Description:FIELD OF THE INVENTION
[0001] The present invention relates to the field of medical science, and more particularly, the present invention relates to the Neurobehavioral disorder classification system based on multimodal data.
BACKGROUND FOR THE INVENTION:
[0002] The following discussion of the background to the invention is intended to facilitate an understanding of the present invention. However, it should be appreciated that the discussion is not an acknowledgment or admission that any of the material referred to was published, known, or part of the common general knowledge in any jurisdiction as of the priority date of the application. The details provided herein the background if belongs to any publication is taken only as a reference for describing the problems, in general terminologies or principles or both of science and technology in the associated prior art.
[0003] As the people increase their engagement towards the social media there are increase cases of the mental disorders such as anxiety, depression etc. The system can help in early detection, diagnosis and treatment by providing care, and helps by giving guidance and suggestions and providing support with the services such as precautions and contacts of the medical professionals of such fields.
[0004] Problems solved by the model:
- Early Disorder detection and Enabling Personalized Treatment
- Care the people who are suffering and people who are not
- Easily access to the healthcare system
- Raising Awareness
- Tracking Mental Health Trends
- Helps in the Survey of the government
[0005] KR101926836B introduces a system that evaluates psychological states by analyzing drawings (like House-Tree-Person tests) using AI-driven techniques. This includes capturing user-drawn images via input devices, processing them on an AI-powered analysis server, and producing quantified psychological diagnostics. The server utilizes predefined psychological rules, extracting features, learning patterns, and recognizing traits to yield objective and standardized results. The system is particularly aimed at efficiently screening high-risk groups, such as individuals with suicidal tendencies, within large populations. It emphasizes accuracy, economic viability, and ease of deployment, overcoming the limitations of traditional manual assessments.
[0006] KR102041848B1 relates to an artificial intelligence-based voice analysis system for early detection of depression, anxiety, early dementia, or suicidal tendencies. This system records the user's regular voice, analyzes pitch, speech speed, or the frequency of specific words, and utilizes statistical analysis and AI algorithms to predict or diagnose mental health-related disorders or abnormalities. By identifying such conditions early, the system can recommend appropriate treatments and preventive measures to improve mental health and mitigate risks effectively.
[0007] KR102427508B1 provides an artificial intelligence-based device and method for managing mental health. The device includes a communication module for data transmission and reception, and a control unit connected to the communication module. The control unit receives biometric and collected data used to determine the likelihood of mental health disorders from an electronic device, analyzes this data using an AI-based model, and determines mental disorder likelihood. Based on the analysis, it selects appropriate mental health management or treatment content and delivers it to the electronic device.
[0008] In light of the foregoing, there is a need for the Neurobehavioral disorder classification system based on multimodal data that overcomes problems prevalent in the prior art.
OBJECTS OF THE INVENTION:
[0009] Some of the objects of the present disclosure, which at least one embodiment herein satisfies, are as follows.
[0010] The principal object of the present invention is to overcome the disadvantages of the prior art by providing the neurobehavioral disorder classification system based on multimodal data.
[0011] Another object of the present invention is to provide the Neurobehavioral disorder classification system based on multimodal data that provides easy-to-use interface, remote access, and tailored feedback for users.
[0012] Another object of the present invention is to provide the Neurobehavioral disorder classification system based on multimodal data that provides high accuracy and specificity in identifying multiple mental disorders using diverse data.
[0013] Another object of the present invention is to provide the Neurobehavioral disorder classification system based on multimodal data that utilizes machine learning and NLP for better analysis and real-time feedback.
[0014] Another object of the present invention is to provide the Neurobehavioral disorder classification system based on multimodal data that is more affordable than clinical assessments and scalable across platforms.
[0015] Another object of the present invention is to provide the Neurobehavioral disorder classification system based on multimodal data that ensures user privacy and secure data handling.
[0016] Another object of the present invention is to provide the Neurobehavioral disorder classification system based on multimodal data that promotes mental health awareness and enables early detection for timely intervention.
[0017] Another object of the present invention is to provide the Neurobehavioral disorder classification system based on multimodal data that is customizable and adaptable to new research or user feedback.
[0018] Other objects and advantages of the present disclosure will be more apparent from the following description, which is not intended to limit the scope of the present disclosure.
SUMMARY OF THE INVENTION:
[0019] The present invention provides Neurobehavioral disorder classification system based on multimodal data. The present invention provides following solutions:
- Online Counseling Platforms
- Community Based Mental Health Programs
- Mental Health Hotlines and Crisis text services
- Mental Health Awareness Campaign
- Apps for Mental Health Tracking
[0020] Multimodal and Real-Time Adaptive Diagnostics:
- Integration of Multimodal Data: Combine textual responses, speech tone analysis, facial emotion recognition, and physiological signals (like heart rate from wearable) to create a holistic diagnostic framework.
- Dynamic Question Flow: Use reinforcement learning to adaptively design a questioning strategy that minimizes time while maximizing diagnostic accuracy.
[0021] AI-Driven Psychometric Modeling:
- Custom Psychometric Tests: Instead of static questionnaires, generate user-specific psychometric tests using natural language processing (NLP) models like GPT or BERT tailored to a person's emotional and linguistic profile.
- Semantic Understanding: Apply cutting-edge large language models (LLMs) to detect subtle semantic patterns indicative of mental disorders, such as metaphor usage, negative sentiment polarity, or overgeneralization.
[0022] Biologically-Inspired Neural Networks:
- Cognitive AI Models: Base the architecture on neuroscience principles, mimicking how human brain regions (e.g., prefrontal cortex, amygdala) process emotions and decision-making.
- Neuro-symbolic AI: Combine symbolic reasoning (logic-based systems) with deep learning to better interpret complex mental health symptoms.
[0023] Predictive Preventive Analytics:
- Early Risk Detection: Identify at-risk users for developing mental disorders even before symptoms become apparent by analyzing subtle patterns in behavior over time (e.g., shifts in social interaction, sleep, or work productivity).
- Longitudinal Tracking: Build models that can predict the trajectory of mental health over weeks or months based on periodic assessments.
[0024] Culturally and Contextually Adaptive AI:
- Cultural Sensitivity Models: Develop models that adjust their assessments based on cultural norms and stigmas about mental health, avoiding biases inherent in Western-centric diagnostic criteria.
- Language Variability: Use advanced NLP pipelines to support multiple languages and dialects while retaining diagnostic accuracy.
[0025] Hybrid AI-Psychologist Collaboration:
- Human-AI Tandem: Create a system that works alongside mental health professionals, offering real-time suggestions, insights, or questions during live therapy sessions.
- Professional Feedback Loop: Allow therapists to provide corrective input into the model, enabling continual improvement in its diagnostic capabilities.
[0026] Ethical and Privacy-Preserving AI:
- Federated Learning: Train the model on decentralized user data (e.g., data never leaves their device) to ensure complete privacy while improving diagnostic capability.
- Emotionally Sensitive Algorithms: Use algorithms designed to adapt their tone and interaction style to avoid worsening a user’s emotional state during assessments.
[0027] Multi-Disorder Interrelation Mapping:
- Symptom Network Analysis: Implement graph-based machine learning to map interrelations between symptoms and mental disorders, providing a probabilistic overview of co-occurring conditions.
- Personalized Disorder Mapping: Build individual "mental health profiles" that show a nuanced picture of comorbid conditions and their underlying causes.
[0028] Augmented Reality (AR) Mental Health Assessment:
- Use AR to create immersive environments for assessments, such as virtual stress-inducing scenarios or relaxation tests, to analyze behavioral responses in real-time.
[0029] Gamified Mental Health Diagnostics:
- Gamification Elements: Develop engaging, game-like interactions where user responses to challenges, choices, or narratives reveal underlying psychological patterns.
- Behavioral Dynamics Analysis: Analyze gameplay metrics, such as risk-taking, perseverance, or emotional reactions, as diagnostic features.
[0030] Explainable AI at the Psychologist Level:
- Develop a novel explainability layer that translates complex model outputs into a form understandable by both users and psychologists, aligning predictions with established diagnostic frameworks like DSM-5.
[0031] Cross-Domain Integration:
- Integrate mental health data with other domains, such as physical health, genetic predispositions, or environmental stress factors, to create a bio-psycho-social diagnostic model.
BRIEF DESCRIPTION OF DRAWINGS:
[0032] Reference will be made to embodiments of the invention, examples of which may be illustrated in accompanying figures. These figures are intended to be illustrative, not limiting. Although the invention is generally described in the context of these embodiments, it should be understood that it is not intended to limit the scope of the invention to these particular embodiments.
[0033] Figure 1 shows a Neurobehavioral disorder classification system based on multimodal data.
DETAILED DESCRIPTION OF DRAWINGS:
[0034] While the present invention is described herein by way of example using embodiments and illustrative drawings, those skilled in the art will recognize that the invention is not limited to the embodiments of drawing or drawings described and are not intended to represent the scale of the various components. Further, some components that may form a part of the invention may not be illustrated in certain figures, for ease of illustration, and such omissions do not limit the embodiments outlined in any way. It should be understood that the drawings and the detailed description thereto are not intended to limit the invention to the particular form disclosed, but on the contrary, the invention is to cover all modifications, equivalents, and alternatives falling within the scope of the present invention as defined by the appended claim.
[0035] As used throughout this description, the word "may" is used in a permissive sense (i.e. meaning having the potential to), rather than the mandatory sense, (i.e. meaning must). Further, the words "a" or "an" mean "at least one” and the word “plurality” means “one or more” unless otherwise mentioned. Furthermore, the terminology and phraseology used herein are solely used for descriptive purposes and should not be construed as limiting in scope. Language such as "including," "comprising," "having," "containing," or "involving," and variations thereof, is intended to be broad and encompass the subject matter listed thereafter, equivalents, and additional subject matter not recited, and is not intended to exclude other additives, components, integers, or steps. Likewise, the term "comprising" is considered synonymous with the terms "including" or "containing" for applicable legal purposes. Any discussion of documents, acts, materials, devices, articles, and the like are included in the specification solely for the purpose of providing a context for the present invention. It is not suggested or represented that any or all these matters form part of the prior art base or were common general knowledge in the field relevant to the present invention.
[0036] In this disclosure, whenever a composition or an element or a group of elements is preceded with the transitional phrase “comprising”, it is understood that we also contemplate the same composition, element, or group of elements with transitional phrases “consisting of”, “consisting”, “selected from the group of consisting of, “including”, or “is” preceding the recitation of the composition, element or group of elements and vice versa.
[0037] The present invention is described hereinafter by various embodiments with reference to the accompanying drawing, wherein reference numerals used in the accompanying drawing correspond to the like elements throughout the description. This invention may, however, be embodied in many different forms and should not be construed as limited to the embodiment set forth herein. Rather, the embodiment is provided so that this disclosure will be thorough and complete and will fully convey the scope of the invention to those skilled in the art. In the following detailed description, numeric values and ranges are provided for various aspects of the implementations described. These values and ranges are to be treated as examples only and are not intended to limit the scope of the claims. In addition, several materials are identified as suitable for various facets of the implementations. These materials are to be treated as exemplary and are not intended to limit the scope of the invention.
[0038] The present invention provides Neurobehavioral disorder classification system based on multimodal data.
[0039] Sensors for Physiological Data:
- Electroencephalography (EEG) Headsets: For capturing brain activity.
- Functional Near-Infrared Spectroscopy (fNIRS) Devices: For measuring brain blood flow.
- Electrocardiogram (ECG) Sensors: For monitoring heart activity.
- Motion Capture Systems: For analyzing body movements and posture.
- Wearable Sensors (Smartwatches, Fitness Trackers): For collecting data like heart rate, sleep patterns, and activity levels.
[0040] Audiovisual Data Acquisition:
- High-Resolution Cameras: For capturing facial expressions, body language, and potentially video recordings of behavior.
- Microphones: For recording speech patterns, tone, and potentially environmental sounds.
[0041] Data Acquisition and Preparation
[0042] Sources of Data:
- Online Sources: There are various online platforms that provide dataset regarding Mental Health, like National Institute of Mental Health (NIMH), World Health Organization (WHO), National Institute of Mental Health and Neuro Sciences (NIMHANS).
- Free Sources: Google Data Search, Kaggle, UCI Machine Learning Repository, Github.
[0043] Data Cleaning:
- Missing Value Management: Missing data may be imputed using any technique such as mean imputation, median imputation, mode imputation, or even more advanced methodologies like multiple imputation.
- Outlier Removal: Outliers can have a huge impact on the performance of the model. They can be identified and removed or handled using techniques like winsorization or capping.
- Data Normalization and Standardization: Scaling the data to a common range ensures that features with different scales contribute equally to the model.
[0044] Feature Engineering:
- Extracting Important Features: Identify and extract the most important features from the data.
- Developing New Features: New features are derived from old ones.
[0045] Data Splitting
- Training Set: Part of the data is used to train the model. The model learns the patterns and relationships that exist between the features and the target variable, i.e., mental disorder.
- Validation Set: Another separate part of the data used for hyperparameter tuning while training the model and performance evaluation.
- Testing Set: Last part of the data reserved for the evaluation of performance of the final model on new, unseen data.
[0046] Algorithm Selection and Training
[0047] Selecting a Suitable Algorithm:
- Logistic Regression: This is best suited for binary classification problems, which predict the probability of a mental disorder.
- Decision Trees: Handles numerical and categorical data by generating decision rules to classify instances.
- Random Forest: This is an ensemble technique in which multiple decision trees are combined to increase accuracy while minimizing overfitting.
- Support Vector Machines (SVM): Excellent for high-dimensional data, even though it can learn a complicated decision boundary.
- Neural Networks: Powerful models that can be able to learn complicated patterns and can be useful to apply large and complex data sets.
[0048] Train the Model
- Feed the chosen algorithm with training data
- Optimize model's parameters through techniques such as gradient descent that minimize the errors of actual and predicted outcomes
[0049] Model Evaluation
[0050] Performance Metrics:
- Accuracy: Total correctness of the model predictions.
- Precision: The number of correctly classified positive predictions out of all the positive predictions.
- Recall: The number of actual positive cases that have been correctly identified.
- F1-Score: It is the harmonic mean of precision and recall.
- Confusion Matrix: It's a table that summarizes the performance of a classification model on a set of test data.
- ROC Curve: It plots true positive rate against the false positive rate at various threshold settings.
- AUC: Area under the ROC curve, an estimate of the overall performance of the model.
[0051] Test on Validation Set:
- The model is tested on the validation set to see if it overfits or underfits.
- Hyper parameters can be adjusted to better the model's performance.
[0052] GUI Implementation
- A Graphical User Interface (GUI) was developed and implemented using the Streamlit Python library to facilitate user interaction with the modal
[0053] Model Deployment
- The trained model is implemented in a clinical decision support system or in a mobile application.
- Ensure the model is available to the clinicians and patients.
[0054] Continuous Monitoring and Improvement
[0055] Monitor Model Performance:
- Monitor the performance of the model over time to detect any degradation or biases.
- Periodically assess the performance of the model on new data to ensure that it is still accurate and reliable.
[0056] Retrain the Model:
- As new data becomes available, the model can be retrained to incorporate the latest information and improve its performance.
- Periodically re-evaluate the model's performance and make necessary adjustments.
[0057] The Mental Disorder Classification System is an advanced tool for classifying mental health disorders through the analysis of user input. It accomplishes this through the use of Natural Language Processing (NLP), Machine Learning, and Data Analytics, analysing responses which may express symptoms of anxiety and depression.
[0058] The system includes an interface for data collection, in which responses are collected from the users, a secure back-end server to process this kind of data, and a cleaning and preparation pipeline for handling the input for analysis. Further, the classification model specifies the disorders a user may be suffering from based on his symptoms. In addition to this, the system offers personalized feedback and allows continuous learning in order to improve its accuracy over time.
[0059] This system addresses the key problems of mental health care issues such as early detection of disorder, easy access to health care, recommending suitable treatment, and tracing the trend of mental health issues. It also consists of other resources such as counselling websites, community-based programs, and awareness programs regarding mental health.
[0060] It has a novelty of early detection of mental disorders, personal guidance based on responses of individuals, and confidential assessment that is beneficial, especially in areas with a shortage of mental health services. In summary, the system in itself provides easier and effective mental health care to advance better support for people dealing with mental health problems.
[0061] The disclosure has been described with reference to the accompanying embodiments herein and the various features and advantageous details thereof are explained with reference to the non-limiting embodiments in the following description. Descriptions of well-known components and processing techniques are omitted so as to not unnecessarily obscure the embodiments herein.
[0062] The foregoing description of the specific embodiments so fully revealed the general nature of the embodiments herein that others can, by applying current knowledge, readily modify and/or adapt for various applications such specific embodiments without departing from the generic concept, and, therefore, such adaptations and modifications should and are intended to be comprehended within the meaning and range of equivalents of the disclosed embodiments. It is to be understood that the phraseology or terminology employed herein is for the purpose of description and not of limitation. Therefore, while the embodiments herein have been described in terms of preferred embodiments, those skilled in the art will recognize that the embodiments herein can be practiced with modification within the scope of the embodiments as described herein.
, Claims:We Claim:
1) A neurobehavioral disorder classification system based on multimodal data, the system comprising:
a data acquisition unit comprising:
i) a microphone configured to capture speech data;
ii) a high-resolution camera configured to capture facial expressions and body language;
iii) one or more physiological sensors;
a processing unit comprising a microcontroller or microprocessor operably coupled to the data acquisition unit, configured to preprocess and normalize the captured multimodal data;
a machine learning module stored in a memory and executed by the processor, trained to classify neurobehavioral disorders based on input data;
a communication module configured to transmit data to and from a remote server or mobile device;
a graphical user interface (GUI) provided via a display unit or mobile application for interaction, feedback presentation, and recommendations to the user; and
a feedback and recommendation module configured to deliver adaptive guidance, intervention strategies, or professional contact suggestions based on the classification outcome.
2) The system as claimed in claim 1, wherein the physiological sensors comprise an electroencephalography (EEG) headset, an electrocardiogram (ECG) module, a heart rate sensor, and a motion detection sensor, galvanic skin response (GSR) sensors and temperature sensors integrated into a wearable device.
3) The system as claimed in claim 1, wherein the machine learning module includes a natural language processing engine configured to analyze user-input textual responses using language models selected from BERT, GPT, or LSTM.
4) The system as claimed in claim 1, wherein the microphone and processing unit are configured to extract and analyze speech features including pitch, prosody, speech rate, and emotion-laden vocabulary to infer emotional states.
5) The system as claimed in claim 1, wherein the high-resolution camera and processor implement a convolutional neural network (CNN)-based model for facial emotion recognition and body posture analysis.
6) The system as claimed in claim 1, wherein the GUI is configured to display culturally adaptive and context-sensitive mental health recommendations in a language selected by the user.
7) The system as claimed in claim 1, wherein the communication module supports federated learning protocols enabling local training of the model while preserving user data privacy.
8) The system as claimed in claim 1, wherein the feedback and recommendation module utilizes a graph-based symptom-interrelation engine to provide multi-disorder profiling and comorbidity visualization.
9) The system as claimed in claim 1, wherein the GUI includes gamified diagnostic tasks and optional augmented reality (AR) environments to enhance user engagement and collect behavioral response data.
10) The system as claimed in claim 1, wherein the display unit is integrated in a mobile device, tablet, or desktop system, and the entire system is configured for remote or in-clinic deployment.