Ultrasonic technology-based sarcopenia risk prediction method and system, and storage medium
The ultrasound-based sarcopenia risk prediction method using muscle thickness and functional measures addresses the limitations of existing technologies by offering a simple and accurate diagnostic tool for sarcopenia, enhancing clinical utility and applicability.
Patent Information
- Application Number
- CN202411114261.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-14
- Publication Date
- 2024-12-20
AI Technical Summary
Existing methods for diagnosing sarcopenia, such as DXA and BIA, are expensive, have radiation risks, are not portable, and lack widespread applicability, while ultrasound technology has not been effectively utilized for a reliable sarcopenia risk prediction model.
A sarcopenia risk prediction method using ultrasound technology measures the thickness of the vastus lateralis and tibialis anterior muscles, combined with grip strength and gait speed, to calculate a prediction probability P using a logistic regression model.
The method provides a simple, reliable, and highly accurate sarcopenia risk prediction, suitable for widespread application, especially in settings lacking DXA or BIA equipment, and supports clinical diagnosis and individualized evaluation.
Smart Images
Figure CN119170248A_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the technical field of sarcopenia risk prediction, and in particular, relates to a sarcopenia risk prediction method, system and storage medium based on ultrasound technology. Background Art
[0002] Sarcopenia is a disease characterized by age-related loss of muscle mass, decreased muscle strength and / or decreased physical function. The onset of sarcopenia is insidious, increasing the risk of falls, disability and death in the elderly, and seriously impairing their quality of life and health. With the aging of the population, sarcopenia has placed a heavy burden on my country's medical system and society. Therefore, early detection of sarcopenia is crucial.
[0003] Sarcopenia is mainly diagnosed by evaluating muscle mass, muscle strength and physical function. At present, the evaluation of muscle strength and physical function is mainly determined by grip strength and gait speed, which are also relatively simple and easy. The evaluation methods of muscle mass include computed tomography (CT), magnetic resonance imaging (MRI), dual-energy X-ray absorptiometry (DXA) and bioelectrical impedance analysis (BIA). CT and MRI can accurately measure skeletal muscle content, but they are expensive, cannot be checked at the bedside, CT is radioactive, and MRI is time-consuming; these shortcomings limit their clinical application in the evaluation of sarcopenia, and they are currently only used for scientific research. DXA and BIA are currently the most commonly used examination methods for diagnosing sarcopenia. However, DXA equipment is expensive, has radiation, and is not portable enough. BIA is not suitable for patients with pacemakers, therapeutic stents, etc., and there are large differences between different models of BIA equipment, which affects the accuracy of the results. Many grassroots hospitals still lack DXA and BIA equipment, which also limits the diagnosis of sarcopenia. Therefore, exploring new technologies that can be widely promoted and applied is of great value to the evaluation of sarcopenia. Ultrasound can accurately assess muscle mass, and it is easy and simple to operate. It can be performed at the bedside and has no contraindications for people who are unable to undergo DXA or BIA examinations. Ultrasound equipment is also widely used in primary hospitals and has great application value.
[0004] At present, more and more studies are using ultrasound to assess sarcopenia at home and abroad. Studies have found that muscle thickness and muscle cross-sectional area measured by ultrasound are significantly correlated with muscle mass measured by MRI or DXA. Our previous studies also found that the cross-sectional area of the biceps brachii and gastrocnemius thickness measured by ultrasound can be used to assess sarcopenia. However, no sarcopenia risk prediction model based on ultrasound technology with significant predictive effect has been seen in the existing technology. Summary of the invention
[0005] In view of the shortcomings of the existing technology (DXA cannot be widely popularized and applied, and BIA has relatively poor accuracy), the purpose of the present invention is to provide a sarcopenia risk prediction method, system and storage medium based on ultrasound technology, and proposes a sarcopenia risk prediction model based on ultrasound technology. The method is simple and easy to implement, and the prediction accuracy is high.
[0006] In order to achieve the above-mentioned purpose, the present invention adopts the following technical solutions:
[0007] A method for predicting sarcopenia risk based on ultrasound technology comprises the following steps:
[0008] 1) The gender, age, grip strength and gait speed of the subjects were collected, and the thickness of the vastus lateralis (VL) and tibialis anterior (TA) were measured by ultrasound technology.
[0009] 2) Calculate the predicted probability P:
[0010] P=e logit(P) / 1+e logit(P) ;
[0011] Logit(P)=9.072-3.560gender+0.052age-2.048TA-1.848VL-0.169grip-0.721gait;
[0012] Wherein, gender indicates gender, gender = 0 when the gender is male, and gender = 1 when the gender is female; age indicates age; VL indicates the thickness of the vastus lateralis muscle; TA indicates the thickness of the tibialis anterior muscle; grip indicates grip strength; gait indicates walking speed;
[0013] 3) When the predicted probability P is between 0.5 and 1, it is predicted to be a high risk of sarcopenia, otherwise it is a low risk.
[0014] Preferably, the grip strength is collected by measuring the grip strength using a JAMAR manual dynamometer according to an international standard test method.
[0015] Preferably, the grip strength measurement method is as follows: the examinee sits on a standard chair with a backrest and flat armrests, with the forearms placed on the armrests, the wrists exactly in the middle of the ends of the chair armrests, the thumbs facing up, and the feet flat on the ground; the thumb is wrapped around one side of the gripper handle and the four fingers around the other side, and the gripper is squeezed for as long as possible until the pointer stops rising; the measurement is repeated twice with the right hand and the left hand respectively, and the maximum value is taken.
[0016] Preferably, the walking speed measurement method is as follows: the person being inspected stands still behind the starting mark line. When the inspector gives the command to start, the person being inspected begins walking at a normal speed. The inspector starts timing when the person's first foot steps out and lands, and stops timing when the person's first foot completely crosses the 4-meter finish line.
[0017] Preferably, a mindray M9 ultrasound machine is used to perform muscle ultrasound examination to measure the thickness of the vastus lateralis muscle and the tibialis anterior muscle.
[0018] Preferably, the thickness of the vastus lateralis muscle and the tibialis anterior muscle are measured as follows: the vastus lateralis muscle uses the distance between the anterior superior iliac spine and the lateral femoral condyle and is marked 2 / 3 of the distance from the anterior superior iliac spine; the tibialis anterior muscle uses the thickest part from the inferior side of the patella to the lateral malleolus, approximately 1 / 4 to 1 / 3 of the distance from the patella; the subject is measured in a supine and relaxed position, with the linear probe perpendicular to the skin surface; when measuring the thickness of the vastus lateralis muscle, the direction is parallel to the longitudinal axis of the body; when measuring the thickness of the tibialis anterior muscle, the direction is perpendicular to the longitudinal axis of the body; the thickness between the muscle fascia is taken as the final value.
[0019] A sarcopenia risk prediction system based on ultrasound technology, comprising:
[0020] A data collection module is used to input the gender, age, grip strength and walking speed of the examinee, and collect the thickness of the vastus lateralis (VL) and the thickness of the tibialis anterior (TA) of the examinee through a muscle ultrasound examination device;
[0021] The risk prediction module calculates the prediction probability P based on the data collected by the data acquisition module;
[0022] P=e logit(P) / 1+e logit(P) ;
[0023] Logit(P)=9.072-3.560gender+0.052age-2.048TA-1.848VL-0.169grip-0.721gait;
[0024] Among them, gender represents gender, gender=0 when the gender is male, and gender=1 when the gender is female; age represents age; VL represents the thickness of the vastus lateralis muscle; TA represents the thickness of the tibialis anterior muscle; grip represents grip strength; and gait represents walking speed.
[0025] Preferably, when the predicted probability P is between 0.5 and 1, it is predicted to be a high risk of sarcopenia, otherwise it is a low risk.
[0026] Preferably, the thickness of the vastus lateralis muscle and the tibialis anterior muscle are measured as follows: the vastus lateralis muscle uses the distance between the anterior superior iliac spine and the lateral femoral condyle and is marked 2 / 3 of the distance from the anterior superior iliac spine; the tibialis anterior muscle uses the thickest part from the inferior side of the patella to the lateral malleolus, approximately 1 / 4 to 1 / 3 of the distance from the patella; the subject is measured in a supine and relaxed position, with the linear probe perpendicular to the skin surface; when measuring the thickness of the vastus lateralis muscle, the direction is parallel to the longitudinal axis of the body; when measuring the thickness of the tibialis anterior muscle, the direction is perpendicular to the longitudinal axis of the body; the thickness between the muscle fascia is taken as the final value.
[0027] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method described above are implemented.
[0028] The present invention adopts the above technical scheme and a more convenient and widely popularized ultrasonic examination method. The measurement method is simple, easy and reliable. The prediction model is reliable, objective and highly accurate. It can accurately predict the risk of sarcopenia for patients who cannot complete DXA or BIA, provide a basis for the diagnosis and treatment of clinical patients and individualized evaluation, and is easy to be widely promoted and applied. BRIEF DESCRIPTION OF THE DRAWINGS
[0029] The drawings in the specification, which constitute a part of the present application, are used to provide a further understanding of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute a limitation on the present application.
[0030] Figure 1 It is a schematic diagram of a specific part of the ultrasonic examination of the present invention.
[0031] Figure 2 It is an illustration of ultrasonic measurement of muscle thickness according to the present invention.
[0032] Figure 3 This is the ROC curve of Example 1.
[0033] Figure 4 This is the ROC curve of Example 2. DETAILED DESCRIPTION
[0034] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.
[0035] It should be noted that the following detailed descriptions are illustrative and are intended to provide further explanation of the present application. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present application belongs.
[0036] Embodiments of the present invention are described in detail below, examples of which 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 intended to be used to explain the present invention, and should not be construed as limiting the present invention.
[0037] In the description of the present invention, unless the context clearly indicates otherwise, the singular form is intended to include the plural form. In addition, it should be understood that when the terms "include" and / or "comprises" are used in this specification, they indicate the presence of features, steps, operations, devices, components and / or their combinations.
[0038] In the description of the present invention, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "clockwise", "counterclockwise" and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the referred device or element must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as limiting the present invention.
[0039] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, unless otherwise specified, "plurality" means two or more, unless otherwise clearly specified.
[0040] In the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", "fixed" and the like should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be an indirect connection through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.
[0041] In the present invention, unless otherwise clearly specified and limited, a first feature being "above" or "below" a second feature may include that the first and second features are in direct contact, or may include that the first and second features are not in direct contact but are in contact through another feature between them. Moreover, a first feature being "above", "above" and "above" a second feature includes that the first feature is directly above and obliquely above the second feature, or simply indicates that the first feature is higher in level than the second feature. A first feature being "below", "below" and "below" a second feature includes that the first feature is directly below and obliquely below the second feature, or simply indicates that the first feature is lower in level than the second feature.
[0042] Embodiment 1:
[0043] A method for predicting sarcopenia risk based on ultrasound technology comprises the following steps:
[0044] 1) The gender, age, grip strength and gait speed of the subjects were collected, and the thickness of the vastus lateralis (VL) and tibialis anterior (TA) were measured by ultrasound technology.
[0045] 2) Calculate the predicted probability P:
[0046] P=e logit(P) / 1+e logit(P) ;
[0047] Logit(P)=9.072-3.560gender+0.052age-2.048TA-1.848VL-0.169grip-0.721gait;
[0048] Wherein, gender indicates gender, gender = 0 when the gender is male, and gender = 1 when the gender is female; age indicates age; VL indicates the thickness of the vastus lateralis muscle; TA indicates the thickness of the tibialis anterior muscle; grip indicates grip strength; gait indicates walking speed;
[0049] 3) When the calculated prediction probability P is between 0.5 and 1, it is predicted to be a high risk of sarcopenia, otherwise it is a low risk.
[0050] Grip strength collection: Grip strength was measured using a JAMAR manual dynamometer. The measurement was performed according to the international standard test method, as follows: The examinee sat comfortably on a standard chair with a backrest and flat armrests, with the forearms placed on the armrests, the wrists just in the middle of the end of the chair armrests, the thumbs facing up, and the feet flat on the ground. The measurement started with the right hand, with the thumb around one side of the gripper handle and four fingers around the other side. The examinee was encouraged to squeeze the gripper as long as possible until the pointer stopped rising. The measurement was then repeated with the left hand. Twice on each side, the maximum value was taken.
[0051] Pace collection: The examinee is required to stand still behind a marked line. When the examiner gives the command "Start!", the examinee starts walking at a normal speed and stops near the finish line 4 meters away. The examiner starts timing when the examinee's first foot steps out and stops timing when the examinee's first foot completely crosses the 4-meter finish line.
[0052] Ultrasound data collection: The mindray M9 ultrasound machine was used for muscle ultrasound examination. The thickness of the vastus lateralis muscle and the tibialis anterior muscle were examined by trained professionals. The vastus lateralis muscle was measured by the distance between the anterior superior iliac spine and the lateral femoral condyle and marked at 2 / 3 of the distance from the anterior superior iliac spine; the tibialis anterior muscle was measured from the lower side of the patella to the thickest part of the lateral malleolus, about 1 / 4 to 1 / 3 of the distance from the patella; Figure 1 As shown in the figure, the subject is measured in a supine and relaxed position, and the linear probe is perpendicular to the skin surface. When measuring the thickness of the vastus lateralis muscle, the direction is parallel to the longitudinal axis of the body; when measuring the thickness of the tibialis anterior muscle, the direction is perpendicular to the longitudinal axis of the body; the thickness between the muscle fascia is taken as the final value, as shown in the figure. Figure 2 shown.
[0053] A sarcopenia risk prediction system based on ultrasound technology, comprising:
[0054] A data collection module is used to input the gender, age, grip strength and walking speed of the examinee, and collect the thickness of the vastus lateralis (VL) and the thickness of the tibialis anterior (TA) of the examinee through a muscle ultrasound examination device;
[0055] The risk prediction module calculates the predicted probability P based on the data collected by the data acquisition module; when the calculated predicted probability P is between 0.5-1, it is predicted to be a high risk of sarcopenia, otherwise it is a low risk.
[0056] P=e logit(P) / 1+e logit(P) ;
[0057] Logit(P)=9.072-3.560gender+0.052age-2.048TA-1.848VL-0.169grip-0.721gait;
[0058] Among them, gender represents gender, gender=0 when the gender is male, and gender=1 when the gender is female; age represents age; VL represents the thickness of the vastus lateralis muscle; TA represents the thickness of the tibialis anterior muscle; grip represents grip strength; and gait represents walking speed.
[0059] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method described above are implemented.
[0060] The experimental research situation and result verification of the present invention are specifically described below:
[0061] Example 1:
[0062] 1. Participant selection
[0063] The participants were mainly inpatients of the First Affiliated Hospital of Zhejiang University School of Medicine and volunteers from some communities in Hangzhou. The study was conducted between July 2022 and January 2024. The survey was conducted by recruiting volunteers who met the inclusion criteria. All participants signed informed consent. This study was approved by the Ethics Review Committee of the First Affiliated Hospital of Zhejiang University School of Medicine.
[0064] Inclusion criteria: Elderly people aged 60 years and above who voluntarily participated in this study.
[0065] Exclusion criteria: 1) severe edema; 2) inconvenience in movement and inability to cooperate in the examination; 3) myositis, dermatomyositis and other diseases that affect muscle status or observation; 4) severe cognitive dysfunction; 5) severe spinal and limb deformities; 6) unstable vital signs and serious cardiovascular and respiratory diseases; 7) patients who refuse to participate in this study.
[0066] 2. Observation indicators
[0067] 2.1 Collection of basic information: One researcher will record the gender and age of the subjects.
[0068] 2.2DXA muscle mass detection: The American GE-Lunar iDXA instrument was used to detect the relative skeletal muscle index (RSMI, i.e. limb skeletal muscle mass, kg / m 2 ). Participants were measured without outer clothing and wearing metal-free clothing to eliminate artifacts that may be caused by clothing. Body composition was assessed by scanning the entire body.
[0069] 2.3 Grip strength: Grip strength was measured using a JAMAR manual dynamometer. The measurement was performed according to the international standard test method. The dominant hand was used for measurement, with the thumb around one side of the gripper handle and four fingers around the other side. The subjects were encouraged to squeeze the gripper for as long as possible until the pointer stopped rising, and repeated once. The maximum value of the two measurement results was taken.
[0070] 2.4 Pace: Using a 4-meter pace measurement, participants started walking at a normal pace and stopped near the finish line at 4 meters. The pace was calculated by calculating the time it took to walk 4 meters.
[0071] 2.5 Ultrasonic data collection: The mindray M9 ultrasound machine was used for ultrasound testing. The ultrasound testing was performed by trained professionals, and the subjects were measured in a supine and relaxed position. The main measurement indicators are as follows:
[0072] a) Vastus lateralis muscle thickness: The distance between the anterior superior iliac spine and the lateral femoral condyle is used for the vastus lateralis muscle and marked at 2 / 3 of the distance from the anterior superior iliac spine; the thickness between the muscle fascia is taken as the final value.
[0073] b) Tibialis anterior muscle thickness: The tibialis anterior muscle is measured from the lower side of the patella to the thickest part of the lateral malleolus, approximately 1 / 4 to 1 / 3 away from the patella; the thickness between the muscle fascia is taken as the final value.
[0074] 3. Data analysis and processing
[0075] All data were processed using SPSS 25.0 (IBM) software, with p < 0.05 considered statistically significant. The data were tested for normal distribution and homogeneity of variance. If the data were normally distributed, the t-test was used for comparison between the two groups, and the chi-square test was used for categorical variables. Sarcopenia was determined according to the 2019 Asian Sarcopenia Diagnostic Criteria (DXA: male < 7.0 kg / m 2 , female<5.4kg / m 2 ; Grip strength: male <28kg, female <18kg; Gait speed: male / female <1.0m / s); The two groups were compared by t-test or chi-square test, and the prediction model was established by binary regression analysis; The area under the curve of the prediction model was calculated by ROC curve.
[0076] 4. Results
[0077] 4.1 Comparison of participants’ baseline data
[0078] The study collected data from 643 cases, including 342 males and 301 females, from July 2022 to January 2024. Excluding missing data and data errors, a total of 456 cases were included in the analysis.
[0079] The baseline characteristics of the participants are shown in Table 1 (based on sarcopenia groups). 260 males and 196 females were included in the final analysis. Among the sarcopenic population, there were 103 males, accounting for 68.7%; among the non-sarcopenic population, there were 157 males, accounting for 51.3%. The age in the sarcopenic group was significantly higher than that in the non-sarcopenic group (79.1±9.0 vs 71.9±7.2; p<0.001), and the thickness of the vastus lateralis and tibialis anterior in the sarcopenic group was significantly lower than that in the non-sarcopenic group (1.12±0.28 vs 1.38±0.36, p<0.001; 2.32±0.35 vs 2.63±0.36, p<0.001).
[0080] Table 1. Baseline characteristics of participants
[0081]
[0082] 4.2 Regression analysis of risk factors for sarcopenia
[0083] Binary regression analysis showed that the risk predictors of sarcopenia included: female (OR = 0.028, 95% CI 0.011-0.071, p < 0.001), age (OR = 1.053, 95% CI 1.011-1.097, p = 0.013), tibialis anterior (OR = 0.129, 95% CI 0.041-0.403, p < 0.001), vastus lateralis (OR = 0.158, 95% CI 0.043-0.577, p < 0.001), grip strength (OR = 0.844, 95% CI 0.798-0.894, p < 0.001), and walking speed (OR = 0.486, 95% CI 0.242-0.976, p < 0.001). (Table 2)
[0084] Table 2. Binary regression analysis of risk factors for sarcopenia
[0085]
[0086] 4.3 Establishment of a sarcopenia risk prediction model based on ultrasound parameters
[0087] The sarcopenia prediction model established based on ultrasound parameters (tibialis anterior MT and vastus lateralis MT) is:
[0088] P=e logit(P) / 1+e logit(P) ;
[0089] Logit(P)=9.072-3.560gender+0.052age-2.048TA-1.848VL-0.169grip-0.721gait.
[0090] Wherein, gender represents gender, gender=0 when the gender is male, and gender=1 when the gender is female; age represents age; TA represents the thickness of the tibialis anterior muscle; VL represents the thickness of the vastus lateralis muscle; grip represents grip strength; and gait represents walking speed.
[0091] The model goodness of fit test p < 0.001, the area under the ROC curve of the model was 0.913 (95% CI: 0.885-0.942), Figure 3 As shown, the results suggest that the model has high discrimination and calibration, and is more accurate than existing models.
[0092] Example 2:
[0093] This example is intended to provide independent external validation.
[0094] 1. Participant selection
[0095] The test was conducted by recruiting inpatients from the First Affiliated Hospital of Zhejiang University School of Medicine, and the data were from February to March 2024. 40 participants were enrolled according to the inclusion and exclusion criteria described in Example 1.
[0096] 2. Data Collection
[0097] The participants' gender, age, grip strength and gait speed were collected, and the participants' vastus lateralis thickness (VL) and tibialis anterior thickness (TA) were collected using standard ultrasound technology, as described in Example 1.
[0098] 3. Data Analysis
[0099] All data were processed using SPSS25.0 (IBM) software, and p<0.05 was considered statistically significant. According to the above model, the predicted probability P of sarcopenia for 40 participants was calculated. When P was between 0.5 and 1, it represented a high risk of sarcopenia, otherwise it was a low risk. Sarcopenia was determined according to the 2019 Asian Sarcopenia Diagnostic Criteria. According to sensitivity = number of true positives / (number of true positives + number of false positives)*100%, specificity = number of true positives / (number of true positives + number of false positives)*100%, the sensitivity and specificity of the prediction model were calculated. The two groups were compared by t-test or chi-square test, and the ROC curve calculated the area under the curve of the model prediction probability P.
[0100] 4. Results
[0101] 4.1 Comparison of participants’ baseline data
[0102] Among the 40 participants, there were 18 males, including 6 with sarcopenia, and 22 females, including 5 with sarcopenia. The baseline characteristics of the participants and the model-predicted probability P are shown in Table 3 (based on sarcopenia grouping).
[0103] Table 3. Baseline characteristics of participants
[0104]
[0105]
[0106] 4.2 Sensitivity and specificity of the prediction model
[0107] Among the 40 participants, 11 were diagnosed with sarcopenia and 29 were diagnosed with non-sarcopenia. The model predicted 10 high-risk cases and 30 low-risk cases. The four-grid table for predicting sarcopenia risk is shown in Table 4. The sensitivity and specificity of the model were 72.7% and 93.1%, respectively. Among them, sensitivity represents the true positive rate, and specificity represents the true negative rate. The closer the two are to 100%, the higher the true positive rate and true negative rate. At present, there is a lack of verification data for ultrasound prediction of sarcopenia in China. The prediction sensitivity and specificity of this model are both high, indicating that it is a good prediction model.
[0108] Table 4. Four-dimensional table of sarcopenia risk
[0109]
[0110] 4.3 Model Validation ROC Curve
[0111] The predicted probability P of sarcopenia for each participant was calculated by the model, and the area under the ROC curve of the prediction model was calculated by ROC curve analysis. The model goodness of fit test p < 0.001, and the area under the curve was 0.912 (95% CI: 0.816-1.000, p < 0.001).
[0112] The present invention proposes to predict the risk of sarcopenia based on ultrasound technology. Ultrasound is a more convenient and widely popularized examination method, and the measurement method is simple, easy and reliable. It provides a basis for the diagnosis and treatment and individualized evaluation of clinical patients. For patients who cannot complete DXA or BIA, it can accurately predict the risk of sarcopenia and is easy to be widely used.
[0113] Based on previous research, this paper uses more accurate indicators to construct a prediction model with a larger amount of data. It is more reliable and objective than previous prediction models, and its accuracy is significantly improved ( Figure 3 The area under the ROC curve of the medium model = 0.913 (95% CI: 0.885-0.942, p < 0.001), Figure 4 The area under the ROC curve was 0.912 (95% CI: 0.816-1.000, p < 0.001), indicating a high prediction accuracy).
[0114] Although the embodiments of the present invention have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limiting the present invention. Ordinary technicians in the field can change, modify, replace, modify, delete some features, add features or re-combine features to form a technical solution in the above embodiments without departing from the principles and purpose of the present invention. Any simple modifications, equivalent changes and modifications made to the above embodiments based on the innovative principles of the present invention are still within the scope of the technical solution of the present invention.
Claims
1. A method for predicting sarcopenia risk based on ultrasound technology, characterized in that: The steps include: 1) Gender, age, grip strength and gait speed of the examinee were collected, and the thickness of the vastus lateralis muscle and tibialis anterior muscle of the examinee were measured by ultrasound technology; 2) Calculate the predicted probability P: P=e logit(P) / 1+e logit(P) ; Logit(P)=9.072-3.560gender+0.052age-2.048TA-1.848VL-0.169grip-0.721gait; Wherein, gender indicates gender, gender = 0 when the gender is male, and gender = 1 when the gender is female; age indicates age; VL indicates the thickness of the vastus lateralis muscle; TA indicates the thickness of the tibialis anterior muscle; grip indicates grip strength; gait indicates walking speed; 3) When the predicted probability P is between 0.5 and 1, it is predicted to be a high risk of sarcopenia, otherwise it is a low risk.
2. The method for predicting sarcopenia risk based on ultrasound technology according to claim 1, characterized in that: Grip strength was measured using a JAMAR manual dynamometer according to international standard test methods.
3. The method for predicting sarcopenia risk based on ultrasound technology according to claim 1, characterized in that: Grip strength is measured as follows: The examinee sits on a standard chair with a backrest and flat armrests, with his forearms placed on the armrests, his wrists exactly in the middle of the ends of the chair armrests, his thumbs facing up, and his feet flat on the ground; wrap his thumb around one side of the handgrip builder's handle and his four fingers around the other side, and squeeze the handgrip builder for as long as possible until the pointer stops rising; repeat the measurement twice with the right hand and twice with the left hand respectively, and take the maximum value of the result.
4. The method for predicting sarcopenia risk based on ultrasound technology according to claim 1, characterized in that: The pace measurement method is as follows: The person being inspected stands still behind the starting mark line. When the inspector gives the command to start, the person being inspected begins walking at a normal speed. The inspector starts timing when the person's first foot steps out and lands, and stops timing when the person's first foot completely crosses the 4-meter finish line.
5. The method for predicting sarcopenia risk based on ultrasound technology according to claim 1, characterized in that: The muscle ultrasound examination was performed using a mindray M9 ultrasound machine to measure the thickness of the vastus lateralis and tibialis anterior muscles.
6. The method for predicting sarcopenia risk based on ultrasound technology according to claim 1, characterized in that: The thickness of the vastus lateralis and tibialis anterior muscles were measured as follows: The vastus lateralis muscle uses the distance between the anterior superior iliac spine and the lateral femoral condyle and is marked at 2 / 3 of the distance from the anterior superior iliac spine. The tibialis anterior muscle uses the thickest part from the inferior side of the patella to the lateral malleolus, approximately 1 / 4 to 1 / 3 of the distance from the patella. The subject is measured in a supine and relaxed position, with the linear probe perpendicular to the skin surface. When measuring the thickness of the vastus lateralis muscle, the direction is parallel to the longitudinal axis of the body; when measuring the thickness of the tibialis anterior muscle, the direction is perpendicular to the longitudinal axis of the body; the thickness between the muscle fascia is taken as the final value.
7. A sarcopenia risk prediction system based on ultrasound technology, characterized in that: include: A data collection module is used to input the gender, age, grip strength and walking speed of the examinee, and collect the thickness of the vastus lateralis muscle and the tibialis anterior muscle of the examinee through a muscle ultrasound examination device; The risk prediction module calculates the prediction probability P based on the data collected by the data acquisition module; P=e logit(P) / 1+e logit(P) ; Logit(P)=9.072-3.560gender+0.052age-2.048TA-1.848VL-0.169grip-0.721gait; Among them, gender represents gender, gender=0 when the gender is male, and gender=1 when the gender is female; age represents age; VL represents the thickness of the vastus lateralis muscle; TA represents the thickness of the tibialis anterior muscle; grip represents grip strength; and gait represents walking speed.
8. The sarcopenia risk prediction system based on ultrasound technology according to claim 7, characterized in that: The thickness of the vastus lateralis and tibialis anterior muscles were measured as follows: The vastus lateralis muscle uses the distance between the anterior superior iliac spine and the lateral femoral condyle and is marked at 2 / 3 of the distance from the anterior superior iliac spine. The tibialis anterior muscle uses the thickest part from the inferior side of the patella to the lateral malleolus, approximately 1 / 4 to 1 / 3 of the distance from the patella. The subject is measured in a supine and relaxed position, with the linear probe perpendicular to the skin surface. When measuring the thickness of the vastus lateralis muscle, the direction is parallel to the longitudinal axis of the body; when measuring the thickness of the tibialis anterior muscle, the direction is perpendicular to the longitudinal axis of the body; the thickness between the muscle fascia is taken as the final value.
9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.