Breast tumor patient postoperative rehabilitation management method and related equipment

Abstract

The invention discloses a postoperative rehabilitation management method for a breast tumor patient and related equipment. The method comprises the following steps: sending an exercise rehabilitation initialization instruction to a target patient under the condition that the intelligent wearable equipment monitors that the operative limb of the target patient is in a natural sagging state; under the condition that the target patient completes the exercise rehabilitation initialization instruction, positioning a shoulder joint on the operative limb side of the target patient based on a movement track collected by an intelligent wearable device; under the condition that the target patient carries out the operation limb movement rehabilitation, the operation limb movement pose of the target patient is predicted through the intelligent wearable device based on the obtained shoulder joint positioning of the target patient, so that movement rehabilitation management is carried out. The multiple problems that postoperative rehabilitation of breast tumors is a key link in continuous treatment, but at present, patient cognition is insufficient, medical resources are not evenly distributed, a rehabilitation path is not clear, and informatization support is insufficient can be solved.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of smart medical care. More specifically, the present invention relates to a postoperative rehabilitation management method and related equipment for breast cancer patients. Background Art

[0002] Currently, breast cancer is one of the most common malignant tumors in women worldwide, and surgery (such as mastectomy or breast-conserving surgery) is the main treatment method. With medical advances, the overall survival rate of breast cancer has increased, but postoperative physical function recovery, psychological reconstruction and improvement of quality of life have become the focus of rehabilitation. Postoperative rehabilitation not only includes wound healing, but also emphasizes upper limb function recovery, lymphedema prevention, psychological adaptation and social function reconstruction. It is an indispensable part of the whole process of breast cancer management. Many patients or their families equate postoperative rehabilitation with recuperation and do not attach importance to scientific rehabilitation training. Postoperative upper limb activity guidance is not standardized, and patients avoid activities for fear of involving the wound, resulting in shoulder joint movement disorders. Postoperative rehabilitation for breast tumors is a key link in continuous treatment, but it is still faced with multiple problems such as insufficient patient awareness, uneven distribution of medical resources, unclear rehabilitation pathways, and insufficient information support. Summary of the Invention

[0003] The Summary of the Invention introduces a series of simplified concepts that will be further described in the Detailed Description of the Invention. The Summary of the Invention is not intended to limit the key features and essential features of the claimed technical solution, nor is it intended to determine the scope of protection of the claimed technical solution.

[0004] To address the challenges of breast cancer postoperative rehabilitation, a key component of ongoing treatment, which currently faces multiple challenges, including insufficient patient awareness, uneven distribution of medical resources, unclear rehabilitation pathways, and insufficient information technology support, the present invention proposes a method for postoperative rehabilitation management of breast cancer patients. The method comprises:

[0005] When the smart wearable device detects that the target patient's operated limb is in a naturally drooping state, a motor rehabilitation initialization instruction is sent to the target patient, wherein the motor rehabilitation initialization instruction is used to instruct the target patient to swing the operated limb upward by a preset angle along the plane where the body is located from the naturally drooping state, and the smart wearable device is used to be worn on the wrist of the target patient's operated limb;

[0006] When the target patient completes the exercise rehabilitation initialization instruction, positioning the shoulder joint of the target patient on the operated limb side based on the movement trajectory collected by the smart wearable device;

[0007] When the target patient undergoes motor rehabilitation of the operated limb, the active posture of the operated limb of the target patient is predicted by the smart wearable device based on the obtained shoulder joint positioning of the target patient to perform motor rehabilitation management.

[0008] Optionally, when the target patient completes the exercise rehabilitation initialization instruction, positioning the shoulder periphery of the target patient on the operated limb side based on the movement trajectory collected by the smart wearable device includes:

[0009] When the target patient completes the exercise rehabilitation initialization instruction, determining the radius and center position of the trajectory arc based on the movement trajectory collected by the smart wearable device;

[0010] The center position of the circle is determined as the relative position of the target patient's operated limb side shoulder joint and the operated limb side wrist.

[0011] Optionally, when the target patient is undergoing motor rehabilitation of the operated limb, the target patient's operated limb activity posture is predicted by the smart wearable device based on the obtained shoulder joint positioning of the target patient to perform motor rehabilitation management, including:

[0012] When the target patient is undergoing motor rehabilitation of the operated limb, the relative position change between the wrist and the operated limb side shoulder joint of the target patient is calculated based on the wrist posture change collected by the smart wearable device;

[0013] The activity posture of the target patient's operated limb is predicted based on the relative position change to perform sports rehabilitation management.

[0014] Optionally, predicting the target patient's surgical limb activity posture based on the relative position change to perform sports rehabilitation management includes:

[0015] Predicting the target patient's surgical limb activity posture based on the relative position change to determine the activity limit range of the surgical limb;

[0016] Formulate exercise rehabilitation action recommendations for the target patient based on historical activity limit range.

[0017] Optionally, predicting the target patient's surgical limb activity posture based on the relative position change to perform sports rehabilitation management includes:

[0018] The matching degree between the target patient's surgical limb activity posture and the ideal activity posture is predicted based on the relative position change, and action prompts are provided.

[0019] Optionally, also include:

[0020] Upon receiving a request for manual drainage assistance for edema from a patient, generating a reminder for the smart wearable device to wear the healthy limb;

[0021] The intelligent wearable device collects the activity posture of the healthy limb end to provide action prompts when the healthy limb performs manual drainage operation on the operated limb side.

[0022] Optionally, also include:

[0023] Upon receiving an edema pressure therapy assistance request from a patient, collecting operation video information;

[0024] Based on the collected operation video information, action prompts are provided for edema pressure treatment.

[0025] In a second aspect, the present invention further provides a postoperative rehabilitation management device for breast cancer patients, comprising:

[0026] a sending unit, configured to send a motor rehabilitation initialization instruction to the target patient when the smart wearable device detects that the target patient's operated limb is in a naturally drooping state, wherein the motor rehabilitation initialization instruction is used to instruct the target patient to swing the operated limb upward by a preset angle along the plane where the body is located from the naturally drooping state, and the smart wearable device is used to be worn on the wrist of the target patient's operated limb;

[0027] a positioning unit, configured to locate the shoulder joint of the target patient on the operated limb side based on the movement trajectory collected by the smart wearable device when the target patient completes the exercise rehabilitation initialization instruction;

[0028] A management unit is used to predict the target patient's surgical limb activity posture through the smart wearable device based on the obtained shoulder joint positioning of the target patient when the target patient is undergoing surgical limb motor rehabilitation, so as to perform motor rehabilitation management.

[0029] In a third aspect, an electronic device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor is configured to implement the steps of the postoperative rehabilitation management method for breast cancer patients as described in any one of the first aspects above when executing the computer program stored in the memory.

[0030] In a fourth aspect, the present invention further proposes a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the postoperative rehabilitation management method for breast cancer patients according to any one of the above items in the first aspect.

[0031] In summary, the postoperative rehabilitation management method for breast cancer patients proposed in this application involves sending a motor rehabilitation initialization instruction to the target patient when a smart wearable device detects that the target patient's operated limb is in a naturally drooping state. The motor rehabilitation initialization instruction is used to instruct the target patient to swing the operated limb upward from the naturally drooping state to a preset angle along the body plane. The smart wearable device is worn on the wrist of the target patient's operated limb. When the target patient completes the motor rehabilitation initialization instruction, the shoulder joint on the operated limb side of the target patient is located based on the movement trajectory captured by the smart wearable device. When the target patient undergoes motor rehabilitation of the operated limb, the smart wearable device is used to predict the active posture of the target patient's operated limb based on the obtained shoulder joint positioning to perform motor rehabilitation management. This allows rehabilitation training to be actively guided by the system rather than passively relying on the patient's subjective judgment, reducing the probability of training delays, improving rehabilitation compliance, and providing a unified starting reference for subsequent posture estimation. The method can establish an accurate rehabilitation movement reference system based on individual differences, making subsequent training trajectory and movement amplitude judgment individually adaptable and quantifiable, solving the problems of inaccurate subjective judgment and large fluctuations in movement starting points in traditional training. It not only supports real-time correction and feedback of postoperative rehabilitation movements, but also can quantify the quality and effect of the training process, build a complete postoperative rehabilitation data closed loop, and assist doctors in remote personalized rehabilitation guidance.

[0032] The postoperative rehabilitation management method for breast tumor patients of the present invention, and other advantages, objectives and features of the present invention will be reflected in part through the following description, and in part will be understood by those skilled in the art through research and practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Various other advantages and benefits will become apparent to those skilled in the art upon reading the detailed description of the preferred embodiment below. The accompanying drawings are for illustration purposes only and are not to be considered as limiting the present description. The same reference symbols are used throughout the drawings to represent the same components. In the drawings:

[0034] Figure 1 A schematic flow chart of a postoperative rehabilitation management method for breast cancer patients provided in an embodiment of the present application;

[0035] Figure 2 A schematic diagram of the structure of a postoperative rehabilitation management device for breast cancer patients provided in an embodiment of the present application;

[0036] Figure 3 A schematic diagram of the structure of an electronic device for postoperative rehabilitation management of breast cancer patients provided in an embodiment of the present application. DETAILED DESCRIPTION

[0037] The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of this application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments described herein can be implemented in a sequence other than that illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or that are inherent to these processes, methods, products or devices. The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the embodiments described are only part of the embodiments of the present application, not all of the embodiments.

[0038] To solve the problem that the current test data is usually presented only in numerical values, doctors still need to rely on experience to interpret, which is easily affected by personal ability, and doctors, nurses and patients lack channels to interpret test results. The laboratory department involves a large amount of data, but the data is currently mostly stored in static documents, which makes the query inefficient. Please refer to Figure 1 , is a flow chart of a postoperative rehabilitation management method for breast cancer patients provided in an embodiment of the present application, which may specifically include: steps S110 to S130.

[0039] S110, when the smart wearable device detects that the target patient's operated limb is in a natural drooping state, a motor rehabilitation initialization instruction is sent to the target patient, and the motor rehabilitation initialization instruction is used to instruct the target patient to swing the operated limb upward by a preset angle along the plane of the body from the natural drooping state, and the smart wearable device is used to be worn on the wrist of the target patient's operated limb.

[0040] S120: When the target patient completes the exercise rehabilitation initialization instruction, the shoulder joint of the target patient on the operated limb side is positioned based on the movement trajectory collected by the smart wearable device.

[0041] S130, when the target patient is undergoing motor rehabilitation of the operated limb, the active posture of the operated limb of the target patient is predicted by the smart wearable device based on the obtained shoulder joint positioning of the target patient, so as to perform motor rehabilitation management.

[0042] For example, during a patient's daily postoperative routine, a smart wearable device (such as a wristband with an integrated IMU sensor) continuously monitors the spatial posture and resting characteristics of the operated limb. This device, worn on the wrist on the operated side, uses an accelerometer to identify the direction of gravity and a gyroscope to measure angular velocity, thereby determining the patient's resting posture. When the system detects that the operated limb is in a naturally drooping state (i.e., the acceleration direction is essentially vertically downward, and the angular velocity approaches zero for a certain period of time), the patient is deemed to be in a training preparation state. At this point, the device proactively issues an "exercise rehabilitation initialization" instruction to the patient via an app pop-up window, voice announcement, or vibration reminder, prompting the patient to raise the operated limb from its naturally drooping position to the side of the body, forward or sideways, to a specified training angle (e.g., 60° forward). The core principle of this process is to use the inertial measurement unit to identify a standard resting posture, thereby ensuring that training exercises begin from a "standard starting point" and avoiding trajectory deviations caused by initial posture inaccuracies. This mechanism enables rehabilitation training to be actively guided by the system rather than passively relying on the patient's subjective judgment, reducing the probability of training delays, improving rehabilitation compliance, and providing a unified starting reference for subsequent posture estimation.

[0043] For example, once the patient begins to perform a lifting movement, the smart wrist device continuously collects the three-axis acceleration and angular velocity changes of the operated limb in space at a high frequency (e.g., 50Hz). Combined with the known reference pose of the initial drooping state, the wrist's posture trajectory in three dimensions is calculated in real time using a posture fusion algorithm (such as complementary filtering, Madgwick filtering, or Mahony filtering). Leveraging the anatomical geometric relationship between the shoulder joint and wrist (i.e., upper arm length and initial posture orientation), the current spatial position of the shoulder joint and its trajectory can be estimated using an inverse kinematic solution. To improve accuracy, the system may require input of characteristic parameters such as patient height, arm length, and weight before surgery or during initial setup as a reference for human body modeling. This step is based on the rigid body motion constraints, deriving a mapping relationship between the distal upper limb sensor trajectory and the proximal joint motion, thereby achieving dynamic spatial positioning of the shoulder joint. This allows for the establishment of a precise rehabilitation movement reference system based on individual differences, making subsequent training trajectory and movement amplitude judgment individually adaptable and quantifiable, addressing the issues of subjective judgment and large fluctuations in movement starting points in traditional training.

[0044] For example, as the patient completes a lifting movement, the system combines continuously collected wrist trajectory data with shoulder joint positioning data to construct a real-time sequence of motion postures for the operated limb. By establishing a local coordinate system with the shoulder joint as the origin and combining it with the wrist position change vector, key kinematic parameters such as the trajectory, range of motion, maximum angle, and average velocity of the operated limb can be derived. The system uses a motion analysis model (which can be a rule-based model or a trained machine learning model, such as an LSTM or GRU) to determine whether the current posture meets the spatial trajectory and velocity requirements of the target rehabilitation training movement. If abnormal patterns occur, such as excessively small angles, discontinuous movements, or shrugging compensation during movement, the system will promptly issue voice or graphical correction prompts. After training is completed, the device automatically generates a rehabilitation assessment report, including metrics such as the maximum abduction angle of the activity, movement continuity score, and number of correction reminders, and uploads it to a cloud database for remote evaluation by the physician. The core principle of this step is to achieve intelligent recognition and quality assessment of complex multi-degree-of-freedom limb movements through spatial posture calculation and trajectory modeling. This mechanism not only supports real-time correction and feedback of postoperative rehabilitation movements, but also quantifies the quality and effectiveness of the training process, builds a complete postoperative rehabilitation data closed loop, and assists doctors in remote personalized rehabilitation guidance.

[0045] In summary, the postoperative rehabilitation management method for breast cancer patients provided in the embodiments of the present application includes sending a motor rehabilitation initialization instruction to the target patient when a smart wearable device detects that the target patient's operated limb is in a naturally drooping state. The motor rehabilitation initialization instruction is used to instruct the target patient to swing the operated limb upward from the naturally drooping state to a preset angle along the body plane. The smart wearable device is worn on the wrist of the target patient's operated limb. When the target patient completes the motor rehabilitation initialization instruction, the shoulder joint of the target patient's operated limb is located based on the movement trajectory captured by the smart wearable device. When the target patient undergoes motor rehabilitation of the operated limb, the smart wearable device is used to predict the active posture of the target patient's operated limb based on the obtained shoulder joint positioning to perform motor rehabilitation management. This allows rehabilitation training to be actively guided by the system rather than passively relying on the patient's subjective judgment, reducing the probability of training delays, improving rehabilitation compliance, and providing a unified starting reference for subsequent posture estimation. It is possible to establish an accurate rehabilitation movement reference system based on individual differences, making subsequent training trajectory and movement amplitude judgment individually adaptable and quantifiable, solving the problems of inaccurate subjective judgment and large fluctuations in movement starting points in traditional training. It not only supports real-time correction and feedback of postoperative rehabilitation movements, but also can quantify the quality and effect of the training process, build a complete postoperative rehabilitation data closed loop, and assist doctors in remote personalized rehabilitation guidance.

[0046] According to some embodiments, when the target patient completes the exercise rehabilitation initialization instruction, positioning the shoulder periphery of the target patient on the operated limb side based on the movement trajectory collected by the smart wearable device includes:

[0047] When the target patient completes the exercise rehabilitation initialization instruction, determining the radius and center position of the trajectory arc based on the movement trajectory collected by the smart wearable device;

[0048] The center position of the circle is determined as the relative position of the target patient's operated limb side shoulder joint and the operated limb side wrist.

[0049] For example, after the target patient completes the system-issued initialization command for rehabilitation to raise the operated limb, the smart wearable device worn on the wrist of the operated limb continuously collects three-dimensional acceleration and angular velocity data during the movement of the operated limb. Based on this data, the system constructs the spatial trajectory of the lifting movement. Since in the initial stages of rehabilitation training, the patient is guided to perform lifting movements that approximate a circular arc along the coronal or sagittal plane of the body, it is reasonable to assume that the wrist trajectory approximates a circular arc in space. The system estimates the radius and center coordinates of this arc by processing the sequence of collected trajectory points (e.g., using least squares fitting or three-point arc fitting). Since the upper arm, as a rigid connector, forms the end point of the rotation radius with the wrist, its center of rotation is the approximate position of the shoulder joint. Therefore, the center coordinates obtained from the fitting can be used as the inferred reference point for "wrist relative to shoulder joint," thereby achieving spatial localization of the shoulder joint on the operated limb side. This localization method does not rely on imaging methods but is based on geometric trajectory inversion, offering the advantages of being non-invasive, real-time, and portable.

[0050] Understandably, this method leverages the fundamental principle in rigid body kinematics that the trajectory of the end points of a single-degree-of-freedom rotating rigid body is a circular arc, and combines spatial interpolation and fitting of the trajectory points to infer the center of rotation, namely the shoulder joint. This method transcends the limitations of traditional methods that rely on subjective arm length estimation or sensor fusion errors. It can generate a personalized shoulder-wrist relationship model based on each patient's actual movement, improving posture recognition accuracy and training standardization. Furthermore, this mechanism allows for dynamic adjustment of the shoulder joint reference point to adapt to changes in patient movement, making it suitable for situations where the shoulder joint position shifts or compensation patterns evolve after surgery.

[0051] In some examples, when the target patient is undergoing motor rehabilitation of the operated limb, predicting the target patient's operated limb activity posture through the smart wearable device based on the obtained shoulder joint positioning of the target patient to perform motor rehabilitation management includes:

[0052] When the target patient is undergoing motor rehabilitation of the operated limb, the relative position change between the wrist and the operated limb side shoulder joint of the target patient is calculated based on the wrist posture change collected by the smart wearable device;

[0053] The activity posture of the target patient's operated limb is predicted based on the relative position change to perform sports rehabilitation management.

[0054] For example, after the target patient enters the motor rehabilitation phase of the operated limb, the smart wearable device will frequently collect spatial posture information of the operated limb's wrist, including key data such as Euler angles (or quaternions), spatial coordinates, and velocity. Combined with the spatial reference point of the shoulder joint (i.e., the center of the wrist rotation arc) previously obtained through trajectory fitting methods, the system calculates the spatial vector difference between the wrist and the shoulder joint within each time slice. This is the current wrist position minus the shoulder joint coordinates, resulting in a sequence of spatial vectors reflecting the amplitude and direction of upper arm rotation. Because the upper arm is a nearly rigid structure, the shoulder-wrist line can be considered the main axis of the operated limb. Based on this, the system establishes a two-point configuration model of the shoulder joint and wrist to infer the spatial posture of the entire operated limb. In a continuous time series, the system derives dynamic parameters such as the operated limb's spatial rotation angle, range of motion (e.g., frontal extension, abduction angle), and movement rhythm based on the relative position vector changes in each frame, combined with the time step. To determine posture trends, dynamic learning and pattern recognition can be supplemented by temporal neural networks such as LSTM to form a personalized posture change model. The system can set comparison rules with the standard rehabilitation movement model. If it is found that the angle does not reach the training threshold, the movement is too fast or accompanied by abnormal swinging, it will automatically issue a real-time correction prompt (such as "the movement range is insufficient" or "please slow down the hand raising speed").

[0055] It is understandable that this step performs rigid body posture deduction, combined with spatial vector difference calculation, to construct the spatial activity trajectory of the patient's operated limb. The system uses the structural logic of known base points and terminal dynamics to complete the restoration of the posture of the entire limb from single-point wrist data. It can adapt to the patient's free lifting movements at different speeds, angles, and paths; it can evaluate the training quality in real time, such as whether the movement meets the angle requirements and whether there are compensatory movements; it can generate quantitative rehabilitation indicators; and it supports remote intervention by rehabilitation therapists or doctors and adjustment of training plans, significantly improving the scientific nature and individual adaptability of rehabilitation.

[0056] In some examples, predicting the target patient's surgical limb activity posture based on the relative position change to perform sports rehabilitation management includes:

[0057] Predicting the target patient's surgical limb activity posture based on the relative position change to determine the activity limit range of the surgical limb;

[0058] Formulate exercise rehabilitation action recommendations for the target patient based on historical activity limit range.

[0059] For example, during the rehabilitation training of the operated limb, the system performs real-time analysis on the wrist spatial trajectory and known shoulder joint positioning data collected by the smart wearable device, calculates the position change vector of the wrist relative to the shoulder joint in a continuous time series, and thereby predicts the dynamic activity posture of the operated limb. In this process, the system can deduce the maximum extension distance and angle change of the operated limb in each direction in three-dimensional space, and automatically identify the patient's operating limb activity limit range in the movement cycle based on the extreme points in the time series, including multi-dimensional indicators such as the forward angle limit, abduction amplitude limit, internal rotation and external rotation activity limits. This limit range reflects both the patient's current physical recovery level and the changing trend of his or her movement execution ability. The system establishes an individualized rehabilitation ability evolution curve by storing and statistically analyzing historical activity limit data in different training cycles. Based on this historical trend, combined with the patient's postoperative recovery period (e.g., week 2, week 6), basic diagnostic information (e.g., procedure type, muscle tension score), and risk thresholds (e.g., avoiding sudden over-extension), the system automatically generates personalized rehabilitation exercise recommendations, such as target angle, number of repetitions, movement rhythm, and auxiliary training modes, for patients to refer to during daily training. These recommendations can be presented through the mobile app interface or as voice prompts in real time during training.

[0060] It is understandable that activity limits, as an external manifestation of muscle elasticity, soft tissue adhesion, and nerve stretching capacity, can more objectively reflect the patient's current level of rehabilitation of the operated limb. By analyzing the dynamic fluctuation trends of these extreme values ​​on the timeline and combining them with the physiological laws of early rehabilitation (e.g., significant active lifting is not recommended in the first two weeks after surgery), the system can construct a rehabilitation plan that combines risk avoidance with gradual progress. This makes training goals scientifically adjustable, avoids one-size-fits-all standard rehabilitation movements, and ensures that task goals match current abilities. Phased progress is quantified and visualized, and doctors can use the extreme value curve to determine whether rehabilitation is stagnant, regressing, or progressing. This enables the generation of individual dynamic training suggestions and the adaptive adjustment of movement amplitude, speed, and frequency, enhancing compliance and rehabilitation effectiveness.

[0061] In some examples, predicting the target patient's surgical limb activity posture based on the relative position change to perform sports rehabilitation management includes:

[0062] The matching degree between the target patient's surgical limb activity posture and the ideal activity posture is predicted based on the relative position change, and action prompts are provided.

[0063] For example, when the patient's operated limb performs rehabilitation training movements, the smart wearable device will collect the spatial posture changes of the wrist in real time, and combine it with the known shoulder joint positioning to continuously calculate the relative position vector and posture parameters (such as direction cosine matrix, Euler angle or quaternion) of the operated limb at each time point. The system uses this data to deduce the actual activity posture sequence of the current operated limb. At the same time, the system pre-stores an ideal standard activity posture model corresponding to the current training project. The model can be derived from the recommended movements in the rehabilitation guide, or it can be constructed through expert data annotation, motion capture system or excellent patient sample library, and is usually represented by a series of spatial point trajectories or angle-time curves. During the actual training process, the system matches and compares the current active posture of the operated limb with the ideal model frame by frame, and uses DTW (dynamic time warping), angle cosine similarity, vector angle or posture error function to quantify the matching degree or deviation value of the current movement (such as error angle, path offset, timing mismatch rate). When the system detects that the matching degree drops below the preset threshold (such as matching similarity <85%, deviation angle >10°), it can generate real-time action prompts, such as "the movement amplitude is too small", "please raise your arms", "the movement is too fast, please slow down the pace" and other voice or graphic feedback to prompt the patient to make timely adjustments.

[0064] It is understandable that based on rigid body posture estimation theory and motion similarity measurement methods, a spatial dynamic posture model is constructed using high-frequency sensor data, which is then aligned with a standardized rehabilitation movement model to achieve quantitative matching analysis. This system can identify posture deviations in real time, enabling immediate detection of non-standard movements during training to prevent the solidification of compensation patterns. It can quantify the quality of standard movement execution and assess the progress or regression of patients' rehabilitation movements through matching trends. It can assist in movement guidance and personalized intervention, providing timely reminders when patients fail to perceive errors, thereby improving training effectiveness. It also supports remote rehabilitation movement comparison evaluation, allowing doctors to monitor the training quality of multiple patients in the background and provide video coaching.

[0065] In some examples, this also includes:

[0066] Upon receiving a request for manual drainage assistance for edema from a patient, generating a reminder for the smart wearable device to wear the healthy limb;

[0067] The intelligent wearable device collects the activity posture of the healthy limb end to provide action prompts when the healthy limb performs manual drainage operation on the operated limb side.

[0068] For example, during the postoperative rehabilitation process, if the patient shows signs of lymphedema on the upper limb on the surgical side, the patient can actively send a manual drainage assistance request through the patient-side APP. After receiving the request, the system identifies the current demand type as self-manual drainage, that is, the patient attempts to perform lymphatic fluid drainage massage on the surgical side limb through the healthy limb. In order to improve the accuracy and effectiveness of the drainage action, the system will generate a healthy limb wearing prompt to guide the patient to wear the smart wearable device on the healthy wrist as a motion collection and guidance end. After the device is started, the system collects the spatial posture data of the healthy limb in real time through the IMU module (accelerometer and gyroscope), and combines the standard motion model of the drainage path (such as a slow sweeping trajectory from the back of the hand on the surgical side to the forearm to the upper arm to the armpit) to intelligently identify and analyze the motion path, speed, and rhythm of the current healthy limb. When it is recognized that the movement deviates from the standard path (such as not covering the key lymphatic drainage area, moving too fast, or pausing unevenly) or the technique is wrong (such as too much force, wrong angle), the system automatically generates real-time correction prompts, such as "Please keep the sweeping direction from the distal end to the armpit", "Please slow down the movement speed" or "Pay attention to the angle of contact between the palm and the skin", and provides feedback to the patient through APP voice broadcast or graphic prompts.

[0069] It is understandable that by combining the spatial trajectory analysis of healthy limb movements with the position assumption of the operated limb, it is possible to deduce whether effective drainage path coverage has been achieved. By incorporating the drainage movements of traditional passive-dependent training into the standardized management and control of wearable devices and movement modeling, the system can achieve dynamic supervision and real-time correction of self-drainage effects. It can realize the digital management of auxiliary movements on the non-operated side and expand the functional boundaries of wearable devices; it can avoid incorrect drainage techniques that lead to ineffective drainage or damage to the operated limb, and improve the safety of lymphatic return training; it supports personalized rhythm prompts and manipulation practice modes to enhance patients' self-management capabilities at home; it forms traceable drainage training data to provide support for medical staff to evaluate training frequency and manipulation accuracy.

[0070] In some examples, this also includes:

[0071] Upon receiving an edema pressure therapy assistance request from a patient, collecting operation video information;

[0072] Based on the collected operation video information, action prompts are provided for edema pressure treatment.

[0073] It is understandable that in the rehabilitation management of edema after breast tumor surgery, when the patient makes a pressure therapy assistance request through the rehabilitation APP or voice control system, the system starts the video acquisition module to guide the patient to record the pressure therapy process in video, focusing on collecting the bandaging action and bandage status information. The system uses the built-in or mobile phone camera to capture real-time images of the bandaging process, and combines AI visual recognition algorithms (such as OpenPose motion recognition and image stretching detection modules) to analyze the key action nodes of the patient's operation, including the bandage winding angle, the winding path coverage, and whether the number of layers and directions are alternating. At the same time, before bandaging each circle of bandage, the system collects the pre-bandage stretching state image information of the corresponding segment of the bandage (i.e., the bandage stretch length and texture deformation in the current handheld state), and predicts the actual bandaging pressure generated by the current bandage through a pre-trained image stretch-tension mapping model (such as a regression network based on CNN or Vision Transformer). The system will compare the estimated current bandage pressure with the preset ideal bandage pressure range (for example, set according to the limb part and the degree of swelling, such as 30-40mmHg) in real time. If the deviation is too large (such as 18mmHg at present), a tension adjustment operation prompt will be generated, such as "Please increase the bandage tension" or "Please reduce the pulling length to avoid overpressure". This feedback will guide the patient to correct the bandage operation in real time through interface prompts or voice broadcasts. The system will continue to collect and analyze the stretching state image and update the bandage pressure estimate in real time until it detects that the pressure value has stably fallen into the ideal range and maintained for more than 2 seconds. At this time, the system will generate a bandage instruction message, such as "The current bandage pressure is appropriate, please fix the bandage and proceed to the next round of bandage" to ensure that each round of wrapping meets the treatment requirements.

[0074] It is understandable that by combining image texture deformation with a physical model of material stress, an AI learning method is used to construct a mapping relationship between the bandage stretching image and the actual pressure, and real-time analysis and feedback are provided during the action sequence. At the same time, the standard pressure is used as a dynamic control target to form a self-regulating control closed loop. The non-contact quantification of bandage tension and dressing pressure improves bandaging accuracy; the introduction of a synchronous feedback mechanism between action execution and pressure control avoids under- or over-pressure caused by traditional empirical bandaging. This helps to standardize and improve the safety of patients' self-help pressure treatment, reducing the need for follow-up visits. The entire operation record is traceable, facilitating remote evaluation and optimization of rehabilitation interventions.

[0075] For example, a patient with postoperative lymphedema uses an elastic bandage for bandage application at home. The system uses the mobile phone camera to identify the bandage's stretched length and texture deformation in real time, and determines that the current bandage pressure is 22 mmHg (the target is 35 mmHg). It prompts: "The current bandage pressure is low, please increase the stretching moderately." The patient adjusts the stretching amplitude for the next circle according to the prompt. After re-analysis, the system prompts: "The current pressure is 34 mmHg, which is close to the ideal value. Please continue to maintain it." The final report generated: The average bandage pressure is 33.8 mmHg, the bandage action compliance rate is 92%, and it is recommended to maintain the current bandage method this week.

[0076] According to some embodiments, the action prompts for edema pressure therapy based on the acquisition of operation video information include: after the bandaging phase of postoperative edema pressure therapy is completed, the system further collects image information of the stretched state of the bandage covering the surface of the affected limb after bandaging through a smart terminal (such as a mobile phone or a head-mounted device). The image can reflect the length deformation, texture extension, interlayer coverage and local uneven force of the current bandage under pressure. The system uses computer vision technology (such as CNN+regression network or Vision Transformer) to extract key texture features (such as texture spacing, stretching direction angle, and uneven density distribution) from the image and combines the material stretching model corresponding to the position area (such as forearm, upper arm, wrist, etc.) to deduce the actual pressure estimate of each bandaged area. To ensure safety and efficacy, the system will compare the estimated pressure with the preset ideal bandaging pressure range (such as the recommended pressure for the forearm is 30-40 mmHg, and for the upper arm is 25-35 mmHg). If the difference between the estimated pressure and the target value exceeds the preset threshold (such as ±5 mmHg), the system will issue a re-bandaging reminder and mark the prompt area (such as "The bandaging pressure near the elbow of the upper arm is insufficient, it is recommended to readjust the tightness of the bandage"). The system will prompt the patient or caregiver to take appropriate measures through graphic overlay, voice feedback or vibration reminders.

[0077] It is understandable that, based on the principle that the surface texture structure of the bandage in the bandaged state is highly correlated with the pressure applied to it, especially in the case of elastic materials, different stretching degrees will form observable characteristic patterns in the image (such as the widening of equidistant lines, surface wrinkle angles, etc.), the "image feature-pressure value" mapping can be completed through a learning model; and then the regional pressure model is used to complete the location determination and multi-segment pressure integration. Achieve post-bandaging quality verification and improve treatment safety; automatically identify local overpressure or underpressure areas during the bandaging process to avoid secondary injuries caused by uneven pressure; build a closed loop of bandaging status, actual pressure and image feature data, and continuously optimize the tension model and image recognition network; enhance patients' confidence in independent treatment and operational capabilities, and reduce the frequency of reliance on nursing intervention.

[0078] For example, suppose a patient completes an upper limb elastic bandage six weeks after surgery and uses a mobile phone camera to capture the bandaged area. The system analyzes the image and responds with: "Current pressure at the distal forearm is 22 mmHg, below the ideal range of 30–40 mmHg. It is recommended to readjust the stretching and proceed to the next bandage." A red overlay box marks the area. The patient follows the prompt to re-bandage and capture the image again. The system confirms the pressure is 32 mmHg and prompts: "Bandage is acceptable. Proceed to the next exercise."

[0079] See also Figure 2 An embodiment of the postoperative rehabilitation management device for breast cancer patients in the embodiments of the present application may include:

[0080] a sending unit 21 configured to send a motor rehabilitation initialization instruction to the target patient when the smart wearable device detects that the target patient's operated limb is in a naturally drooping state, wherein the motor rehabilitation initialization instruction is used to instruct the target patient to swing the operated limb upward by a preset angle along the plane of the body from the naturally drooping state, and the smart wearable device is used to be worn on the wrist of the target patient's operated limb;

[0081] a positioning unit 22 for positioning the shoulder joint of the target patient on the operated limb side based on the movement trajectory collected by the smart wearable device when the target patient completes the exercise rehabilitation initialization instruction;

[0082] The management unit 23 is used to predict the target patient's surgical limb activity posture through the smart wearable device based on the obtained shoulder joint positioning of the target patient when the target patient is undergoing surgical limb motor rehabilitation, so as to perform motor rehabilitation management.

[0083] In summary, the postoperative rehabilitation management device for breast cancer patients provided in the embodiments of the present application sends a motor rehabilitation initialization instruction to the target patient when the smart wearable device detects that the target patient's operated limb is in a naturally drooping state. The motor rehabilitation initialization instruction is used to instruct the target patient to swing the operated limb upward from the naturally drooping state to a preset angle along the body plane. The smart wearable device is used to be worn on the wrist of the target patient's operated limb. When the target patient completes the motor rehabilitation initialization instruction, the shoulder joint of the target patient's operated limb is located based on the movement trajectory captured by the smart wearable device. When the target patient undergoes motor rehabilitation of the operated limb, the smart wearable device is used to predict the active posture of the target patient's operated limb based on the obtained shoulder joint positioning to perform motor rehabilitation management. Rehabilitation training is actively guided by the system rather than passively relying on the patient's subjective judgment, reducing the probability of training delay, improving rehabilitation compliance, and providing a unified starting reference for subsequent posture estimation. It can establish an accurate rehabilitation movement reference system based on individual differences, making subsequent training trajectory and movement amplitude judgment individually adaptable and quantifiable, solving the problems of inaccurate subjective judgment and large fluctuations in movement starting points in traditional training. It not only supports real-time correction and feedback of postoperative rehabilitation movements, but also can quantify the quality and effect of the training process, build a complete postoperative rehabilitation data closed loop, and assist doctors in remote personalized rehabilitation guidance.

[0084] like Figure 3 As shown, an embodiment of the present application further provides an electronic device 300, including a memory 310, a processor 320, and a computer program 311 stored in the memory 320 and executable on the processor. When the processor 320 executes the computer program 311, the steps of any one of the above-mentioned methods for postoperative rehabilitation management of breast cancer patients are implemented:

[0085] When the smart wearable device detects that the target patient's operated limb is in a naturally drooping state, a motor rehabilitation initialization instruction is sent to the target patient, wherein the motor rehabilitation initialization instruction is used to instruct the target patient to swing the operated limb upward by a preset angle along the plane where the body is located from the naturally drooping state, and the smart wearable device is used to be worn on the wrist of the target patient's operated limb;

[0086] When the target patient completes the exercise rehabilitation initialization instruction, positioning the shoulder joint of the target patient on the operated limb side based on the movement trajectory collected by the smart wearable device;

[0087] When the target patient undergoes motor rehabilitation of the operated limb, the active posture of the operated limb of the target patient is predicted by the smart wearable device based on the obtained shoulder joint positioning of the target patient to perform motor rehabilitation management.

[0088] Since the electronic device introduced in this embodiment is a device used to implement a postoperative rehabilitation management device for breast cancer patients in the embodiment of this application, based on the method introduced in the embodiment of this application, technical personnel in this field can understand the specific implementation of the electronic device of this embodiment and its various variations. Therefore, how the electronic device implements the method in the embodiment of this application will not be introduced in detail here. As long as the equipment used by technical personnel in this field to implement the method in the embodiment of this application falls within the scope of protection of this application.

[0089] In the specific implementation process, the computer program 311 can be implemented when executed by the processor Figure 1 Any implementation manner in the corresponding embodiment:

[0090] When the smart wearable device detects that the target patient's operated limb is in a naturally drooping state, a motor rehabilitation initialization instruction is sent to the target patient, wherein the motor rehabilitation initialization instruction is used to instruct the target patient to swing the operated limb upward by a preset angle along the plane where the body is located from the naturally drooping state, and the smart wearable device is used to be worn on the wrist of the target patient's operated limb;

[0091] When the target patient completes the exercise rehabilitation initialization instruction, positioning the shoulder joint of the target patient on the operated limb side based on the movement trajectory collected by the smart wearable device;

[0092] When the target patient undergoes motor rehabilitation of the operated limb, the active posture of the operated limb of the target patient is predicted by the smart wearable device based on the obtained shoulder joint positioning of the target patient to perform motor rehabilitation management.

[0093] It should be noted that, in the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant description of other embodiments.

[0094] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0095] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0096] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0097] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0098] The present application also provides a computer program product, which includes computer software instructions. When the computer software instructions are executed on a processing device, the processing device is caused to execute the following Figure 1 The process of postoperative rehabilitation management for breast cancer patients in the corresponding embodiment.

[0099] A computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function according to the embodiment of the present application is generated in whole or in part. 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 computer-readable storage medium. 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 a wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) method. The computer-readable storage medium can be any available medium that a computer can store or a data storage device such as a server or data center that includes one or more available media integrated. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid state drive (SSD)).

[0100] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0101] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of units is only a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interface, device or unit, which can be electrical, mechanical or other forms.

[0102] Units described as separate components may or may not be physically separate, and 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 these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0103] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0104] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the various embodiments of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0105] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for postoperative rehabilitation management of breast tumor patients, characterized in that: include: When the smart wearable device detects that the target patient's operated limb is in a naturally drooping state, a motor rehabilitation initialization instruction is sent to the target patient, wherein the motor rehabilitation initialization instruction is used to instruct the target patient to swing the operated limb upward by a preset angle along the plane where the body is located from the naturally drooping state, and the smart wearable device is used to be worn on the wrist of the target patient's operated limb; When the target patient completes the exercise rehabilitation initialization instruction, positioning the shoulder joint of the target patient on the operated limb side based on the movement trajectory collected by the smart wearable device; When the target patient undergoes motor rehabilitation of the operated limb, the active posture of the operated limb of the target patient is predicted by the smart wearable device based on the obtained shoulder joint positioning of the target patient to perform motor rehabilitation management.

2. The method according to claim 1, wherein When the target patient completes the exercise rehabilitation initialization instruction, positioning the shoulder periphery of the target patient on the operated limb side based on the movement trajectory collected by the smart wearable device includes: When the target patient completes the exercise rehabilitation initialization instruction, determining the radius and center position of the trajectory arc based on the movement trajectory collected by the smart wearable device; The center position of the circle is determined as the relative position of the target patient's operated limb side shoulder joint and the operated limb side wrist.

3. The method according to claim 2, wherein When the target patient is undergoing motor rehabilitation of the operated limb, predicting the target patient's operated limb activity posture through the smart wearable device based on the obtained shoulder joint positioning of the target patient to perform motor rehabilitation management, including: When the target patient is undergoing motor rehabilitation of the operated limb, the relative position change between the wrist and the operated limb side shoulder joint of the target patient is calculated based on the wrist posture change collected by the smart wearable device; The activity posture of the target patient's operated limb is predicted based on the relative position change to perform sports rehabilitation management.

4. The method according to claim 3, wherein The method of predicting the target patient's surgical limb activity posture based on the relative position change to perform sports rehabilitation management includes: Predicting the target patient's surgical limb activity posture based on the relative position change to determine the activity limit range of the surgical limb; Formulate exercise rehabilitation action recommendations for the target patient based on historical activity limit range.

5. The method according to claim 3, wherein The method of predicting the target patient's surgical limb activity posture based on the relative position change to perform sports rehabilitation management includes: The matching degree between the target patient's surgical limb activity posture and the ideal activity posture is predicted based on the relative position change, and action prompts are provided.

6. The method according to claim 1, wherein Also includes: Upon receiving a request for manual drainage assistance for edema from a patient, generating a reminder for the smart wearable device to wear the healthy limb; The intelligent wearable device collects the activity posture of the healthy limb end to provide action prompts when the healthy limb performs manual drainage operation on the operated limb side.

7. The method according to claim 1, wherein Also includes: Upon receiving an edema pressure therapy assistance request from a patient, collecting operation video information; Based on the collected operation video information, action prompts are provided for edema pressure treatment.

8. A postoperative rehabilitation management device for breast cancer patients, characterized in that: include: a sending unit, configured to send a motor rehabilitation initialization instruction to the target patient when the smart wearable device detects that the target patient's operated limb is in a naturally drooping state, wherein the motor rehabilitation initialization instruction is used to instruct the target patient to swing the operated limb upward by a preset angle along the plane where the body is located from the naturally drooping state, and the smart wearable device is used to be worn on the wrist of the target patient's operated limb; a positioning unit, configured to locate the shoulder joint of the target patient on the operated limb side based on the movement trajectory collected by the smart wearable device when the target patient completes the exercise rehabilitation initialization instruction; A management unit is used to predict the target patient's surgical limb activity posture through the smart wearable device based on the obtained shoulder joint positioning of the target patient when the target patient is undergoing surgical limb motor rehabilitation, so as to perform motor rehabilitation management.

9. An electronic device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor is configured to implement the steps of the postoperative rehabilitation management method for breast tumor patients as described in any one of claims 1 to 7 when executing the computer program stored in the memory.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the postoperative rehabilitation management method for breast tumor patients according to any one of claims 1 to 7 is implemented.

Images