Newborn encephalopathy assessment system

Abstract

The invention discloses a newborn encephalopathy assessment system, and relates to the technical field of newborn encephalopathy assessment. The invention aims to improve the evaluation effect on neonatal encephalopathy. Comprising a whole body motion (GMs) quality evaluation unit which can record and analyze activity awakening state videos of the newborns so as to identify and classify GMs of the newborns and identify high-risk children with abnormal motion development in the early stage; and the neurology evaluation unit is used for evaluating the maturity of the nervous system of the newborn by detecting a plurality of indexes such as adaptive capacity, muscular tension and original reflex of the newborn. According to the neonatal training system, the whole-body movement quality of the neonatal is evaluated, multiple indexes such as the adaptive capacity, the muscular tension and the original reflex of the neonatal are comprehensively evaluated in combination with the neurology evaluation unit, and the comprehensive evaluation is beneficial for doctors to more accurately know the nervous system development condition of the neonatal, so that a personalized treatment scheme is formulated, and the neonatal training efficiency is improved. The treatment effect is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of neonatal encephalopathy assessment, and in particular to a neonatal encephalopathy assessment system. Background Art

[0002] In the prior art, neonatal encephalopathy refers to abnormalities in the brain structure and / or function of newborns due to various reasons before and after birth, which may cause a series of motor, cognitive, emotional and behavioral disorders. Since the nervous system of newborns is not fully developed, early encephalopathy assessment is crucial for timely identification of abnormalities, formulation of rehabilitation plans and improvement of prognosis.

[0003] Traditional neonatal encephalopathy assessment mainly relies on the physician's clinical experience, neurological examination, and imaging diagnosis. However, these methods are often limited by the physician's personal experience, subjective judgment, and the accuracy and availability of equipment. In addition, traditional assessment methods may be difficult to accurately identify abnormal motor development in the early stages (including the preterm stage), resulting in a delay in the best time for early rehabilitation intervention.

[0004] In view of the above background, the present invention proposes a new neonatal encephalopathy assessment system to achieve a comprehensive, objective and accurate assessment of the neurodevelopmental status of neonates, improve the accuracy and reliability of neonatal encephalopathy assessment, and provide strong support for early rehabilitation intervention. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings of the prior art and to propose a neonatal encephalopathy assessment system.

[0006] In order to achieve the above object, the present invention adopts the following technical solutions:

[0007] A system for evaluating encephalopathy in newborns, comprising a unit for evaluating the quality of general movements (GMs):

[0008] The unit is able to record and analyze videos of newborns' active wakefulness to identify and classify GMs in newborns and identify those at high risk for abnormal motor development at an early stage;

[0009] Neurological Assessment Unit:

[0010] This unit assesses the maturity of the newborn's nervous system by testing multiple indicators including adaptability, muscle tone and primitive reflexes.

[0011] Preferably: the GMs quality assessment unit includes a video recording facility, which uses a professional camera or a high-performance smartphone to record videos while using soft and uniform light to understand the status of the newborn.

[0012] Further: the GMs quality assessment unit also includes a video processing module, which can pre-process the recorded video, including denoising, contrast enhancement, brightness adjustment, and use a video processing algorithm to detect the motion area in the video, extract the movement trajectory and features of the infant, and GMs-related features, such as the amplitude, speed, direction, and frequency of the movement.

[0013] Further: The evaluation system further includes an artificial intelligence algorithm module, which is capable of using a deep learning model, such as a convolutional neural network (CNN) or a recurrent neural network (RNN), to classify GMs, and use a large amount of labeled GMs video data to train and tune the model.

[0014] As a preferred solution of the present invention: the artificial intelligence algorithm module can also perform intelligent analysis on the collected video, identify the movements, expressions, and reactions of the newborn, evaluate its autonomous movement ability, contact and reaction ability, and use sensors to collect the newborn's physiological data, such as heart rate, respiratory rate, and blood oxygen saturation, and use AI technology to perform intelligent analysis on the physiological data to evaluate the newborn's physiological state and health condition.

[0015] As a further solution of the present invention: the evaluation system also combines brain MRI images and EEG data, uses AI technology to perform brain function analysis, and evaluates the development and functional status of the newborn's cerebral hemispheres, ventricles, thalamus, and bilateral basal ganglia regions.

[0016] As a further embodiment of the present invention: the specific assessment steps of the neurological assessment unit include placing a red ball in front of the eyes of the newborn to observe its tracking ability, using a rattle or soft sound stimulation to observe its auditory response, using a tactile stimulus to gently touch the newborn to observe its reaction sensitivity, performing passive muscle tension tests and active muscle tension tests, and observing the hug reflex.

[0017] On the basis of the above scheme: During the assessment preparation stage, the neurological assessment unit selects a warm and softly lit room for the assessment, ensures that the newborn is in a comfortable state, and prepares red balls, rattles, tactile stimuli, and a recording sheet or electronic device for recording the assessment results.

[0018] On the basis of the above scheme: the evaluation system can generate a detailed evaluation report according to the GMs classification results and neurological evaluation results, including the classification of GMs, evaluation basis, observations and suggestions, as well as various indicators and result analysis of neurological evaluation.

[0019] The beneficial effects of the present invention are:

[0020] 1. A neonatal encephalopathy assessment system that can identify high-risk infants with abnormal motor development in the early neonatal period through a general movement (GMs) quality assessment unit, which helps doctors take timely rehabilitation intervention measures to prevent or reduce the damage of encephalopathy to the neonatal nervous system, thereby improving their future quality of life.

[0021] 2. A neonatal encephalopathy assessment system that not only evaluates the quality of the neonate's overall movement, but also combines with a neurological assessment unit to conduct a comprehensive assessment of multiple indicators such as the neonate's adaptability, muscle tone, and primitive reflexes. This comprehensive assessment helps doctors understand the neonate's nervous system development more accurately, thereby formulating personalized treatment plans and improving treatment outcomes.

[0022] 3. A neonatal encephalopathy assessment system that uses an automated assessment method based on video processing technology and artificial intelligence algorithms to improve the efficiency and accuracy of the assessment. Doctors only need to record a video of the newborn and input relevant information, and the system can automatically complete the analysis and assessment and generate a detailed assessment report. This not only saves doctors’ time and energy, but also improves the objectivity and reliability of the assessment.

[0023] 4. A neonatal encephalopathy assessment system that uses advanced artificial intelligence technologies such as deep learning to continuously learn and optimize the assessment model. With the accumulation of data and the improvement of algorithms, the system's assessment accuracy and generalization ability will continue to improve, providing more precise support for the early detection and treatment of neonatal encephalopathy.

[0024] 5. A neonatal encephalopathy assessment system that helps parents understand the neonatal nervous system development through observing the assessment process and learn how to observe and promote the neonatal neurodevelopment at home, which helps to enhance parents' attention and participation in the neonatal health. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 This is a system block diagram of a neonatal encephalopathy assessment system proposed by the present invention. DETAILED DESCRIPTION

[0026] The technical solution of this patent is further described in detail below in conjunction with specific implementation methods.

[0027] The embodiments of the present invention are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and cannot be understood as limiting the present invention.

[0028] Embodiment 1:

[0029] A neonatal encephalopathy assessment system includes a general movement (GMs) quality assessment unit. GMs quality assessment can identify high-risk infants with abnormal motor development outcomes at an early stage (including the preterm stage) and guide early rehabilitation intervention. The specific assessment process includes the following categories:

[0030] (1) Video recording facilities

[0031] Use a professional camera or a high-performance smartphone to record the video to ensure it is clear;

[0032] Use a stable tripod to keep the picture stable;

[0033] Ensure that the light is soft and even, LED light or natural light can be used;

[0034] Turn on the recording to record the newborn's voice and fully understand its condition;

[0035] (2) Video recording environment settings

[0036] Keep the background simple and distraction-free;

[0037] The space needs to be spacious and safe;

[0038] Ensure appropriate temperature and humidity, and make newborns comfortable to wear;

[0039] (3) Video recording process and guidance

[0040] Newborns are videotaped while awake and active, and stimulated with music and physical contact;

[0041] Record movement characteristics, reactions, and emotional states;

[0042] (4) Based on video processing technology and artificial intelligence algorithms, GMs are identified and classified. The identification and classification process includes the following steps:

[0043] 1: Process the video

[0044] Collect basic information of the newborn, including date of birth, gender, weight, height, and medical history of the newborn, including the mother's pregnancy, delivery process, and various indicators and characteristics of the newborn after birth;

[0045] Use high-resolution video equipment to record the baby's active wakefulness state video and then pre-process the video, including denoising, contrast enhancement, brightness adjustment, motion detection and tracking;

[0046] Use video processing algorithms, such as background subtraction and frame difference, to detect moving areas in the video;

[0047] Track the detected motion area and extract the baby's motion trajectory and features;

[0048] Extract GMs-related features from the video, such as the amplitude, speed, direction, frequency, etc. of the movement;

[0049] The feature selection algorithm is used to screen out the features that have the greatest influence on the classification of GMs.

[0050] 2: Using artificial intelligence algorithms for learning and model optimization and verification

[0051] Build deep learning models, such as convolutional neural networks (CNNs) or recurrent neural networks (RNNs), for classification of GMs;

[0052] Use a large amount of labeled GMs video data to train the model so that it can automatically learn and identify the characteristics of GMs;

[0053] Tune the trained model to improve its classification accuracy and generalization ability;

[0054] Use an independent validation dataset to validate the model to ensure its reliability in practical applications; apply the trained model to new GMs video data to achieve automated classification;

[0055] AI technology is used to intelligently analyze the collected videos to identify the movements, expressions, and reactions of newborns; by analyzing the newborns’ limb movements, head rotations, facial expressions, etc., their autonomous movement ability, contact, and reaction abilities are evaluated;

[0056] Use sensors to collect newborns' physiological data, such as heart rate, respiratory rate, blood oxygen saturation, etc., and use AI technology to intelligently analyze the physiological data to assess the newborns' physiological state and health;

[0057] Combining brain MRI images and EEG data, AI technology is used to analyze brain function and assess the development and functional status of the newborn's cerebral hemispheres, ventricles, thalamus, bilateral basal ganglia and other areas;

[0058] Based on the classification results, a detailed assessment report is generated, including the classification of GMs, assessment basis, observations and recommendations;

[0059] The evaluation system also includes a neurological evaluation unit, which evaluates the maturity of the newborn's nervous system by detecting multiple indicators such as the adaptability, muscle tension, and primitive reflexes of the newborn. The evaluation process includes the following steps:

[0060] (1) Assessment preparation

[0061] Choose a warm, softly lit room for the assessment and make sure the newborn is comfortable;

[0062] Prepare assessment tools such as red balls, tactile stimuli such as rattles, and record sheets or electronic devices to record assessment results;

[0063] (1) Refinement of evaluation steps

[0064] Place a red ball about 20 cm in front of the newborn's eyes, slowly move the red ball left and right, and observe whether the newborn's eyes can accurately track the movement of the red ball;

[0065] Gently shake a rattle or make a soft sound next to the newborn's ear and observe whether the newborn shows any auditory response such as frowning or turning his head;

[0066] Use a gentle tactile stimulus (such as a finger or a soft-bristled brush) to gently touch the newborn's hands, feet, or cheeks to see if they respond quickly.

[0067] Passive muscle tension test: by checking the newborn's scarf sign, forearm retraction, lower limb rebound, and popliteal angle, etc., to assess whether its passive muscle tension is normal;

[0068] Ask the newborn to try to lift his head while lying on his back to observe the active contraction of the cervical flexor and extensor muscles; gently pull the newborn's hands or feet to observe whether he or she shows active muscle tone of clenching or resistance;

[0069] Hold the newborn upright with both feet touching the ground or the assessor's hands and observe whether the newborn will take steps on his own.

[0070] By suddenly changing the newborn's posture or sound stimulation, observe whether he or she will have a hugging reflex of abducting the arms, clenching the fists and pressing them against the chest.

[0071] The above is a preferred specific implementation manner of the present invention, and the protection scope of the present invention is not limited thereto. Any modification, equivalent substitution and improvement made by any technician familiar with the field within the technical scope disclosed by the present invention in combination with the prior art or public common sense, within the spirit and principle of the present invention, shall be covered by the protection scope of the present invention.

Claims

1. A system for evaluating encephalopathy in newborns, characterized in that: Includes a unit for assessing the quality of general movements (GMs): The unit is able to record and analyze videos of newborns' active wakefulness to identify and classify GMs in newborns and identify those at high risk for abnormal motor development at an early stage; Neurological Assessment Unit: This unit assesses the maturity of the newborn's nervous system by testing multiple indicators including adaptability, muscle tone and primitive reflexes.

2. A neonatal encephalopathy assessment system according to claim 1, characterized in that: The GMs quality assessment unit includes a video recording facility that uses a professional camera or a high-performance smartphone to record videos while using soft and uniform light to understand the status of the newborn.

3. A neonatal encephalopathy assessment system according to claim 2, characterized in that: The GMs quality assessment unit also includes a video processing module, which can pre-process the recorded video, including denoising, contrast enhancement, brightness adjustment, and use a video processing algorithm to detect the motion area in the video, extract the movement trajectory and features of the infant, and GMs-related features such as the amplitude, speed, direction, and frequency of the movement.

4. A neonatal encephalopathy assessment system according to claim 3, characterized in that: The evaluation system further includes an artificial intelligence algorithm module, which is capable of classifying GMs using a deep learning model, such as a convolutional neural network (CNN) or a recurrent neural network (RNN), and training and tuning the model using a large amount of labeled GMs video data.

5. A neonatal encephalopathy assessment system according to claim 4, characterized in that: The artificial intelligence algorithm module can also perform intelligent analysis on the collected videos, identify the movements, expressions, and reactions of newborns, evaluate their autonomous movement ability, contact and reaction ability, and use sensors to collect the newborn's physiological data, such as heart rate, respiratory rate, and blood oxygen saturation. Through AI technology, the physiological data can be intelligently analyzed to evaluate the newborn's physiological state and health condition.

6. A neonatal encephalopathy assessment system according to claim 5, characterized in that: The evaluation system also combines brain MRI images and EEG data, and uses AI technology to perform brain function analysis to evaluate the development and functional status of the newborn's cerebral hemispheres, ventricles, thalamus, and bilateral basal ganglia regions.

7. A neonatal encephalopathy assessment system according to claim 6, characterized in that: The specific assessment steps of the neurological assessment unit include placing a red ball in front of the newborn's eyes to observe its tracking ability, using a rattle or soft sound stimulation to observe its auditory response, using a tactile stimulus to gently touch the newborn to observe its reaction sensitivity, performing passive muscle tension tests and active muscle tension tests, and observing the hug reflex.

8. A neonatal encephalopathy assessment system according to claim 7, characterized in that: During the assessment preparation stage, the neurological assessment unit selects a warm and softly lit room for the assessment, ensures that the newborn is in a comfortable state, and prepares a red ball, a rattle tactile stimulus, and a recording sheet or electronic device for recording the assessment results.

9. A neonatal encephalopathy assessment system according to claim 8, characterized in that: The evaluation system can generate a detailed evaluation report based on the GMs classification results and neurological evaluation results, including the classification of GMs, evaluation basis, observations and suggestions, and various indicators and result analysis of neurological evaluation.

Images