Description:
BACKGROUND
Field of the invention
[001] Embodiments of the present invention generally relate to a Major Depressive Disorder (MDD) diagnosing device and particularly to an Internet of Things (IoT) based device and method for detection of Major Depressive Disorder.
Description of Related Art
[002] Major Depressive Disorder (MDD) is a primary mental health issue characterized by bad mood, loss of interest, hopeless as well as anxiety, cognitive impairment, and even suicidal ideation. Depression is a second leading cause of emergence of several chronic diseases such as diabetes, heart disease, and so on. Traditionally, the Major Depressive Disorder (MDD) was predicted manually in an individual. However, manual work increases a chance of human errors. Moreover, the manual work involves a labor cost, slow performance, and so on, while keeping an aspect of the human error at high all time.
[003] To overcome the aforementioned issues, automated systems have been developed for detection of Major Depressive Disorder (MDD). However, currently available systems are unable to provide results with higher accuracy as the percentage of prior effects that are considered for prediction of the MDD depends upon food habits and lifestyle. There are several test kits commercially available that can diagnose the MDD but the extent of certainty depends from manufacturer to manufacturer, leading to less accurate test results.
[004] There is thus a need for an improved and advanced device and method for detection of Major Depressive Disorder that can administer the aforementioned issues in a more efficient manner.
SUMMARY
[005] Embodiments in accordance with the present invention provide an Internet of Things (IoT) based device for detection of Major Depressive Disorder (MDD). The device comprising: an input unit embedded with an Electroencephalogram (EEG) capturing unit placed over a head of an individual, to measure electrical activity of brain cells in form of EEG signals. The device further comprising: a processing unit connected to the input unit, and configured to: receive the EEG signals from the input unit; pre-process the EEG signals for removing noise from the captured EEG signals by using a pre-processing technique; extract features from the pre-processed EEG signals by using a feature extraction technique; classify the received EEG signals based on the extracted features for predicting an output selected from “depression” or “no depression” by using a trained deep learning technique; and display the predicted output on a display unit.
[006] Embodiments in accordance with the present invention provide a method for detection of Major Depressive Disorder (MDD). The method comprising steps of: receiving Electroencephalogram (EEG) signals of an individual from an input unit; pre-processing the EEG signals for removing noise from the EEG signals by using a pre-processing technique; extracting features from the pre-processed EEG signals by using a feature extraction technique; classifying the received EEG signals based on the extracted features for predicting an output selected from “depression” or “no depression” by using a trained deep learning technique; and displaying the predicted output on a display unit.
[007] Embodiments of the present invention may provide a number of advantages depending on its particular configuration. First, embodiments of the present application may provide an Internet of Things (IoT) based device for detection of Major Depressive Disorder (MDD).
[008] Next, embodiments of the present application may provide a handheld and automated device to screen Electroencephalography (EEG) input signal for detection and classification of Major Depressive Disorder (MDD) through already trained deep learning models.
[009] Next, embodiments of the present application may provide an EEG and AI-based device that may help practitioners to identify results with higher accuracy.
[0010] These and other advantages will be apparent from the present application of the embodiments described herein.
[0011] The preceding is a simplified summary to provide an understanding of some embodiments of the present invention. This summary is neither an extensive nor exhaustive overview of the present invention and its various embodiments. The summary presents selected concepts of the embodiments of the present invention in a simplified form as an introduction to the more detailed description presented below. As will be appreciated, other embodiments of the present invention are possible utilizing, alone or in combination, one or more of the features set forth above or described in detail below.
BRIEF DESCRIPTION OF THE DRAWINGS
[0012] The above and still further features and advantages of embodiments of the present invention will become apparent upon consideration of the following detailed description of embodiments thereof, especially when taken in conjunction with the accompanying drawings, and wherein:
[0013] FIG. 1 illustrates a block diagram of an Internet of Things (IoT) based device for detection of Major Depressive Disorder (MDD), according to an embodiment of the present invention;
[0014] FIG. 2 illustrates a block diagram of components of a processing unit of the device, according to an embodiment of the present invention; and
[0015] FIG. 3 depicts a flowchart of a method for detection of the Major Depressive Disorder (MDD) in an individual by using the device, according to an embodiment of the present invention.
[0016] The headings used herein are for organizational purposes only and are not meant to be used to limit the scope of the description or the claims. As used throughout this application, 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). Similarly, the words “include”, “including”, and “includes” mean including but not limited to. To facilitate understanding, like reference numerals have been used, where possible, to designate like elements common to the figures. Optional portions of the figures may be illustrated using dashed or dotted lines, unless the context of usage indicates otherwise.
DETAILED DESCRIPTION
[0017] The following description includes the preferred best mode of one embodiment of the present invention. It will be clear from this description of the invention that the invention is not limited to these illustrated embodiments but that the invention also includes a variety of modifications and embodiments thereto. Therefore, the present description should be seen as illustrative and not limiting. While the invention is susceptible to various modifications and alternative constructions, it should be understood, that there is no intention to limit the invention to the specific form disclosed, but, on the contrary, the invention is to cover all modifications, alternative constructions, and equivalents falling within the scope of the invention as defined in the claims.
[0018] In any embodiment described herein, the open-ended terms "comprising", "comprises”, and the like (which are synonymous with "including", "having” and "characterized by") may be replaced by the respective partially closed phrases "consisting essentially of", “consists essentially of", and the like or the respective closed phrases "consisting of", "consists of”, the like.
[0019] As used herein, the singular forms “a”, “an”, and “the” designate both the singular and the plural, unless expressly stated to designate the singular only.
[0020] FIG. 1 illustrates a block diagram of an Internet of Things (IoT) based device 100 for detection of Major Depressive Disorder (MDD), according to an embodiment of the present invention. According to an embodiment of the present invention, the device 100 may be a deep learning-based real-time diagnosis device that may be configured to diagnose an individual with Major Depressive Disorder (MDD). The device 100 may be a handheld and automated device to screen Electroencephalography (EEG) input signal for detection and classification of the Major Depressive Disorder (MDD) through already trained deep learning models.
[0021] In an embodiment of the present invention, the device 100 may comprise an input unit 102 that may be an EEG capturing unit. The device 100 may further comprise a processing unit 104, a memory unit 106, a display unit 108, a converter 110, a database 112, and a prediction monitoring application 114.
[0022] In an embodiment of the present invention, the input unit 102 may be placed over a head of an individual. The input unit 102 may be configured to measure electrical activity of brain cells in form of EEG signals. In an embodiment of the present invention, the input unit 102 may be configured to transmit the EEG signals to the processing unit 104.
[0023] The processing unit 104 may be configured to process the EEG signals by executing computer executable instructions to generate an output, in an embodiment of the present invention. The output may be “depression” or no depression”. The processing unit 104 may be a microcontroller that may be configured to process the EEG signals received from the input unit 102, in an embodiment of the present invention. The microcontroller may be, but not limited to, Raspberry Pi, Beagle Board, Arduino, and so forth, in an embodiment of the present invention. Embodiments of the present invention are intended to include or otherwise cover any type of the microcontroller including known related art and/or later developed technologies.
[0024] The processing unit 104 may be configured to transmit the processed EEG signals to the database 112, in an embodiment of the present invention. In an embodiment of the present invention, the computer executable instructions may be a deep learning algorithm that may be trained and deployed using an open-source dataset corpus to classify the Major Depressive Disorder (MDD) in real time. In an embodiment of the present invention, the MDD classification may be performed for predicting whether the individual is diagnosed with the depression or not. The deep learning algorithm may be, but not limited to, a long short-term memory algorithm, a bidirectional long short-term memory algorithm, Bidirectional Encoder Representations from Transformers (BERT), and so forth. Embodiments of the present invention are intended to include or otherwise cover any type of the deep learning algorithms including known related art and/or later developed technologies.
[0025] The memory unit 106 may be a non-transitory data storage medium that may be configured to store the computer executable instructions for processing the EEG signals, according to an embodiment of the present invention. The memory unit 106 may be, but not limited to, a Random-Access Memory (RAM) device, a Read Only Memory (ROM) device, a flash memory, and so forth. Embodiments of the present invention are intended to include or otherwise cover any type of the memory unit 106 including known, related art, and/or later developed technologies.
[0026] In an embodiment of the present invention, the display unit 108 may be configured to display the predicted result based on the output generated by the processing unit 104. According to embodiments of the present invention, the display unit 108 may be, but not limited to, a Light Emitting Diode (LED) display, an Organic Light Emitting Diode (OLED) display, a Liquid Crystal Display (LCD), and so forth. Embodiments of the present invention are intended to include or otherwise cover any type of the display unit 108 including known, related art, and/or later developed technologies.
[0027] In an embodiment of the present invention, the device 100 may comprise a power supply unit (not shown) that may be configured to supply power to the processing unit 104 of the device 100. The power supply unit may be configured to receive a first pre-defined supply voltage from a main power source that may be an external power source such as, but not limited to, an Alternating Current (AC) power source, a Direct Current (DC) power source, and so forth. In a preferred embodiment of the present invention, the main power source may be 220 Volts Alternating Current (AC) power source. Embodiments of the present invention are intended to include or otherwise cover any type of the main power source including known, related art, and/or later developed technologies. In a preferred embodiment of the present invention, the first pre-defined voltage may be 220 Volts (V).
[0028] In an embodiment of the present invention, the converter 110 may be connected to the power supply unit. The converter 110 may be configured to step down the first pre-defined voltage to a second pre-defined voltage to supply the power to the processing unit 104 of the device 100. In a preferred embodiment of the present invention, the second pre-defined voltage may be 5 Volts (V).
[0029] The database 112 may be used to store the predicted result remotely, in an embodiment of the present invention. The database 112 may be, but not limited to, a distributed database, a personal database, an end-user database, a commercial database, a Structured Query Language (SQL) database, an operational database, a relational database, an object-oriented database, a graph database, and so forth. In a preferred embodiment of the present invention, the database 112 may be a cloud-based database. Embodiments of the present invention are intended to include or otherwise cover any type of the database 112 including known, related art, and/or later developed technologies.
[0030] The prediction monitoring application 114 may be installed within the device 100, in an embodiment of the present invention. In another embodiment of the present invention, the prediction monitoring application 114 may be installed within a user device (not shown) that may communicate with the device 100 through a communication unit (not shown).
[0031] In an embodiment of the present invention, the prediction monitoring application 114 may enable a user to view the predicted output on the device 100 or the user device. The user may be, but not limited to, caregivers, patients, doctors, practitioners, and so forth. Embodiments of the present invention are intended to include or otherwise cover any type of the user.
[0032] In an embodiment of the present invention, the user device may be a device used by the user to remotely monitor the predicted output. The user device may be, but not limited to, a personal computer, a consumer device, and alike. Embodiments of the present invention are intended to include or otherwise cover any type of the user device including known, related art, and/or later developed technologies.
[0033] The communication unit may enable the processing unit 104 of the device 100 to connect to a communication network (not shown) that may be a Wireless Fidelity (Wi-Fi) network to transmit the predicted result to the user device. The communication unit may be, but not limited to, an Intel communication unit, a Qualcomm communication unit, a Broadcom communication unit, a Espressif communication unit, and so forth. Embodiments of the present invention are intended to include or otherwise cover any type of the communication unit, including known, related art, and/or later developed technologies.
[0034] FIG. 2 illustrates a block diagram of components of the processing unit 104 of the device 100, according to an embodiment of the present invention. The components may comprise a data receiving module 200, a data processing module 202, a feature extraction module 204, a training module 206, a classification module 208, and output module 210.
[0035] The data receiving module 200 may be configured to receive the EEG signals from the input unit 102, in an embodiment of the present invention. The data receiving module 200 may be configured to transmit the EEG signals to the data processing module 202.
[0036] The data processing module 202 may be configured to receive the EEG signals from the data receiving module 200 in real-time. Further, the data processing module 202 may be configured to pre-process the EEG signals for removing noise from the EEG signals. The data processing module 202 may be configured to pre-process the EEG signals by using a pre-processing technique. In an embodiment of the present invention, the data processing module 202 may be configured to transmit the pre-processed EEG signals to the feature extraction module 204, in an embodiment of the present invention.
[0037] The feature extraction module 204 may be configured to extract features from the pre-processed EEG signals by using a feature extraction technique, in an embodiment of the present invention. The feature extraction technique may comprise algorithms such as, but not limited to, a Linear Predictive Coding, a Probabilistic Linear Discriminate Analysis, and so forth. Embodiments of the present invention are intended to include or otherwise cover any type of the feature extraction technique, including known, related art, and/or later developed technologies. The feature extraction module 204 may be configured to store the extracted features to the memory unit 106, in an embodiment of the present invention.
[0038] In an embodiment of the present invention, the training module 206 may be configured to access the extracted features stored in the memory unit 106. Further, the training module 206 may be configured to utilize the stored features as a set of training data to predict the MDD in the individual, in an embodiment of the present invention.
[0039] The classification module 208 may be configured to classify the received EEG signals for predicting the MDD in the individual, in an embodiment of the present invention. The classification module 208 may be configured to classify the received EEG signals based on the extracted features. The classification module 208 may be configured to classify the EEG signals for predicting the output by using a trained deep learning technique, in an embodiment of the present invention. The classification module 208 may be configured to transmit the predicted output to the output module 210.
[0040] The output module 210 may be configured to display the predicted output on the display unit 108, in an embodiment of the present invention.
[0041] FIG. 3 depicts a flowchart of a method 300 for detection of the Major Depressive Disorder (MDD) in the individual by using the device 100, according to an embodiment of the present invention.
[0042] At step 302, the device 100 may receive the EEG signals from the input unit 102.
[0043] At step 304, the device 100 may pre-process the EEG signals for removing the noise from the EEG signals by using the pre-processing technique.
[0044] At step 306, the device 100 may extract the features from the pre-processed EEG signals by using the feature extraction technique.
[0045] At step 308, the device 100 may classify the received EEG signals based on the extracted features to predict the output.
[0046] At step 310, the device 100 may display the predicted output onto the display unit 108.
[0047] While the invention has been described in connection with what is presently considered to be the most practical and various embodiments, it is to be understood that the invention is not to be limited to the disclosed embodiments, but on the contrary, is intended to cover various modifications and equivalent arrangements included within the scope of the appended claims.
[0048] This written description uses examples to disclose the invention, including the best mode, and also to enable any person skilled in the art to practice the invention, including making and using any devices or systems and performing any incorporated methods. The patentable scope the invention is defined in the claims, and may include other examples that occur to those skilled in the art. Such other examples are intended to be within the scope of the claims if they have structural elements that do not differ from the literal language of the claims, or if they include equivalent structural elements within substantial differences from the literal languages of the claims. , Claims:CLAIMS
I/We Claim:
1. An Internet of Things (IoT) based device (100) for detection of Major Depressive Disorder (MDD), the device (100) comprising:
an input unit (102) embedded with an Electroencephalography (EEG) capturing unit placed over a head of an individual, to measure electrical activity of brain cells in form of EEG signals; and
a processing unit (104) connected to the input unit (102), and configured to:
receive the captured EEG signals from the input unit (102);
pre-process the EEG signals for removing noise from the captured EEG signals by using a pre-processing technique;
extract features from the pre-processed EEG signals by using a feature extraction technique;
classify the received EEG signals based on the extracted features for predicting an output selected from “depression” or “no depression” by using a trained deep learning technique; and
display the predicted output on a display unit (108).
2. The device (100) as claimed in claim 1, wherein the processing unit (104) is a microcontroller.
3. The device (100) as claimed in claim 1, comprising a database (112) configured to store the predicted output remotely.
4. The device (100) as claimed in claim 3, wherein the database (112) is a cloud-based database.
5. The device (100) as claimed in claim 1, comprising a prediction monitoring application (114) configured to enable a user to monitor the predicted output.
6. The device (100) as claimed in claim 1, wherein the trained deep learning technique is selected from a long short-term memory technique, a bidirectional long short-term memory technique, Bidirectional Encoder Representations from Transformers (BERT), or a combination thereof.
7. The device (100) as claimed in claim 1, comprising a converter (110) to step down a power of a first pre-defined voltage to a second pre-defined voltage to supply the power to the processing unit (104) of the device (100).
8. A method for detection of Major Depressive Disorder (MDD) by using a device (100), the method comprising steps of:
receiving captured EEG signals from an input unit (102);
pre-processing the EEG signals for removing noise from the captured EEG signals by using a pre-processing technique;
extracting features from the pre-processed EEG signals by using a feature extraction technique;
classifying the received EEG signals based on the extracted features for predicting an output selected from “depression” or “no depression” by using a trained deep learning technique; and
displaying the predicted output on a display unit (108).
9. The method as claimed in claim 8, comprising a step of enabling a user to monitor the predicted output by a prediction monitoring application (114) installed within the device (100).
10. The method as claimed in claim 8, comprising a step of storing the predicted output remotely in a database (112).
Date: February 06, 2023
Place: Noida

Nainsi Rastogi
Patent Agent (IN/PA-2372)
Agent for the Applicant