DESC:EARLIEST PRIORITY DATE:
This Application claims priority from a provisional patent application filed in India having Patent Application No. 202221037546, filed on October 30, 2022, and titled MEDICAL PERSONAL INFORMATION.
FIELD OF INVENTION
[0001] Embodiments of the present disclosure relate to a field of data processing and more particularly to a system and a method to provide a plurality of insights regarding one or more health conditions of a patient.
BACKGROUND
[0002] Medical data refers to any information related to health of a patient, a medical history of the patient, and treatment of the patient. The medical data includes patient information, clinical observations, laboratory results, medication records, electronic health records (EHRs), radiology data, imaging data, genomic data, telehealth data, remote monitoring data, patient-reported data, surgical records, pathology reports, public health data, biometric data, behavioral health data, social determinants of health (SDOH) data and the like.
[0003] Conventionally, the medical data of the patient is stored across different healthcare providers in various formats. Such a fragmentation of the medical data causes difficulties for healthcare providers in accessing the medical data and assessing the health conditions of the patient, leading to potential treatment errors. Further, the healthcare providers encounter difficulties in searching, retrieving and modifying the medical data stored on paper-based records and data storage units function based on different protocols, leading to repeated diagnostic tests and jeopardizing the safety of the patient. Furthermore, fragmentation of the medical data hinders the patient from making proactive healthcare decisions, consulting a medical practitioner having relevant specialization and the like. Moreover, the storage of medical data utilizing inadequate data security measures causes privacy vulnerabilities. Additionally, the lack of real-time updates in the medical data impairs the quality of medical care.
[0004] Hence, there is a need for an improved system and method to provide a plurality of insights regarding one or more health conditions of a patient to address the aforementioned issue(s).
OBJECTIVE OF THE INVENTION
[0005] An objective of the invention is to provide a plurality of insights regarding one or more health conditions of a patient based on a plurality of medical data of the patient.
[0006] Another objective of the invention is to visualize the plurality of insights to support decision making.
[0007] Yet another objective of the invention is to secure the plurality of medical data by encrypting the plurality of medical data.
[0008] Yet another objective of the invention is to shortlist one or more medical practitioners corresponding to the one or more health conditions of the patient and scheduling an appointment of the patient with the one or more medical practitioners based on an input from the patient.
[0009] Yet another objective of the invention is to recommend one or more treatment plans for the patient corresponding to the one or more health conditions.
[0010] Yet another objective of the invention is to notify the patient regarding one or modifications performed on the plurality of medical data.
[0011] Yet another objective of the invention is to display the plurality of medical data and a corresponding contributing channel in a user interface upon authenticating the patient.
BRIEF DESCRIPTION
[0012] In accordance with an embodiment of the present disclosure, a system to provide a plurality of insights regarding one or more health conditions of a patient is provided. The system includes a processing subsystem hosted on a server and configured to execute on a network to control bidirectional communications among a plurality of modules. The processing subsystem includes a data acquisition module configured to receive a plurality of medical data of the patient from a plurality of contributing channels. The data acquisition module is also configured to categorize the plurality of medical data received into a plurality of categories including one or more patient histories, one or more medical images, and one or more prescriptions. The processing subsystem also includes an image processing module configured to detect one or more regions corresponding to one or more body parts from the one or more medical images. The image processing module is also configured to generate bounding boxes and segmentation masks for each of the one or more regions detected on the one or more medical images using a feature pyramid network technique. The image processing module is further configured to identify a first vector corresponding to one or more physical changes of the patient based on bounding boxes and segmentation masks. The processing subsystem also includes a text processing module configured to analyze the one or more patient histories and the one or more prescriptions using at least one natural language processing technique. The text processing module is also configured to identify a second vector corresponding to one or more health status of the patient based on analysis of the one or more patient histories and the one or more prescriptions. The processing subsystem further includes an insights generation module configured to generate the plurality of insights regarding the one or more health conditions detected based on the first vector and the second vector identified by the image processing module, and the text processing module respectively using a plurality of neural network techniques.
[0013] In accordance with another embodiment of the present disclosure, a method to provide a plurality of insights regarding one or more health conditions of a patient is provided. The method includes receiving, by a data acquisition module, a plurality of medical data of the patient from a plurality of contributing channels. The method also includes categorizing, by the data acquisition module, the plurality of medical data received into a plurality of categories including one or more patient histories, one or more medical images, and one or more prescriptions. The method further includes detecting, by an image processing module, one or more regions corresponding to one or more body parts from the one or more medical images. The method also includes generating, by the image processing module, bounding boxes and segmentation masks for each of the one or more regions detected on the one or more medical images using a feature pyramid network technique. The method further includes identifying, by the image processing module, a first vector corresponding to one or more physical changes of the patient based on bounding boxes and segmentation masks. The method also includes analyzing, by a text processing module, the one or more patient histories and the one or more prescriptions using at least one natural language processing technique. The method further includes identifying, by the text processing module, a second vector corresponding to one or more health status of the patient based on analysis of the one or more patient histories and the one or more prescriptions. The method also includes generating, by an insights generation module, the plurality of insights regarding the one or more health conditions detected based on the first vector and the second vector identified by the image processing module, and the text processing module respectively using a plurality of neural network techniques.
[0014] To further clarify the advantages and features of the present disclosure, a more particular description of the disclosure will follow by reference to specific embodiments thereof, which are illustrated in the appended figures. It is to be appreciated that these figures depict only typical embodiments of the disclosure and are therefore not to be considered limiting in scope. The disclosure will be described and explained with additional specificity and detail with the appended figures.
BRIEF DESCRIPTION OF THE DRAWINGS
[0015] The disclosure will be described and explained with additional specificity and detail with the accompanying figures in which:
[0016] FIG. 1 is a block diagram representation of a system to provide a plurality of insights regarding one or more health conditions of a patient in accordance with an embodiment of the present disclosure;
[0017] FIG. 2 is a block diagram representation of one embodiment of the system of FIG. 1 in accordance with an embodiment of the present disclosure.
[0018] FIG. 3 is a schematic representation of an exemplary embodiment of the system of FIG. 1, in accordance with an embodiment of the present disclosure;
[0019] FIG. 4 is a block diagram of a computer or a server in accordance with an embodiment of the present disclosure; and
[0020] FIG. 5 is a flow chart representing the steps involved in a method to provide a plurality of insights regarding one or more health conditions of a patient in accordance with an embodiment of the present disclosure.
[0021] Further, those skilled in the art will appreciate that elements in the figures are illustrated for simplicity and may not have necessarily been drawn to scale. Furthermore, in terms of the construction of the device, one or more components of the device may have been represented in the figures by conventional symbols, and the figures may show only those specific details that are pertinent to understanding the embodiments of the present disclosure so as not to obscure the figures with details that will be readily apparent to those skilled in the art having the benefit of the description herein.
DETAILED DESCRIPTION
[0022] For the purpose of promoting an understanding of the principles of the disclosure, reference will now be made to the embodiment illustrated in the figures and specific language will be used to describe them. It will nevertheless be understood that no limitation of the scope of the disclosure is thereby intended. Such alterations and further modifications in the illustrated system, and such further applications of the principles of the disclosure as would normally occur to those skilled in the art are to be construed as being within the scope of the present disclosure.
[0023] The terms "comprises", "comprising", or any other variations thereof, are intended to cover a non-exclusive inclusion, such that a process or method that comprises a list of steps does not include only those steps but may include other steps not expressly listed or inherent to such a process or method. Similarly, one or more devices or sub-systems or elements or structures or components preceded by "comprises... a" does not, without more constraints, preclude the existence of other devices, sub-systems, elements, structures, components, additional devices, additional sub-systems, additional elements, additional structures, or additional components. Appearances of the phrase "in an embodiment", "in another embodiment" and similar language throughout this specification may, but not necessarily do, all refer to the same embodiment.
[0024] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this disclosure belongs. The system, methods, and examples provided herein are only illustrative and not intended to be limiting.
[0025] In the following specification and the claims, reference will be made to a number of terms, which shall be defined to have the following meanings. The singular forms “a”, “an”, and “the” include plural references unless the context clearly dictates otherwise.
[0026] Embodiments of the present disclosure relate to a system and a method to provide a plurality of insights regarding one or more health conditions of a patient. The system includes a processing subsystem hosted on a server and configured to execute on a network to control bidirectional communications among a plurality of modules. The processing subsystem includes a data acquisition module configured to receive a plurality of medical data of the patient from a plurality of contributing channels. The data acquisition module is also configured to categorize the plurality of medical data received into a plurality of categories including one or more patient histories, one or more medical images, and one or more prescriptions. The processing subsystem also includes an image processing module configured to detect one or more regions corresponding to one or more body parts from the one or more medical images. The image processing module is also configured to generate bounding boxes and segmentation masks for each of the one or more regions detected on the one or more medical images using a feature pyramid network technique. The image processing module is further configured to identify a first vector corresponding to one or more physical changes of the patient based on bounding boxes and segmentation masks. The processing subsystem also includes a text processing module configured to analyze the one or more patient histories and the one or more prescriptions using at least one natural language processing technique. The text processing module is also configured to identify a second vector corresponding to one or more health status of the patient based on analysis of the one or more patient histories and the one or more prescriptions. The processing subsystem further includes an insights generation module configured to generate the plurality of insights regarding the one or more health conditions detected based on the first vector and the second vector identified by the image processing module, and the text processing module respectively using a plurality of neural network techniques.
[0027] FIG. 1 is a block diagram representation of a system (10) to provide a plurality of insights regarding one or more health conditions of a patient in accordance with an embodiment of the present disclosure. The system (10) includes a processing subsystem (20) hosted on a server (30) and configured to execute on a network (40) to control bidirectional communications among a plurality of modules. In a specific embodiment, an integrated database (50) may be associated with the processing subsystem (20) to store data associated with the plurality of modules. In some embodiments, the integrated database (50) may include a structured query language database, a non-structured query language database, a columnar database and the like.
[0028] Further, in one embodiment, the server (30) may be a cloud-based server. In another embodiment, the server (30) may be a local server. In one example, the network (40) may be a private or public local area network (LAN) or wide area network (WAN), such as the Internet. In another embodiment, the network (40) may include both wired and wireless communications according to one or more standards and/or via one or more transport mediums.
[0029] Furthermore, in one example, the network (40) may include wireless communications according to one of the 802.11 or Bluetooth specification sets, or another standard or proprietary wireless communication protocol. In yet another embodiment, the network (40) may also include communications over a terrestrial cellular network, including, a GSM (global system for mobile communications), CDMA (code division multiple access), and/or EDGE (enhanced data for global evolution) network.
[0030] Additionally, the processing subsystem (20) includes a data acquisition module (60) configured to receive a plurality of medical data of the patient from a plurality of contributing channels. In one embodiment, the plurality of contributing channels may include a hospital, a clinic, and a doctor. The data acquisition module (60) is also configured to categorize the plurality of medical data received into a plurality of categories including one or more patient histories, one or more medical images, and one or more prescriptions. In some embodiments, the one or more patient histories may include, but are not limited to, clinical observations, laboratory results, medication records, electronic health records (EHRs), radiology data, genomic data, telehealth data, remote monitoring data, patient-reported data, surgical records, pathology reports, behavioral health data and the like.
[0031] Moreover, in one embodiment, the data acquisition module (60) may be configured to pre-process the plurality of medical data through a plurality of steps prior to categorizing the plurality of medical data. In such an embodiment, the plurality of steps may include filtering of noise, omission of missing values, and conversion of the plurality of medical data into a common datatype. In one embodiment, the common datatype may include a string. For example, consider a scenario in which a patient A may have sought treatment from a hospital B and a hospital C. The data acquisition module (60) may receive the plurality of medical data of the patient A from the hospital B and the hospital C. The data acquisition module (60) may further classify the plurality of medical data into the plurality of categories including patient history, medical images, and prescriptions. The data acquisition module (60) may utilize optical character recognition technique to identify textual data from the plurality of medical data. Further, the data acquisition module (60) may convert the plurality of medical data into the string except the medical images.
[0032] Further, the processing subsystem (20) includes an image processing module (70) configured to detect one or more regions corresponding to one or more body parts from the one or more medical images. In continuation with the ongoing example, consider a scenario in which the medical images may include a chest X-ray of the patient A. The image processing module (70) may detect a region of chest of the patient A in the chest X-ray. The region of the chest may include a tumor.
[0033] Furthermore, the image processing module (70) is configured to generate bounding boxes and segmentation masks for each of the one or more regions detected on the one or more medical images using a feature pyramid network technique. In one embodiments, the bounding boxes may include axis-aligned bounding box, oriented bounding box, rotated bounding box, minimum bounding rectangle, bounding ellipse, bounding sphere, minimum enclosing circle, bounding pyramid, segmented bounding box, hierarchical bounding boxes. In some embodiments, the segmentation masks may include object masks, instance masks, semantic masks, binary masks, region masks, pixel masks, object segmentation masks, image masks, class masks, binary segment masks. In continuation with the ongoing example, the image processing module (70) may generate bounding boxes and segmentation masks for the region detected on the chest X-ray.
[0034] Additionally, the image processing module (70) is configured to identify a first vector corresponding to one or more physical changes of the patient based on bounding boxes and segmentation masks. In one embodiment, the first vector may include, size, shape, texture, progression and the like. In continuation with the ongoing example, the image processing module (70) may identify the first vector corresponding to the tumor based on the bounding boxes and the segmentation masks. The first vector may include size of the tumor, shape of the tumor, and a texture of the tumor. The image processing module (70) may be able to identify progression of the tumor based on at least two chest X-rays taken over a period of time.
[0035] Also, the processing subsystem (20) includes a text processing module (80) configured to analyze the one or more patient histories and the one or more prescriptions using at least one natural language processing technique. In one embodiment, the at least one natural language processing technique may include tokenization, stop word removal, stemming, lemmatization, part of speech tagging, named entity recognition, parsing, information retrieval and the like. In continuation with the ongoing example, the text processing module (80) may tokenize the textual data present in the prescriptions and the medical history of the patient A to obtain a tokenized data. As used herein, the tokenization may be defined as breaking down the textual data into words.
[0036] Further, the text processing module (80) may remove stop words such as ‘and’, the’, ‘in’, and ‘etc’ from the tokenized data since the stop words may carry semantic meaning. Further, the text processing module (80) may reduce words present in the tokenized data into corresponding root forms by performing the stemming and lemmatization. The text processing module (80) may then identify different part of speech in the tokenized data to understand structure of various sentences present in the tokenized data. Further, the text processing module (80) may identify different entities present in the tokenized data such as a disease, medicines, treatment protocols and the like. Furthermore, the text processing module (80) may parse the tokenized data to understand syntax and semantics of the tokenized data to retrieve information from the tokenized data.
[0037] Furthermore, the text processing module (80) is configured to identify a second vector corresponding to one or more health status of the patient based on analysis of the one or more patient histories and the one or more prescriptions. In one embodiment, the second vector may include various symptoms, medication details, details of treatment and the like. In continuation with the ongoing example, the text processing module (80) may identify the second vector corresponding to the one or more health status of the patient A. The second vector may provide information such that the patient A is experiencing fatigue, reduction in blood count, the treatment details of the patient A, and the medication details of the patient A.
[0038] Furthermore, the processing subsystem (20) includes an insights generation module (90) configured to generate the plurality of insights regarding the one or more health conditions detected based on the first vector and the second vector identified by the image processing module (70), and the text processing module (80) respectively using a plurality of neural network techniques. In some embodiments, the plurality of neural network techniques may include, but not limited to, feedforward neural networks, convolutional neural networks, recurrent neural networks, long short-term memory networks, gated recurrent unit networks, autoencoders, generative adversarial networks, variational autoencoders, siamese networks, self-attention mechanisms, and the like.
[0039] Moreover, in one embodiment, the one or more health conditions detected may include a disease, one or more comorbidities and the like. In some embodiments, the plurality of insights may include, severity of the disease, progression of the disease, treatment effectiveness, medication adherence, risk assessment, complications of the disease and the like. In continuation with the ongoing example, the insights generation module (90) may generate the plurality of insights regarding the one or more health conditions of the patient A detected based on the first vector and the second vector. The one or more health conditions detected may include lung cancer. The plurality of insights may assess the severity as ‘severe’ and the risk as ‘high’ based on the first vector and the second vector. The plurality of insights may also provide information regarding the medical adherence of the patient A as ‘complying’ since the patient A is adhering to the medications prescribed.
[0040] FIG. 2 is a block diagram representation of one embodiment of the system (10) of FIG. 1 in accordance with an embodiment of the present disclosure. The system (10) of FIG. 1 includes the data acquisition module (60), the image processing module (70), the text processing module (80), and the insights generation module (90). In one embodiment, the system (10) of FIG. 1 may include the processing subsystem (20) including a visualization module (100) configured to visualize the plurality of insights through at least one of a chart, a diagram, and graph in a user interface.
[0041] Further, visualization of the plurality of insights may help the health care provider and the patient to understand the plurality of insights. In one embodiment, the user interface may be associated with a device including a phone, a laptop, a personal digital assistant and the like. In a specific embodiment, the user device may be associated with the patient, a medical practitioner, and a health care provider. In continuation with the ongoing example, the visualization module (100) may be configured to visualize progression of the one or more health conditions of the patient A and the medical adherence of the patient A through the diagram to aid the healthcare provider to understand the same.
[0042] Furthermore, in one embodiment, the processing subsystem (20) may include an encryption module (110) configured to encrypt the plurality of medical data for securing the plurality of medical data. In some embodiments, the encryption module (110) may encrypt the plurality of medical data by at least one of an encryption technique including symmetric encryption, asymmetric encryption, hash functions, hybrid encryption, end-to-end encryption, full disk encryption, homomorphic encryption, quantum encryption, post-quantum cryptography. In continuation with the ongoing example, the encryption module (110) may encrypt the plurality of medical data of the patient A to secure the plurality of medical data.
[0043] Additionally, in some embodiments, the processing subsystem (20) may include a scheduling module (120) configured to identify one or more specializations corresponding to the one or more health conditions detected. In such an embodiment, the scheduling module (120) may be configured to shortlist one or more medical practitioners corresponding to each of the one or more specializations identified. In one embodiment, the scheduling module (120) may also be configured to schedule an appointment with the one or more medical practitioners based on an input from the patient. In continuation with the ongoing example, the scheduling module (120) may be configured to identify oncology as the one or more specialization corresponding to the lung cancer of the patient A. The scheduling module (120) may further shortlist the one or more medical practitioners who are oncologists. The scheduling module (120) may further schedule the appointment with at least one of the oncologists based on the input from the patient A.
[0044] Moreover, in one embodiment, the processing subsystem (20) may include a recommendation module (130) configured to recommend one or more treatment plans for each of the one or more health conditions detected. In one embodiment, the one or more treatment plans may include dietary recommendations, lifestyle changes, workout plans and the like. In continuation with the ongoing example, the recommendation module (130) may recommend protein rich food for the patient A and along with an advisory to refrain from smoking.
[0045] Further, in one embodiment, the processing subsystem (20) may include an access control module (140) configured to authenticate the patient by receiving one or more credentials from the patient through the user interface. In such an embodiment, the access control module (140) may also be configured to query the integrated database (50) with one or more keywords provided by the patient upon authenticating the patient. In one embodiment, the access control module (140) may be configured to display the plurality of medical data and the corresponding plurality of contributing channels returned by the integrated database (50) in the user interface upon querying the integrated database (50).
[0046] Furthermore, in some embodiments, the one or more keywords may include, the plurality of categories, the plurality of contributing channels and the like. In one embodiment, the one or more credentials may include a username, a password and the like. In continuation with the ongoing example, the access control module (140) may authenticate the patient A by receiving the username and the password associated with the patient A. Upon authentication, the access control module (140) may enable the patient A to query the integrated database (50) with ‘medical images’ as the one or more keywords. In response to the query, the integrated database (50) may return the medical images associated with the patient A which were stored in the integrated database (50) by the data acquisition module (60). The access control module (140) may further display the medical images returned by the integrated database (50) in the user interface.
[0047] Moreover, in some embodiments, the processing subsystem (20) may include a notification module (150) configured to notify the patient regarding one or more modifications performed on the plurality of medical data since a previous active session of the patient. In continuation with the ongoing example. the notification module (150) may monitor the one or more modification in the plurality of medical data since the previous active session of the patient. The notification module (150) may track the previous active session of the patient A based on an authentication time provided by the access control module (140). The notification module (150) may notify the patient A regarding the one or more modifications performed on the plurality of medical data by the plurality of contributing channels.
[0048] FIG. 3 is a schematic representation of an exemplary embodiment (160) of the system (10) of FIG. 1 in accordance with an embodiment of the present disclosure. Consider a scenario in which a patient X (170) may have sought treatment from a doctor Y (180) and a hospital Z (190). The doctor Y (180) and the hospital Z (190) may have the plurality of medical data of the patient X (170). The data acquisition module (60) may receive the plurality of medical data of the patient X (170) from the doctor Y (180) as well as the hospital Z (190). The encryption module (110) may secure the plurality of medical data by encrypting the plurality of medical data. The data acquisition module (60) may further categorize the medical data into the one or more patient histories, the one or more medical images and the one or more prescriptions.
[0049] Further, the one or more medical images may include two magnetic resonance imaging (MRI) of the patient X (170) that were captured in two different months. The two MRI may include spine of the patient X (170). The image processing module (70) may detect one or more regions of the spine having misalignments from each of the two MRI. The image processing module (70) may generate the bounding boxes and the segmentation masks for each of the one or more regions present in each of the two MRI using the feature pyramid network technique. The image processing module (70) may identify the first vector corresponding to the one or more physical changes of the patient X (170) based on the bounding boxes and the segmentation masks.
[0050] Furthermore, the first vector may include the size, the shape, the texture, and the progression of the misalignments. Further, the text processing module (80) may be configured to analyze the one or more patient histories and the one or more prescriptions using at least one natural language processing technique. The text processing module (80) may identify the second vector corresponding to the one or more health status of the patient X (170) based on the analysis of the one or more patient histories and the one or more prescriptions. The second vector may include the medication details, various symptoms, details of treatment and the like. The insights generation module (90) may generate the plurality of insights regarding the one or more health conditions detected as ‘scoliosis’.
[0051] Moreover, the insights generation module (90) may generate the plurality of insights such as severity as ‘mild’, and the risk assessment as high. The visualization module (100) may visualize the plurality of insights through the graph and the chart in the user interface to provide understanding of the plurality of insights. The scheduling module (120) may identify ‘orthopedic’ as the one or more specializations corresponding to the one or more health conditions detected.
[0052] Further, the scheduling module (120) may shortlist the one or more medical practitioners who are specialized in the orthopedic and may schedule the appointment with the one or more medical practitioners based on the input provided by the patient X (170). The recommendation module (130) may recommend stretching exercises for the patient X (170) to reduce the effect of scoliosis. The access control module (140) may authenticate the patient X (170) by receiving the username and the password associated with the patient X (170). The access control module (140) may query the integrated database (50) with the one or more keywords ‘ prescriptions’. The access control module (140) may display the one or more prescriptions returned by the integrated database (50) on the user interface.
[0053] Furthermore, the notification module (150) may track the one or more modifications in the plurality of medical data from the last active session of the user X and notify the user X regarding the same. Consider another scenario in which, the hospital Z (190) may modify the medication for the patient X (170). The notification module (150) may notify the patient X (170) regarding the modification.
[0054] FIG. 4 is a block diagram of a computer or a server (30) in accordance with an embodiment of the present disclosure. The server (30) includes processor(s) (200), and memory (210) operatively coupled to the bus (220). The processor(s) (200), as used herein, includes any type of computational circuit, such as, but not limited to, a microprocessor, a microcontroller, a complex instruction set computing microprocessor, a reduced instruction set computing microprocessor, a very long instruction word microprocessor, an explicitly parallel instruction computing microprocessor, a digital signal processor, or any other type of processing circuit, or a combination thereof.
[0055] The memory (210) includes several subsystems stored in the form of executable program which instructs the processor to perform the method steps illustrated in FIG. 1. The memory (210) is substantially similar to the system (10) of FIG.1. The memory (210) has the following subsystems: the processing subsystem (20) including the data acquisition module (60), the image processing module (70), the text processing module (80), the insights generation module (90), the visualization module (100), the encryption module (110), the scheduling module (120), the recommendation module (130), the access control module (140) and the notification module (150). The plurality of modules of the processing subsystem (20) performs the functions as stated in FIG. 1 and FIG. 2. The bus (220) as used herein refers to be the internal memory channels or computer network (40) that is used to connect computer components and transfer data between them. The bus (220) includes a serial bus or a parallel bus, wherein the serial bus transmit data in bit-serial format and the parallel bus transmit data across multiple wires. The bus (220) as used herein, may include but not limited to, a system bus, an internal bus, an external bus, an expansion bus, a frontside bus, a backside bus, and the like.
[0056] The processing subsystem (20) includes a data acquisition module (60) configured to receive a plurality of medical data of the patient from a plurality of contributing channels. The data acquisition module (60) is also configured to categorize the plurality of medical data received into a plurality of categories including one or more patient histories, one or more medical images, and one or more prescriptions. The processing subsystem (20) also includes an image processing module (70) configured to detect one or more regions corresponding to one or more body parts from the one or more medical images. The image processing module (70) is also configured to generate bounding boxes and segmentation masks for each of the one or more regions detected on the one or more medical images using a feature pyramid network technique. The image processing module (70) is further configured to identify a first vector corresponding to one or more physical changes of the patient based on bounding boxes and segmentation masks. The processing subsystem (20) also includes a text processing module (80) configured to analyze the one or more patient histories and the one or more prescriptions using at least one natural language processing technique. The text processing module (80) is also configured to identify a second vector corresponding to one or more health status of the patient based on analysis of the one or more patient histories and the one or more prescriptions. The processing subsystem (20) further includes an insights generation module (90) configured to generate the plurality of insights regarding the one or more health conditions detected based on the first vector and the second vector identified by the image processing module (70), and the text processing module (80) respectively using a plurality of neural network techniques.
[0057] The processing subsystem (20) also includes a visualization module (100) configured to visualize the plurality of insights through at least one of a chart, diagram, and graph in a user interface.
[0058] The processing subsystem (20) also includes an encryption module (110) configured to encrypt the plurality of medical data for securing the plurality of medical data.
[0059] The processing subsystem (20) further includes a scheduling module (120) configured to identify one or more specializations corresponding to the one or more health conditions detected. The scheduling module (120) is also configured to shortlist one or more medical practitioners corresponding to each of the one or more specializations identified. The scheduling module (120) is further configured to schedule an appointment with the one or more medical practitioners based on an input from a patient.
[0060] The processing subsystem (20) also includes a recommendation module (130) configured to recommend one or more treatment plans for each of the one or more health conditions detected.
[0061] The processing subsystem (20) also includes an access control module (140) configured to authenticate a patient by receiving one or more credentials from the patient through a user interface. The access control module (140) is also configured to query an integrated database (50) with one or more keywords provided by the patient upon authenticating the patient. The access control module (140) is further configured to display the plurality of medical data and the corresponding plurality of contributing channels returned by the integrated database (50) in the user interface upon querying the integrated database (50).
[0062] The processing subsystem (20) also includes a notification module (150) configured to notify a patient regarding one or more modifications performed on the plurality of medical data since a previous active session of the patient.
[0063] Computer memory elements may include any suitable memory device(s) for storing data and executable program, such as read only memory, random access memory, erasable programmable read only memory, electrically erasable programmable read only memory, hard drive, removable media drive for handling memory cards and the like. Embodiments of the present subject matter may be implemented in conjunction with program modules, including functions, procedures, data structures, and application programs, for performing tasks, or defining abstract data types or low-level hardware contexts. Executable program stored on any of the above-mentioned storage media may be executable by the processor(s) (200).
[0064] FIG. 5 is a flow chart representing the steps involved in a method (300) to provide a plurality of insights regarding one or more health conditions of a patient in accordance with an embodiment of the present disclosure. The method (300) includes receiving a plurality of medical data of the patient from a plurality of contributing channels in step 310. In one embodiment, receiving a plurality of medical data of the patient from a plurality of contributing channels includes receiving a plurality of medical data of the patient from a plurality of contributing channels by a data acquisition module. In one embodiment, the plurality of contributing channels may include a hospital, a clinic, and a doctor.
[0065] The method (300) also includes categorizing the plurality of medical data received into a plurality of categories including one or more patient histories, one or more medical images, and one or more prescriptions in step 320. In one embodiment, categorizing the plurality of medical data received into a plurality of categories including one or more patient histories, one or more medical images, and one or more prescriptions includes categorizing the plurality of medical data received into a plurality of categories including one or more patient histories, one or more medical images, and one or more prescriptions by the data acquisition module. In some embodiments, the one or more patient histories may include, but are not limited to, clinical observations, laboratory results, medication records, electronic health records (EHRs), radiology data, genomic data, telehealth data, remote monitoring data, patient-reported data, surgical records, pathology reports, behavioral health data and the like. In one embodiment, the data acquisition module may be configured to pre-process the plurality of medical data through a plurality of steps prior to categorizing the plurality of medical data. In such an embodiment, the plurality of steps may include filtering of noise, omission of missing values, and conversion of the plurality of medical data into a common datatype. In one embodiment, the common datatype may include a string.
[0066] The method (300) also includes detecting one or more regions corresponding to one or more body parts from the one or more medical images in step 330. In one embodiment, detecting one or more regions corresponding to one or more body parts from the one or more medical images includes detecting one or more regions corresponding to one or more body parts from the one or more medical images by an image processing module.
[0067] The method (300) also includes generating bounding boxes and segmentation masks for each of the one or more regions detected on the one or more medical images using a feature pyramid network technique in step 340. In one embodiment, generating bounding boxes and segmentation masks for each of the one or more regions detected on the one or more medical images using a feature pyramid network technique includes generating bounding boxes and segmentation masks for each of the one or more regions detected on the one or more medical images using a feature pyramid network technique by the image processing module. In one embodiments, the bounding boxes may include axis-aligned bounding box, oriented bounding box, rotated bounding box, minimum bounding rectangle, bounding ellipse, bounding sphere, minimum enclosing circle, bounding pyramid, segmented bounding box, hierarchical bounding boxes. In some embodiments, the segmentation masks may include object masks, instance masks, semantic masks, binary masks, region masks, pixel masks, object segmentation masks, image masks, class masks, binary segment masks.
[0068] The method (300) also includes identifying a first vector corresponding to one or more physical changes of the patient based on bounding boxes and segmentation masks in step 350. In one embodiment, identifying a first vector corresponding to one or more physical changes of the patient based on bounding boxes and segmentation masks includes identifying a first vector corresponding to one or more physical changes of the patient based on bounding boxes and segmentation masks by the image processing module. In one embodiment, the first vector may include, size, shape, texture, progression and the like.
[0069] The method (300) also includes analyzing the one or more patient histories and the one or more prescriptions using at least one natural language processing technique in step 360. In one embodiment, analyzing the one or more patient histories and the one or more prescriptions using at least one natural language processing technique includes analyzing the one or more patient histories and the one or more prescriptions using at least one natural language processing technique by a text processing module. In one embodiment, the at least one natural language processing technique may include tokenization, stop word removal, stemming, lemmatization, part of speech tagging, named entity recognition, parsing, information retrieval and the like.
[0070] The method also includes identifying a second vector corresponding to one or more health status of the patient based on analysis of the one or more patient histories and the one or more prescriptions in step 370. In one embodiment, identifying a second vector corresponding to one or more health status of the patient based on analysis of the one or more patient histories and the one or more prescriptions includes identifying a second vector corresponding to one or more health status of the patient based on analysis of the one or more patient histories and the one or more prescriptions by the text processing module. In one embodiment, the second vector may include various symptoms, medication details, details of treatment and the like.
[0071] The method further includes generating the plurality of insights regarding the one or more health conditions detected based on the first vector and the second vector identified by the image processing module, and the text processing module respectively using a plurality of neural network techniques in step 380. In one embodiment, generating the plurality of insights regarding the one or more health conditions detected based on the first vector and the second vector identified by the image processing module, and the text processing module respectively using a plurality of neural network techniques includes generating the plurality of insights regarding the one or more health conditions detected based on the first vector and the second vector identified by the image processing module, and the text processing module respectively using a plurality of neural network techniques by an insights generation module. In some embodiments, the plurality of neural network techniques may include, but not limited to, feedforward neural networks, convolutional neural networks, recurrent neural networks, long short-term memory networks, gated recurrent unit networks, autoencoders, generative adversarial networks, variational autoencoders, siamese networks, self-attention mechanisms, and the like. In one embodiment, the one or more health conditions detected may include a disease, one or more comorbidities and the like. In some embodiments, the plurality of insights may include, severity of the disease, progression of the disease, treatment effectiveness, medication adherence, risk assessment, complications of the disease and the like.
[0072] Various embodiments of the system and method to provide the plurality of insights regarding one or more medical conditions of the patient above enable various advantages. The data acquisition module is capable of receiving the plurality of medical data of the patient from the plurality of contributing channels and storing the plurality of the medical data in the integrated database in the common format, thereby avoiding the fragmentation of the plurality of medical data. By avoiding the fragmentation of the plurality of medical data, the system supports the healthcare providers to search, retrieve and modify the plurality of medical data easily, thereby avoiding repeated diagnostic tests along with enhancing safety of the patient.
[0073] Further, the encryption module is capable of securing the plurality of medical data by encrypting the same, thereby eliminating the privacy concerns. Combination of the image processing module, the text processing module, and the insights generation module are capable of generating the plurality of insights regarding the one or more health conditions of the patient. The plurality of insights help the health care providers to assess the conditions of the patient, thereby reducing the potential treatment errors. The access control module provides a way for the patient to access the plurality of medical data by authenticating the patient, thereby helping the patient to make proactive healthcare decisions.
[0074] Furthermore, the recommendation module is capable of recommending the one or more treatment plans for the patient, thereby supporting the recovery of the patient. The notification module is capable of notifying the patient regarding the one or more modifications in the patient, thereby enabling the patient to take informed decisions based on the latest data. The scheduling module is capable of shortlisting the one or more medical practitioners who have relevant specializations corresponding to the one or more health conditions of the patient, thereby helping the patient to seek the optimal care. Also the scheduling module is capable of scheduling the appointment of the patient with the one or more medical practitioners, thereby saving time and effort of the patient. The visualization module is capable of visualizing the plurality of insights for rendering a quick understanding of the same to the health care providers as well as the patient.
[0075] It will be understood by those skilled in the art that the foregoing general description and the following detailed description are exemplary and explanatory of the disclosure and are not intended to be restrictive thereof. While specific language has been used to describe the disclosure, any limitations arising on account of the same are not intended.
[0076] 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, the 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 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.

,CLAIMS:1. A system (10) to provide a plurality of insights regarding one or more health conditions of a patient comprising:
characterized in that:
a processing subsystem (20) hosted on a server (30) and configured to execute on a network (40) to control bidirectional communications among a plurality of modules comprising:
a data acquisition module (60) configured to:
receive a plurality of medical data of the patient from a plurality of contributing channels;
categorize the plurality of medical data received into a plurality of categories comprising one or more patient histories, one or more medical images, and one or more prescriptions;
an image processing module (70) configured to:
detect one or more regions corresponding to one or more body parts from the one or more medical images;
generate bounding boxes and segmentation masks for each of the one or more regions detected on the one or more medical images using a feature pyramid network technique;
identify a first vector corresponding to one or more physical changes of the patient based on bounding boxes and segmentation masks;
a text processing module (80) configured to:
analyze the one or more patient histories and the one or more prescriptions using at least one natural language processing technique;
identify a second vector corresponding to one or more health status of the patient based on analysis of the one or more patient histories and the one or more prescriptions; and
an insights generation module (90) configured to generate the plurality of insights regarding the one or more health conditions detected based on the first vector and the second vector identified by the the image processing module (70), and the text processing module (80) respectively using a plurality of neural network techniques.
2. The system (10) as claimed in claim 1, wherein the plurality of contributing channels comprises a hospital, a clinic, and a doctor.
3. The system (10) as claimed in claim 1, wherein the processing subsystem (20) comprises a visualization module (100) configured to visualize the plurality of insights through at least one of a chart, diagram, and graph in a user interface.
4. The system (10) as claimed in claim1, wherein the data acquisition module (60) is configured to pre-process the plurality of medical data through a plurality of steps prior to categorizing the plurality of medical data, wherein the plurality of steps comprising filtering of noise, omission of missing values, and conversion of the plurality of medical data into a common datatype.
5. The system (10) as claimed in claim 1, wherein the processing subsystem (20) comprises an encryption module (110) configured to encrypt the plurality of medical data for securing the plurality of medical data.
6. The system (10) as claimed in claim1, wherein the processing subsystem (20) comprises a scheduling module (120) configured to :
identify one or more specializations corresponding to the one or more health conditions detected;
shortlist one or more medical practitioners corresponding to each of the one or more specializations identified; and
schedule an appointment with the one or more medical practitioners based on an input from the patient.
7. The system (10) as claimed in claim1, wherein the processing subsystem (20) comprises a recommendation module (130) configured to recommend one or more treatment plans for each of the one or more health conditions detected.
8. The system (10) as claimed in claim1, wherein the processing subsystem (20) comprises an access control module (140) configured to:
authenticate the patient by receiving one or more credentials from the patient through a user interface;
query an integrated database (50) with one or more keywords provided by the patient upon authenticating the patient; and
display the plurality of medical data and the corresponding plurality of contributing channels returned by the integrated database (50) in the user interface upon querying the integrated database (50).
9. The system (10) as claimed in claim 1, wherein the processing subsystem (20) comprises a notification module (150) configured to notify the patient regarding one or more modifications performed on the plurality of medical data since a previous active session of the patient.
10. A method (300) comprising:
characterized in that:
receiving, by a data acquisition module, a plurality of medical data of the patient from a plurality of contributing channels; (310)
categorizing, by the data acquisition module, the plurality of medical data received into a plurality of categories comprising one or more patient histories, one or more medical images, and one or more prescriptions; (320)
detecting, by an image processing module, one or more regions corresponding to one or more body parts from the one or more medical images; (330)
generating, by the image processing module, bounding boxes and segmentation masks for each of the one or more regions detected on the one or more medical images using a feature pyramid network technique; (340)
identifying, by the image processing module, a first vector corresponding to one or more physical changes of the patient based on bounding boxes and segmentation masks; (350)
analyzing, by a text processing module, the one or more patient histories and the one or more prescriptions using at least one natural language processing technique; (360)
identifying, by the text processing module, a second vector corresponding to one or more health status of the patient based on analysis of the one or more patient histories and the one or more prescriptions; (370) and
generating, by an insights generation module, the plurality of insights regarding the one or more health conditions detected based on the first vector and the second vector identified by the image processing module, and the text processing module respectively using a plurality of neural network techniques. (380)
Dated this 25th day of October 2023
Signature

Jinsu Abraham
Patent Agent (IN/PA-3267)
Agent for the Applicant