INTEGRATED MACHINE LEARNING MODELS FOR ENHANCED SECURITY OF HEALTHCARE DATA

Abstract

ABSTRACT “INTEGRATED MACHINE LEARNING MODELS FOR ENHANCED SECURITY OF HEALTHCARE DATA” The present invention provides integrated machine learning models for enhanced security of healthcare data that enhances the patient’s data’s security by analyzing the application user’s movement and scrolling pattern and classifies it as suspicious or unsuspicious using a Convolutional Neural Network and Random Forest Classification approach. If the outcome indicates suspicious behavior, the user’s profile will be locked and a warning notice will be sent to higher authorities right away. The model also utilizes Time Series Analysis to compute the scope of the clinical equipment used by the patient, and if it is altered within that scope, it will be allowed to change the value; otherwise, it will require authentication from two or more senior doctors to verify there is no harm. The key advantage of utilizing the model is the added high-security function, which protects data better than any other system now available. Figure 1

Specification

Description:TECHNICAL FIELD
[0001] The present invention relates to the field of machine learning models, and more particularly, the present invention relates to the integrated machine learning models for enhanced security of healthcare data.
BACKGROUND ART
[0002] The following discussion of the background of the invention is intended to facilitate an understanding of the present invention. However, it should be appreciated that the discussion is not an acknowledgment or admission that any of the material referred to was published, known, or part of the common general knowledge in any jurisdiction as of the application's priority date. The details provided herein the background if belongs to any publication is taken only as a reference for describing the problems, in general terminologies or principles or both of science and technology in the associated prior art.
[0003] Problem being solved:
- Utilizing the model is the added high-security function, which protects data better than any other system now available.
- Reduce human labor to almost 0% in terms of monitoring security cameras all day, saving organizations money by allowing the algorithm to handle the heavy lifting.
[0004] Problem in the existing product:
- The existing models lack security functions and there was no model or system analyzes the suspicious activity.
- Earlier lacks efficiency and scalability as there was no continuous monitoring in the security part and also they did not provide authentications from doctor
[0005] Following are some of the existing solutions:
- Machine Learning Algorithms: It can be used to analyze the ambient of the hospitals to analyze patient's mood.
- Security Enhancement in SVM: Using solely cloud resources, a cloud framework is used to analyze digital records.
[0006] In light of the foregoing, there is a need for Integrated machine learning models for enhanced security of healthcare data that overcomes problems prevalent in the prior art associated with the traditionally available method or system, of the above-mentioned inventions that can be used with the presented disclosed technique with or without modification.
[0007] All publications herein are incorporated by reference to the same extent as if each individual publication or patent application were specifically and individually indicated to be incorporated by reference. Where a definition or use of a term in an incorporated reference is inconsistent or contrary to the definition of that term provided herein, the definition of that term provided herein applies, and the definition of that term in the reference does not apply.
OBJECTS OF THE INVENTION
[0008] The principal object of the present invention is to overcome the disadvantages of the prior art by providing integrated machine learning models for enhanced security of healthcare data.
[0009] Another object of the present invention is to provide integrated machine learning models for enhanced security of healthcare data that adds high-security feature that provides a higher level of protection of the data than any of the current systems.
[0010] Another object of the present invention is to provide integrated machine learning models for enhanced security of healthcare data that can reduce human work to almost 0% in observing the security cameras all day long and hence will save the organizations' money, by letting the algorithm do the hard work for them.
[0011] Another object of the present invention is to provide integrated machine learning models for enhanced security of healthcare data that continues improving in accuracy and efficiency which allows them to settle on better decisions, with time ML algorithms gain insight.
[0012] Another object of the present invention is to provide integrated machine learning models for enhanced security of healthcare data that learns to make more accurate predictions faster.
[0013] The foregoing and other objects of the present invention will become readily apparent upon further review of the following detailed description of the embodiments as illustrated in the accompanying drawings.
SUMMARY OF THE INVENTION
[0014] The present invention relates to integrated machine learning models for enhanced security of healthcare data.
[0015] The model shown in Fig. 1 lets the authority examine the motion of the logged-in user, scrolling pattern, and the time that the logged-in person spends within side the affected person's report. If the person spends much less than a minute, he/she may be taking a photograph of the report that's forbidden and assume the person spends extra than 10 min he/she may be memorizing the records that are once more forbidden, for he may use those sensitive records and the patient will need to suffer.
[0016] An incorporated front digicam jogging with the software will be of added benefit, it will be able to tune the motion of the person and draw conclusions with the aid of schooling an ML version with it. It is advised to keep information within side the cloud with the aid of using offerings like AWS, Google Clouds, and so forth., so that even within side the case of any ransomware assault the touchy records concerning the affected person aren't tempered/stolen.
[0017] Considering the significance and sensitivity of the person's clinical gadgets such as pacemaker, urine output tracking tool, multisensory pedometer, and so forth wherein surprising increase/decrease of the scope of the tool may be dangerous for the affected person, for this it is proposed to have an ML version skilled within side the unique tool's dataset that can calculate the scope of the tool wherein there's no damage to the affected person and while accelerated past that scope would require the authentication of Doctor(s).
[0018] Here it is assumed that the devices can only be controlled by the software used by the particular hospital/clinic.
[0019] CNN: To detect objects, recognize faces, and so on, CNN (Convolutional Neural
[0020] Network) uses pictorial recognition and sorting.
[0021] They're formed up of neurons with learnable weights and biases. Each neuron takes a huge number of inputs and computes a weighted sum, which it then passes through an activation function before producing an output.
[0022] CNNs are naturally used to classify images, cluster them based on resemblance, and eventually analyze items.
[0023] Many CNN-based algorithms can classify faces, street signs, animals, and other objects.
[0024] RF Classifier: Many decision trees are integrated to create an RF classifier or Random Forest Classifier. The RF classifier's goal is to combine many decision trees into more relevant and accurate results. It determines the mean of each decision tree and allocates the mean value to the forecasted variable for regression. The RF uses a widely held voting method for classifying instances. If three trees predicted yes and two trees predicted no, the predicted variable will be set to yes. The root or parent node of the tree is determined using entropy and information gain.
[0025] Time Series Analysis: A Time Series Analysis is a technique for examining a collection of data points over a period of time. Instead of randomly recording data points, time-series monitors record datasets at regular intervals over a preset period of time. This type of research, on the other hand, entails more than simply collecting data over time. Time-series data is distinguished from other types of data by its ability to represent how variables change over time. To put it another way, time is a crucial element since it indicates how data evolves through time as well as the effects.
[0026] While the invention has been described and shown with reference to the preferred embodiment, it will be apparent that variations might be possible that would fall within the scope of the present invention.
BRIEF DESCRIPTION OF DRAWINGS
[0027] So that the manner in which the above-recited features of the present invention can be understood in detail, a more particular description of the invention, briefly summarized above, may have been referred by embodiments, some of which are illustrated in the appended drawings. It is to be noted, however, that the appended drawings illustrate only typical embodiments of this invention and are therefore not to be considered limiting of its scope, for the invention may admit to other equally effective embodiments.
[0028] These and other features, benefits, and advantages of the present invention will become apparent by reference to the following text figure, with like reference numbers referring to like structures across the views, wherein:
[0029] Figure 1: Flow of application (including model).
DETAILED DESCRIPTION OF THE INVENTION
[0030] While the present invention is described herein by way of example using embodiments and illustrative drawings, those skilled in the art will recognize that the invention is not limited to the embodiments of drawing or drawings described and are not intended to represent the scale of the various components. Further, some components that may form a part of the invention may not be illustrated in certain figures, for ease of illustration, and such omissions do not limit the embodiments outlined in any way. It should be understood that the drawings and the detailed description thereto are not intended to limit the invention to the particular form disclosed, but on the contrary, the invention is to cover all modifications, equivalents, and alternatives falling within the scope of the present invention as defined by the appended claim.
[0031] As used throughout this description, the word "may" is used in a permissive sense (i.e. meaning having the potential to), rather than the mandatory sense, (i.e. meaning must). Further, the words "a" or "an" mean "at least one" and the word "plurality" means "one or more" unless otherwise mentioned. Furthermore, the terminology and phraseology used herein are solely used for descriptive purposes and should not be construed as limiting in scope. Language such as "including," "comprising," "having," "containing," or "involving," and variations thereof, is intended to be broad and encompass the subject matter listed thereafter, equivalents, and additional subject matter not recited, and is not intended to exclude other additives, components, integers, or steps. Likewise, the term "comprising" is considered synonymous with the terms "including" or "containing" for applicable legal purposes. Any discussion of documents, acts, materials, devices, articles, and the like are included in the specification solely for the purpose of providing a context for the present invention. It is not suggested or represented that any or all these matters form part of the prior art base or were common general knowledge in the field relevant to the present invention.
[0032] In this disclosure, whenever a composition or an element or a group of elements is preceded with the transitional phrase "comprising", it is understood that we also contemplate the same composition, element, or group of elements with transitional phrases "consisting of", "consisting", "selected from the group of consisting of, "including", or "is" preceding the recitation of the composition, element or group of elements and vice versa.
[0033] The present invention is described hereinafter by various embodiments with reference to the accompanying drawing, wherein reference numerals used in the accompanying drawing correspond to the like elements throughout the description. This invention may, however, be embodied in many different forms and should not be construed as limited to the embodiment set forth herein. Rather, the embodiment is provided so that this disclosure will be thorough and complete and will fully convey the scope of the invention to those skilled in the art. In the following detailed description, numeric values and ranges are provided for various aspects of the implementations described. These values and ranges are to be treated as examples only and are not intended to limit the scope of the claims. In addition, several materials are identified as suitable for various facets of the implementations. These materials are to be treated as exemplary and are not intended to limit the scope of the invention.
[0034] The present invention relates to integrated machine learning models for enhanced security of healthcare data.
[0035] The model shown in Fig. 1 lets the authority examine the motion of the logged-in user, scrolling pattern, and the time that the logged-in person spends within side the affected person's report. If the person spends much less than a minute, he/she may be taking a photograph of the report that's forbidden and assume the person spends extra than 10 min he/she may be memorizing the records that are once more forbidden, for he may use those sensitive records and the patient will need to suffer.
[0036] An incorporated front digicam jogging with the software will be of added benefit, it will be able to tune the motion of the person and draw conclusions with the aid of schooling an ML version with it. It is advised to keep information within side the cloud with the aid of using offerings like AWS, Google Clouds, and so forth., so that even within side the case of any ransomware assault the touchy records concerning the affected person aren't tempered/stolen.
[0037] Considering the significance and sensitivity of the person's clinical gadgets such as pacemaker, urine output tracking tool, multisensory pedometer, and so forth wherein surprising increase/decrease of the scope of the tool may be dangerous for the affected person, for this it is proposed to have an ML version skilled within side the unique tool's dataset that can calculate the scope of the tool wherein there's no damage to the affected person and while accelerated past that scope would require the authentication of Doctor(s).
[0038] Here it is assumed that the devices can only be controlled by the software used by the particular hospital/clinic.
[0039] CNN: To detect objects, recognize faces, and so on, CNN (Convolutional Neural
[0040] Network) uses pictorial recognition and sorting.
[0041] They're formed up of neurons with learnable weights and biases. Each neuron takes a huge number of inputs and computes a weighted sum, which it then passes through an activation function before producing an output.
[0042] CNNs are naturally used to classify images, cluster them based on resemblance, and eventually analyze items.
[0043] Many CNN-based algorithms can classify faces, street signs, animals, and other objects.
[0044] RF Classifier: Many decision trees are integrated to create an RF classifier or Random Forest Classifier. The RF classifier's goal is to combine many decision trees into more relevant and accurate results. It determines the mean of each decision tree and allocates the mean value to the forecasted variable for regression. The RF uses a widely held voting method for classifying instances. If three trees predicted yes and two trees predicted no, the predicted variable will be set to yes. The root or parent node of the tree is determined using entropy and information gain.
[0045] Time Series Analysis: A Time Series Analysis is a technique for examining a collection of data points over a period of time. Instead of randomly recording data points, time-series monitors record datasets at regular intervals over a preset period of time. This type of research, on the other hand, entails more than simply collecting data over time. Time-series data is distinguished from other types of data by its ability to represent how variables change over time. To put it another way, time is a crucial element since it indicates how data evolves through time as well as the effects.
[0046] Unique features of our solution include the following:
- The main benefit of using the model is the added high-security feature that provides a higher level of protection of the data than any of the current systems.
- It can reduce human work to almost 0% in observing the security cameras all day long and hence will save the organizations' money, by letting the algorithm do the hard work for them.
- With time ML algorithms gain insight, they continue improving in accuracy and efficiency which allows them to settle on better decisions.
- In our case of CNN, Random Forest, and Time Series Analysis, as the amount of data grows, the algorithms learn to make more accurate predictions faster.
[0047] Outcomes of our proposed model:
[0048] It is proposed to have multiple Machine Learning Algorithms in the application, for monitoring the user's movement, expression, object detection along with understanding the pattern of scrolling in the report that the user does and data storage in the cloud rather than storing it locally.
[0049] The CNN network is utilized to draw-out the high-level prominent information from the video frames for this purpose.
[0050] Random Forest to deduce information from the pattern of scrolling and Time Series Analysis for predicting the scope of the clinical device that is used by a patient.
[0051] Applications of the Invention:
- Mood Analysis Of Patients: Helps in avoidance of mental and physical sickness, illness, and infection.
- Better Safety and Efficiency: Analyzes user's movement and scrolling pattern and classifies it as suspicious or unsuspicious.
- Spatiotemporal Elements: Spatiotemporal elements, such as human action detection, are critical in recognizing distinct behaviors in surveillance video data.
[0052] Various modifications to these embodiments are apparent to those skilled in the art from the description and the accompanying drawings. The principles associated with the various embodiments described herein may be applied to other embodiments. Therefore, the description is not intended to be limited to the 5 embodiments shown along with the accompanying drawings but is to be providing the broadest scope consistent with the principles and the novel and inventive features disclosed or suggested herein. Accordingly, the invention is anticipated to hold on to all other such alternatives, modifications, and variations that fall within the scope of the present invention and appended claims.
, Claims:CLAIMS
We Claim:
1) A machine learning-based security system for healthcare data, the system comprising:
- a user behavior analysis module configured to monitor user actions within a patient's record, including scrolling patterns, time spent on individual sections, and motion analysis;
- a convolutional neural network (CNN) module configured to analyze video frames from an integrated front camera to detect user motion and facial expressions;
- a random forest classifier module configured to analyze scrolling patterns and classify user actions as potentially suspicious or non-suspicious based on behavioral patterns;
- a time series analysis module configured to monitor the operational scope of clinical devices connected to the system, detecting deviations that may require medical staff intervention;
- a cloud-based data storage and management system for securely storing patient data and mitigating risks associated with ransom ware attacks;
- wherein the system enhances security by analyzing user activity and device data to prevent unauthorized access or misuse of sensitive healthcare information.
2) The system as claimed in claim 1, wherein the user behavior analysis module flags user actions as suspicious if the time spent in a patient's record is below a pre-defined minimum threshold, indicating potential unauthorized data capture.
3) The system as claimed in claim 1, the system further comprising an alert mechanism that triggers a notification to the healthcare authority if user behavior is classified as suspicious based on predefined time or scrolling thresholds.
4) The system as claimed in claim 1, wherein the CNN module performs real-time facial recognition and movement tracking to detect anomalies in user behavior, enhancing monitoring accuracy without requiring manual observation.

Documents