient during the entire radiotherapy process, the time of occurrence, or the severity. Based on the summary of symptom occurrence and through comprehensive scoring, a radiotherapy tolerance assessment is obtained, which is used to quantify the patient's overall tolerance to this radiotherapy. The post-radiotherapy monitoring data, symptom occurrence summary, and radiotherapy tolerance assessment are combined to obtain a comprehensive monitoring report, which is used to provide data support for subsequent radiotherapy plan adjustments.

[0045] The above is an introduction to the method embodiments. The following describes the solution described in this application through device embodiments.

[0046] Figure 3 This is a block diagram illustrating a patient safety monitoring and feedback device for stereotactic radiosurgery, according to an exemplary embodiment. The device is used for patient safety monitoring and feedback methods in stereotactic radiosurgery. (Refer to...) Figure 3 The device includes a radiotherapy data acquisition module, a symptom analysis model module, a symptom early warning module, a real-time data acquisition module, a data fusion module, and a report generation module.

[0047] Radiotherapy data acquisition module: used to acquire radiotherapy treatment data, including raw planning data, target area information, organs at risk information, and baseline clinical information; Symptom analysis model module: used to obtain a pre-trained symptom type prediction model, which is a prediction model group based on LSTM neural network, including a first model for target area location prediction and a second model for organ at risk distance prediction; Symptom warning module: used to obtain a personalized minute-level monitoring and reminder scheme based on a pre-trained symptom type prediction model. The personalized minute-level monitoring and reminder scheme includes a predetermined number of time nodes and monitoring and reminder content corresponding to each time node. Real-time data acquisition module: used to obtain patient treatment process records, which include time-symptom-dosage correspondence sequences; Data fusion module: used to obtain multiple core vital signs and control commands, which are used to adjust or stop treatment to protect patient safety; Report generation module: used to generate a comprehensive monitoring report, which includes post-radiotherapy monitoring data, a summary of symptom occurrence, and an assessment of radiotherapy tolerance.

[0048] A patient safety monitoring and feedback device for stereotactic radiosurgery, comprising: a processor; and a memory storing computer-readable instructions, wherein when executed by the processor, the computer-readable instructions implement any one of the above-described methods for patient safety monitoring and feedback in stereotactic radiosurgery.

[0049] A computer-readable storage medium, characterized in that the computer-readable storage medium stores program code, the program code being invoked by a processor to execute the method as described in any one of claims 1 to 7.

[0050] Figure 4This is a schematic diagram of a patient safety monitoring and feedback device for stereotactic radiosurgery provided in an embodiment of the present invention, as shown below. Figure 4 As shown, the patient safety monitoring and feedback device for stereotactic radiosurgery may include the above-mentioned Figure 3 The illustrated patient safety monitoring and feedback device for stereotactic radiosurgery is shown. Optionally, the patient safety monitoring and feedback device 410 for stereotactic radiosurgery may include a first processor 2001.

[0051] Optionally, the patient safety monitoring and feedback device 410 for stereotactic radiosurgery may also include a memory 2002 and a transceiver 2003.

[0052] The first processor 2001, memory 2002, and transceiver 2003 can be connected via a communication bus.

[0053] The following is combined with Figure 4 A detailed description of each component of the patient safety monitoring and feedback device 410 used in stereotactic radiosurgery is provided below: The first processor 2001 is the control center of the patient safety monitoring and feedback device 410 for stereotactic radiosurgery. It can be a single processor or a collective term for multiple processing elements. For example, the first processor 2001 can be one or more central processing units (CPUs), application-specific integrated circuits (ASICs), or one or more integrated circuits configured to implement embodiments of the present invention, such as one or more digital signal processors (DSPs), or one or more field-programmable gate arrays (FPGAs).

[0054] Optionally, the first processor 2001 can perform various functions of the patient safety monitoring and feedback device 410 for stereotactic radiosurgery by running or executing software programs stored in the memory 2002 and calling data stored in the memory 2002.

[0055] In a specific implementation, as one example, the first processor 2001 may include one or more CPUs, for example... Figure 4 CPU0 and CPU1 are shown in the diagram.

[0056] In a specific implementation, as one example, the patient safety monitoring and feedback device 410 for stereotactic radiosurgery may also include multiple processors, such as... Figure 4 The first processor 2001 and the second processor 2004 are shown in the diagram. Each of these processors can be a single-core processor or a multi-core processor. Here, a processor can refer to one or more devices, circuits, and / or processing cores used to process data (such as computer program instructions).

[0057] The memory 2002 is used to store the software program that executes the present invention, and is controlled by the first processor 2001 to execute it. The specific implementation method can be referred to the above method embodiment, and will not be repeated here.

[0058] Optionally, the memory 2002 may be a read-only memory (ROM) or other type of static storage device capable of storing static information and instructions, random access memory (RAM) or other type of dynamic storage device capable of storing information and instructions, or electrically erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed discs, laser discs, optical discs, digital universal discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited thereto. The memory 2002 may be integrated with the first processor 2001 or may exist independently, and may be connected via the interface circuit of the patient safety monitoring and feedback device 410 for stereotactic radiosurgery. Figure 4 (Not shown in the image) is coupled to the first processor 2001, and this embodiment of the invention does not specifically limit this.

[0059] The transceiver 2003 is used to communicate with network devices or with terminal devices.

[0060] Alternatively, transceiver 2003 may include a receiver and a transmitter. Figure 4 (Not shown separately). The receiver is used to implement the receiving function, and the transmitter is used to implement the transmitting function.

[0061] Optionally, the transceiver 2003 can be integrated with the first processor 2001 or exist independently, and can be connected via the interface circuit of the patient safety monitoring and feedback device 410 for stereotactic radiosurgery. Figure 4 (Not shown in the image) is coupled to the first processor 2001, and this embodiment of the invention does not specifically limit this.

[0062] It should be noted that, Figure 4 The structure of the patient safety monitoring and feedback device 410 for stereotactic radiosurgery shown in the diagram does not constitute a limitation on the router. Actual knowledge structure identification devices may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0063] Furthermore, the technical effects of the patient safety monitoring and feedback device 410 used for stereotactic radiosurgery can be referred to the technical effects of the patient safety monitoring and feedback method for stereotactic radiosurgery described in the above method embodiments, and will not be repeated here.

[0064] It should be understood that the first processor 2001 in the embodiments of the present invention may be a central processing unit (CPU), or it may be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc.

[0065] It should also be understood that the memory in the embodiments of the present invention can be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. The non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate synchronous DRAM (DDR SDRAM), enhanced synchronous DRAM (ESDRAM), synchronous linked DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0066] The above embodiments can be implemented, in whole or in part, by software, hardware (such as circuits), firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, all or part of the processes or functions described in the embodiments of the present invention are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more sets of available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. A semiconductor medium can be a solid-state drive.

[0067] It should be understood that the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. A and B can be singular or plural. Additionally, the character " / " in this article generally indicates an "or" relationship between the preceding and following related objects, but it can also represent an "and / or" relationship. Please refer to the context for a more accurate understanding.

[0068] In this invention, "at least one" means one or more, and "more than one" means two or more. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of a single item or a plurality of items. For example, at least one of a, b, or c can represent: a, b, c, ab, ac, bc, or abc, where a, b, and c can be a single item or multiple items.

[0069] It should be understood that, in various embodiments of the present invention, the order of the above-mentioned process numbers does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0070] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0071] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the devices, apparatuses, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0072] In the several embodiments provided by this invention, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another device, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0073] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0074] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0075] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0076] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method for patient safety monitoring and feedback in stereotactic radiosurgery, characterized in that, A system for patient safety monitoring and feedback in stereotactic radiosurgery, comprising: a monitoring planning unit, a monitoring unit, and a reporting unit; the monitoring planning unit including a radiotherapy data acquisition module and a symptom analysis model module; the monitoring unit including a symptom early warning module and a real-time data acquisition module; and the reporting unit including a data fusion module and a report generation module; characterized in that it includes: Radiotherapy data acquisition module: used to acquire radiotherapy treatment data, including raw planning data, target area information, organs at risk information, and baseline clinical information; Symptom analysis model module: used to obtain a pre-trained symptom type prediction model, which is a prediction model group based on LSTM neural network, including a first model for target area location prediction and a second model for organ at risk distance prediction; Symptom warning module: used to obtain personalized minute-level monitoring and reminder schemes, wherein the personalized minute-level monitoring and reminder schemes include a predetermined number of time nodes, and the monitoring and reminder content corresponding to each time node; Real-time data acquisition module: used to obtain patient treatment process records, which include time-symptom-dosage correspondence sequences; Data fusion module: used to obtain multiple core vital signs and control commands, which are used to adjust or stop treatment to protect patient safety; Report generation module: used to generate a comprehensive monitoring report, which includes post-radiotherapy monitoring data, a summary of symptom occurrence, and an assessment of radiotherapy tolerance.

2. The patient safety monitoring and feedback method for stereotactic radiosurgery according to claim 1, characterized in that, The radiotherapy data acquisition module includes: The radiotherapy planning parameters are collected to obtain the raw planning data, which include the prescription dose parameters, total irradiation duration, baseline dose rate, and dose rate dynamic change curve. Collect the geometric features of the target area to obtain target area information, wherein the geometric features of the target area include the location and / or volume of the target area; Geometric features of organs at risk are collected, and spatial relationship analysis is performed to obtain information about organs at risk, including spatial relationship data between the target area and the organs at risk. Clinical information is collected to obtain baseline clinical information, which includes age, gender, ECOG score and comorbidities, including hypertension, diabetes and history of cerebrovascular disease. By merging the original planning data, target area information, organ at risk information, and baseline clinical information, radiotherapy treatment data is obtained.

3. The patient safety monitoring and feedback method for stereotactic radiosurgery according to claim 1, characterized in that, The symptom analysis model module includes: Historical case data of a predetermined number of patients undergoing brain radiotherapy were collected to obtain historical case data. The historical case data included radiotherapy planning parameters, pain scores and physiological change follow-up records, and physiological monitoring equipment record sheets. The radiotherapy planning parameters included dose rate time series and target area location or distance to organs at risk. The physiological monitoring equipment record sheets recorded real-time physiological change data collected during radiotherapy, including blood oxygen saturation, heart rate, and body movement. The pain scores and physiological change follow-up records were post-processed to extract the main symptom sequences, which were then added to the historical case data. The main symptom types included limb numbness / tingling, headache / dizziness, cardiovascular reaction, skin burning, visual abnormalities, or dysphagia. Based on the historical database, radiotherapy data feature vectors are extracted. These radiotherapy data feature vectors include mean dose rate, peak dose rate, slope of change, target volume, target location encoding, or distance to organs at risk. A symptom type prediction model is constructed based on a multi-layer neural network structure. The multi-layer neural network structure includes an input layer, a hidden layer, and an output layer. The input layer is used to receive the feature vector of radiotherapy data, and the output layer is used to output the prediction probability matrix of the main symptom type at a preset number of time nodes. The symptom type prediction model is a prediction model group based on an LSTM neural network. The prediction model group includes a first model for target area location prediction and a second model for distance prediction of organs at risk. Using the radiotherapy data features as input features, a symptom type prediction model is trained to obtain a pre-trained symptom type prediction model.

4. The patient safety monitoring and feedback method for stereotactic radiosurgery according to claim 1, characterized in that, The symptom warning module includes: Radiotherapy treatment data is input into a pre-trained symptom type prediction model to predict symptoms and obtain the output of symptom types. The output of symptom types includes the prediction of target area location and the prediction of organs at risk. The predicted target area location is combined with a knowledge base for matching analysis to identify N symptoms that may occur or may worsen, resulting in a priority symptom set. The knowledge base includes symptom association rules, symptom evolution paths, or symptom severity mapping tables. The prediction of the organs at risk is combined with a knowledge base for matching analysis to identify N symptoms that are currently occurring or may worsen, thus obtaining a set of secondary symptoms. Priority identifiers are assigned to each symptom in the priority symptom set to generate a priority observation sequence. When there is a gap in the priority observation sequence, symptoms are extracted from the secondary symptom set to supplement it, resulting in patient observation instructions. The patient observation instructions include reminder instructions to guide the patient in observing physical signs and manifestations. The reminder instructions are combined with the corresponding feedback mechanism to obtain a patient observation guidance plan and a doctor's monitoring focus. The patient observation guidance plan includes time point identifiers, monitoring content descriptions, expected symptom information, and / or feedback method descriptions. The feedback mechanism includes a binary yes or no assessment method to confirm discrete symptoms. The doctor's monitoring focus includes physiological parameter monitoring items, subjective feeling assessment items, or physical sign observation items. Based on the set of priority symptoms and the patient observation guidance plan, a personalized minute-level monitoring reminder plan is generated. The personalized minute-level monitoring reminder plan includes a predetermined number of time nodes and monitoring reminder content corresponding to each time node.

5. The patient safety monitoring and feedback method for stereotactic radiosurgery according to claim 1, characterized in that, The real-time data acquisition module includes: Based on the generated personalized minute-level monitoring and reminder scheme, a multimodal reminder signal is obtained through the timed triggering mechanism during the radiotherapy treatment process. The multimodal reminder signal includes a voice broadcast signal and a vibration feedback signal. An auditory prompting module and a tactile feedback module are used for state guidance to obtain patient feedback. The state guidance includes short and clear verbal instructions and tactile alarms. The system collects real-time feedback from patients through a patient feedback terminal, and obtains feedback content with time nodes, including the presence and severity of symptoms. By using the parameter acquisition module of the radiotherapy equipment, radiotherapy operation data at this time point is collected to obtain the time-symptom-dose correspondence sequence; Based on the time-symptom-dose correspondence sequence, the patient's treatment process record is obtained through data integration and structuring.

6. The patient safety monitoring and feedback method for stereotactic radiosurgery according to claim 1, characterized in that, The data fusion module includes: During radiotherapy, multiple core vital signs of the patient are monitored to obtain real-time physiological characteristic parameters, including blood oxygen saturation, heart rate, and body movement. The patient's treatment process is recorded and then processed to obtain fused data. The fused data processing includes establishing a patient feedback-physiological parameter time correspondence table. The fused data is compared with baseline values ​​to obtain the magnitude of change in physiological parameters. The baseline comparison calculation includes calculating the magnitude of change in physiological parameters relative to the patient's baseline value. A threshold determination module is used to determine safety and obtain control instructions. The safety determination includes providing early warning information when any physiological feature parameter in the received set of physiological feature parameters exceeds its corresponding preset value. The control instructions are used to adjust or stop treatment to protect patient safety.

7. The patient safety monitoring and feedback method for stereotactic radiosurgery according to claim 1, characterized in that, The report generation module includes: By integrating radiotherapy treatment data, patient treatment process records, multiple core vital signs and control commands, post-radiotherapy monitoring data is obtained. Based on the post-radiotherapy monitoring data, after processing by the symptom statistics module, a summary of symptom occurrence is obtained. The summary of symptom occurrence includes all symptoms actually experienced by the patient during the entire radiotherapy process, the time of occurrence, or the severity. Based on the summary of symptom occurrence and through comprehensive scoring, a radiotherapy tolerance assessment is obtained, which is used to quantify the patient's overall tolerance to this radiotherapy. The post-radiotherapy monitoring data, symptom occurrence summary, and radiotherapy tolerance assessment are combined to obtain a comprehensive monitoring report, which is used to provide data support for subsequent radiotherapy plan adjustments.

8. A patient safety monitoring and feedback device for stereotactic radiosurgery, wherein the patient safety monitoring and feedback device for stereotactic radiosurgery is used to implement the patient safety monitoring and feedback method for stereotactic radiosurgery as described in any one of claims 1-7, characterized in that, The device includes: Radiotherapy data acquisition module: used to acquire radiotherapy treatment data, including raw planning data, target area information, organs at risk information, and baseline clinical information; Symptom analysis model module: used to obtain a pre-trained symptom type prediction model, which is a prediction model group based on LSTM neural network, including a first model for target area location prediction and a second model for organ at risk distance prediction; Symptom warning module: used to obtain personalized minute-level monitoring and reminder schemes, wherein the personalized minute-level monitoring and reminder schemes include a predetermined number of time nodes, and the monitoring and reminder content corresponding to each time node; Real-time data acquisition module: used to obtain patient treatment process records, which include time-symptom-dosage correspondence sequences; Data fusion module: used to obtain multiple core vital signs and control commands, which are used to adjust or stop treatment to protect patient safety; Report generation module: used to generate a comprehensive monitoring report, which includes post-radiotherapy monitoring data, a summary of symptom occurrence, and an assessment of radiotherapy tolerance.

9. A patient safety monitoring and feedback device for stereotactic radiosurgery, characterized in that, The patient safety monitoring and feedback processor for stereotactic radiosurgery; a memory storing computer-readable instructions that, when executed by the processor, implement the method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium contains program code that can be invoked by a processor to execute the method as described in any one of claims 1 to 7.

Images