AU2021102832A4 - System & method for automatic health prediction using fuzzy based machine learning - Google Patents

Abstract

SYSTEM & METHOD FOR AUTOMATIC HEALTH PREDICTION USING FUZZY BASED MACHINE LEARNING ABSTRACT The present invention is related to a system & method for automatic health prediction using fuzzy based machine learning. The objective of present invention is to solve the anomalies presented in the prior art techniques related to health prediction using fuzzy based machine learning. 26 DRAWINGS Health Parameters Doctor Panel Prediction of Health AA FIGURE 1 27

Description

DRAWINGS

Health Parameters

Doctor Panel Prediction of Health

AA

FIGURE 1

SYSTEM & METHOD FOR AUTOMATIC HEALTH PREDICTION USING FUZZY BASED MACHINE LEARNING FIELD OF INVENTION

[001]. The present invention related to field of human health prediction

technology field, in particular to a based on genetic algorithm and

fuzzy logic based prediction algorithm of the indicators of the health

of the human body.

[002]. Particularly, some aspects of the invention relate to automatic

health prediction using fuzzy based machine learning.

[003]. More particularly, the present invention is related to a system &

method for automatic health prediction using fuzzy based machine

learning.

BACKGROUND & PRIOR ART

[004]. Medical field data has created interest among the researchers.

Development of system supporting decision making in prediction

of disease using the dataset of the medical field using the technique

of data mining. A novel method is proposed in this invention based

on knowledge system for prediction of diseases using techniques of

removal of noise, clustering and prediction. Fuzzy rules are

generated using classification trees and regression trees that are

used in the system based on the knowledge system. Testing of the

proposed method is done on various medical dataset of public.

Remarkable improvement is obtained by the proposed method for

prediction of disease in the datasets of Cleveland, pima Indian

diabetes etc. Combining the rule based fuzzy with noise removal

CART along with the clustering techniques is effective in

prediction of disease from dataset of real world. This system based

on knowledge assist medical practitioners in the clinical analytical

method in healthcare practice.

[005]. Some of the prior work is listed herewith:

[006]. CN110097973A Human body health index predicting

algorithm based on genetic algorithm and BP neural network The

invention discloses a human body health index predicting algorithm

based on a genetic algorithm and a BP neural network. The

algorithm comprises the following steps of (1), acquiring sign data

and performing genetic coding for forming initial population, and

successively calculating individual adaptability, selecting operator,

crossover operator and variation operator of the initial population;

(2), setting a highest heredity generation number I of a fusion layer

to 100, and inputting the population after respective calculation of

the individual adaptability, selecting operator, crossover operator and

variation operator into the fusion layer respectively; and (3),

inputting the population with the fusion layer which satisfies an

iteration requirement into a BP neural network, and realizing human

body health index predicting through training and learning of the BP

neural network. According to the predicting algorithm, the acquired

initial data are processed by means of the genetic algorithm, an

optimal solution of the data can be realized; the optimal solution is

input into the BP neural network for regularizing the data which are

input into the BP neural network, improving weight precision, training efficiency, network performance and network approaching capability in the BP neural network.

[007]. US20190019582A1 SYSTEMS AND METHODS FOR

PREDICTING MULTIPLE HEALTH CARE OUTCOMES Systems

and methods for predicting multiple health care outcomes are

provided. In one embodiment, a method includes receiving clinical

data relating to a patient, calculating, with a multi-tasking deep

neural network model, a plurality of health outcomes for the patient

based on the received clinical data, and displaying one or more of the

plurality of health outcomes. In this way, the richness of health care

data may be leveraged to predict multiple health care outcomes with

a single predictive model.

[008]. AU2021100303A4 HETEROGENEOUS RECURRENT

CONVOLUTION NEURAL NETWORK FORRISK PREDICTION IN EHR DATASET HETEROGENEOUS RECURRENT CONVOLUTION NEURAL NETWORK FOR RISK PREDICTION

IN EHR DATASET Abstract: In recent years, the medical field is

attracted by the Electronic Health Record (EHR) in predicting

diseases. EHR is beneficial for both the providers and the patients.

The utilization of EHR improves the treatment of patients with

proper care through accessing patient health records, practically low

in cost, high participation of patients, and transparency. Electronic

Health Record (EHR) installation in medical practice provides

sufficient patient care and the available patient's data is accurate in

EHR aids diagnosis and treatment. This technology reduces the risk

of medical malpractice by providing a clinical alert to physicians.

Heterogeneous Recurrent Convolutional Neural Networks (HRCNN)

enables the connection among various heterogeneous medical

incidents for Convolutional Neural Networks (CNN) model. The

proposed model is effective in determining the patient's complete

health details and many hospitals are looking forward to

implementing Electronic Health records. Automatic prediction independent of human supervision is the main advantage of the CNN model. CNN generates a fixed output by acquiring fixed input. The novel deep learning scheme is developed through the association of

Heterogeneous Recurrent Convolutional Neural Networks (HRCNN)

with Electronic Health Record (EHR) to predict the risk factors of

comorbid diseases. The proposed invention is intended in developing

a learning infrastructure that can link the sparse convolutional layer

and local pooling of heterogeneous attributes and hence, it can

represent the relationships among various heterogeneous attributes.

The proposed model is intended in predicting the progression of

patient conditions. Heterogeneous Recurrent Convolutional Neural

Networks (HRCNN) accomplishes better performance on risk

predictions

[009]. US20200074573A1 SYSTEM AND METHOD FOR

PROVIDING A PATIENT-SPECIFIC PREDICTION MODEL IN A USER APPLICATION FOR EFFECTIVENESS

DETERMINATIONS in some embodiments, a patient dataset

including digital medical images and other patient data may be

obtained. The other patient data may include specific patient health

data associated with a patient and historical patient data derived from

a population related to the patient. The historical patient data may

indicate medical inventions provided to patients of the related

population, health effects of the medical interventions, and costs of

the medical interventions. In some embodiments, a neural network

specific to the patient may be configured for a user application using

at least part of the patient dataset. As an example, the user

application may include neural network. Based on the specific

patient health data, health effects and intervention costs related to

individual interventions for the patient may be predict via the neural

network of the user application. The net health benefits for the

individual interventions may be provided via the user interface based

on the predicted health effects and intervention costs.

[0010]. W02020102435AI PREDICTION OF FUTURE ADVERSE

HEALTH EVENTS USING NEURAL NETWORKS BY PRE PROCESSING INPUT SEQUENCES TO INCLUDE PRESENCE

FEATURES Methods, systems, and apparatus, including

computer programs encoded on computer storage media, for

predicting future adverse health events using neural networks. One

of the methods includes receiving electronic health record data for a

patient; generating, from the electronic health record data, an input

sequence comprising a respective feature representation at each of a

plurality of time window time steps, comprising, for each time

window time step: determining, for each of the possible numerical

features, whether the numerical feature occurred during the time

window; and generating, for each of the possible numerical features,

one or more presence features that identify whether the numerical

feature occurred during the time window; and processing the input

sequence using a neural network to generate a neural network output

that characterizes a predicted likelihood that an adverse health event

will occur to the patient.

[0011]. US10770180B1 Processing clinical notes using recurrent

neural networks Methods, systems, and apparatus, including

computer programs encoded on computer storage media, for

predicting future patient health using neural networks. One of the

methods includes receiving electronic health record data for a

patient; generating a respective observation embedding for each of

the observations, comprising, for each clinical note: processing the

sequence of tokens in the clinical note using a clinical note

embedding LSTM to generate a respective token embedding for each

of the tokens; and generating the observation embedding for the

clinical note from the token embedding's; generating an embedded

representation, comprising, for each time window: combining the

observation embedding's of observations occurring during the time

window to generate a patient record embedding; and processing the

embedded representation of the electronic health record data using a

prediction recurrent neural network to generate a neural network

output that characterizes a future health status of the patient.

[0012]. US20210125721A1 PROCESSING CLINICAL NOTES

USING RECURRENT NEURAL NETWORKS Methods, systems,

and apparatus, including computer programs encoded on computer

storage media, for predicting future patient health using neural

networks. One of the methods includes receiving electronic health

record data for a patient; generating a respective observation

embedding for each of the observations, comprising, for each clinical

note: processing the sequence of tokens in the clinical note using a

clinical note embedding LSTM to generate a respective token

embedding for each of the tokens; and generating the observation

embedding for the clinical note from the token embedding's;

generating an embedded representation, comprising, for each time

window: combining the observation embedding's of observations

occurring during the time window to generate a patient record

embedding; and processing the embedded representation of the

electronic health record data using a prediction recurrent neural

network to generate a neural network output that characterizes a

future health status of the patient.

[0013]. US20180168516A1 SYSTEMS AND METHODS TO

SUPPORT MEDICAL THERAPY DECISIONS Systems and

methods for supporting medical therapy decisions are disclosed that

utilize predictive models and electronic medical records (EMR) data

to provide predictions of health conditions over varying time

horizons. Embodiments also determine a 0-100 health risk index

value that represents the "risk" for a patient to acquire a health

condition based on a combination of real-time and predicted EMR

data. The systems and methods receive EMR data and use the

predictive models to predict one or more data values from the EMR

data as diagnostic criteria. In some embodiments, the health

condition trying to be avoided is Sepsis and the health risk index is a

Sepsis Risk Index (SRI). In some embodiments, the predictive

models are neural network models such as time delay neural

networks.

[0014]. CN11798980A Complex medical biological signal

processing method and device based on deep learning network The

invention relates to a complex medical biological signal processing

method and device based on a deep learning network, and the

method comprises the steps: collecting complex medical biological

data, wherein the complex medical biological data are multivariate

heterologous data including two or more of electrocardiogram data,

heart sound data and blood oxygen data; constructing a

convolutional neural network model, and sequentially inputting the

complex medical biological data into a convolutional layer and a

pooling layer of the convolutional neural network model for

standardized preprocessing; constructing a multi-functional recurrent

neural network model, classifying the preprocessed complex medical

biological data, and separating the electro cardio data, the heart

sound data and/or the blood oxygen data; and constructing a front

end prediction model, inputting the complex medical biological data

into the model, and outputting judgment results of human health

condition prediction, identity recognition and/or action recognition.

According to the invention, the problems of multifunction, diagnosis

precision and accuracy of the wearable device can be solved.

[0015]. CN112614590A Old people energy loss risk prediction

method and system based on machine learning The invention

discloses an old people energy loss risk prediction method and

system based on machine learning, and belongs to the field of big

data health condition analysis and prediction. The method comprises

the following steps of obtaining basic data of old people. The social

economic data and the medical history information data form a

sample data set and perform preprocessing on the sample data set.

The pre-processed sample data is characterized by a random forest

model and the like. The multi-layer neural network is established

through the extracted features, the sample data is used for training,

and the loss risk prediction model of the old people is obtained.

Relevant data of a to-be-detected person are acquired, and the risk

prediction model is input to obtain the prediction risk value. The

invention can conveniently and accurately predict the risk of the old

people....

[0016]. 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.

[0017]. 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 dictates otherwise. Also, as used in the

description herein, the meaning of "in" includes "in" and "on" unless

the context clearly dictates otherwise.

[0018]. 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.

[0019]. 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.

[0020]. 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

[0021]. The present invention mainly cures and solves the technical

problems existing in the prior art. In response to these problems, the

present invention provides a system & method for automatic health

prediction using fuzzy based machine learning.

[0022]. The present invention discloses a

Smart health predicting system, characterized in that includes: For

collecting human health evaluation value information of the

information acquisition part, and the information collecting part of the

wireless-connected center prediction unit , and with the center

prediction unit is connected with the display terminal, the information

collecting part worn on the user's human body; The center prediction

unit is used for the acquisition of the information collecting part of

the pre-evaluation value information to obtain the user health rating,

when the health score is less than the present value, the center

prediction unit is also used for the fuzzy logic algorithm DNN depth

to the health score evaluation value information corresponding to the

analysis, illness forecasts the table; The display terminal for

displaying the health score, is also used to display said disease

forecasts the table.

OBJECTIVE OF THE INVENTION

[0023]. The principle objective of the present invention is to provide a

system & method for automatic health prediction using fuzzy based

machine learning.

BRIEF DESCRIPTION OF DRAWINGS

[0024]. Further 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.

[0025]. In order that the advantages of the present invention will be

easily understood, a detailed 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:

[0026]. Figure 1 shows an exemplary representation of a system

& method for automatic health prediction using fuzzy based machine

learning, according to the present invention.

DETAIL DESCRIPTION

[0027]. The present invention discloses a system & method for

automatic health prediction using fuzzy based machine learning.

[0028]. Figure 1 shows the exemplary representation of a system

& method for automatic health prediction using fuzzy based machine

learning, according to the present invention.

[0029]. Although the present disclosure has been described with the

purpose of to a system & method for automatic health prediction using

fuzzy based machine learning, 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.

[0030]. A Smart health predicting system, characterized in that includes:

For collecting human health evaluation value information of the

information acquisition part, and the information collecting part of

the wireless-connected center prediction unit , and with the center

prediction unit is connected with the display terminal, the

information collecting part worn on the user's human body; The

center prediction unit is used for the acquisition of the information

collecting part of the pre-evaluation value information to obtain the

user health rating, when the health score is less than the present

value, the center prediction unit is also used for the fuzzy logic

algorithm DNN depth to the health score evaluation value

information corresponding to the analysis, illness forecasts the table;

The display terminal for displaying the health score, is also used to

display said disease forecasts the table.

[0031]. A human health predicting process comprises the following

steps: The face visual representation of the predicted user is

acquired. The face visual representation of the predicted user is

detected by the trained health state detection model, and the health

state detection result of the predicted user is obtained. A preset

predicting operation corresponding to the health state detection result

of the predicted user is performed.

[0032]. Wherein health predicting unit in the computing device are

respectively ARM WIFI module, power supply, FLASH, keyboard,

display screen, is connected with the pre-diagnosis module fuzzy

logic, is connected to and through the network interface internet,

through the distal end of the medical service unit remote medical

diagnosis, physiological data acquisition device, remote diagnosis

device and health predicting unit through between WIFI module to

realize a transition.

[0033]. Techniques that are based on fuzzy rule such as classification

trees and regression trees along with expectation maximization

technique is implemented for detection of the disease. The proposed

invention is evaluated using the datasets of the real world from the

repositories of medical field. A system based on knowledge is

proposed for the diagnosis of disease using principal component

analysis method and CART which is based on the fuzzy rule for the

techniques of the reasoning in the system. Data clustering is done

using EM in the medical dataset of medical field. The discovery is

ruled by the system based on knowledge using CART. Classification

of problems is done by the applicable approach. Dataset is of the

same nature but huge amount of work in done on data clustering

with removal of noise with the technique of fuzzy based on the rules

for diagnosing the disease for exploiting the utility and potential of

the data set. More importance is given to the classification of disease

with the approach of machine learning that increments. This method

is evaluated using the dataset included additionally in the system.

The data set is huge hence the proposed method achieves the

efficiency by computing the data set in the medical field. Common

[0034]. features of the data set are clustered for detecting the presence

the disease which is then classified based on the features of the

clusters of the data set thereby classifying the disease.,

Claims (3)

1. I/We claim:

   A system for automatic health prediction using fuzzy

   based machine learning, comprises, a

   Smart health predicting system, characterized in that

   includes: For collecting human health evaluation

   value information of the information acquisition

   part, and the information collecting part of the

   wireless-connected center prediction unit , and with

   the center prediction unit is connected with the

   display terminal, the information collecting part

   worn on the user's human body; The center

   prediction unit is used for the acquisition of the

   information collecting part of the pre-evaluation

   value information to obtain the user health rating,

   when the health score is less than the present value, the center prediction unit is also used for the fuzzy logic algorithm DNN depth to the health score evaluation value information corresponding to the analysis, illness forecasts the table; The display terminal for displaying the health score, is also used to display said disease forecasts the table.
2. 2. The system for automatic health prediction using fuzzy

   based machine learning as claimed in claim 1,

   wherein a human health predicting process

   comprises the following steps: The face visual

   representation of the predicted user is acquired. The

   face visual representation of the predicted user is

   detected by the trained health state detection model,

   and the health state detection result of

   the predicted user is obtained. A

   preset predicting operation corresponding to the health state detection result of the predicted user is performed.
3. 3. The system for automatic health prediction using fuzzy

   based machine learning as claimed in claim 1,

   wherein health predicting unit in the computing

   device are respectively arm wife module, power

   supply, flash, keyboard, display screen, is connected

   with the pre-diagnosis module fuzzy logic, is

   connected to and through the network interface

   internet, through the distal end of the medical

   service unit remote medical diagnosis, physiological

   data acquisition device, remote diagnosis device and

   health predicting unit through between WIFI

   module to realize a transition.

   FIGURE 1 DRAWINGS