A digital diagnosis and treatment method and system for detecting the disease stage of a patient with Parkinson's disease

Abstract

The application provides a digital diagnosis and treatment method and system for detecting the disease stage of a Parkinson's disease patient, which is based on the characteristic changes of the Parkinson's disease patient in terms of voice, and realizes the evaluation of the disease stage of the Parkinson's disease patient by extracting the characteristics of the voice sample of the Parkinson's disease patient and classification, so as to facilitate the timely grasp of the disease state of the Parkinson's disease patient. Meanwhile, the application matches a targeted digital therapy prescription according to the evaluation result of the Parkinson's disease patient, and in the process of using the prescription to regulate the body state, the voice sample of the patient is continuously collected to realize the continuous monitoring of the disease state of the patient. According to the above evaluation and monitoring results, in combination with the historical medical records of the Parkinson's disease patient, the change of the disease of the Parkinson's disease patient is tracked in real time, the diagnosis and treatment effect of the current digital therapy prescription is judged, and the next digital therapy prescription of the Parkinson's disease patient is adjusted in time, so as to delay the disease course of the Parkinson's disease patient.

Description

Technical Field

[0001] This invention relates to the field of medical diagnostics, and more specifically, to a digital diagnostic method and system for detecting the stage of Parkinson's disease in patients. Background Technology

[0002] Parkinson's disease (PD) is a common neurodegenerative disease, with an annual increase of 100,000 cases in my country. Like many neurological disorders, the diagnosis of PD relies heavily on the clinical experience of specialists. Most patients do not undergo specific scoring assessments; instead, their condition is roughly determined based on their presentation at the time of consultation, leading to physical stimulation and medication treatment. Besides the lack of specific assessment methods and understanding of symptoms, the high cost and complex diagnostic process also cause many patients to delay seeking medical attention until their condition worsens, missing the optimal treatment window. During periods of severe symptoms, the physical and psychological inconvenience further complicates access to care. Meanwhile, the development of internet communication technology and the widespread use of smart mobile devices have made data collection more convenient and faster, providing technical support for convenient pathological assessment systems.

[0003] Therefore, with the increasing aging of society, it is urgent to research a convenient and quick Parkinson's disease assessment system that utilizes intelligent mobile devices and can be used in primary healthcare institutions or even at home. This is of great significance for improving the early diagnosis rate of Parkinson's disease and improving the daily lives of middle-aged and elderly people. Once this technology matures, it will also make it possible to diagnose other similar diseases. Summary of the Invention

[0004] This invention addresses the technical problems existing in the prior art by providing a digital diagnostic method and system for detecting the stage of Parkinson's disease in patients.

[0005] According to a first aspect of the present invention, a digital diagnostic method is provided for assessing and continuously monitoring the disease stage of a Parkinson's disease patient, comprising:

[0006] Obtain personal information uploaded by Parkinson's disease patients, such as gender, age, and medical history;

[0007] Parkinson's disease patients take a speech test on the system according to the prompts. The system performs a preliminary quality assessment of the speech samples and collects speech samples that can be used for the next step of feature extraction and classification. If the speech quality does not meet the requirements, the patient is required to re-record the speech samples until they meet the quality requirements.

[0008] The system extracts features from speech samples that can be used to determine the disease status of Parkinson's disease patients;

[0009] The system will classify the extracted speech features, obtain scores for pathological indicators of Parkinson's disease, and complete the assessment of the patient's disease status.

[0010] The system matches targeted digital therapy prescriptions based on the patient's disease status information. The content of the digital therapy prescriptions mainly consists of training corpora based on the assessment results, while also collecting voice samples from the patient during the training process.

[0011] The system extracts and classifies the features of speech samples from the training process, and combines the evaluation results to monitor the patient's disease progression.

[0012] According to a second aspect of the present invention, a digital diagnostic system for detecting the stage of Parkinson's disease in patients is provided, comprising a data acquisition device and a cloud server;

[0013] The data acquisition device is used to assess Parkinson's disease patients based on the characteristics of dysarthria in Parkinson's disease and to collect speech samples corresponding to Parkinson's disease patients; wherein, it acquires health status information uploaded by Parkinson's disease patients and test completion information of the speech corpus test group; and based on the health status information and the test completion information, it issues digital therapy prescriptions and organizes targeted speech corpus training groups.

[0014] The cloud server includes:

[0015] The data analysis module is used to perform signal processing and feature extraction on the collected speech samples to obtain speech features; to identify and classify the speech features to identify speech features related to Parkinson's disease patients; and to track the changes and stages of Parkinson's disease patients' conditions by continuously monitoring and evaluating the speech features of Parkinson's disease patients; based on the changes in Parkinson's disease patients' conditions, stages of disease, and historical medical information, to determine the effectiveness of the digital therapy prescription, and to continuously update the digital prescription according to the evaluation results. The digital prescription mainly includes speech training.

[0016] This invention provides a digital diagnostic method and system for detecting the disease stage of Parkinson's disease. Based on the characteristic changes in speech patterns of Parkinson's patients, this method periodically collects and analyzes speech samples from Parkinson's patients to achieve assessment and continuous monitoring of the disease. Furthermore, this invention can be used in the assessment of each stage of Parkinson's disease, allowing doctors to promptly grasp the patient's condition and prescribe targeted digital therapy. This enables timely adjustment of the patient's physical condition and, based on basic diagnostic information and the patient's medical history, real-time tracking of disease progression, assessment of the effectiveness of current digital therapy prescriptions, and timely adjustment of the next treatment plan, thereby slowing the progression of Parkinson's disease. Attached Figure Description

[0017] Figure 1 A flowchart of a digital diagnostic method for detecting the stage of Parkinson's disease in patients provided by this invention;

[0018] Figure 2 A schematic diagram of the vocal organs;

[0019] Figure 3 A schematic diagram of the structure of a digital diagnostic and treatment system for detecting the stage of Parkinson's disease in patients provided by the present invention;

[0020] Figure 4 A schematic diagram of the structure of a cloud service platform that supports the implementation and management of digital therapy is provided. Detailed Implementation

[0021] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention. In addition, the technical features of the various embodiments or individual embodiments provided by the present invention can be arbitrarily combined with each other to form feasible technical solutions. Such combinations are not constrained by the order of steps and / or structural composition patterns, but must be based on the ability of those skilled in the art to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection claimed by the present invention.

[0022] Figure 1 A flowchart of a digital diagnostic and treatment method for assessing and continuously monitoring the disease stage of Parkinson's disease patients, as provided by this invention, is shown below. Figure 1 As shown, the method includes:

[0023] S1 retrieves personal information uploaded by Parkinson's disease patients, such as gender, age, and medical history.

[0024] Understandably, in this embodiment, patients can upload their health status information and daily life information to the digital diagnosis and treatment system, so that doctors can judge the changes in the Parkinson's disease patient's condition based on the changes in the patient's health status information and daily life information, and propose targeted treatment plans.

[0025] Patients' daily habits have a significant impact on the course of Parkinson's disease. After the onset of Parkinson's disease, patients often experience muscle rigidity and sudden onset of symptoms, which greatly affects their daily lives. Patients need to engage in certain rehabilitation exercises and strictly control their diet and lifestyle in order to slow down the progression of Parkinson's disease.

[0026] S2. Parkinson's disease patients take a speech test on the system according to the prompts. The system performs a preliminary quality assessment of the speech samples and collects speech samples that can be used for the next step of feature extraction and classification. If the speech quality does not meet the requirements, the patient is required to re-record the speech samples until they meet the quality requirements.

[0027] In this embodiment, the system needs to perform a preliminary quality assessment of the speech samples before extracting and classifying speech features.

[0028] S3, the system extracts features from speech samples that can be used to determine the disease status of Parkinson's disease patients.

[0029] The S4 system classifies the extracted speech features to obtain scores for pathological indicators of Parkinson's disease, thus completing the assessment of the patient's disease status.

[0030] Understandably, speech samples from Parkinson's disease patients were collected for the corpus training group, and speech features were extracted from the speech samples to identify speech features related to Parkinson's disease.

[0031] Understandably, based on speech features, the corresponding state of the speech organs is matched on the Parkinson's Disease Rating Scale (UPDRS). Then, based on the correlation between the states of various speech organs in Parkinson's patients, as well as the health status information and historical medical information of Parkinson's patients, the current stage of Parkinson's disease is determined, and the patient is assessed and the stage of the disease is identified, such as early, middle, or late stage.

[0032] Specifically, Parkinson's disease encompasses multiple stages. Based on the speech patterns of Parkinson's patients, their disease stage can be identified and classified, specifically as follows:

[0033] Early stage:

[0034] ① Hoarseness or weakness in voice: Parkinson's disease patients may experience hoarseness, weakness, or inability in their voice, resulting in a decrease in voice quality.

[0035] ② Lack of vocal variation and expression: The patient's voice may lack pitch variation and expression, and the tone may become monotonous.

[0036] ③ Incoherent tone and pace: The patient's speech rhythm may become incoherent, including speaking too fast or too slow, and unnatural pauses.

[0037] Mid-term stage:

[0038] ① Unstable pitch changes: The patient's pitch control may become unstable, resulting in jumping or breaking sounds.

[0039] ② Blurred pronunciation: Parkinson's disease patients may experience blurred or unclear pronunciation, with a decrease in the clarity and accuracy of syllables.

[0040] ③ Rhythm and fluency problems: Patients may have difficulty with speech rhythm and fluency, resulting in a discontinuous, incoherent, or unstable speaking rhythm.

[0041] Late stage:

[0042] ① Unclear speech: The patient's pronunciation may become more unclear, and the accuracy and comprehensibility of the speech expression will decrease.

[0043] ②Speech difficulties: Parkinson's disease patients may experience speech difficulties, including phoneme substitution, omission, or repetition.

[0044] ③ Weakened sound: The intensity and projection of the sound are reduced, causing the patient's voice to sound softer or more distant.

[0045] As an example, determining the current stage of Parkinson's disease based on the correlation between the speech organs matched in the Parkinson's Disease Rating Scale (UPDRS) includes: determining the speech state of the Parkinson's disease patient based on the correlation between the speech organs matched in the Parkinson's Disease Rating Scale (UPDRS), and calculating the values ​​of various pathological indicators of the Parkinson's disease patient; determining the current stage of Parkinson's disease based on the comparison results between preset standard thresholds and the values ​​of various pathological indicators of the Parkinson's disease patient.

[0046] Understandably, based on the relationships between multiple nodes (the states of various speech organs in a Parkinson's patient), health status information, and historical medical information, the system calculates the values ​​of various pathological indicators for Parkinson's patients. It then calculates the difference between each pathological indicator value and a preset standard threshold, and calculates the score or impact level of each pathological indicator based on the difference. Based on the scores of each pathological indicator, a comprehensive score for all pathological indicators is calculated, which can be obtained through weighted summation. Based on the comprehensive score of all pathological indicators, the current stage of Parkinson's disease in the patient is determined.

[0047] Among them, the various pathological indicators include fundamental frequency, linear prediction parameters, line spectrum pair parameters, linear prediction cepstral parameters, Mel frequency standard cepstral parameters, accent sensitivity parameters, frequency perturbation or frequency perturbation quotient, amplitude perturbation or amplitude perturbation quotient, harmonic-to-noise ratio, glottal-to-noise ratio, fundamental frequency standard deviation, and vocalization fundamental frequency range.

[0048] S5: The system matches targeted digital therapy prescriptions based on the patient's disease status information. The content of the digital therapy prescriptions mainly consists of training corpora based on the assessment results, while also collecting voice samples from the patient during the training process.

[0049] Understandably, after the system issues targeted digital treatment prescriptions to Parkinson's disease patients, it uses a training corpus to diagnose and treat these patients, and collects speech samples from them in response to the training corpus. These speech samples can be collected using smartphones, portable recording devices, or speech acquisition equipment.

[0050] Step 6: The system extracts and classifies the features of the speech samples from the training process, and combines the evaluation results to monitor the patient's disease progression.

[0051] Understandably, by observing the disease status and changes in Parkinson's patients in real time and combining this with historical medical information, the effectiveness of digital therapy prescriptions can be determined. In other words, whether the Parkinson's patients' conditions have improved after digital treatment, if so, indicates that this digital treatment method has a certain effect.

[0052] See Figure 3 The present invention provides a digital diagnostic and treatment system for detecting the stage of Parkinson's disease in patients, comprising a data acquisition device 31 and a cloud server 32.

[0053] The data acquisition device 31 is used to diagnose and treat Parkinson's disease patients based on digital therapy prescriptions and to collect speech samples corresponding to Parkinson's disease patients; wherein, it acquires health status information uploaded by Parkinson's disease patients and test completion information of the speech corpus test group; and according to the health status information and the test completion information, it issues digital therapy prescriptions and organizes targeted speech corpus training groups.

[0054] Cloud server 32 includes:

[0055] The data analysis module 321 is used to perform signal processing and feature extraction on the collected speech samples to obtain speech features; to identify and classify the speech features to identify speech features related to Parkinson's disease patients; and to track the changes in the condition and the stage of Parkinson's disease patients by continuously monitoring and evaluating the speech features of Parkinson's disease patients; and to determine the execution effect of the digital therapy prescription based on the changes in the condition, the stage of the disease, and historical medical information of Parkinson's disease patients.

[0056] It is understood that the digital diagnostic and treatment system for detecting the stage of Parkinson's disease provided by the present invention corresponds to the digital diagnostic and treatment method for detecting the stage of Parkinson's disease provided in the foregoing embodiments. The relevant technical features of the digital diagnostic and treatment system for detecting the stage of Parkinson's disease can be referred to the relevant technical features of the digital diagnostic and treatment method for detecting the stage of Parkinson's disease, and will not be repeated here.

[0057] It should be noted that, see Figure 4 This provides a cloud service platform, and using a cloud database to store data is an effective way to support the implementation and management of digital therapy. The following is a general process for storing the voice data of Parkinson's disease patients in a cloud database for digital therapy:

[0058] Data Acquisition: Collect speech data from Parkinson's disease patients using digital therapy applications or devices. This can include speech features such as vowels and labial sounds.

[0059] Data transmission: The collected voice data is transmitted to a cloud server. This can be done via an internet connection, using encryption protocols to protect the security of the data transmission.

[0060] Data storage: A corresponding data storage structure is created in a cloud database to store the voice data of Parkinson's disease patients. Data can be identified and categorized based on the patient's unique identifier or other identifying information to ensure data accuracy and privacy.

[0061] Data Management: Establish an appropriate data management system, including measures such as data backup, version control, and access control, to ensure data integrity, availability, and security.

[0062] Data analytics: By utilizing speech data from cloud databases, data analytics and machine learning algorithms are applied to assess the speech characteristics and disease stages of Parkinson's disease patients. This can provide useful information for patient diagnosis, treatment, and follow-up.

[0063] Privacy protection: When storing and processing voice data, relevant privacy regulations and compliance requirements must be met, such as data encryption, anonymization, and access control, in order to protect patients' privacy rights.

[0064] Data sharing and collaboration: Cloud databases can facilitate data sharing and collaboration among healthcare professionals to improve treatment outcomes and disease management for Parkinson's disease patients.

[0065] This invention provides a digital diagnostic and treatment method and system for detecting the disease stage of Parkinson's disease. By periodically collecting and analyzing the characteristics of speech samples from Parkinson's patients, long-term detection and monitoring of Parkinson's disease can be achieved. This invention can also be used in the assessment of each stage of Parkinson's disease, allowing doctors to promptly grasp the patient's condition and prescribe targeted digital therapy. This enables timely adjustment of the patient's physical condition and, based on basic diagnostic information and the patient's medical history, real-time tracking of disease changes allows for assessment of the effectiveness of the current digital therapy prescription, facilitating timely adjustments to the next treatment plan and thus slowing the progression of Parkinson's disease.

[0066] It should be noted that the descriptions of each embodiment in the above embodiments have different focuses. For parts that are not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0067] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0068] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0069] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0070] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0071] Although preferred embodiments of the invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including both the preferred embodiments and all changes and modifications falling within the scope of the invention.

[0072] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. A digital diagnostic system for detecting the stage of Parkinson's disease in patients, characterized in that, Includes data acquisition devices and cloud servers; The data acquisition device is used to assess Parkinson's disease patients based on the characteristics of dysarthria in Parkinson's disease and to collect speech samples corresponding to Parkinson's disease patients; wherein, it acquires health status information uploaded by Parkinson's disease patients and test completion information of the speech corpus test group; and based on the health status information and the test completion information, it issues digital therapy prescriptions and organizes targeted speech corpus training groups. The cloud server includes: The data analysis module is used to perform signal processing and feature extraction on the collected speech samples to obtain speech features; to identify and classify the speech features to identify speech features related to Parkinson's disease patients; and to track the changes and stages of Parkinson's disease patients' conditions by evaluating and continuously monitoring the speech features of Parkinson's disease patients; and to determine the effectiveness of the digital therapy prescription based on the changes in Parkinson's disease patients' conditions, stages of disease, and historical medical information. The method involves assessing and continuously monitoring the speech characteristics of Parkinson's disease patients to track changes in their condition and disease stages, including: Based on the identified speech features of Parkinson's disease patients, relevant items of the Parkinson's Disease Rating Scale (UPDRS) are matched; Based on the current patient's speech characteristics, the items matched in the Parkinson's Disease Rating Scale (UPDRS) are used to determine the current stage of Parkinson's disease in the patient; The effectiveness of the digital therapy prescription is determined based on the historical and current stages of the disease. Based on the correlations between the speech organs matched in the Parkinson's Disease Rating Scale (UPDRS) using the aforementioned speech features, the current stage of Parkinson's disease in the patient is determined, including: Based on the correlation between speech organs matched in the Parkinson's Disease Rating Scale (UPDRS) based on speech features, the speech status of Parkinson's disease patients is determined, and the values ​​of various pathological indicators of Parkinson's disease patients are calculated. Based on the comparison results between the preset standard threshold and the values ​​of various pathological indicators of the Parkinson's disease patients, the current stage of Parkinson's disease is determined. The comparison results between preset standard thresholds and the values ​​of various pathological indicators of the Parkinson's disease patient determine the current stage of the disease, including: Calculate the difference between the value of each pathological indicator and the preset standard threshold, and calculate the score of each pathological indicator based on the difference; Calculate the overall score of each pathological indicator based on the score of each pathological indicator; Based on the comprehensive scores of various pathological indicators, the current stage of Parkinson's disease in patients is determined.

Images