System and application for evaluation of speech disorder of parkinson patient and patient-customized speech-language treatment

Abstract

The present invention relates to a system and application for Parkinson's patient-customized speech disorder evaluation and treatment, which determine and provide a patient-customized treatment protocol by combining treatment modules according to evaluation results of the vocalization and pronunciation of a Parkinson's patient. The system and application for Parkinson's patient-customized speech disorder evaluation and treatment of the present invention determine a treatment protocol by combining the most appropriate modules for a patient which are determined via pre-evaluation from among pre-prepared treatment modules for each step, evaluate the patient's voice again at each treatment, and change the treatment protocol to be suitable for the patient at the next treatment, thereby providing the most appropriate treatment protocol to the patient at each time of treatment to maximize the treatment effect.

Description

A system and application for assessing speech disorders in Parkinson's patients and providing personalized speech-language therapy.

[0001] The present invention relates to a system and application for evaluating speech disorders in Parkinson's patients and providing customized speech-language therapy, and more specifically, to a system and application for evaluating and treating speech disorders in Parkinson's patients, which can maximize the treatment effect by determining and providing a customized speech-language therapy protocol by combining treatment modules according to the evaluation results of the Parkinson's patient's voice and pronunciation.

[0002]

[0003] Parkinson's disease is a representative neurodegenerative disease, pathologically characterized by the degeneration of dopaminergic neurons in the substantia nigra pars compacta. With the aging population, its incidence continues to rise, making it an intractable disease that poses significant social and economic challenges. Furthermore, the severity of Parkinson's disease is highlighted not only in the elderly population, but also in the fact that approximately 20% of patients develop the disease under the age of 50.

[0004] Parkinson's disease is most closely associated with aging, and genetic and environmental factors are known to influence its development. However, because the exact cause of Parkinson's disease is unknown, treatments are primarily focused on symptom relief rather than a fundamental cure. Levodopa, amantidine, and MAO-B inhibitors are used to treat Parkinson's disease. However, these medications have problematic side effects and, limited in that they only alleviate a subset of the disease's symptoms.

[0005] Parkinson's disease is a rapidly increasing disease. The number of patients treated for Parkinson's disease in Korea was 96,764 in 2016, but this number increased to 111,312 in 2020, an average annual increase of 3.6%. According to the World Health Organization (WHO), as of 2019, the number of patients with Parkinson's disease worldwide is estimated to be over 8.5 million, with approximately 1 million in the United States and 1.2 million in Europe.

[0006] The total medical expenses for Parkinson's disease patients in Korea increased by 25.3%, from KRW 437.6 billion in 2016 to KRW 548.2 billion in 2020, and the medical expenses per patient increased from KRW 4.523 million in 2016 to KRW 4.925 million in 2020. Currently, speech-language therapy (voice therapy) is a legally non-covered item, and the patient pays approximately KRW 50,000-80,000 for a single 30-40 minute session, and treatment is typically performed 2-4 times a week.

[0007] Currently, the demand for speech-language therapy for Parkinson's patients is very high, but hospitals are not proactive in providing treatment services due to a lack of personnel and space in each hospital and low treatment costs. In addition, treatment is not provided appropriately due to the difficulty of Parkinson's patients having to visit the hospital in person despite their mobility difficulties.

[0008] Korean Patent Publication No. 10-1921890 discloses a patient classification method that enables customized language rehabilitation by collecting evaluation data on the patient's cognitive and language functions and classifying the patient based on the collected data. Korean Patent Publication No. 10-2041774 discloses a method for providing content for language rehabilitation. However, a technology that can provide continuous language therapy to Parkinson's disease patients has not yet been developed.

[0009] Accordingly, the inventors of the present invention have made efforts to address this existing unmet need, and have thus established a new technology that provides patient-tailored speech disorder evaluation and treatment, with a treatment protocol adjusted according to the patient's symptoms, at a desired location using a smartphone application, instead of receiving speech-language therapy by visiting a hospital, thereby completing the present invention.

[0010] [Prior Art Literature]

[0011] [Patent Document]

[0012] (Patent Document 1) Patent Document 1. Republic of Korea Patent Publication No. 10-1921890

[0013] (Patent Document 2) Patent Document 2. Republic of Korea Patent Publication No. 10-2041774

[0014]

[0015] In order to solve the above-mentioned problem, one object of the present invention is to provide a system for evaluating and treating speech disorders tailored to a Parkinson's patient, including a server, which includes (i) a data storage unit for storing the voice and information of a Parkinson's patient; and (ii) a control unit for evaluating the voice and information of the Parkinson's patient and, based on the results, combining treatment modules selected from the group consisting of breathing training, oral motor training, strength training, pitch training, and pronunciation training to determine a treatment protocol tailored to the patient.

[0016] Another object of the present invention is to provide a method for evaluating and treating speech disorders tailored to a Parkinson's patient, comprising: (a) storing voice and information input by a Parkinson's patient; (b) evaluating the voice and information of the Parkinson's patient; and (c) determining a treatment protocol tailored to the patient by combining treatment modules selected from the group consisting of breathing training, oral motor training, strength training, pitch training, and pronunciation training based on the evaluation results.

[0017] Another object of the present invention is to provide an application stored in a medium for executing the above-described personalized speech disorder evaluation and treatment method for Parkinson's patients in combination with hardware.

[0018]

[0019] Unless otherwise defined, scientific and technical terms used in connection with the present invention have the meanings commonly understood by those of ordinary skill in the art. Furthermore, unless the context requires otherwise, singular terms include plurals and plural terms include the singular. In this specification,

[0020] It should be understood that terms such as "include" or "have" are intended to specify the presence of a feature, number, step, operation, component, part, or combination thereof described herein, but do not preclude the possibility of the presence or addition of one or more other features, numbers, steps, operations, components, parts, or combinations thereof.

[0021] The terms “unit” and “module” described herein mean a unit that processes at least one function or operation, which may be implemented by hardware, software, or a combination of hardware and software.

[0022] Each part and each module described herein is not necessarily meant to refer to a physically distinct and separate component. They are merely functionally distinct based on the operations performed by the respective part or module.

[0023] When it is said that a component is connected or connected to another component, it can be understood that it may be directly connected or connected to that other component, but there may also be other components in between.

[0024] Hereinafter, the present invention will be described in detail using the attached drawings.

[0025] A system for evaluating and treating speech disorders tailored to Parkinson's patients

[0026] One embodiment of the present invention provides a system for evaluating and treating speech disorders tailored to a Parkinson's patient, including a server (200), which includes (i) a data storage unit (202) for storing the voice and information of a Parkinson's patient; and (ii) a control unit (203) for evaluating the voice and information of the Parkinson's patient and, based on the results, combining treatment modules selected from the group consisting of breathing training, oral motor training, strength training, pitch training, and pronunciation training to determine a treatment protocol tailored to the patient.

[0027] In the present invention, speech disorder refers to a type of communication disorder including articulation disorder (i.e. pronunciation disorder) in which speech sounds are produced inaccurately, fluency disorder in which the flow of speech is not fluent, and voice disorder in which voice control is difficult.

[0028] In the present invention, the server (200) may include a database and a processor, etc. The server may be a server capable of communicating with a terminal (e.g., a patient terminal).

[0029] In the present invention, the system for evaluating and treating speech disorders tailored to Parkinson's patients may include a patient terminal (100) or a therapist terminal (300) in addition to the server (200). The patient terminal (100) may include an input unit (101), a display unit (102), and a voice transmission unit (103). The therapist terminal (300) may include an input unit (301), a display unit (302), a writing unit (303), and a transmission unit (304).

[0030] In the present invention, the terminal may preferably be a smart device such as a smartphone, laptop, desktop (PC), or tablet, but is not limited thereto. The terminal may include a processor, memory, and a display.

[0031] FIG. 1 is a schematic diagram illustrating a system for evaluating and treating speech disorders tailored to Parkinson's patients according to the present invention. Referring to FIG. 1, customized speech-language therapy is provided to Parkinson's patients through the system for evaluating speech disorders tailored to Parkinson's patients according to the present invention. Treatment is performed according to a treatment protocol transmitted to a Parkinson's patient terminal, and the Parkinson's patient proceeds with treatment according to the instructions of the treatment protocol. Specifically, the Parkinson's patient receives speech-language therapy using a patient terminal according to the contents of the treatment protocol displayed on the patient terminal, and all information, such as the patient's voice, generated during the treatment process is transmitted, stored, and analyzed by the system for treating speech disorders tailored to Parkinson's patients according to the present invention, and is used to determine the next treatment protocol. The therapist reviews the results of analyzing the patient's treatment performance level transmitted to the therapist terminal and uses them to revise them if necessary, and there is no direct real-time contact between the therapist and the Parkinson's patient.

[0032] FIG. 2 is a drawing illustrating in more detail the system for evaluating and treating speech disorders tailored to Parkinson's patients according to the present invention. Referring to FIG. 2, the system for evaluating and treating speech disorders tailored to Parkinson's patients according to the present invention includes a voice collection unit (201), a data storage unit (202), a control unit (203), a treatment protocol transmission unit (204), a voice transmission unit (205), a feedback provision unit (206), and a report provision unit (207).

[0033] In the present invention, the treatment module in the patient-tailored treatment protocol preferably essentially includes breathing training, oral motor training, strength training, vocal training, and pronunciation training modules, and may be characterized in that it is configured step by step in the order of breathing, oral motor training, strength, vocal training, and pronunciation.

[0034] Figure 3 is a diagram illustrating a process for selecting a patient-tailored treatment module of the present invention. Figure 3 exemplarily illustrates module selection according to evaluation indices for stages 1 and 2 for each Parkinson's patient. A represents a breathing training module, and B represents an oral motor training module. As shown in Figure 3, in stages 1 (breathing training) and 2 (oral motor training), measurement indices such as vowel extension and paragraph reading are selected, and whether the results are normal or abnormal is determined, and the module for the corresponding stage is selected accordingly. The number and types of measurement indices may vary for each stage.

[0035] FIG. 4 is a diagram illustrating a process for establishing a patient-tailored treatment protocol of the present invention. It exemplarily illustrates a process for determining a first-time treatment protocol by combining patient-tailored treatment modules selected for each step after going through the patient-tailored treatment module selection process illustrated in FIG. 3. A represents a breathing training module, B represents an oral motor training module, C represents a strength training module, D represents a voice training module, E represents a pronunciation training module, and F represents an additional training module. The number following the alphabet represents the module number. As illustrated in FIG. 4, the patient-tailored treatment protocol of the present invention consists of treatment modules most desirable for the patient in Step 1 (breathing training), Step 2 (oral motor training), Step 3 (strength training), Step 4 (voice training), and Step 5 (pronunciation training), and may include additional training modules (e.g., vocal cord muscle stretching) depending on the patient. The number of treatment modules may vary for each step.

[0036] Fig. 5 is a diagram illustrating a process for establishing a patient-tailored treatment protocol of the present invention. It exemplarily illustrates a process for determining a treatment protocol after the first session after the patient-tailored treatment protocol establishment process illustrated in Fig. 4. A represents a breathing training module, B represents an oral motor training module, C represents a strength training module, D represents a voice training module, and E represents a pronunciation training module. The number following the alphabet represents the module number. Each session is numbered A1-1, A2-2, and if the patient does not reach the daily evaluation criteria, a session with the same goal (e.g., A1-3-1) is repeated (the goal is the same, but the activity content and feedback within the session are changed). The number of sessions for performing the treatment protocol may vary for each patient.

[0037] In the present invention, the voice of the Parkinson's patient may be characterized in that it is evaluated according to one or more measurement indicators selected from the group consisting of vowel prolongation, alternating movement speed, sentence reading, paragraph reading, picture description, and a voice-related checklist, but is not limited thereto.

[0038] In the present invention, the system for evaluating and treating speech disorders customized for Parkinson's patients may be characterized by additionally including a voice collection unit (201) that converts the voice of a Parkinson's patient into voice data and collects it.

[0039] In the present invention, the system for evaluating and treating speech disorders tailored to a Parkinson's patient may be characterized by further including a treatment protocol transmission unit (204) that transmits the patient-tailored treatment protocol.

[0040] In the present invention, the system for evaluating and treating speech disorders tailored to a Parkinson's patient may be characterized by further including a voice transmission unit (205) that transmits voices generated while a Parkinson's patient is performing treatment according to the patient-tailored treatment protocol.

[0041] In the present invention, the system for evaluating and treating speech disorders tailored to a Parkinson's patient may be characterized by further including a feedback provision unit (206) that provides feedback to the Parkinson's patient in real time. Specifically, the feedback provision unit may be characterized by providing feedback to the Parkinson's patient using information collected while the Parkinson's patient is performing treatment according to the patient-tailored treatment protocol (e.g., the degree of symptoms of the Parkinson's patient to be treated, the degree of symptom improvement or worsening, the degree of treatment performance of the patient, etc.). If the degree of treatment performance of the Parkinson's patient does not reach a set standard, the system may determine in real time and display a message on the patient terminal so that the treatment can be performed again under the patient's choice.

[0042] In the present invention, the system for evaluating and treating speech disorders tailored to a Parkinson's patient may be characterized by further including a report providing unit (207) that provides a report based on the results of Parkinson's patient treatment according to the patient-tailored treatment protocol.

[0043] In the present invention, the report may be characterized by being at least one selected from the group consisting of a report for a Parkinson's patient and a report for a therapist. The report for a Parkinson's patient may be characterized by displaying sentences indicating parts that were performed well and parts that were not performed well in the treatment on the patient terminal immediately after the treatment is completed. The report for a therapist may be characterized by displaying a graph indicating the voice input by the patient while the treatment is being performed and the level of treatment performance. The therapist may review the report for a therapist and, if necessary, revise it to complete a report for a doctor, and provide the completed report for a doctor.

[0044] Figure 6 schematically illustrates the functions of a server included in the patient-tailored speech disorder evaluation and treatment system of the present invention.

[0045] Figure 7 schematically illustrates the functions and connections of a patient terminal, a server, and a therapist terminal in a patient-tailored speech disorder evaluation and treatment system of the present invention.

[0046] FIG. 8 specifically illustrates a method for generating a treatment protocol by a patient-tailored speech disorder evaluation and treatment system of the present invention, which prepares a library in which multiple training contents are predetermined according to the difficulty level of each module, selects the most suitable training for the patient based on the evaluation results of the patient's (subject's) voice, etc., and combines them to configure an overall treatment protocol.

[0047] Voice measurement indicators in Parkinson's patients

[0048] 1) Vowel extension pronunciation

[0049] Specifically, among the above measurement indicators, vowel prolongation refers to the longest value among multiple prolongations of the vowel "A" and is measured by pronouncing the vowel "A" as long as possible after inhaling. This includes the following parameters:

[0050] (i) Maximum Phonation Time (MPT; seconds),

[0051] (ii) Mean intensity (dB),

[0052] (iii) Standard deviation of fundamental frequency (FoSD; Hz),

[0053] (iv) Jitter percent (hereinafter referred to as Jitt; %),

[0054] (v) Shimmer percent (hereinafter referred to as Shim; %), and

[0055] (vi) Noise to Harmonic ratio (NHR).

[0056] 2) Diadochokinetis (DDK)

[0057] Specifically, among the above measurement indices, the alternating movement refers to the alternating movement speed of continuously repeating the same syllable (e.g., puh-puh-puh…) and the serial movement speed of continuously repeating two or more different syllables (e.g., puh-ta-ka-puh-ta-ka-puh-ta-keo…). The patient is measured by having him / her repeat sounds such as / puh / or / puh-ta-keo / as quickly and accurately as possible in one breath after inhaling. Preferably, it means measuring the number of repetitions of the alternating movement speed and the serial movement speed for 5 seconds and dividing it by the required time to present the number of repetitions per second. Consonant accuracy refers to the ratio of consonants correctly spoken by the patient for 5 seconds, and the formula for consonant accuracy is as follows: [Consonant accuracy = (total number of consonants - number of incorrect consonants) / total number of consonants X 100]. Repetition regularity measures how regular or periodic the intervals of syllable repetitions are, and measures the standard deviation of the intervals of alternating movement repetitions. It includes the following parameters:

[0058] (i) Alternating Motion Rate (AMR): The number of repetitions per second, consonant accuracy and repetition regularity for the sounds / peo / , / teo / and / keo / , and

[0059] (ii) Sequential Motion Rate (SMR): The number of repetitions per second, consonant accuracy, and repetition regularity for the / putter / sound.

[0060] 3) Reading sentences

[0061] Specifically, among the above measurement indicators, sentence reading is measured by having the patient read a given sentence visually once or twice and then read it aloud. Articulation accuracy refers to the ratio of consonants and vowels that the patient correctly pronounces, and the formula for articulation accuracy is as follows: [Articulation accuracy = (total number of consonants and vowels - number of incorrect consonants and vowels) / total number of consonants and vowels X 100]. It includes the following parameters:

[0062] (i) Standard deviation of fundamental frequency (FoSD; Hz),

[0063] (ii) Mean intensity (dB), and

[0064] (iii) Articulation accuracy (%).

[0065] 4) Read the paragraph

[0066] Specifically, among the above measurement indicators, sentence reading is measured by having the subject read a given paragraph visually once or twice and then read it aloud. The subject is instructed to read naturally and comfortably, as if in everyday conversation, without missing a single word. The number of syllables per breath is calculated by measuring the total time spent reading the paragraph and the number of breaths, then dividing the total number of syllables by the number of breaths. The overall speech rate is calculated by dividing the total time spent reading the paragraph by the number of syllables, and then calculating the number of syllables read per second. The articulation ratio refers to the percentage of the paragraph reading that is comprised of the patient's speaking segment, excluding pauses. A pause refers to a non-speaking segment that is at least 0.2 seconds long, including noises, sighs, coughs, and breathing sounds. The pause ratio refers to the percentage of the entire paragraph reading that is comprised of pauses, excluding the patient's speaking segment. Articulation accuracy refers to the percentage of consonants and vowels that the patient accurately pronounces. The formula for articulation accuracy is as follows: [Articulation accuracy = (total number of consonants and vowels - number of incorrect consonants and vowels) / total number of consonants and vowels X 100]. This includes the following parameters:

[0067] (i) Standard deviation of fundamental frequency (FoSD; Hz),

[0068] (ii) Mean intensity (dB),

[0069] (iii) Number of syllables per breath

[0070] (iv) Whole speech rate (seconds / syllables),

[0071] (v) Articulation percentage (%)

[0072] (vi) Pause percentage (%), and

[0073] (vii) Articulation accuracy (%).

[0074] 5) Describing the picture

[0075] Specifically, among the above measurement indicators, the picture description is measured by asking the user to describe a given picture. This includes the following parameters:

[0076] (i) Standard deviation of fundamental frequency (FoSD; Hz), and

[0077] (ii) Mean intensity (dB).

[0078] 6) Voice-related checklist

[0079] Specifically, as an example of a checklist related to voice among the above measurement indicators, tools such as the Voice-Related Quality of Life (V-RQOL) and the Voice Handicap Index (VHI) measure the presence of voice problems and psychological aspects in Parkinson's patients by self-reporting and scoring them. For example, in the Voice Handicap Index tool, patients are asked to select a score from 0 ("Never") to 4 ("Always") for the item "Because of my voice, others have difficulty understanding me." Previous studies have shown that this measurement tool significantly affects the daily life and quality of life of Parkinson's patients. Therefore, the scores on the voice checklist are compared between pre- and post-assessment to examine whether there are any changes in the psychological aspects of the patient, and it is used as a tool to supplement objective measurement indicators.

[0080] In the present invention, the information regarding the Parkinson's patient may be characterized as information regarding the environment and situations in which the patient frequently uses their voice. For example, a questionnaire for collecting information regarding the environment and situations is as follows:

[0081] a) Where do you often go or where do you often go? (Please select three or more.)

[0082] Restaurants and cafes, companies, homes, hospitals and pharmacies, sports facilities, religious facilities, department stores and supermarkets, travel destinations, and public institutions.

[0083] A) What are the patient's past or present interests? (Please select at least three.)

[0084] Cooking, Crafts, Family Reading, Religion, Films and Music, Travel, Broadcasting

[0085] In the present invention, the control unit may be characterized by combining treatment modules using an artificial intelligence algorithm to determine a personalized treatment protocol for the patient. The present invention may be characterized by selecting and combining modules based on the results of a voice analysis of the Parkinson's patient. Here, the modules analyze the patient's voice and information according to evaluation indicators, and divide the difficulty level for each module stage to create a treatment protocol.

[0086] In the present invention, the treatment module may be characterized in that it essentially consists of five stages of breathing training, oral motor training, strength training, pitch training, and pronunciation training within each session, and additional modules such as vocal cord muscle stretching are selected according to the patient's voice characteristics.

[0087] In the present invention, the treatment module may be characterized by being at least one selected from the group consisting of breathing training, oral motor training, strength training, vocal training, and pronunciation training.

[0088] Figure 3 is a diagram illustrating the process of establishing a personalized treatment protocol according to the present invention. Referring to Figure 3, the system for personalized evaluation and speech-language therapy for Parkinson's patients according to the present invention has multiple modules prepared according to the level of difficulty for each treatment stage, and based on the patient's voice evaluation results, an artificial intelligence algorithm selects and combines the most appropriate modules to determine a personalized treatment protocol optimized for each Parkinson's patient.

[0089] Figures 4 and 5 are diagrams illustrating an artificial intelligence algorithm for determining a patient-tailored treatment protocol of the present invention.

[0090] In the present invention, it may be characterized in that a Parkinson's patient is treated according to the patient-tailored treatment protocol transmitted to the patient terminal.

[0091] In the present invention, the treatment according to the patient-tailored treatment protocol may be preferably characterized in that it is performed for 20 to 40 minutes at a time.

[0092] In the present invention, the treatment according to the patient-tailored treatment protocol may preferably be characterized by being composed of 1 to 5 steps at a time.

[0093] In the present invention, treatment according to the patient-tailored treatment protocol may be preferably performed 4 to 7 times per week.

[0094] In the present invention, it may be characterized in that the information obtained through the treatment results according to the patient-tailored treatment protocol is utilized in determining the treatment protocol for the next round to change the treatment protocol.

[0095] Assessment and treatment of speech disorders tailored to Parkinson's patients

[0096] Another embodiment of the present invention provides a method for evaluating and treating speech disorders tailored to a Parkinson's patient, comprising: (a) storing voice and information input by a Parkinson's patient; (b) evaluating the voice and information of the Parkinson's patient; and (c) determining a personalized treatment protocol by combining treatment modules selected from the group consisting of breathing training, oral motor training, strength training, pitch training, and pronunciation training based on the evaluation results.

[0097] In the present invention, the treatment module in the patient-tailored treatment protocol preferably essentially includes breathing training, oral motor training, strength training, vocal training, and pronunciation training modules, and may be characterized in that it is configured step by step in the order of breathing, oral motor training, strength, vocal training, and pronunciation.

[0098] In the present invention, the voice of the Parkinson's patient may be characterized in that it is evaluated according to one or more measurement indicators selected from the group consisting of vowel prolongation, alternating movement speed, sentence reading, paragraph reading, picture description, and a voice-related checklist, but is not limited thereto.

[0099] In the present invention, the step (c) of the method for evaluating and treating speech disorders tailored to Parkinson's patients may be characterized by determining a patient-tailored treatment protocol by combining treatment modules using an artificial intelligence algorithm.

[0100] In the present invention, the method for evaluating and treating speech disorders tailored to Parkinson's patients may further include a step of converting the voice into voice data and collecting it.

[0101] In the present invention, the method for evaluating and treating speech disorders tailored to a Parkinson's patient may further include a step of transmitting speech produced by a Parkinson's patient while performing treatment according to the patient-tailored treatment protocol.

[0102] In the present invention, the method for evaluating and treating speech disorders tailored to a Parkinson's patient may further include a step of providing feedback to the Parkinson's patient in real time.

[0103] In the present invention, the method for evaluating and treating speech disorders tailored to a Parkinson's patient may further include a step of providing a report based on the results of evaluating and treating a Parkinson's patient according to the patient-tailored treatment protocol.

[0104] In the present invention, the method for evaluating and treating speech disorders tailored to a Parkinson's patient may further include a step in which the Parkinson's patient performs treatment according to the patient-tailored treatment protocol.

[0105] In the present invention, the treatment may be preferably characterized in that it is performed for 20 to 40 minutes at a time.

[0106] In the present invention, the treatment may be preferably performed 4 to 7 times per week.

[0107] In the present invention, the method for evaluating and treating speech disorders tailored to a Parkinson's patient may further include a step of changing the treatment protocol by utilizing information obtained through the treatment results according to the patient-tailored treatment protocol in determining the treatment protocol for the next round.

[0108] In the present invention, specific details regarding the voice measurement index, information, treatment module, number of treatments and stages, etc. are the same as those described above with respect to the voice therapy system customized for Parkinson's patients.

[0109] Application for assessing and treating Parkinson's speech disorders

[0110] Another embodiment of the present invention provides an application stored in a medium for executing the method for evaluating and treating speech disorders tailored to a Parkinson's patient in combination with hardware.

[0111] The personalized voice therapy method for Parkinson's patients according to the present invention can be implemented in the form of program instructions that can be executed through various computing devices and recorded on a computer-readable medium. Specifically, the method can be configured as a PC-based program or an application specifically for mobile devices. The application to which the present invention is applied can be installed on a user's terminal via a file provided by a file distribution system.

[0112] In the present invention, the medium includes magnetic media such as hard disks, floppy disks, and magnetic tapes, optical media such as CDROMs and DVDs, magneto-optical media such as floptical disks, and hardware devices specifically configured to store and execute program commands such as ROMs, RAMs, and flash memories.

[0113] In the present invention, a Parkinson's patient may be characterized by receiving treatment according to instructions based on a personalized treatment protocol displayed on an application on a patient terminal. During the treatment, the Parkinson's patient's voice is transmitted to the application, allowing an assessment of the Parkinson's patient's voice and speech impairment, and the next treatment protocol is determined based on this assessment.

[0114] By using the application of the present invention, instead of having to visit a hospital to receive speech disorder evaluation and treatment, a Parkinson's patient can receive automated, patient-tailored speech disorder evaluation and treatment at a desired location using a smartphone application.

[0115] Linkage with other treatments besides speech impediment treatment

[0116] The present invention may be characterized by its extension to other treatments, such as psychotherapy, exercise therapy, and cognitive therapy, in addition to speech disorder treatment. If other treatments, such as exercise therapy, are required in addition to speech disorder treatment, the present invention may be characterized by simultaneous implementation of these treatments. Information obtained during each treatment process can be used to develop other treatment protocols and provide relevant information to Parkinson's patients.

[0117] Specifically, if speech impediment symptoms worsen as the disease progresses, psychological difficulties may arise, so the duration of psychotherapy can be increased when establishing a psychotherapy protocol. Furthermore, exercise therapy protocols can be established in conjunction with psychotherapy, increasing the amount or intensity of exercise. If cognitive symptoms worsen, exercise therapy protocols can be established based on research showing improved cognitive function following physical activity, increasing the amount or intensity of exercise. In cases where cognitive symptoms worsen significantly, the difficulty of speech impediment treatment, psychotherapy, and exercise therapy can be reduced to provide a coordinated approach.

[0118]

[0119]

[0120]

[0121]

[0122]

[0123] The system and application for evaluating and treating speech disorders customized for Parkinson's patients of the present invention determine a treatment protocol by combining the most appropriate modules for the patient based on the results of a preliminary evaluation among treatment modules prepared in advance for each stage, and by evaluating the patient's voice again at each treatment and changing the treatment protocol to suit the patient at the next treatment, the most appropriate treatment protocol can be provided to the patient at each session, thereby maximizing the treatment effect.

[0124] Specifically, unlike the conventional technology that comprehensively evaluates evaluation criteria to determine a single final treatment protocol, the system for evaluating and treating speech disorders customized for Parkinson's patients of the present invention evaluates the evaluation results according to evaluation indices for each module to determine the difficulty of each module, thereby providing a patient-customized treatment protocol having different difficulty levels for each module, rather than a single comprehensively evaluated difficulty level.

[0125] In addition, it is expected that the system will be expanded to be linked with other treatments for Parkinson's patients, such as psychotherapy and exercise therapy, in addition to speech disorder treatment, enabling integrated care for Parkinson's patients. It is also expected that the system can be expanded to other neurological diseases, such as dementia and stroke, in addition to Parkinson's.

[0126]

[0127] Figure 1 is a schematic diagram illustrating a system for evaluating speech disorders and providing speech-language therapy tailored to Parkinson's patients according to the present invention.

[0128] Figure 2 is a drawing showing in more detail the system for evaluating speech disorders and speech-language therapy tailored to Parkinson's patients of the present invention.

[0129] Figure 3 is a diagram illustrating the patient-tailored treatment module selection process of the present invention. Figure 3 exemplifies module selection based on the first and second stage evaluation indicators for each Parkinson's patient. A represents the breathing training module, and B represents the oral motor training module.

[0130] Figure 4 is a diagram illustrating the process of establishing a patient-tailored treatment protocol of the present invention. It exemplarily illustrates the process of determining the first treatment protocol by combining the patient-tailored treatment modules selected at each stage after the patient-tailored treatment module selection process illustrated in Figure 3. A represents a breathing training module, B represents an oral motor training module, C represents a strength training module, D represents a voice training module, E represents a pronunciation training module, and F represents an additional training module. The number following the alphabet represents the module number.

[0131] Fig. 5 is a diagram illustrating a process for establishing a patient-tailored treatment protocol of the present invention. It exemplarily illustrates a process for determining a treatment protocol after the first session after the patient-tailored treatment protocol establishment process illustrated in Fig. 4. A represents a breathing module, B represents an oral motor module, C represents an intensity module, D represents a sound module, and E represents a pronunciation module. The number following the alphabet represents the module number. Each session is numbered A1-1, A2-2, and if the patient does not reach the daily evaluation criteria, a session with the same goal (e.g., A1-3-1) is repeated (the goal is the same, but the activity content and feedback within the session are changed).

[0132] Figure 6 schematically illustrates the functions of a server included in the patient-tailored speech disorder evaluation and treatment system of the present invention.

[0133] Figure 7 schematically illustrates the functions and connections of a patient terminal, a server, and a therapist terminal in a patient-tailored speech disorder evaluation and treatment system of the present invention.

[0134] FIG. 8 specifically illustrates a method for generating a treatment protocol by a patient-tailored speech disorder evaluation and treatment system of the present invention, which prepares a library in which multiple training contents are predetermined according to the difficulty level of each module, selects the most suitable training for the patient based on the evaluation results of the patient's (subject's) voice, etc., and combines them to configure an overall treatment protocol.

[0135]

[0136] Hereinafter, the present invention will be described in more detail through the following examples. However, these examples are intended solely to illustrate the present invention and should not be construed as limiting the scope of the present invention. The following examples are provided to more fully explain the present invention to those of average skill in the art.

[0137]

[0138] 1. Analysis of voice characteristics in Parkinson's patients

[0139] 1-1. Type analysis according to anatomical location of the damaged area

[0140] The types of voice features analyzed according to the anatomical location of the patient's damaged area are shown in Table 3 below.

[0141] Lesion stage Lesion area Paralysis Dysphagia type Upper motor neurons / pyramidal tract Upper motor neurons of the left or right hemisphere Unilateral upper motor neuron type Upper motor neurons of the left and right hemisphere Spastic type Extrapyramidal tract Basal ganglia and control circuit Hypoparakinetic type Basal ganglia and control circuit Hyperkinetic type Cerebellum Cerebellum and cerebellar control circuit Ataxic Pseudomotor neuron Unilateral or bilateral lower motor neuron and muscle damage Flaccid type Lesions in two or more locations Mixed type

[0142] 1-2: Analysis of Voice Characteristics of Hypokinetic Dysarthria in Parkinson's Disease Patients. The voice characteristic types analyzed based on the anatomical location of the damaged area correspond to hypokinetic dysarthria. The clinical characteristics of Parkinson's patients and the speech characteristics of hypokinetic dysarthria are as follows.

[0143] (i) Parkinsonism is characterized by resting tremor, bradykinesia, hypokinesia, postural instability, and rigidity.

[0144] (ii) Parkinson's patients have a narrow range of motion, slow or rapid repetitive movements, and microkinesia.

[0145] (iii) In terms of breathing, there is shallow and irregular breathing cycle, and the voice is too soft to be heard, and the maximum phonation time (MPT) is reduced and the number of syllables per breath is reduced compared to normal adults.

[0146] (iv) In vocalization, vocal cord stiffness and dysfunction make it difficult to start vocalization, reduce intensity, and reduce the range of changes in frequency and intensity.

[0147] (v) In vocalization, jitter and shimmer values ​​increase due to a decrease in the regularity of vocal cord vibration, resulting in voice tremors, roughness, breathiness, and hoarseness.

[0148] (vi) In pronunciation, the mobility and range of the articulatory organs are reduced, resulting in inaccurate pronunciation, short rushes, and short and fast speech rates. In addition, the serial motor rate (SMR) and alternate repetitive motor rate (AMR) of articulatory alternation movements may be slow or progress rapidly.

[0149] (vii) In pitch or rhythm, there are monotonous pitches, decreased stress, monotonous volume, inappropriate pauses and changes in pace.

[0150] 1-3: Module configuration based on evaluation indicator results

[0151] Each module is divided into stages based on the results of assessment indicators for Parkinson's patients. These modules are structured based on prior literature on Parkinson's patients and hypokinetic dysarthria. When selecting modules, each assessment indicator has its own criteria for normal and abnormal, and the module's difficulty level is determined based on the number of abnormalities (Table 4).

[0152] (i) The breathing training module is determined using evaluation indicators such as 1) maximum phonation duration during vowel prolongation and 2) number of syllables per breath during paragraph reading.

[0153] (ii) The oral motor training module is determined using evaluation indicators such as 1) alternating movement speed, 2) serial movement speed, 3) consonant accuracy, and 4) repetition accuracy during articulatory alternation movement.

[0154] (iii) The intensity training module is determined using evaluation indicators such as 1) average intensity during vowel prolongation, 2) average intensity during sentence reading, 3) average intensity during paragraph reading, and 4) average intensity during picture description.

[0155] (iv) The pitch training module is determined using evaluation indicators such as 1) standard deviation of fundamental frequency during vowel extension, 2) standard deviation of fundamental frequency during sentence reading, 3) standard deviation of fundamental frequency during paragraph reading, and 4) standard deviation of fundamental frequency during picture description.

[0156] (v) Pronunciation training modules are determined by using additional evaluation indices of intensity, pitch, sound quality, and speaking rate in addition to pronunciation evaluation indices. Pronunciation is determined by evaluation indices such as 1) articulation accuracy during sentence reading and 2) articulation accuracy during paragraph reading, and intensity is determined by evaluation indices such as 1) average intensity during sentence reading, 2) average intensity during paragraph reading, and 3) average intensity during picture description. Speech rate is determined by evaluation indices such as 1) overall speaking rate, 2) articulation ratio, and 3) pause ratio during paragraph reading, and sound quality is determined by evaluation indices such as 1) jitter percentage, 2) shimmer percentage, and 3) noise-to-overtone ratio during vowel pronunciation. Each evaluation indice has normal and abnormal criteria, and pronunciation training modules 1 to 4 are selected when the number of abnormal pronunciation evaluation indices is 0. Pronunciation training modules 5 to 8 are selected when the number of abnormal pronunciation evaluation indices is 1 or 2. Afterwards, the module is selected based on the highest number of abnormalities among the evaluation indicators of intensity, speech rate, pitch, and sound quality. If the highest number of abnormalities for each evaluation indicator is the same, the difficulty is determined in the order of speech rate, intensity, pitch, and sound quality. For example, if the number of abnormalities for intensity and speech rate is the same (3), the module that includes intensity among the pronunciation training modules is selected.

[0157] (vi) Vocal muscle stretching is an additional training module that is selected only for those who need it, and is determined by sound quality evaluation indices. It is selected when there is at least one abnormality among 1) jitter percentage, 2) shimmer percentage, and 3) noise-to-overtone ratio during vowel extension. If there is zero abnormality, the additional training module is not selected. However, module configuration based on measurement indices is not limited to those mentioned above.

[0158] Module Number Evaluation Index Criteria Normal / Abnormal Breathing 1 Prolonged Vowel Phonation Maximum Phonation Duration 10 seconds or more Normal Less than 10 seconds Abnormal 2 Paragraph Reading Number of Syllables per Breath 16 syllables or more Normal Less than 16 syllables Abnormal Oral Movement 1 Alternating Articulation Movement Alternating Movement Speed ​​ / per / , / ter / , / ker / All 5 times or more Normal Less than 5 times Abnormal 2 Alternating Articulation Movement Serial Movement Speed ​​ / per / , / ter / , / ker / , / per / / All 95% or more Normal Less than 95% Abnormal 3 Alternating Articulation Movement Consonant Accuracy / per / , / ter / , / ker / , / per / / All 95% or more Normal Less than 95% Abnormal 4 Alternating Articulation Movement Repetition Regularity / per / , / ter / , / ker / , / per / / All less than 30ms Normal More than 30ms Abnormal Intensity 1 Prolonged Vowel Phonation Average Intensity 75dB or more Normal Less than 75dB Abnormal 2 Sentence Reading Average Intensity 70dB or more Normal 70dB Less thanAbnormalReading 3 paragraphsAverage intensity 65 dB or moreNormalLess than 65 dBAbnormal4Explain the pictureAverage intensity 65 dB or moreNormalLess than 65 dBAbnormalPitch 1Vowel prolongationStandard deviation of fundamental frequency Less than 6 HzNormalMore than 6 HzAbnormal2Reading sentencesStandard deviation of fundamental frequency 15 Hz to 40 HzNormalLess than 15 Hz or more than 40 HzAbnormal3Reading paragraphsStandard deviation of fundamental frequency 15 Hz to 40 HzNormalLess than 15 Hz or more than 40 HzAbnormal4Explain the pictureStandard deviation of fundamental frequency 15 Hz to 40 HzNormalLess than 15 Hz or more than 40 HzAbnormalPronunciation 1Reading sentencesArticulation accuracy 98% or moreNormalLess than 98%Abnormal2Reading paragraphsArticulation accuracy 97% or moreNormalLess than 97%AbnormalSpeech rate 1Reading paragraphsTotal speech rate 4.5 syllables / sec or moreNormal4.5 pitches / seconds or lessAbnormalReading 2 paragraphsArticulation ratio85% or moreNormalLess than 85%AbnormalReading 3 paragraphsPause ratioLess than 15%Normal15% or moreAbnormalIntensityReading 1 sentenceAverage intensity70 dB or moreNormalLess than 70 dBAbnormalReading 2 paragraphsAverage intensity65 dB or moreNormalLess than 65 dBAbnormal3Explain the pictureAverage intensity65 dB or moreNormalLess than 65 dBAbnormalPitchReading 1 sentenceStandard deviation of fundamental frequency15 Hz to 40 HzNormalLess than 15 Hz or more than 40 HzAbnormalReading 2 paragraphsStandard deviation of fundamental frequency15 Hz to 40 HzNormalLess than 15 Hz or more than 40 HzAbnormalExplain the pictureStandard deviation of fundamental frequency15 Hz to 40 HzNormalLess than 15 Hz or more than 40 HzAbnormalSound quality1Vowel prolongationJitter percentageLess than 1.04%Normal1.04% or moreAbnormal2Vowel prolongationShimmer Percentage Less than 3.81% Normal More than 3.81% Abnormal 3 Vowel extension noise to overtone ratio Less than 0.19 Normal More than 0.19 Abnormal.

[0159] (In the above speech speed module, the standard for reading paragraphs is based on paragraphs containing sentences of 3-8 words, and the standard may vary depending on the length of the paragraph.)

[0160] 2. Setting goals for evaluating and treating Parkinson's dysarthria

[0161] Treatment of speech disorders in Parkinson's patients aims to (i) improve social communication through a type-specific approach; and (ii) improve naturalness and intelligibility of speech through an approach to the speech production subsystems (respiration, phonation, articulation, and prosody).

[0162]

[0163] 3. Module setup through analysis of representative voice characteristics of Parkinson's patients

[0164] 3-1. Basic Module

[0165] The basic module consists of five main components: breathing training, oral motor training, strength training, vocal training, and pronunciation training. It is conducted four to seven times a week for five weeks (20 to 35 sessions in total). Each session lasts 20 to 40 minutes, but the duration may vary depending on the patient's severity. The module is based on the typical vocal characteristics of Parkinson's patients, and the structure of the module varies depending on the patient's vocal characteristics. Each module has different participation times, difficulty levels, and levels.

[0166] 3-2. Example of module configuration

[0167] An example of a combined module configuration based on representative voice characteristics of Parkinson's patients is shown in Table 5 below.

[0168] Step Module Module Selection Criteria 1 Breathing Breathing Module 1 Abnormal 0 Breathing Module 2 Abnormal 1 Breathing Module 3 Abnormal 2 Oral Movement Oral Movement Module 1 Abnormal 0 or 1 Oral Movement Module 2 Abnormal 2 or 3 Oral Movement Module 3 Abnormal 4 Intensity Intensity Module 1 Abnormal 0 or 1 Intensity Module 2 Abnormal 2 or 3 Intensity Module 3 Abnormal 4 4 Pitch Pitch Module 1 Abnormal 0 or 1 Pitch Module 2 Abnormal 2 or 3 Pitch Module 3 Abnormal 4 5 Pronunciation Pronunciation Module 1 Abnormal 0, Intensity Most Abnormal Pronunciation Module 2 Abnormal 0, Speech Rate Most Abnormal Pronunciation Module 3 Abnormal 0, Pitch Most Abnormal Pronunciation Module 4 Abnormal 0, Sound Quality Most Abnormal Pronunciation Module 5: 1 or 2 abnormal pronunciations, Intensity Most Abnormal Pronunciation Module 6: 1 or 2 abnormal pronunciations, Speech Rate Most Abnormal Pronunciation Module 7: 1 or 2 abnormal pronunciations, Pitch Most Abnormal Pronunciation Module 8: 1 or 2 abnormal pronunciations, Voice Quality Most Abnormal Additional Vocal Muscle Stretching Additional Module 1: 1 or more abnormal voice quality

[0169] 4. Establishing treatment protocols and providing feedback through module combinations

[0170] 4-1. Breathing training

[0171] An example of a treatment protocol for breathing training established from a combined module configuration is shown in Table 6 below.

[0172] Basic ModuleBreathing Module 1● Week 1: Breathing: Repeat abdominal breathing while sitting. Vocalization: Pronounce one syllable (e.g., oo, s) for a long time in one breath.● Week 2: Breathing: Repeat while holding your breath between inhalations and exhalations. Vocalization: Count to a number in one breath, gradually increasing the number.● Week 3: Breathing: Repeat while holding your breath between inhalations and exhalations. Vocalization: Pronounce short words (e.g., pear, tree, banana) in succession in one breath.● Week 4: Breathing: Inhale in small breaths, then exhale through your nose and mouth. Vocalization: Inhale deeply and then say a short sentence in one breath. (e.g., hello, thank you)● Week 5: Breathing: Inhale in small breaths, then exhale through your nose and mouth. Vocalization: Inhale deeply and say a long sentence in one breath. (ex. What's for dinner today?) Breathing Module 2 ● Week 1: Breathing: Repeat abdominal breathing while sitting and bending over. Breathing: Repeat abdominal breathing while straightening your back and pushing the chair with your hands. ● Week 2: Breathing: Repeat abdominal breathing while sitting. Vocalization: Pronunciation: Pronounce one syllable (e.g., oo, s) for a long time in one breath. ● Week 3: Breathing: Repeat while holding your breath between inhalations and exhalations. Vocalization: Count to a number in one breath and gradually increase the number. ● Week 4: Breathing: Repeat while holding your breath between inhalations and exhalations. Vocalization: Say short words (e.g., pear, tree, banana) in succession in one breath. ● Week 5: Breathing: Inhale in divided breaths, then exhale through your nose and mouth. Vocalization: Inhale fully and say short sentence expressions in one breath. (e.g. Hello, Thank you)Breathing Module 3● Week 1: Breathing: Lean back on a chair and repeat abdominal breathing while focusing on your lower abdomen. Breathing: Sit down and bend your back while repeating abdominal breathing.● Week 2: Breathing: Straighten your back, push the chair with your hands, and repeat abdominal breathing. Vocalization: Pronounce one syllable (e.g. Woo, S) for a long time per breath.● Week 3: Breathing: Repeat abdominal breathing while sitting.English: Vocalization: Count numbers in one breath, gradually increasing the number of numbers. ● Week 4: Breathing: Repeat with a breath hold between inhalation and exhalation. Vocalization: Say short words (e.g., pear, tree, banana) in succession in one breath. ● Week 5: Breathing: Repeat with a breath hold between inhalation and exhalation. Vocalization: After breathing in deeply, say short sentences in one breath. (e.g., hello, thank you) Feedback Example 1. Straighten your body and raise your head to look straight ahead. 2. Be careful not to raise your chest when you breathe in. 3. Feel your lower abdomen expanding like a balloon when you breathe in. 3. Speak while being careful not to collapse the end of your sentences.

[0173] 4-2. Oral motor training

[0174] An example of a treatment protocol for oral motor training established from a combined module configuration is shown in Table 7 below. Training movements can be provided on a screen on a patient terminal to help the patient understand.

[0175] Basic Module Oral Exercise Module 1 ● Week 1: Tongue Exercise 1: Raise and lower the tip of your tongue. Tongue Exercise 2: Put strength on the tip of your tongue and push the left and right cheeks for 3 seconds. ● Week 2: Tongue Exercise 1: Put strength on the tip of your tongue and stick it out to the left and right. Tongue Exercise 2: Put strength on the tip of your tongue as if pushing it forward and then release it. ● Week 3: Tongue Exercise 1: Put strength on the tip of your tongue and stick it out to the lower left and lower right. Tongue Exercise 2: Place your entire tongue against the roof of your mouth and push it out for 3 seconds. ● Week 4: Tongue Exercise 1: Place the tip of your tongue against your upper teeth and move it backward along the roof of your mouth. Tongue Exercise 2: Keep the tip of your tongue against the roof of your mouth and do not lift it, then gradually lower your lower jaw. ● Week 5: Tongue Exercise 1: Keep the tip of your tongue against the roof of your mouth and do not lift it, then gradually lower your lower jaw. Tongue Exercise 2: Move your tongue in a circular motion inside your mouth. Oral Exercise Module 2 ● Week 1: Lip Exercise: Pull in the corners of your mouth and make an exaggerated smile for 5 seconds. Tongue Exercise: Raise and lower the tip of your tongue. ● Week 2: Cheek Exercise: Take a deep breath in both cheeks and burst them while saying / pa, pu / . Tongue Exercise: Put strength into the tip of your tongue and stick it out to the left and right. ● Week 3: Tongue Exercise 1: Put strength into the tip of your tongue and stick it out to the lower left and lower right. Tongue Exercise 2: Put strength into the tip of your tongue and push the left and right cheeks out for 3 seconds. ● Week 4: Tongue Exercise 1: Place the tip of your tongue against your upper teeth and move it back along the roof of your mouth. Tongue Exercise 2: Put strength into the tip of your tongue as if pushing it forward, then release it. ● Week 5: Tongue Exercise 1: Place the tip of your tongue against the roof of your mouth and keep it there, then gradually lower your lower jaw. Tongue Exercise 2: Place your entire tongue against the roof of your mouth and push it out for 3 seconds. Oral Exercise Module 3 ● Week 1: Lip Exercise: Repeat while moving your lips as much as possible and making the / u-ee / sound. Tongue Exercise: Raise and lower the tip of your tongue. ● Week 2: Cheek Exercise: Repeat puffing out and sucking in your cheeks. Tongue Exercise: Put strength on the tip of your tongue and stick it out to the left and right. ● Week 3: Lip Exercise: Pull in the corners of your mouth and make an exaggerated smile for 5 seconds.Tongue exercise: Put strength into the tip of your tongue and stick it out to the lower left / lower right. ● Week 4: Cheek exercise: Take a deep breath in both cheeks and burst them while saying / pa, pu / . Tongue exercise: Place the tip of your tongue on your upper teeth and move it back along the roof of your mouth. ● Week 5: Lip exercise: After making a kissing motion, pull in the corners of your mouth and smile exaggeratedly. Tongue exercise: Place the tip of your tongue on the roof of your mouth and keep it there, then gradually lower your lower jaw.

[0176] 4-3. Vocal muscle stretching training

[0177] An example of a treatment protocol for vocal cord muscle stretching training established from a combined module configuration is shown in Table 8 below.

[0178] Additional Modules Vocal Cord Stretching Module 11. Laryngeal Muscle Massage Massage the larynx in an inward circular motion. Massage the larynx up and down. 2. Neck Stretch Move your head left and right. Move your head forward and backward. Slowly turn your head to the right and left. 3. Shoulder Stretch Rotate your shoulders forward and backward. Shrug your shoulders and then forcefully lower them.

[0179] 4-4. Strength training

[0180] An example of a treatment protocol for strength training established from a combined module configuration is shown in Table 9 below.

[0181] Basic Module Intensity Module 1 ● Week 1: Pronounce / i, oo, ah / in a loud voice, stopping short. ● Week 2: Pronounce / i, oo, ah / in a loud voice, holding it in place. ● Week 3: Pronounce / a-u / , / a-i / , / u-a / , / u-i / , etc. in a loud voice, holding it in place. Count by extending one number every 0.5 seconds with strong intensity. ● Week 4: Pronounce / a-u / , / a-i / , / u-a / , / u-i / , etc. in a loud voice, holding it in place. Read words with various vowels with strong intensity. ● Week 5: Pronounce / i, oo, ah / , etc. in succession from soft to loud. Read sentences with various vowels with strong intensity. Intensity Module 2 ● Week 1: Find a comfortable pitch. Pronounce / i, oo, etc. in a loud voice, separating them into soft, medium, and loud voices. ● Week 2: Pronounce / i, oo, Pronounce / a / in short bursts. ● Week 3: Pronounce / i, oo, ah / in a loud voice for a long time. ● Week 4: Pronounce / a-u / , / a-i / , / u-a / , / u-i / , etc. in a loud voice for a short time. Count by extending one number every 0.5 seconds with strong force. ● Week 5: Pronounce / a-u / , / a-i / , / u-a / , / u-i / , etc. in a loud voice for a long time. Read words and short sentences with various vowels with strong force. Strength Module 3 ● Week 1: Find a comfortable pitch. Pronounce in a small, medium, and large voices. ● Week 2: Pronounce / i, oo, ah / in a loud voice for a short time. Pronounce / i, oo, ah / in a short burst, alternating between small and large voices. ● Week 3: Pronounce / i, oo, ah / in a loud voice for a long time. Alternating between small and large voices. ● Week 4: Pronounce / a-u / , / a-i / , / u-a / , / u-i / etc. in a loud voice. Count by extending one number every 0.5 seconds with strong force. ● Week 5: Pronounce / a-u / , / a-i / , / u-a / , / u-i / etc. in a loud voice.Read words and short sentences with a variety of vowels at high intensity. Feedback examples: 1. Provide visual feedback on volume to help the patient vary their intensity. 2. Take a deep breath before speaking. 3. Try using a slightly louder voice. 4. Try using abdominal strength instead of straining your voice. 5. Take short breaths between words. 6. Keep your throat moist by drinking water in between.

[0182] 4-5. Sound training

[0183] An example of a treatment protocol for sound training established from a combined module configuration is shown in Table 10 below.

[0184] Basic ModulePitch Module 1● Week 1: Gliding Training: Use vowels to connect low-high and high-low notes to make sounds.● Week 2: Gliding + Singing: After gliding training, sing songs such as 'School bell rings' and 'Happy Birthday'.● Week 3: Gliding + Following the notes: After gliding training, follow the notes according to the suggested pitches. Feedback is provided for both pitch and intensity.● Week 4: Gliding + Saying words: After gliding training, have students read the words. Feedback is provided for both pitch and intensity.● Week 5: Gliding + Saying sentences expressing daily life: After gliding training, have students ask questions or read sentences expressing daily life. At this time, provide feedback on both pitch and intensity. Pitch Module 2 ● Week 1: Gliding Training Using vowels, slowly go up or down one note at a time. ● Week 2: Gliding Training Using vowels, connect low-high and high-low to make sounds. Connect low-high-low to make sounds using vowels. ● Week 3: Gliding + Singing After gliding training, sing songs such as 'School bell rings' and 'Happy Birthday' using vowels. ● Week 4: Gliding + Saying words After gliding training, try reading the words. At this time, provide feedback on both pitch and intensity. ● Week 5: Singing + Speaking sentences expressing daily life After singing practice, ask questions or read sentences expressing daily life. At this time, provide feedback on both pitch and intensity. Pitch Module 3 ● Week 1: Humming Practice Hum (e.g., / heum / ) while fixing a note and pronouncing it for an extended period. While humming, make sounds by connecting low-high, high-low notes. ● Week 2: Gliding Practice Gliding Use vowels to slowly go up or down one note at a time. Make sounds by connecting low-high, high-low notes using vowels. ● Week 3: Singing + Singing Use vowels to make sounds by connecting low-high, low-high notes. Sing songs such as 'School bell rings' and 'Happy Birthday' using vowels.● Week 4: Singing + Saying Words After singing, have the patient read the words. At this time, provide feedback on both pitch and intensity. ● Week 5: Singing + Saying Sentences Expressing Daily Life After singing, have the patient ask questions or read sentences expressing daily life. At this time, provide feedback on both pitch and intensity. Feedback Examples 1. Provide visual feedback on pitch to help the patient change their pitch. 2. Take a deep breath before speaking. 3. Try to raise the pitch using falsetto. 4. If it is difficult to sing in one go, go up and down slowly. 5. Try to go as high / low as possible. 6. Be careful not to misspell the sound in the middle. 7. Open your mouth wide on vowels when reading a sentence. 8. Try to add rhyme when reading a sentence.

[0185] 4-6. Pronunciation training

[0186] An example of a treatment protocol for pronunciation training established from a combined module configuration is shown in Table 11 below. The feedback and the structure of the presented words and sentences are changed according to the characteristics of the Parkinson's patient.

[0187] Basic Module Pronunciation Module 1 ● Check previous steps: Maintaining good posture, deep breathing, loud voice ● Week 1: Words and phrases ● Week 2: Sentences - Expressions for daily life ● Week 3: Sentences - Sentences related to the topic (declarative sentences, interrogative sentences, proverbs, etc.) ● Week 4: Paragraphs - 3 to 5 sentences, adjusted according to difficulty ● Week 5: Monologue - Structure a monologue situation with questions related to the topic ● Activities and feedback examples: - Listen to the recording and read the words out loud. (Provide feedback by comparing them to the patient's words and instructions.) - Pronounce all consonants as accurately as possible. - Exaggerate the vowels / ㅏ, ㅜ, ㅣ / as much as possible. - Think of a slightly louder voice when reading. - Take a deep breath and speak immediately. Pronunciation Module 2 ● Check previous steps: Maintaining good posture, deep breathing, loud voice ● Week 1: Words and phrases ● Week 2: Sentences - Expressions for daily life ● Week 3: Sentences - Sentences related to the topic (declarative sentences, interrogative sentences, proverbs) ● Week 4: Paragraph - Adjust to the level of difficulty with 3 to 5 sentences ● Week 5: Monologue - Structure a monologue situation with questions related to the topic ● Activity and feedback examples: - Use the pacing board to control the speaking speed. (Say one word each time the color of the board shown on the screen moves.) - Use a metronome to control the speaking speed. (Output one syllable per beat to the metronome.) - Provide visual aids for breathing sections to control the speaking speed. - The speed is too fast. Should we read it again slowly? - Try reducing the number of words you say per breath. - Try opening your mouth wider and speaking clearly. - Increase the intensity a little more and slow down the speaking speed.Pronunciation Module 3● Check previous steps: Maintain good posture, deep breathing, loud voice● Week 1: Words and phrases● Week 2: Sentences - Expressions for daily life● Week 3: Sentences - Sentences related to the topic (declarative sentences, interrogative sentences, proverbs, etc.)● Week 4: Paragraphs - 3 to 5 sentences, adjusted according to difficulty● Week 5: Monologue - Structure the monologue situation with questions related to the topic● Activity and feedback examples:- Listen carefully to the intonation of the recording and read along. (Use lines as a visual aid to show intonation changes.)- Read again according to the intonation after the marked pause.- Take a deep breath and speak immediately.- The pitch is monotonous. Should I add a little more intonation? Pronunciation Module 4 Use the yawn-sigh technique to induce good voice quality. Here, the yawn-sigh technique refers to an effective way to reduce tension in vocal hyperfunction situations such as laryngeal elevation, tongue upward and forward elevation, and vocal cord tightening. ● Check previous steps: Maintaining good posture, abdominal breathing, loud voice ● Week 1: Words and phrases ● Week 2: Sentences - Expressions from daily life ● Week 3: Sentences - Sentences related to the topic (declarative sentences, questions, proverbs, etc.) ● Week 4: Paragraphs - Adjust the difficulty with 3 to 5 sentences ● Week 5: Monologue - Structure the monologue situation with questions related to the topic ● Examples of activities and feedback: - How do you feel when you yawn? - Do you feel soft and relaxed? - Take a deep breath and read the first syllable softly. - Sigh and read the words consecutively. - Read naturally without yawning. - Let's increase the intensity a little here.

[0188] 4-6-1. Examples of words and sentence structures used in pronunciation training

[0189] (a) Daily life expressions

[0190]

[0191] (I) Words and phrases

[0192]

[0193] (all) sentences

[0194]

[0195] (A) Paragraph

[0196]

[0197]

[0198]

[0199] (Ma) Monologue

[0200]

[0201]

[0202]

[0203] The foregoing description of the present invention is provided for illustrative purposes only, and it will be apparent to those skilled in the art that various modifications and variations are possible without departing from the technical spirit of the present invention. The scope of the present invention is indicated by the claims that follow rather than the detailed description set forth above, and all changes or modifications derived from the claims and their equivalents should be construed as being included within the scope of the present invention.

[0204]

[0205] [Explanation of symbols]

[0206] 100: Patient terminal

[0207] 200: Server

[0208] 300: Therapist Terminal

[0209] 101: Input section

[0210] 102: Display

[0211] 103: Voice transmission unit

[0212] 201: Voice Collection Unit

[0213] 202: Data storage

[0214] 203: Control Unit

[0215] 204: Transmission unit

[0216] 205: Voice transmission unit

[0217] 206: Feedback Provider

[0218] 207: Report Provider

[0219] 301: Input section

[0220] 302: Display section

[0221] 303: Writing Department

[0222] 304: Transmission

[0223]

[0224] The system and application for evaluating and treating speech disorders customized for Parkinson's patients of the present invention determine a treatment protocol by combining the most appropriate modules for the patient based on the results of a preliminary evaluation among the treatment modules for each stage prepared in advance, and by evaluating the patient's voice again at each treatment and changing the treatment protocol for the next treatment to suit the patient, thereby providing the most appropriate treatment protocol for the patient at each session and maximizing the treatment effect. In addition to speech disorder treatment, the system can be expanded to be linked with other treatments for Parkinson's patients, such as psychotherapy and exercise therapy, so that integrated Parkinson's patient care is expected to be possible. In addition, it can be expanded and applied to other neurological diseases, such as dementia and stroke, in addition to Parkinson's, so that the industrial applicability is very excellent.

Claims

1. (i) a data storage unit that stores the voice and information of a Parkinson's patient; and (ii) A system for evaluating and treating speech disorders tailored to a Parkinson's patient, including a server, which includes a control unit that evaluates the voice and information of the Parkinson's patient and determines the difficulty of each treatment module, which is composed of a breathing training module, an oral motor training module, a strength training module, a voice training module, and a pronunciation training module, based on the results, and determines a treatment protocol tailored to the patient by combining each module based on the difficulty.

2. A system for evaluating and treating speech disorders tailored to Parkinson's patients, wherein the control unit determines the difficulty of each treatment module based on the number of abnormal results of the evaluation of the evaluation index of each module.

3. In paragraph 1, the evaluation indicators of the breathing training module are the maximum vocalization duration during vowel extension and the number of syllables per breath during paragraph reading. The evaluation indicators of the above oral motor training module are alternating movement speed, serial movement speed, consonant accuracy, and repetition accuracy during articulatory alternation movement. The evaluation indicators of the above strength training module are the average strength during vowel prolongation, the average strength during sentence reading, the average strength during paragraph reading, and the average strength during picture description. The evaluation indices of the above sound training module are the standard deviation of the fundamental frequency during vowel extension, the standard deviation of the fundamental frequency during sentence reading, the standard deviation of the fundamental frequency during paragraph reading, and the standard deviation of the fundamental frequency during picture description. The evaluation index of the above pronunciation training module consists of a pronunciation evaluation index and one additional evaluation index selected from the group consisting of a speech rate evaluation index, a strength evaluation index, a pitch evaluation index, and a sound quality evaluation index. The pronunciation evaluation indicators of the above pronunciation training module are articulation accuracy during sentence reading and articulation accuracy during paragraph reading. The speech rate evaluation indicators of the above pronunciation training module are the overall speech rate, articulation rate, and pause rate during paragraph reading. The intensity evaluation indicators of the above pronunciation training module are the average intensity during sentence reading, the average intensity during paragraph reading, and the average intensity during picture description. The sound evaluation indices of the above pronunciation training module are the standard deviation of the fundamental frequency during sentence reading, the standard deviation of the fundamental frequency during paragraph reading, and the standard deviation of the fundamental frequency during picture description. A system for evaluating and treating speech disorders customized for Parkinson's patients, characterized in that the sound quality evaluation indices of the above pronunciation training module are jitter percentage, shimmer percentage, and noise-to-overtone ratio during vowel extension.

4. A system for evaluating and treating speech disorders tailored to Parkinson's patients, characterized in that the voice of the Parkinson's patient in paragraph 1 is evaluated according to one or more measurement indicators selected from the group consisting of vowel prolongation, alternating movement speed, sentence reading, paragraph reading, picture description, and a voice-related checklist.

5. A system for evaluating and treating speech disorders tailored to a Parkinson's patient, characterized in that in paragraph 1, the system further includes a feedback provision unit that provides feedback to a Parkinson's patient in real time.

6. A system for evaluating and treating speech disorders tailored to a Parkinson's patient, characterized in that in paragraph 1, the system further includes a report providing unit that provides a report based on the results of Parkinson's patient treatment according to the patient-tailored treatment protocol.

7. A system for evaluating and treating speech disorders tailored to Parkinson's patients, characterized in that the treatment protocol is changed by utilizing information obtained through treatment results according to the patient-tailored treatment protocol in determining the treatment protocol for the next round.

Images