Claims:CLAIMS
We claim:
1. A computer implemented method for centralized health monitoring using convolutional neural network, wherein the computer implemented method is performed by a computing unit proving user interface or mobile application for accessing system, wherein the computing unit comprises a processor, a memory communication unit, wherein the computer implemented method comprising steps of:
train the central server using databases and test cases and registering the patient to the system (101);
capture periodically physiological and health related parameter through smart wearable devices or bed attached gadgets having biomedical sensors (102);
transmitting collected data periodically to central server (103);
analyzing, by the first layer of convolutional neural network, the collected data of a patient with the past collected data of same patient (104);
analyzing, by the second layer of convolutional neural network, output of first layer with the data of other patient having same health issues and stored data in database 1205);
alarming or sending notification to the healthcare worker or doctor if any abnormality found (106);

2. The method as claimed in claim 1, wherein physiological or health related parameters are but not limited to body temperature, oxygen level (SpO2), heart rate variability, motion, sleep, stress, fitness level, recovery level, effect of a workout routine on health, caloric expenditure.

3. The method as claimed in claim 1, wherein the communication network may be based on the WiFi, Bluetooth, Local Area Network, Wide Area Network or the combination thereof and smart wearable devices or bed attached gadgets may be but not limited to smart watch, electronic tag, chest strip or any biomedical sensor-based gadgets.

4. A system for centralized health monitoring using convolutional neural network, the system comprising:

a communication network (201) to transmit/receive data from other embodiments of the system;
database (202) to train the central server according to the machine learning model;
a central server (203) equipped with convolutional neural network;
smart wearable devices or bed attached gadgets having various biomedical sensor (204) to continuously collect physiological or health parameters;
a computing unit (205) providing user interface or mobile application for accessing the system;
healthcare worker and doctor module (206) for accessing data related to patient and getting alarm/notification sent by central server;
train the central server using databases and test cases and registering the patient to the system (101);
capture periodically physiological and health related parameter through smart wearable devices or bed attached gadgets having biomedical sensors (102);
transmitting collected data periodically to central server (103);
analyzing, by the first layer of convolutional neural network, the collected data of a patient with the past collected data of same patient (104);
analyzing, by the second layer of convolutional neural network, output of first layer with the data of other patient having same health issues and stored data in database 1205);
alarming or sending notification to the healthcare worker or doctor if any abnormality found (206).
, Description:Centralized health monitoring system using Convolution Neural Network
FIELD OF INVENTION
[0001] The present invention relates to the field of health monitoring system. The field of the invention is to provide a method for centralized health monitoring system using convolution neural network.
[0002] More particularly, this present invention relates to the field of centralized health monitoring system to automate the process of monitoring health and its related parameters automatically using convolution neural network.

BACKGROUND & PRIOR ART

[0003] The subject matter discussed in the background section should not be assumed to be prior art merely as a result of its mention in the background section. Similarly, a problem mentioned in the background section or associated with the subject matter of the background section should not be assumed to have been previously recognized in the prior art. The subject matter in the background section merely represents different approaches, which in-and-of-themselves may also be inventions.

[0004] In today’s world, with the advancement in technology, world is moving toward automation. Patient’s health monitoring is one of the such field that requires automation because the health monitoring of patient’s timely and regularly is one of the crucial tasks for providing proper and timely treatment. Further, as we also know that, in this global pandemic situation due to covid-19 disease where most of the population of the world is affected by this disease. Patients are getting infected from the covid disease and health care service providers are unable to provide service at hospital due to limited bed availability at hospital. The major population of the world is affected by the disease and health system is collapsed and unable to fulfil the demands at time due to many constraints. The human resources in the hospitals are also getting over stressed due to the large number of people getting infected and admitted in the hospital. Due to the limited number of human resources, health care workers are bound to work day and night. Hence, there is a need of such centralized system that can automatically captures the physiological and health related parameters of the patient and can alar the healthcare workers or doctors to provide timely response or treatment for saving human life.

[0005] There is a need of such a centralized system that can automatically captures and assess the captured data. Further, if there is any abnormality or crucial data is captured related to a patient, then the system will alarm the health care worker or doctor regarding the said situation. Hence, there is a need of such a system that can automate the said process. One such advanced approach to perform automation is machine learning models. Machine learning models are one of the most advanced and current technology which is used for automation. There are various kinds of machine learning models used for providing automation or artificial intelligence which are broadly divided in two types namely supervised learning and unsupervised learning. One kind of machine learning model which is used for automation is convolution neural network. convolution neural network is one of the machine learning methodology used for providing artificial intelligence. convolutional neural network is widely used in providing improved performance and high level of features abstraction in comparison to traditional models. The convolution neural network is a kind of deep learning models which refers to the use of multiple layers in the network. convolution neural network is a variation in which unbounded number of layers with bounded size is used for providing faster response, improved performance and high level of abstraction. In convolution neural network, the layers involved may be heterogeneous in nature. In convolution neural network, each level learns to transform its input data into a slightly more abstract and composite representation.

[0006] Hence, developing health monitoring systems using convolution neural network can automate the said process and improvise the performance of the health monitoring system. Further, there may be the time come in which hospitals will run in its fullest capacity and not able to provide services to more patients. There is a need of the centralized system which can provide health related services to the patients at home and can monitor the said patients remotely. The use of such kind of automated and centralized health monitoring system will also reduce the load on health care workers and doctors also. There is no need of manually taking physiological and health related parameters regularly as such kind of system will automatically captures such kind of data timely and regularly.

[0007] Hence, developing such kind of centralized and automated health monitoring system using convolutional neural network is a necessity of today’s era and aim of the present invention. There is various prior art that aim to resolve the issue of providing health monitoring system which are discussed below:

[0008] US6442432 B2 – A data communication system is provided which permits collaboration between distributed clinicians regarding distributed or remote implantable medical devices (IMDs). A central computing resource capable of storing and distributing patient device and clinician location and contact data is provided, as well as a network providing communication with the computing resource. A deployed IMD may be polled by an interface device external to the host patient, and data may be transmitted to the interface device by wireless communication. This data may be transmitted to a central computer for storage and distribution. The data may be distributed to various clinicians in communication with the central computer. These clinicians may use this information, either directly or indirectly, to contact remote clinicians and medical devices in communication with the network.

[0009] US6168563 B1 – A system and method that enables a health care provider to monitor and manage a health condition of a patient. The system includes a health care provider apparatus operated by a health care provider and a remotely programmable patient apparatus that is operated by a patient. The health care provider develops a script program using the health care provider apparatus and then sends the script program to a remotely programmable patient apparatus through a communication network such as the World Wide Web. The script program is a computer-executable patient protocol that provides information to the patient about the patient's health condition and that interactively monitors the patient health condition by asking the patient questions and by receiving answers to those questions. The answers to these health-related questions are then forwarded as patient data from the remotely programmable patient apparatus to the health care provider apparatus through the communication network. The patient data may also include information supplied by a physiological monitoring device such as a blood glucose monitor that is connected to the remotely programmable patient apparatus. When the patient data arrives at the health care provider apparatus, the patient data is processed for further management of the patient's health condition by the health care provider, such as forwarding another script program to the remotely programmable patient apparatus.

[0010] US4803625 A – A personal health monitor includes sensors for measuring patient weight, temperature, blood pressure, and ECG waveform. The monitor is coupled to a central unit via modems and includes a computer which is programmed to prompt a patient to take prescribed medication at prescribed times, to use the sensors to measure prescribed health parameters, and to supply answers to selected questions. Medication compliance information, test results, and patient answers are compiled in a composite log which is automatically transmitted to the central unit. The computer is also programmed automatically to disconnect the monitor from an alternating current power source and to rely on internal battery power during certain periods of patient-monitor interaction, such as during use of the ECG module. In this way, danger to the patient and complexity of the ECG module are minimized. The computer is also programmed to compare measured test information with predetermined expected values, and in the event of a discrepancy, to collect additional information from the patient to assist trained personnel at the central unit in interpreting the composite log. The computer is also programmed to alert the central unit promptly in the event one or more measured parameters falls outside of a prescribed normal range. The normal range for a given parameter is made to vary in accordance with the measured value of one or more other parameters in order to reduce the incidence of false alarms.

[0011] US5544661 A – A patient monitoring system which includes a portable device and a central station. The portable device includes an ECG and a photo-plethysmograph connected to the patient; arrhythmia analysis apparatus; an expert system for determining if a pre-established critical parameter set has been exceeded; and a wireless wide area communication device for automatically contacting the central station via a public cellular phone network when the critical parameter set has been exceeded. When the central station is contacted, the patient's ECG waveforms, measurements, and trends, are sent to the central monitoring station and a two-way voice channel between the patient and the central station is automatically opened. The central station includes a computerized facility which has a station from which a clinician can observe the real time data being sent from the patient, the patients historical records and from which the clinician can talk to the patient and activate therapeutic devices attached to the patient such as an external defibrillator, a pacer or an automatic drug infusion device.

[0012] US5038800 A – A system for monitoring a patient by using a local area network (LAN) to connect a central monitor, located at a nurse's station, to one or more bedside monitors, wherein the bedside monitor measures the patient's condition, for instance an electrocardiogram (ECG). The LAN provides data from the bedside monitor to the central monitor at a rate sufficient for the central monitor to display all information contained within the bedside monitor in substantially real time. The LAN also allows a user at the central station or at another bedside monitor to remotely read or adjust the bedside monitor settings.

[0013] EP1197178 B1 – A wireless bi-directional portable patient monitor incorporated into a mobile clinical information management system includes a communications interface to receive patient data from a wireless local area network (WLAN) within a medical care facility and transmit care parameters as needed to the wireless network (WLAN) in response. The portable patient monitor includes a processor connected to the communications interface to process the patient data and the care parameters. A display is connected to the processor to display the processed patient data to the health care provider. The monitor includes an input device connected to the processor to allow a change in the care parameters by the health care provider. The portable patient monitor is also configured to allow wireless transport on the health care provider for extended periods. The mobile clinical information management system includes a number of bedside patient monitors to connect to the patients and transmit the patient data. The system also includes the wireless network coupled to the bedside patient monitors and the portable patient monitors to improve efficiencies in the delivery of health care in the medical care facility .

[0014] Besides this, there are various prior arts in the state of the art that claims to resolve the problem of providing health monitoring system but the approach adopted for solving the same need to be further refined. Hence, there is a need to provide more efficient and improved process that provide further automation and centralized health monitoring system using convolutional neural network. The aim of the present invention is to provide autonomous and centralized health monitoring system that can automatically captures and analyze the data and warn the health care workers or doctors for providing medical attendance to particular patient remotely.

[0015] Groupings of alternative elements or embodiments of the invention disclosed herein are not to be construed as limitations. Each group member can be referred to and claimed individually or in any combination with other members of the group or other elements found herein. One or more members of a group can be included in, or deleted from, a group for reasons of convenience and/or patentability. When any such inclusion or deletion occurs, the specification is herein deemed to contain the group as modified thus fulfilling the written description of all Markus groups used in the appended claims.

[0016] As used in the description herein and throughout the claims that follow, the meaning of “a,” “an,” and “the” includes plural reference unless the context clearly dictate otherwise. Also, as used in the description herein, the meaning of “in” includes “in” and “on” unless the context clearly dictates otherwise.

[0017] The recitation of ranges of values herein is merely intended to serve as a shorthand method of referring individually to each separate value falling within the range. Unless otherwise indicated herein, each individual value is incorporated into the specification as if it were individually recited herein. All methods described herein can be performed in any suitable order unless otherwise indicated herein or otherwise clearly contradicted by context.

[0018] The use of any and all examples, or exemplary language (e.g. “such as”) provided with respect to certain embodiments herein is intended merely to better illuminate the invention and does not pose a limitation on the scope of the invention otherwise claimed. No language in the specification should be construed as indicating any non-claimed element essential to the practice of the invention.

[0019] The above information disclosed in this Background section is only for enhancement of understanding of the background of the invention and therefore it may contain information that does not form the prior art that is already known in this country to a person of ordinary skill in the art.

SUMMARY OF THE INVENTION

[0020] Before the present systems and methods, are described, it is to be understood that this application is not limited to the particular systems, and methodologies described, as there can be multiple possible embodiments which are not expressly illustrated in the present disclosure. It is also to be understood that the terminology used in the description is for the purpose of describing the particular versions or embodiments only and is not intended to limit the scope of the present application. This summary is provided to introduce concepts related to methods for autonomous vehicle driving and traffic sign identification based on deep learning models and the concepts are further described below in the detailed description. This summary is not intended to identify essential features of the claimed subject matter nor is it intended for use in determining or limiting the scope of the claimed subject matter.

[0021] The present invention mainly solves the technical problems existing in the prior art. In response to these problems, the present invention discloses a method for centralized health monitoring system using convolutional neural network. The solution to the said problem need to be further optimized so that the health monitoring system should be more reliable, efficient, faster response time, better accuracy and more assistance will be provided so that timely assistance and treatment can save the human life.

[0022] The proposed invention is based on the convolution neural network. The present invention mainly solves the technical problems existing in the prior art. In response to these problems, the present invention discloses a method and system for centralized health monitoring and timely monitor the patients (hospital admitted or home isolated) about any health-related issues and collect various physiological and health related parameters using biomedical sensors periodically which are updated to the centralized server. The given solution is based on the convolutional neural network which are competent enough to train themselves through the past scans/data and database provided to the said model on the central server. The proposed invention comprises of central server which comprises of the initial database which is used to train the convolutional neural network to automatically identity the any health-related anomalies based on the collected data analysis related to the patient. The said system is trained enough using the test cases and databases that can identify any kind of health-related issues and infer the data available about the patient and detect timely any health abnormality and alarm the health care worker or doctor. The said model is backed with the database of patients monitored data. The said convolutional neural network makes the server machine smart and intelligent. The convolutional neural network used here comprises of two layers. The first layer is used to infer the data collected at any point of time with the past data of same patient which further goes through the second layer which analyzes the said collected data at with the trained data and data of other patients infected with same disease and gives better analysis. If the analyzed data shows any abnormality, then the health care worker or doctor of the corresponding patient is alarmed by the system for timely treatment and assistance.

[0023] The proposed invention comprises smart wearable devices which may be in the form smart watch, electronic tag, chest strap or any kind of smart wearable devices for home isolated patient and gadgets along with biomedical sensor in bed for hospital admitted patient which are registered with the patients that need to be monitored. These smart wearable devices bed attached biomedical sensors gather the data/information continuously. The said data is locally stored within the small memory provided within the smart wearable device. These smart wearable devices or bed attached gadgets comprise various biomedical sensors which automatically measures and records a plurality of physiological and health parameters data from sensors in contact with the patient's body. The smart wearable device or bed attached gadgets collects various kind of physiological and other parameters including but not limited to body temperature, heart rate variability, oxygen level (SpO2), motion, sleep, stress, fitness level, recovery level, effect of a workout routine on health, caloric expenditure etc. Further, these smart wearable devices or bed attached gadgets periodically update the collected data to a database on the central server in which it is stored along with similar health histories for other patients. The said smart wearable devices communicates to the communication network through Bluetooth standard protocol. The collected data is analyzed by the convolutional neural network as stated in the above paragraph and alarm the healthcare worker or doctor registered to the patient in the system for timely assistance.

[0024] The present invention discloses a computer implemented method for centralized health monitoring system using convolutional neural network, wherein the computer implemented method is performed by a computing unit, wherein the computing unit comprises a processor and memory, communication unit. The said system also comprises a central server which is equipped with the convolutional neural network to automatically detect the health abnormality with respect to the collected data. The computing unit is in communication with the central server via any communication means. The said computing device provide user interface to interact with the system and helps in registering the patients to be monitored. The said user interface may be in the form of mobile application also. Further, unique wearable devices or bed gadgets are registered with the patients to collect various physiological and health related parameters of a patient. The computer implemented method comprising steps of: obtaining various physiological and health parameters periodically using biomedical sensors in smart wearable devices or bed gadgets, transmitting the collected physiological and health parameters to the central server through communication network, analyzing the collected data by first layer of convolutional neural network with the past data of same patient, analyzing the output of first layer by the second layer with the data of other patients with same problems/diseases and stored data and if there is any abnormal pattern then alarm the health care worker or doctor registered with the patient for timely assistance and treatment.

[0025] An aspect of the present disclosure relates to a computer implemented method for centralized health monitoring system using convolutional neural network, wherein the computing unit/mobile terminal comprises a processor and memory, communication unit and a user interface or mobile application to access the system, the method comprises: registering the patient, associating smart wearable devices or bed installed gadgets with the patient, automatically obtaining various physiological and health parameters periodically using biomedical sensors in smart wearable devices or bed attached gadgets, periodically transmitting the gathered data to the central server through communication network, analyzing the collected data by first layer of convolutional neural network with the past data of same patient, analyzing the output of first layer by the second layer with the data of other patients with same problems/diseases and stored data and if there is any abnormal pattern then alarm the health care worker or doctor registered with the patient for timely assistance and treatment.

[0026] Another aspect of the present disclosure relates to system for centralized health monitoring system using convolutional neural network, wherein the computing unit/mobile terminal comprises a processor and memory, communication unit and a user interface or mobile application to access the system, the method comprises: registering the patient, associating smart wearable devices or bed installed gadgets with the patient, automatically obtaining various physiological and health parameters periodically using biomedical sensors in smart wearable devices or bed attached gadgets, periodically transmitting the gathered data to the central server through communication network, analyzing the collected data by first layer of convolutional neural network with the past data of same patient, analyzing the output of first layer by the second layer with the data of other patients with same problems/diseases and stored data and if there is any abnormal pattern then alarm the health care worker or doctor registered with the patient for timely assistance and treatment.

[0027] This summary is provided to introduce a selection of concepts in a simplified form that are further described below in the detailed description. This summary is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used to limit the scope of the claimed subject matter.

OBJECTIVE OF THE INVENTION

[0028] A primary object of the present invention is to provide a method for centralized health monitoring system using convolutional neural network. The aim of the present method is to provide better and reliable process without human intervention to automatically collect the required data regularly and provide timely assistance and treatment to the patient.
[0029] Yet another object of the present invention is to provide a system for centralized health monitoring system using convolutional neural network. The system comprising a server equipped with convolutional neural network that automatically assess the collected data and alarm the registered health care worker or doctor for providing assistance or treatment to the patient.

BRIEF DESCRIPTION OF DRAWINGS

[0030] To clarify various aspects of some example embodiments of the present invention, a more particular description of the invention will be rendered by reference to specific embodiments thereof which are illustrated in the appended drawings. It is appreciated that these drawings depict only illustrated embodiments of the invention and are therefore not to be considered limiting of its scope. The invention will be described and explained with additional specificity and detail through the use of the accompanying drawings.

[0031] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the embodiments belong. Although methods and materials similar or equivalent to those described herein can be used in the practice or testing, suitable methods and materials are described below. In case of conflict, the patent specification, including definitions, will control. In addition, the materials, methods, and examples are illustrative only and not intended to be limiting.

[0032] In order that the advantages of the present invention will be easily understood, a detail description of the invention is discussed below in conjunction with the appended drawings, which, however, should not be considered to limit the scope of the invention to the accompanying drawings, in which:

[0033] Figure 1 shows flow diagram of the method for centralized health monitoring system using convolutional neural network in accordance with the present invention.
[0034] Figure 2 shows a block-diagram of system in accordance with the present invention.

DETAIL DESCRIPTION

[0035] The present invention relates to a method and system for centralized health monitoring system using convolutional neural network.

[0036] Although the present disclosure has been described with the purpose of providing a system for centralized health monitoring system using convolutional neural network, it should be appreciated that the same has been done merely to illustrate the invention in an exemplary manner and to highlight any other purpose or function for which explained structures or configurations could be used and is covered within the scope of the present disclosure.

[0037] Some embodiments of this disclosure, illustrating all its features, will now be discussed in detail. The words and other forms thereof are intended to be open ended in that an item or items following any one of these words is not meant to be an exhaustive listing of such item or items, or meant to be limited to only the listed item or items. It must also be noted that as used herein and in the appended claims, the singular forms "a," "an," and "the" include plural references unless the context clearly dictates otherwise. Although any systems and methods similar or equivalent to those described herein can be used in the practice or testing of embodiments of the present disclosure, the exemplary systems and methods are now described. The disclosed embodiments are merely exemplary of the disclosure, which may be embodied in various forms.

[0038] Various modifications to the embodiment will be readily apparent to those skilled in the art and the generic principles herein may be applied to other embodiments. However, one of ordinary skill in the art will readily recognize that the present disclosure is not intended to be limited to the embodiments illustrated, but is to be accorded the widest scope consistent with the principles and features described herein.
[0039] Figure 1 show a flow diagram representing the steps involved in process of centralized health monitoring using convolutional neural network in accordance with the present invention. According to the present invention, the computer implemented method first Train central server using database/test cases according to convolutional neural network at step 101. The smart wearable devices or bed attached gadgets collect data periodically related to physiological and other health related parameters using various kinds of biomedical sensors at step 102. The captured or collected data related to patient may be but not limited to body temperature, oxygen level (SpO2), heart rate variability, motion, sleep, stress, fitness level, recovery level, effect of a workout routine on health, caloric expenditure or any kind of health-related parameter. The computer implemented method further comprising the steps of: periodically and automatically transmitting the collected data to the central server at step 103. The first layer of convolutional neural network, at central server, analyzes the data collected related to a patient with the past data of same patient at step 204. The output of first layer is taken as input to the second layer of convolutional neural network. The second layer of convolutional neural network then analyzes the output of first layer with the data of other patient having same kind of health issued and test cases stored in the database at step 205. If the central server determines any abnormality or health issues in the collected data, send an alarm to the healthcare worker or doctor registered to that patient at step 206.
[0040] Figure 2 shows the block-diagram of system centralized heath monitoring using convolutional neural network comprising smart wearable devices or bed attached gadgets (204) for collecting timely and automatically physiological and other health related parameters using biomedical sensors. Patient or user can also input the data by accessing the said system using mobile application or user interface if any. The data collected by the smart wearable devices is captured periodically. The collected data is periodically transmitted to the central server via the network means (201). The said network means may be WiFi/Bluetooth/LAN/WAN or any other technology used for transmitting the data from one location to the another. The smart wearable devices or bed attached gadgets may be smart watches, electronic tag, chest strip or any kind of smart wearable device. The communication network (201) helps in transmitting and receiving data to and from the other embodiments of the system. The said communication network may be WiFi/Bluetooth/LAN/WAN. The databases (202) reside at the central server which is used to train the central server according to the adopted convolutional neural network and helps the central server in analyzing and identifying/inferring the gathered data. The central server (203) uses convolutional neural network and process the data according to the present invention. The said central server is trained using the past data provided in the database and test cases. The computing unit (205) helps as a user interface to the user and aids in accessing the said system. Further, the healthcare workers or doctors (206) and user/patient can access the said system using mobile application also.
[0041] The figures and the foregoing description give examples of embodiments. Those skilled in the art will appreciate that one or more of the described elements may well be combined into a single functional element. Alternatively, certain elements may be split into multiple functional elements. Elements from one embodiment may be added to another embodiment. For example, order of processes described herein may be changed and are not limited to the manner described herein. Moreover, the actions of any flow diagram need not be implemented in the order shown; nor do all of the acts need to be necessarily performed. Also, those acts that are not dependent on other acts may be performed in parallel with the other acts. The scope of embodiments is by no means limited by these specific examples.

[0042] Although implementations for invention have been described in a language specific to structural features and/or methods, it is to be understood that the appended claims are not necessarily limited to the specific features or methods described. Rather, the specific features and methods are disclosed as examples of implementations for the invention.