CN112826504B - Game parkinsonism grade assessment method and device - Google Patents
Game parkinsonism grade assessment method and device Download PDFInfo
- Publication number
- CN112826504B CN112826504B CN202110016956.0A CN202110016956A CN112826504B CN 112826504 B CN112826504 B CN 112826504B CN 202110016956 A CN202110016956 A CN 202110016956A CN 112826504 B CN112826504 B CN 112826504B
- Authority
- CN
- China
- Prior art keywords
- leg
- hand
- game
- sign data
- symptom
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 208000027089 Parkinsonian disease Diseases 0.000 title claims abstract description 43
- 206010034010 Parkinsonism Diseases 0.000 title claims abstract description 43
- 238000000034 method Methods 0.000 title claims abstract description 24
- 208000024891 symptom Diseases 0.000 claims abstract description 65
- 230000033001 locomotion Effects 0.000 claims abstract description 61
- 238000011156 evaluation Methods 0.000 claims abstract description 17
- 206010044565 Tremor Diseases 0.000 claims abstract description 14
- 238000007477 logistic regression Methods 0.000 claims abstract description 12
- 230000003930 cognitive ability Effects 0.000 claims abstract description 6
- 238000000605 extraction Methods 0.000 claims abstract description 4
- 238000005070 sampling Methods 0.000 claims description 26
- 208000018737 Parkinson disease Diseases 0.000 claims description 23
- 238000011065 in-situ storage Methods 0.000 claims description 18
- 230000001429 stepping effect Effects 0.000 claims description 18
- 208000001613 Gambling Diseases 0.000 claims description 6
- 230000019771 cognition Effects 0.000 claims description 4
- 230000001149 cognitive effect Effects 0.000 claims description 4
- 238000005096 rolling process Methods 0.000 claims description 4
- 238000013507 mapping Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 claims description 3
- 238000012549 training Methods 0.000 claims description 3
- 230000004888 barrier function Effects 0.000 claims 1
- 230000008569 process Effects 0.000 abstract description 6
- 210000002414 leg Anatomy 0.000 description 51
- 230000001133 acceleration Effects 0.000 description 13
- 238000001514 detection method Methods 0.000 description 4
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 4
- 208000012639 Balance disease Diseases 0.000 description 2
- 206010061533 Myotonia Diseases 0.000 description 2
- 238000003745 diagnosis Methods 0.000 description 2
- VYFYYTLLBUKUHU-UHFFFAOYSA-N dopamine Chemical compound NCCC1=CC=C(O)C(O)=C1 VYFYYTLLBUKUHU-UHFFFAOYSA-N 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 210000004247 hand Anatomy 0.000 description 2
- 206010006100 Bradykinesia Diseases 0.000 description 1
- 208000006083 Hypokinesia Diseases 0.000 description 1
- 206010071390 Resting tremor Diseases 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000002490 cerebral effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000003111 delayed effect Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 229960003638 dopamine Drugs 0.000 description 1
- 231100000880 dysequilibrium Toxicity 0.000 description 1
- 238000013210 evaluation model Methods 0.000 description 1
- 238000012854 evaluation process Methods 0.000 description 1
- 210000003414 extremity Anatomy 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000028327 secretion Effects 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 210000000689 upper leg Anatomy 0.000 description 1
- 210000000707 wrist Anatomy 0.000 description 1
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/40—Detecting, measuring or recording for evaluating the nervous system
- A61B5/4076—Diagnosing or monitoring particular conditions of the nervous system
- A61B5/4082—Diagnosing or monitoring movement diseases, e.g. Parkinson, Huntington or Tourette
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
- A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Neurology (AREA)
- Biomedical Technology (AREA)
- Medical Informatics (AREA)
- Physics & Mathematics (AREA)
- Neurosurgery (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Engineering & Computer Science (AREA)
- Veterinary Medicine (AREA)
- Heart & Thoracic Surgery (AREA)
- Physiology (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Developmental Disabilities (AREA)
- Dentistry (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention discloses a method and a device for evaluating a parkinsonism symptom grade in a game, which are characterized in that motion sign data of hands and legs are collected in the game process, feature extraction is carried out on the collected data by combining game logic, six feature values of a hand flexibility index, a hand tremor index, a hand associated cognitive ability score, a leg flexibility index, a leg tremor index and a leg associated cognitive ability score are obtained, the feature values of the six feature values are input into a parkinsonism symptom grade evaluation logistic regression model, and parkinsonism symptom evaluation grades are output. In the above way, the invention evaluates the parkinsonism grade from the two aspects of the motor symptoms and the non-motor symptoms, so that the result is more reliable.
Description
Technical Field
The invention relates to the field of intelligent diagnosis of parkinsonism, in particular to a method and a device for evaluating a gambling parkinsonism symptom grade.
Background
Parkinson's disease, also called paralysis agitans, is a disease which frequently occurs in middle-aged and elderly people and is mainly characterized by resting tremor, bradykinesia, myotonia and dysequilibrium. The early symptoms of the Parkinson disease are not obvious, the public has insufficient knowledge of the Parkinson disease, patients often realize that the parkinsonism detection needs to be carried out after the motor symptoms such as stationary tremor, myotonia, gesture balance disorder and the like are generated, but the parkinsonism detection is probably the middle and later stages of the parkinsonism at the moment, and the delayed treatment rate of the parkinsonism clinically reaches up to 60 percent. Conventional parkinsonism preliminary detection generally uses a unified parkinsonism rating scale (UPDRS) or an improved scale, and patients need to complete a questionnaire according to regulations under the guidance of professional medical staff so as to obtain a preliminary judgment result. The existing parkinsonism assessment depends on professional equipment, meanwhile, participation of professional medical staff is needed, the assessment cost is high, the accuracy of an assessment result is mainly dependent on the knowledge level and diagnosis experience of the professional medical staff, the assessment process is complex, early symptoms are difficult to find, and therefore the assessment method with simple assessment process and high accuracy is provided and becomes a problem to be solved urgently.
Disclosure of Invention
The invention aims to solve the defects in the prior art and provide a game parkinsonism detection method and device, wherein the method comprehensively analyzes hand and leg movement sign data of a detected person in the game process, cognitive ability scoring and other game data in the game process, so as to infer the probability of illness, simplify the evaluation process, improve the judgment accuracy and enable early evaluation of parkinsonism to be possible.
The aim of the invention can be achieved by adopting the following technical scheme:
the method for evaluating the parkinsonism symptom level of the game is applied to the configuration of a handheld intelligent mobile terminal and an intelligent wearable device, and comprises the following steps of:
obtaining game logic, wherein the game logic is preset;
initializing game parameters;
acquiring hand movement sign data and leg movement sign data in real time;
according to the game logic and game parameters, extracting symptom characteristics of the hand movement sign data and the leg movement sign data, and outputting a hand symptom characteristic set and a leg symptom characteristic set;
inputting the hand symptom feature set and the leg symptom feature set into a parkinsonism symptom grade assessment logistic regression model, and outputting a parkinsonism symptom grade assessment analysis result.
Further, the game logic sets operations to be performed by hands and legs during the game and related scenes, specifically as follows:
hand operation: when a bright track curve appears on the screen, the finger needs to slide along the track curve on the screen; when red and blue clickable bodies appear on the screen, the finger needs to click the blue clickable body on the screen to avoid the red clickable body.
Leg operation: when a path appears on the screen, the in-situ stepping action is needed to control the virtual object to move forward until reaching the end point of the path; when a lateral rolling obstacle appears on the screen, the in-situ stepping action needs to be stopped so as to control the virtual object to avoid the obstacle.
The virtual object is the mapping of the subject in the game in the real world, and the in-situ stepping motion of the subject can be mapped into the forward walking motion of the virtual object in the game in real time.
Further, the game parameters include, but are not limited to:
L set : a sequence of point sets set by a bright track curve;
N blue : blue number of stitchable contacts;
N red : red number of clickable contacts;
Step need : the number of steps of a specified journey that correctly require in-situ stepping;
Avoid need : the number of obstacles correctly needed to be avoided in a given journey.
Further, the hand movement sign data and the leg movement sign data are obtained through real-time data acquisition. Nine-axis data of hand can be collected in real time to hand intelligent wearing equipment and are transmitted to intelligent mobile terminal through bluetooth. Nine-axis data of shank can be gathered in real time to shank intelligent wearing equipment and are transmitted to intelligent mobile terminal through bluetooth.
Further, the symptom characteristic extraction is specifically performed as follows:
the hand symptom feature set is calculated according to the game parameters, the hand movement sign data and data actually generated by hand operation in a game, and comprises a hand tremor index and a hand associated cognition level score, and specifically comprises the following steps:
calculating the hand tremor index:
tolerance＝0.1*std(Hand n )
wherein tolerance is latitude, std (·) represents standard deviation, hand n For a sequence of hand movement sign data,for the kth set of hand movement sign data with sampling frequency as window, sampleen copy (·) represents sample entropy, mean (·) represents taking the mean, < ->For the average value of 3 output results of entropy of the kth group of hand movement sign data samples with the sampling frequency as a window, fre is the sampling frequency, max (·) represents the maximum value, and k=1, 2, …, K and K are preset groups of hand movement sign data.
Calculating the hand-associated cognitive level score:
N red +N blue ＝N blueP +N blueN +N redP +N redN
wherein N is blueP To correctly click the blue clickable body times N blueN Number of times of incorrect non-clicking blue clickable object, N redP For correctly not clicking red clickable times, N redN To incorrectly click on a red clickable volume, bpr is the rate at which blue clickable volume is correctly clicked, and rpr is the rate at which red clickable volume is correctly not clicked.
The leg symptom feature set is calculated according to the game parameters, the leg movement sign data and data actually generated by leg operation in the game, and comprises a leg agility index, a leg tremor index and a leg association cognition level score, and specifically comprises the following steps:
calculating the leg agility index:
wherein Step need Step for the number of steps required for in situ stepping real Is the number of steps actually taken in place.
Calculating the leg tremor index:
tolerance＝0.3*std(Leg n )
wherein tolerance is latitude, std (·) represents standard deviation, leg n For the sequence of leg movement sign data,for leg movement sign data of group p with sampling frequency as window, +.>Sample entropy is represented by sampleEntropy (, mea) for the average of 3 output results of sample entropy of the p-th set of leg movement sign data with sampling frequency as a windown (·) represents the average, fre is the sampling frequency, max (·) represents the maximum, p=1, 2, …, P is the preset number of sets of leg movement sign data.
Calculating the leg-associated cognitive ability score:
wherein, avoid need To Avoid the number of obstacles and Avoid real In order to actually avoid the number of obstacles.
Further, the parkinson's disease grade evaluation logistic regression model outputs a parkinson's disease grade, the hand symptom feature set and the leg symptom feature set are used as explanatory variables, whether the parkinson's disease is ill or not is used as an explanatory variable, the explanatory variables and the explanatory variables are used as training data to be input into the parkinson's disease grade evaluation logistic regression model, and the parkinson's disease grade evaluation model is trained through continuous self-learning.
Further, a gamified parkinson's disease-like grade evaluation device applied to configuring a hand-held intelligent mobile terminal and an intelligent wearable device, the device comprising:
a logic and parameter obtaining unit, configured to obtain the game logic and initialize the game parameter, where the game logic is preset;
the data acquisition unit is used for acquiring the hand movement sign data and the leg movement sign data in real time;
the data processing unit is used for extracting symptom characteristics of the game parameters, the hand movement sign data and the leg movement sign data and outputting the hand symptom characteristic set and the leg symptom characteristic set;
and the evaluation unit is used for inputting the hand symptom feature set and the leg symptom feature set into the parkinsonism grade evaluation logistic regression model and outputting a parkinsonism grade evaluation result.
Compared with the prior art, the invention has the following advantages and effects:
according to the invention, limb action signals and game data of a subject are acquired in the game process, a hand movement sign data set and a leg movement sign data set of the subject are respectively obtained, hand behavior characteristics and leg behavior characteristics of the subject are obtained, and then the Parkinson disease grade of the subject is calculated. The method can objectively and accurately evaluate the parkinsonism grade of the subject. Compared with the traditional method for assessing the parkinsonism grade, the invention not only considers the motor symptoms of parkinsonism, but also evaluates the parkinsonism grade from the aspects of body and heart by combining with the assessment of cognitive ability, and promotes the secretion of cerebral dopamine in a game mode by using an entertainment mode, thereby helping the rehabilitation of patients.
In addition, the invention has the following advantages:
1) The subject can perform the assessment of the parkinsonian symptom level in the form of a game at any time and any place;
2) The subjects can achieve the purposes of rehabilitation and observing rehabilitation effects in a form of playing games for a long time;
3) The invention can add more parameter characteristics to evaluate the parkinsonism level, and has the characteristics of expandability and portability.
Drawings
Fig. 1 is a flowchart of a method for evaluating a parkinsonism-like level of gambling according to the present invention.
FIG. 2 is a flow chart of an embodiment of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions in the present specification will be clearly and completely described below, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art without making any inventive effort, are intended to be within the scope of the present invention, based on the embodiments herein.
The game is running game software installed on an intelligent mobile terminal, a section of virtual path is preset by the game software to be displayed on a display screen of the mobile terminal, a starting point and an ending point are set on the path, and a subject in the real world starts from the starting point to the ending point through in-situ stepping control of a virtual object in the virtual world. In the virtual path, a bright curve track, red and blue dotted touch bodies and a transverse rolling obstacle can appear, so that a subject needs to slide along the bright curve by using a finger, click the blue dotted touch body in a limited time, avoid clicking the red dotted touch body, stop stepping in situ when the transverse obstacle appears, and avoid being knocked over by the obstacle.
In an embodiment of the invention, a subject holds the intelligent mobile terminal and wears the intelligent wearing equipment, wherein the intelligent wearing equipment comprises a hand intelligent wearing equipment and a leg intelligent wearing equipment. The intelligent hand wearing equipment is worn on the wrist, nine-axis data of the hand can be acquired in real time and transmitted to the intelligent mobile terminal through Bluetooth; leg intelligent wearing equipment wears in thigh department, can gather the nine data of shank in real time and transmit intelligent mobile terminal through bluetooth.
Example 1
Fig. 1 is a flowchart of a method for evaluating a parkinsonism-like level of a gambling of the present invention, and fig. 2 is a flowchart of an embodiment of the present invention. An example of an application of the method for evaluating a gamified parkinson's disease-like level is specifically described below with reference to fig. 2, and as shown in fig. 2, the method includes the steps of:
step S1: obtaining game logic, wherein the game logic is preset:
the game logic sets operations and related scenes needed to be performed by hands and legs when the intelligent mobile terminal is held in the hand, and the operations are specifically as follows:
hand operation: when a bright track curve appears on the screen, the finger needs to slide on the screen according to the track of the curve; when red and blue clickable bodies appear on the screen, the finger needs to click the blue clickable body on the screen to avoid the red clickable body;
leg operation: when a path appears on the screen, the virtual object is controlled to move forward by performing in-situ stepping action until reaching the end point; when a transverse rolling obstacle appears on the screen, the in-situ stepping action is required to be stopped so as to control the virtual object to avoid the obstacle;
the virtual object is a mapping of a subject in the real world in a game, and the in-situ stepping motion of the subject can be mapped into forward walking motion of the virtual object in the game in real time.
Step S2: initializing game parameters:
L set ＝[(x 1 ,y 1 ),(x 2 ,y 2 ),…,(x N ,y N )]
N blue ＝10
N red ＝10
Step need ＝10
Avoid need ＝3
step S3: acquiring hand movement sign data and leg movement sign data:
the hand movement sign data are nine-axis data acquired through the hand intelligent wearing equipment, the leg movement sign data are nine-axis data acquired through the leg intelligent wearing equipment, and the nine-axis data comprise three-axis acceleration data Ac x 、Ac y 、Ac z And triaxial angular velocity data An x 、An y 、An z Three-axis attitude angle data roll, pitch, yaw;
step S4: the game parameters of the step S1 and the hand and leg movement sign data acquired in the step S2 are subjected to symptom feature extraction, and a hand symptom feature set and a leg symptom feature set are output:
the hand symptom feature set comprises a hand tremor index and a hand associated cognitive level score, and is specifically calculated as follows:
N red +N blue ＝N blueP +N blueN +N redP +N redN
wherein L is real For the point set sequence of the curve that actually slides, min (·) is the minimum, max (·) is the maximum,representation->Euclidean distance between two points, +.>Is L set I < th > point, < th >>Is L real I, j=2, 3, …, N is L real 、L set A preset number of sequences;
frc is the sampling frequency of the intelligent wearable device, ac x 、Ac y 、Ac z Is triaxial acceleration data An x 、An y 、An z Is triaxial angular velocity data, roll, pitch, yaw is triaxial attitude angle data, AC is total acceleration, AN is total angular velocity, ANG is total angle, AC n For the combined acceleration sequence, AN n For the angular velocity sequence, ANG n For angular sequence, AC tolerance To meet the acceleration tolerance, AN tolerance ANG for angular velocity tolerance tolerance For angle tolerance, std (·) is standard deviation, mean (·) is mean,for the average of 3 output results of sample entropy of the kth combined acceleration array with sampling frequency as window, +.>For the average of 3 output results of sample entropy of the kth combined angular velocity array of the window with the sampling frequency, < +.>For the average value of 3 output results of sample entropy of the kth combination angle array of the window with the sampling frequency, AC max Maximum sample entropy, AN, for combining acceleration data with sampling frequency as window packet max ANG for maximum sample entropy of the window packet of the angular velocity data at the sampling frequency max For maximum sample entropy of the angle data with sampling frequency as window grouping, k=1, 2, …, K is the preset group number of hand movement sign data;
N blueP to correctly click the blue clickable body times N blueN Number of times of incorrect non-clicking blue clickable object, N redP For correctly not clicking red clickable times, N redN To incorrectly click on a red clickable volume, bpr is the rate at which blue clickable volume is correctly clicked, and rpr is the rate at which red clickable volume is correctly not clicked.
The leg symptom feature set includes a leg agility index, a leg tremor index, and a leg associated cognitive level score, calculated as follows:
frc＝40
AC tolerance ＝0.3*std(AC n )
AN tolerance ＝0.3*std(AN n )
ANG tolerance ＝0.3*std(ANG n )
wherein Step need Step for the number of steps required for in situ stepping real The number of steps for the actual in situ stepping;
frc is the sampling frequency of the intelligent wearable device, ac x 、Ac y 、Ac z Is triaxial acceleration data An x 、An y 、An z Is triaxial angular velocity data, roll, pitch, yaw is triaxial attitude angle data, AC is total acceleration, AN is total angular velocity, ANG is total angle, AC n For the combined acceleration sequence, AN n For the angular velocity sequence, ANG n For angular sequence, AC tolerance To meet the acceleration tolerance, AN tolerance ANG for angular velocity tolerance tolerance For angle tolerance, std (·) is standard deviation,for the average of 3 output results of the entropy of the p-th combined acceleration series sample of the window with the sampling frequency, +.>For the average value of 3 output results of the entropy of the window p-th combined angular velocity array samples with the sampling frequency,/L>For a tie value of 3 output results of sample entropy of the window p-th combination angle array with sampling frequency, AC max Maximum sample entropy, AN, for combining acceleration data with sampling frequency as window packet max ANG for maximum sample entropy of the window packet of the angular velocity data at the sampling frequency max For maximum sample entropy of the angle data, wherein the sampling frequency is used as a window group, and p=1, 2, …, and P are preset groups of leg movement sign data;
Avoid need to Avoid the number of obstacles and Avoid real The number of obstacles is actually avoided;
step S5: output parkinson's symptom assessment grade:
the hand symptom feature set, the leg symptom feature set and the parkinsonism disease condition or not mark are used as training data to be input into a parkinsonism assessment logistic regression model, and the parkinsonism assessment logistic regression model of the parkinsonism assessment grade is trained through continuous self learning. The model can continuously perfect by continuously feeding the hand symptom feature set and the leg symptom feature set with the parkinsonism disease condition or non-parkinsonism disease condition marks, and the parkinsonism symptom grade evaluation grade can be output only by feeding the hand symptom feature set and the leg symptom feature set during evaluation.
Example two
A gambling parkinson's disease assessment device for configuring a handheld mobile terminal and an intelligent wearable device, the device comprising:
the logic and parameter acquisition unit is used for acquiring game logic and setting game parameters, wherein the game logic is preset;
the data acquisition unit is used for acquiring hand movement sign data and leg movement sign data in real time;
the data processing unit is used for extracting symptom characteristics of game parameters, hand movement sign data and leg movement sign data and outputting a hand symptom characteristic set and a leg symptom characteristic set;
and the evaluation unit is used for inputting the hand symptom feature set and the leg symptom feature set into the parkinsonism grade evaluation logistic regression model and outputting parkinsonism grade evaluation.
It should be noted that, in the above embodiment of the apparatus, each unit included is only divided according to the functional logic, but not limited to the above division, so long as the corresponding function can be implemented; in addition, the specific names of the functional units are also only for distinguishing from each other, and are not used to limit the protection scope of the present invention.
In addition, it will be understood by those skilled in the art that all or part of the steps in the above embodiments may be performed by a program to instruct related hardware, and the corresponding program may be stored in a computer readable storage medium, such as a ROM/RAM, a magnetic disk or an optical disk, etc.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, and alternatives falling within the spirit and principles of the invention.
Claims (5)
1. The method for evaluating the parkinsonism symptom level of the game is applied to the configuration of a handheld intelligent mobile terminal and an intelligent wearable device, and is characterized by comprising the following steps of:
obtaining game logic, wherein the game logic is preset;
initializing game parameters, the game parameters comprising:
L set : a sequence of point sets set by a bright track curve;
N blue : blue number of stitchable contacts;
N red : red number of clickable contacts;
Step need : the number of steps of a specified journey that correctly require in-situ stepping;
Avoid need : the number of barriers to be avoided correctly under a specified journey;
acquiring hand movement sign data and leg movement sign data in real time;
according to the game logic and game parameters, extracting symptom characteristics of the hand movement sign data and the leg movement sign data, and outputting a hand symptom characteristic set and a leg symptom characteristic set;
the symptom characteristic extraction is specifically performed as follows:
the hand symptom feature set is calculated according to the game parameters, the hand movement sign data and data actually generated by hand operation in the game, and comprises a hand tremor index and a hand associated cognition level score, and specifically comprises the following steps:
calculating the hand tremor index:
tolerance＝0.1*std(Hand n )
wherein tolerance is latitude, std (·) represents standard deviation, hand n For a sequence of hand movement sign data,for the kth set of hand movement sign data with sampling frequency as window, sampleen copy (·) represents sample entropy, mean (·) represents taking the mean, < ->For the average value of 3 output results of entropy of a kth group of hand movement sign data samples with sampling frequency as a window, fre is the sampling frequency, max (·) is the maximum value, and k=1, 2, …, K and K are preset groups of hand movement sign data;
calculating the hand-associated cognitive level score:
N red +N blue ＝N blueP +N blueN +N redP +N redN
wherein N is blueP To correctly click the blue clickable body times N blueN Number of times of incorrect non-clicking blue clickable object, N redP For correctly not clicking red clickable times, N redN For the number of false clicks on the red clickable touch object, bpr is the rate of correct clicks on the blue clickable touch object, rpr is the rate of correct non-clicks on the red clickable touch object;
the leg symptom feature set is calculated according to the game parameters, the leg movement sign data and data actually generated by leg operation in the game, and comprises a leg agility index, a leg tremor index and a leg association cognition level score, and specifically comprises the following steps:
calculating the leg agility index:
wherein Step need Step for the number of steps required for in situ stepping real The number of steps for the actual in situ stepping;
calculating the leg tremor index:
tolerance＝0.3*std(Leg n )
wherein tolerance is latitude, std (·) represents standard deviation, leg n For the sequence of leg movement sign data,to be at sampling frequencyLeg movement sign data of group p with rate of window,>for the average value of 3 output results of the entropy of the P-th group of leg movement sign data samples with the sampling frequency as a window, sampleen (-) represents the sample entropy, mean (-) represents the average value, fre is the sampling frequency, max (-) represents the maximum value, p=1, 2, …, and P is the preset group number of the leg movement sign data;
calculating the leg-associated cognitive ability score:
wherein, avoid need To Avoid the number of obstacles and Avoid real The number of obstacles is actually avoided;
inputting the hand symptom feature set and the leg symptom feature set into a parkinsonism symptom grade assessment logistic regression model, and outputting a parkinsonism symptom grade assessment analysis result.
2. The method for gambling parkinson's disease grade assessment according to claim 1, wherein the game logic sets the operations that the hands and legs need to perform during the game and the associated scenarios, specifically as follows:
hand operation: when a bright track curve appears on the screen, the finger needs to slide along the track curve on the screen; when red and blue clickable bodies appear on the screen, the finger needs to click the blue clickable body on the screen to avoid the red clickable body;
leg operation: when a path appears on the screen, the in-situ stepping action is needed to control the virtual object to move forward until reaching the end point of the path; when a transverse rolling obstacle appears on the screen, the in-situ stepping action is required to be stopped so as to control the virtual object to avoid the obstacle;
the virtual object is the mapping of the subject in the game in the real world, and the in-situ stepping motion of the subject can be mapped into the forward walking motion of the virtual object in the game in real time.
3. The method for gambling parkinson's disease grade assessment according to claim 1, wherein the hand movement sign data and the leg movement sign data are obtained by real-time data acquisition.
4. A gamified parkinson's disease grade assessment method according to claim 3, wherein the parkinson's disease grade assessment logistic regression model outputs a parkinson's disease grade, the hand symptom feature set and the leg symptom feature set are used as explanatory variables, whether parkinson's disease is ill or not is used as explanatory variables, the explanatory variables and the explanatory variables are used as training data to be inputted into the parkinson's disease grade assessment logistic regression model, and the parkinson's disease grade assessment model is trained by continuous self-learning.
5. A parkinson's disease grade assessment device applying the gamified parkinson's disease grade assessment method of any one of claims 1 to 4, applied to configuring a hand-held smart mobile terminal and a smart wearable device, characterized in that the device comprises:
a logic and parameter obtaining unit, configured to obtain the game logic and initialize the game parameter, where the game logic is preset;
the data acquisition unit is used for acquiring the hand movement sign data and the leg movement sign data in real time;
the data processing unit is used for extracting symptom characteristics of the game parameters, the hand movement sign data and the leg movement sign data and outputting the hand symptom characteristic set and the leg symptom characteristic set;
and the evaluation unit is used for inputting the hand symptom feature set and the leg symptom feature set into the parkinsonism grade evaluation logistic regression model and outputting a parkinsonism grade evaluation result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110016956.0A CN112826504B (en) | 2021-01-07 | 2021-01-07 | Game parkinsonism grade assessment method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110016956.0A CN112826504B (en) | 2021-01-07 | 2021-01-07 | Game parkinsonism grade assessment method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112826504A CN112826504A (en) | 2021-05-25 |
| CN112826504B true CN112826504B (en) | 2024-03-26 |
Family
ID=75926544
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110016956.0A Active CN112826504B (en) | 2021-01-07 | 2021-01-07 | Game parkinsonism grade assessment method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112826504B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101316935A (en) * | 2006-11-28 | 2008-12-03 | 博奥生物有限公司 | Method and composition for esophagus cancer diagnosis, prognosis and survival rate improvement |
| WO2011062890A1 (en) * | 2009-11-18 | 2011-05-26 | The Mclean Hospital Corporation | Method for diagnosing adhd and related behavioral disorders |
| WO2013049156A1 (en) * | 2011-09-26 | 2013-04-04 | President And Fellows Of Harvard College | Quantitative methods and systems for neurological assessment |
| CN104398263A (en) * | 2014-12-25 | 2015-03-11 | 中国科学院合肥物质科学研究院 | Method for quantitatively evaluating symptoms of tremor of patient with Parkinson's disease according to approximate entropy and cross approximate entropy |
| CN107157450A (en) * | 2017-06-19 | 2017-09-15 | 中国科学院计算技术研究所 | Quantitative estimation method and system are carried out for the hand exercise ability to patient Parkinson |
| CN109326341A (en) * | 2018-09-20 | 2019-02-12 | 武汉体育学院 | A kind of rehabilitation motion guiding method and apparatus |
| EP3600011A1 (en) * | 2017-03-30 | 2020-02-05 | Battista, Luigi | A device and relative method for determining extrapyramidal symptoms, in particular motor symptoms of parkinson's disease |
| CN110946556A (en) * | 2019-12-27 | 2020-04-03 | 南京信息工程大学 | Parkinson resting state tremor evaluation method based on wearable somatosensory network |
| CN111012312A (en) * | 2019-12-25 | 2020-04-17 | 中国科学院合肥物质科学研究院 | Portable Parkinson's disease bradykinesia monitoring intervention device and method |
| WO2020120999A1 (en) * | 2018-12-14 | 2020-06-18 | Pd Neurotechnology Ltd | Monitor system of multiple parkinson's disease symptoms and their intensity |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050153267A1 (en) * | 2004-01-13 | 2005-07-14 | Neuroscience Solutions Corporation | Rewards method and apparatus for improved neurological training |
| GB201008089D0 (en) * | 2010-05-14 | 2010-06-30 | Manus Neurodynamica Ltd | Apparatus for use in diagnosing neurological disorder |
| US11490851B2 (en) * | 2016-03-14 | 2022-11-08 | Newton Howard | Neuroanalytic, neurodiagnostic, and therapeutic tools |
| US20180184948A1 (en) * | 2016-12-30 | 2018-07-05 | Mindmaze Holding Sa | System, method and apparatus for diagnosis and therapy of neuromuscular or neurological deficits |
-
2021
- 2021-01-07 CN CN202110016956.0A patent/CN112826504B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101316935A (en) * | 2006-11-28 | 2008-12-03 | 博奥生物有限公司 | Method and composition for esophagus cancer diagnosis, prognosis and survival rate improvement |
| WO2011062890A1 (en) * | 2009-11-18 | 2011-05-26 | The Mclean Hospital Corporation | Method for diagnosing adhd and related behavioral disorders |
| WO2013049156A1 (en) * | 2011-09-26 | 2013-04-04 | President And Fellows Of Harvard College | Quantitative methods and systems for neurological assessment |
| CN104398263A (en) * | 2014-12-25 | 2015-03-11 | 中国科学院合肥物质科学研究院 | Method for quantitatively evaluating symptoms of tremor of patient with Parkinson's disease according to approximate entropy and cross approximate entropy |
| EP3600011A1 (en) * | 2017-03-30 | 2020-02-05 | Battista, Luigi | A device and relative method for determining extrapyramidal symptoms, in particular motor symptoms of parkinson's disease |
| CN107157450A (en) * | 2017-06-19 | 2017-09-15 | 中国科学院计算技术研究所 | Quantitative estimation method and system are carried out for the hand exercise ability to patient Parkinson |
| CN109326341A (en) * | 2018-09-20 | 2019-02-12 | 武汉体育学院 | A kind of rehabilitation motion guiding method and apparatus |
| WO2020120999A1 (en) * | 2018-12-14 | 2020-06-18 | Pd Neurotechnology Ltd | Monitor system of multiple parkinson's disease symptoms and their intensity |
| CN111012312A (en) * | 2019-12-25 | 2020-04-17 | 中国科学院合肥物质科学研究院 | Portable Parkinson's disease bradykinesia monitoring intervention device and method |
| CN110946556A (en) * | 2019-12-27 | 2020-04-03 | 南京信息工程大学 | Parkinson resting state tremor evaluation method based on wearable somatosensory network |
Non-Patent Citations (8)
| Title |
|---|
| Chen, YQ ; Yang, XD ; (...) ; Yu, HC.PdAssist: Objective and Quantified Symptom Assessment of Parkinson's Disease via Smartphone.2017 IEEE INTERNATIONAL CONFERENCE ON BIOINFORMATICS AND BIOMEDICINE (BIBM) .2018,939-945. * |
| Liu, SY ; Shen, Z ; (...) ; Miao, CY.A Fuzzy Logic Based Parkinson's Disease Risk Predictor.2014 IEEE INTERNATIONAL CONFERENCE ON FUZZY SYSTEMS (FUZZ-IEEE).2015,1624-1631. * |
| Siyuan Liu,etc.Pumpkin Garden: A Mobile Game Platform for Monitoring Parkinson’s Disease Symptoms.International Conference on human aspects of IT for the aged population 2018.2018,546-560. * |
| Vaz, PG ; Reis, AL and Cardoso, J.Supination/pronation movement quantification using stereoscopic vision based system towards Parkinson's Disease assessment - A pilot study.BIOMEDICAL SIGNAL PROCESSING AND CONTROL.2020,全文. * |
| 体感游戏对帕金森病患者认知、步态的影响;夏敏;江一静;郑得忠;王辉兴;詹增土;林志诚;临床荟萃;20200907;第35卷(第10期);900-903 * |
| 基于Microsoft Kinect体感系统的帕金森患者、卒中后轻偏瘫患者及正常人群的步态分析研究;曹雅;《中国优秀硕士学位论文全文数据库 医药卫生科技辑》;20180315(第3期);全文 * |
| 帕金森病患者轻度认知障碍的功能磁共振研究进展;陆婧;陈军;许启仲;张亮;谭慧;卒中与神经疾病;20151226;第22卷(第06期);377-380 * |
| 步态训练在帕金森病康复治疗中的研究进展;刘姁霖, 王丹, 杨伟伟;中国康复医学杂志;20190315;第34卷(第3期);354-359 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112826504A (en) | 2021-05-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2020257777A1 (en) | Wearable joint tracking device with muscle activity and methods thereof | |
| CN103706106B (en) | A kind of self adaptation continuous action training method based on Kinect | |
| JP2015514467A (en) | System for acquiring and analyzing muscle activity and method of operation thereof | |
| Song et al. | Activities of daily living-based rehabilitation system for arm and hand motor function retraining after stroke | |
| Lin et al. | Development of a badminton teaching system with wearable technology for improving students’ badminton doubles skills | |
| CN109635644A (en) | A kind of evaluation method of user action, device and readable medium | |
| CN113505662B (en) | Body-building guiding method, device and storage medium | |
| US20200129811A1 (en) | Method of Coaching an Athlete Using Wearable Body Monitors | |
| CN110478860B (en) | Hand dysfunction virtual rehabilitation system based on natural interaction of hand and object | |
| Raina et al. | CoMBaT: Wearable technology based training system for novice badminton players | |
| CN106073793A (en) | Attitude Tracking based on micro-inertia sensor and recognition methods | |
| Yang et al. | Hand rehabilitation using virtual reality electromyography signals | |
| CN109126045A (en) | intelligent motion analysis and training system | |
| Pan et al. | Multisensor-based 3D gesture recognition for a decision-making training system | |
| Mekruksavanich et al. | Badminton activity recognition and player assessment based on motion signals using deep residual network | |
| Kinger et al. | Deep learning based yoga pose classification | |
| Rad et al. | Smartswim, a novel imu-based coaching assistance | |
| Portaz et al. | Exploring raw data transformations on inertial sensor data to model user expertise when learning psychomotor skills | |
| CN112826504B (en) | Game parkinsonism grade assessment method and device | |
| CN110801227B (en) | Method and system for testing three-dimensional color block obstacle based on wearable equipment | |
| CN110458076A (en) | A kind of teaching method based on computer vision and system | |
| CN115985462A (en) | Rehabilitation and intelligence-developing training system for children cerebral palsy | |
| US20180218791A1 (en) | System and method for remote diagnosis of disease progression | |
| Antico et al. | A Virtual Assistant for Home Rehabilitation: the 2Vita-B Physical Project | |
| CN107506041A (en) | A kind of wearable mouse control method based on motion sensor |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |