Description:BACKGROUND
Field of Invention
[001] Embodiments of the present invention generally relate to a system for predicting hypothyroid disease and particularly to a system for predicting hypothyroid disease using ensemble models.
Description of Related Art
[002] Hypothyroidism is a medical condition characterized by insufficient production of thyroid hormone. This deficiency can affect vital functions like heart rate, body temperature, and overall metabolism. It is more commonly observed in elderly women. The recommended treatment involves thyroid hormone replacement administered under the care of a medical practitioner.
[003] Furthermore, if hypothyroidism is diagnosed at an early stage, it can be effectively managed with minimal medication and precautions. Prioritizing prevention over post-diagnosis treatment can lead to a healthy lifestyle without the need for medication or dietary restrictions.
[004] Predicting hypothyroidism accurately before its onset in the human body is a challenging task, primarily because the predictive factors rely on individual food habits and lifestyles. While there are commercially available test kits to detect hypothyroidism, the certainty of results can vary significantly between manufacturers, often resulting in a lack of definitive accuracy.
[005] There is thus a need for a system for predicting hypothyroid disease using ensemble models that can overcome the shortcomings faced by the traditional methods in a more efficient manner.
SUMMARY
[006] Embodiments in accordance with the present invention provide a system for predicting hypothyroid disease using ensemble models. The system comprising: a processor located on an application server. The system further comprising: a storage medium comprising programming instructions executable by the processor. The storage medium comprises: a data pre-processing module configured to perform a pre-processing on a dataset collected from a pre-defined repository for removing noisy and missing data from the dataset; wherein the dataset is bifurcated into a training dataset and a testing dataset. The storage medium further comprises: a feature selection module configured to minimize input variables from the training dataset by using a feature selection technique to improve the prediction of hypothyroid disease. The storage medium further comprises: a training module configured to train machine learning models by using the training dataset. The storage medium further comprises: a prediction module configured to execute the trained machine learning models on the minimized dataset to predict the presence of the hypothyroid disease in a patient. The storage medium further comprises: an evaluation module configured to evaluate the trained machine learning models by using the testing dataset.
[007] Embodiments in accordance with the present invention further provide a method for predicting hypothyroid disease using ensemble models. The method comprising steps of: performing a pre-processing on a dataset collected from a pre-defined repository for removing noisy and missing data from the dataset; wherein the dataset is bifurcated into a training dataset and a testing dataset; minimizing input variables from the training dataset by using a feature selection technique to improve the prediction of hypothyroid disease; training machine learning models by using the training dataset; and executing the trained machine learning models on the minimized dataset to predict a presence of the hypothyroid disease in a patient.
[008] Embodiments of the present invention may provide a number of advantages depending on their particular configuration. First, embodiments of the present application provide a system for predicting hypothyroid disease using ensemble models.
[009] Next, embodiments of the present application may provide a system for predicting hypothyroid disease using ensemble models that is accurate in the results obtained.
[0010] Next, embodiments of the present application may provide a system for predicting hypothyroid disease using ensemble models that is flexible for any age/gender group of patients.
[0011] Next, embodiments of the present application may provide a system for predicting hypothyroid disease using ensemble models that can be implemented in any hardware and software environment.
[0012] Next, embodiments of the present application may provide a system for predicting hypothyroid disease using ensemble models that is easy to use and cost-effective.
[0013] Next, embodiments of the present application may provide a system for predicting hypothyroid disease using ensemble models that incur low overtime maintenance costs.
[0014] These and other advantages will be apparent from the present application of the embodiments described herein.
[0015] The preceding is a simplified summary to provide an understanding of some embodiments of the present invention. This summary is neither an extensive nor exhaustive overview of the present invention and its various embodiments. The summary presents selected concepts of the embodiments of the present invention in a simplified form as an introduction to the more detailed description presented below. As will be appreciated, other embodiments of the present invention are possible utilizing, alone or in combination, one or more of the features set forth above or described in detail below.
BRIEF DESCRIPTION OF THE DRAWINGS
[0016] The above and still further features and advantages of embodiments of the present invention will become apparent upon consideration of the following detailed description of embodiments thereof, especially when taken in conjunction with the accompanying drawings, and wherein:
[0017] FIG. 1 illustrates a block diagram depicting a system for predicting hypothyroid disease using ensemble models, according to an embodiment of the present invention; and
[0018] FIG. 2 depicts a flowchart of a method for predicting hypothyroid disease using ensemble models, according to another embodiment of the present invention.
[0019] The headings used herein are for organizational purposes only and are not meant to be used to limit the scope of the description or the claims. As used throughout this application, the word "may" is used in a permissive sense (i.e., meaning having the potential to), rather than the mandatory sense (i.e., meaning must). Similarly, the words “include”, “including”, and “includes” mean including but not limited to. To facilitate understanding, like reference numerals have been used, where possible, to designate like elements common to the figures. Optional portions of the figures may be illustrated using dashed or dotted lines, unless the context of usage indicates otherwise.
DETAILED DESCRIPTION
[0020] The following description includes the preferred best mode of one embodiment of the present invention. It will be clear from this description of the invention that the invention is not limited to these illustrated embodiments but that the invention also includes a variety of modifications and embodiments thereto. Therefore, the present description should be seen as illustrative and not limiting. While the invention is susceptible to various modifications and alternative constructions, it should be understood, that there is no intention to limit the invention to the specific form disclosed, but, on the contrary, the invention is to cover all modifications, alternative constructions, and equivalents falling within the spirit and scope of the invention as defined in the claims.
[0021] In any embodiment described herein, the open-ended terms "comprising", "comprises”, and the like (which are synonymous with "including", "having” and "characterized by") may be replaced by the respective partially closed phrases "consisting essentially of", “consists essentially of", and the like or the respective closed phrases "consisting of", "consists of”, the like.
[0022] As used herein, the singular forms “a”, “an”, and “the” designate both the singular and the plural, unless expressly stated to designate the singular only.
[0023] FIG. 1 illustrates a block diagram depicting a system 100 for predicting hypothyroid disease using ensemble models, according to an embodiment of the present invention. In an embodiment of the present invention, the system 100 may predict hypothyroid in a group of patients with their features published in a pre-defined repository. According to embodiments of the present invention, the features published in the pre-defined repository may be, but not limited to, an age of the patient, a gender of the patient, symptoms of hypothyroid in the patient, and so forth. In a preferred embodiment of the present invention, there may be a total of 28 features related to the patient published in the pre-defined repository. Embodiments of the present invention are intended to include or otherwise cover any features related to the patient published in the pre-defined repository, including known, related art, and/or later developed technologies. According to embodiments of the present invention, the patient may be of any age group and any gender such as, but not limited to, a child, an adolescent, an adult, an old age, and so forth. Embodiments of the present invention are intended to include or otherwise cover any age group or gender of the patient.
[0024] According to an embodiment of the present invention, the system 100 may comprise a user device 102, a computer application 104, a database 106, a dataset 108, an application server 110, a processor 112, and a storage medium 114.
[0025] In an embodiment of the present invention, the user device 102 may be a device used by the patient to upload features into the system 100, those features may later be published into the pre-defined repository. The user device 102 may further be configured to receive the prediction of the hypothyroid disease in the patient, in an embodiment of the present invention.
[0026] The user device 102 may be, but not limited to, a personal computer, a consumer device, and alike. Embodiments of the present invention are intended to include or otherwise cover any type of the user device 102 including known, related art, and/or later developed technologies. In an embodiment of the present invention, the personal computer may be, but not limited to, a desktop, a server, a laptop, and alike. Embodiments of the present invention are intended to include or otherwise cover any type of the personal computer including known, related art, and/or later developed technologies.
[0027] Further, in an embodiment of the present invention, the consumer device may be, but not limited to, a tablet, a mobile phone, a notebook, a netbook, a smartphone, a wearable device, and so forth. Embodiments of the present invention are intended to include or otherwise cover any type of the consumer device including known, related art, and/or later developed technologies. Embodiments of the present invention are intended to include or otherwise cover any type of the user device 102 including known, related art, and/or later developed technologies.
[0028] According to an embodiment of the present invention, the user device 102 may comprise software applications such as, but not limited to, a healthcare application, a medical consultation application, an emergency services application, and the like. In a preferred embodiment of the present invention, the user device 102 may comprise a computer application 104 that may be a computer-readable program installed in the user device 102 for executing functions associated with the system 100.
[0029] In an embodiment of the present invention, the database 106 may store the dataset 108. The dataset 108 may further comprise the pre-defined repository that may be stored in the database 106, in an embodiment of the present invention. In an embodiment of the present invention, the dataset 108 stored in the database 106 may have already been trained for prediction of the hypothyroid disease in the patient. The dataset 108 may further be bifurcated into a testing dataset and a training dataset, in an embodiment of the present invention. In an embodiment of the present invention, the bifurcation of the dataset 108 in the testing dataset and the training dataset may take place in a ratio of 70:30 respectively.
[0030] In an embodiment of the present invention, the testing dataset may test the pre-defined repository provided by the patient for prediction of the hypothyroid disease in the patient. The pre-defined repository with various predictions of the hypothyroid disease levels may further be stored under the training dataset, the training dataset may train the model for better and more accurate prediction of the hypothyroid disease in the patient using the pre-defined repository, in an embodiment of the present invention.
[0031] According to embodiments of the present invention, the database 106 may be for example, but not limited to, a distributed database, a personal database, an end-user database, a commercial database, a Structured Query Language (SQL) database, a non-SQL database, an operational database, a relational database, an object-oriented database, a graph database, a cloud server database, and so forth. Embodiments of the present invention are intended to include or otherwise cover any type of the database 106 including known, related art, and/or later developed technologies.
[0032] Further, the database 106 may be stored in a cloud server, in an embodiment of the present invention. In an embodiment of the present invention, the cloud server may be remotely located. In an exemplary embodiment of the present invention, the cloud server may be a public cloud server. In another exemplary embodiment of the present invention, the cloud server may be a private cloud server. In yet another embodiment of the present invention, the cloud server may be a dedicated cloud server. According to embodiments of the present invention, the cloud server may be, but not limited to, a Microsoft Azure cloud server, an Amazon AWS cloud server, a Google Compute Engine (GEC) cloud server, an Amazon Elastic Compute Cloud (EC2) cloud server, and so forth. Embodiments of the present invention are intended to include or otherwise cover any type of the cloud server including known, related art, and/or later developed technologies.
[0033] In an embodiment of the present invention, the application server 110 may be a hardware on which the processor 112 may be installed. According to embodiments of the present invention, the application server 110 may be, but not limited to, a motherboard, a wired board, a mainframe, and so forth. Embodiments of the present invention are intended to include or otherwise cover any type of the application server 110, including known, related art, and/or later developed technologies.
[0034] In an embodiment of the present invention, the processor 112 may be located on the application server 110. The processor 112 may be configured to execute the computer-readable instructions to generate an output relating to the system 100. According to embodiments of the present invention, the processor 112 may be, but not limited to, a Programmable Logic Control (PLC) unit, a microprocessor, a development board, and so forth. Embodiments of the present invention are intended to include or otherwise cover any type of the processor 112 including known, related art, and/or later developed technologies.
[0035] In an embodiment of the present invention, the storage medium 114 may store computer programmable instructions in form of programming modules. The storage medium 114 may be a non-transitory storage medium, in an embodiment of the present invention. In an embodiment of the present invention, the storage medium 114 may store the medical image uploaded by the user through the computer application 104 installed in the user device 102. The storage medium 114 may communicate with the processor 112 and execute a computer-readable set of instructions present in storage medium 114, in an embodiment of the present invention.
[0036] According to embodiments of the present invention, the storage medium 114 may be, but not limited to, a Random-Access Memory (RAM), a Static Random-access Memory (SRAM), a Dynamic Random-access Memory (DRAM), a Read Only Memory (ROM), an Erasable Programmable Read-only Memory (EPROM), an Electrically Erasable Programmable Read-only Memory (EEPROM), a NAND Flash, a Secure Digital (SD) memory, a cache memory, a Hard Disk Drive (HDD), a Solid-State Drive (SSD) and so forth. Embodiments of the present invention are intended to include or otherwise cover any type of the storage medium 114, including known, related art, and/or later developed technologies. In an embodiment of the present invention, the storage medium 114 further comprises a data pre-processing module 116, a feature selection module 118, a training module 120, a prediction module 122, and an evaluation module 124.
[0037] In an embodiment of the present invention, the data pre-processing module 116 may be configured to perform a pre-processing on the dataset 108 collected from the pre-defined repository. The pre-processing may be performed for removing noisy and missing data from the dataset 108 additionally, the pre-processing may format the data stored in the dataset 108 in accordance with the machine learning models, in an embodiment of the present invention. In an embodiment of the present invention, upon pre-processing of the dataset 108, the dataset 108 may be bifurcated into the training dataset and the testing dataset. The bifurcation of the dataset 108 in the testing dataset and the training dataset may take place in the ratio of 70:30 respectively, in an embodiment of the present invention.
[0038] In an embodiment of the present invention, the data pre-processing module 116 may be configured to transmit the training dataset to the feature selection module 118. The data pre-processing module 116 may further be configured to transmit the training dataset to the training module 120, in an embodiment of the present invention.
[0039] In an embodiment of the present invention, the feature selection module 118 may be configured to minimize input variables from the training dataset received from the data pre-processing module 116. By minimizing the input variables from the training dataset, the prediction of the hypothyroid disease may be improved, in an embodiment of the present invention. In an embodiment of the present invention, the input variables may be minimized by using a feature selection technique. In a preferred embodiment of the present invention, the feature selection technique may be a chi-square test method. Embodiments of the present invention are intended to include or otherwise cover any feature selection technique for minimization of the input variables, including known, related art, and/or later developed technologies. In an embodiment of the present invention, the chi-square test method may be calculated by using the equation (1):
X2 = S [(O-E)2 / E] --- (1)
wherein X2 may be a chi-square statistics O may be a frequency, and E may be an expected frequency.
[0040] In an embodiment of the present invention, the feature selection module 118 may be configured to transmit the minimized dataset 108 to the training module 120.
[0041] In an embodiment of the present invention, the training module 120 may be configured to train machine learning models by the using the training dataset received from the data pre-processing module 116. According to embodiments of the present invention, the machine learning models may be, but not limited to, a bagging model, a random forest model, a grad boost model, an ada boost model, and so forth. Embodiments of the present invention are intended to include or otherwise cover any machine learning models utilized by the training module 120 for training, including known, related art, and/or later developed technologies. In an embodiment of the present invention, the trained machine learning models may be binary classification models.
[0042] In an embodiment of the present invention, the random forest model (also known as random decision forest model) may be based on supervised learning and may be implemented in both classification and regression problems. It may be the ensemble method that may include numerous constructions of decision trees to perform various tasks, in an embodiment of the present invention.
[0043] In an embodiment of the present invention, the grad boost model (also known as gradient boosting model) may be based on supervised learning and may be implemented in both classification and regression problems. It may be the ensemble method that may include repetitive training process of the model, in an embodiment of the present invention.
[0044] In an embodiment of the present invention, the ada boost model also known as adaptive boosting model) may be used with the decision tree of one level. The ada boost model may be prepared a base model and weights may be assigned equally on each of datapoints, in an embodiment of the present invention.
[0045] In an embodiment of the present invention, the prediction module 122 may be configured to execute the trained machine learning models on the minimized dataset 108. Upon execution of the trained machine learning models on the minimized dataset 108, the prediction module 122 may predict the presence of the hypothyroid disease in patient, in an embodiment of the present invention.
[0046] In an exemplary embodiment of the present invention, the predictions made by the random forest model may be tabulated in a table 1:
Random Forest Model True: 1 True: 0 Class Precisions
Prediction: 1 2460 0 100%
Prediction: 0 9 223 97%
Class Recall 99.8% 100%

Table 1
[0047] In an embodiment of the present invention, the table 1 may represents the results obtained by the random forest model and the accuracy obtained may be 99.75%.
[0048] In an exemplary embodiment of the present invention, the predictions made by the grad boost model may be tabulated in a table 2:
Grad Boost Model True: 1 True: 0 Class Precisions
Prediction: 1 1045 5 99.7%
Prediction: 0 9 85 90.2%
Class Recall 99.3% 95.3%

Table 2
[0049] In an embodiment of the present invention, the table 2 may represents the results obtained by the grad boost model and the accuracy obtained may be 98.97%.
[0050] In an exemplary embodiment of the present invention, the predictions made by the ada boost model may be tabulated in a table 3:
Ada Boost Model True: 1 True: 0 Class Precisions
Prediction: 1 1025 16 98.6%
Prediction: 0 26 75 76.2%
Class Recall 97.8% 84.3%

Table 3
[0051] In an embodiment of the present invention, the table 3 may represents the results obtained by the ada boost model and the accuracy obtained may be 96.67%.
[0052] In an exemplary embodiment of the present invention, the predictions made by the bagging model may be tabulated in a table 4:
Bagging Model True: 1 True: 0 Class Precisions
Prediction: 1 1048 3 98.6%
Prediction: 0 6 88 97.8
Class Recall 97.8% 84.3%

Table 4
[0053] In an embodiment of the present invention, the table 4 may represents the results obtained by the bagging model and the accuracy obtained may be 99.53%.
[0054] In an embodiment of the present invention, the accuracy percentage of the bagging model, the random forest model, the grad boost model, and the ada boost model may be tabulated in a table 5:
Model Accuracy
Random Forest Model 99.75%
Grad Boost Model 98.97%
Ada Boost Model 96.67%
Bagging Model 99.53%

Table 5
[0055] In an embodiment of the present invention, the random forest model may predict the presence of the hypothyroid disease in the patient with the accuracy of 99.75%. The grad boost model may predict the presence of the hypothyroid disease in the patient with the accuracy of 98.97%, in an embodiment of the present invention. In an embodiment of the present invention, the ada boost model may predict the presence of the hypothyroid disease in the patient with the accuracy of 96.67%. The bagging model may predict the presence of the hypothyroid disease in the patient with the accuracy of 99.53%, in an embodiment of the present invention.
[0056] In an embodiment of the present invention, the evaluation module 124 may be configured to evaluate the trained machine learning models by using the testing dataset. The evaluation of the trained machine learning models may be carried out in 3 categories, categories may be accuracy, precision, and recall, in an embodiment of the present invention.
[0057] In an embodiment of the present invention, the accuracy may be a numerical magnitude, referred as ‘accuracy score’. The accuracy score may be a ratio of number of correct predictions to the total number of interpretations. The accuracy score may be calculated by using the equation (2):
accuracy score = [ (TP+TN) / (TP+FP+FN+TN)] --- (2)
wherein TP may be true positives, TN may be true negatives, FP may be false positives, and FN may be false negatives.
[0058] In an embodiment of the present invention, the precision may be a numerical magnitude, referred as ‘accuracy score’. The precision score may be a ratio of number of positive observations to the total number of predicted positive observations. The precision score may be calculated by using the equation (3):
precision score = [ (TP) / (TP+FP)] --- (3)
wherein TP may be true positives, and FP may be false positives.
[0059] In an embodiment of the present invention, the recall may be a numerical magnitude, referred to as ‘recall score’. The recall score may be a ratio of correctly predicted positive observations to the sum of predicted positive and negative observations. The recall score may be calculated by using the equation (4):
recall score = [ (TP) / (TP+FN)] --- (4)
wherein TP may be true positives, and FN may be false negatives.
[0060] FIG. 2 depicts a flowchart of a method 200 for predicting hypothyroid disease using ensemble models, according to another embodiment of the present invention.
[0061] At step 202, the system 100 may perform the pre-processing on the dataset 108 collected from the pre-defined repository for removing noisy and missing data from the dataset 108. The dataset 108 is further bifurcated into the training dataset and the testing dataset.
[0062] At step 204, the system 100 may minimize input variables from the training dataset by using the feature selection technique to improve the prediction of hypothyroid disease.
[0063] At step 206, the system 100 may train machine learning models by using the training dataset.
[0064] At step 208, the system 100 may execute the trained machine learning models on the minimized dataset 108 to predict the presence of the hypothyroid disease in the patient.
[0065] Embodiments of the invention are described above with reference to block diagrams and schematic illustrations of methods and systems according to embodiments of the invention. It will be understood that each block of the diagrams and combinations of blocks in the diagrams can be implemented by computer program instructions. These computer program instructions may be loaded onto one or more general purpose computers, special purpose computers, or other programmable data processing apparatus to produce machines, such that the instructions which execute on the computers or other programmable data processing apparatus create means for implementing the functions specified in the block or blocks. Such computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means that implement the function specified in the block or blocks.
[0066] While the invention has been described in connection with what is presently considered to be the most practical and various embodiments, it is to be understood that the invention is not to be limited to the disclosed embodiments, but on the contrary, is intended to cover various modifications and equivalent arrangements included within the spirit and scope of the appended claims.
[0067] This written description uses examples to disclose the invention, including the best mode, and also to enable any person skilled in the art to practice the invention, including making and using any devices or systems and performing any incorporated methods. The patentable scope of the invention is defined in the claims, and may include other examples that occur to those skilled in the art. Such other examples are intended to be within the scope of the claims if they have structural elements that do not differ from the literal language of the claims, or if they include equivalent structural elements within substantial differences from the literal languages of the claims. , Claims:CLAIMS
I/We Claim:
1. A system (100) for predicting hypothyroid disease using ensemble models, the system (100) comprising:
a processor (112) located on an application server (110); and
a storage medium (114) comprising programming instructions executable by the processor (112), wherein the storage medium (114) comprises:
a data pre-processing module (116) configured to perform a pre-processing on a dataset (108) collected from a pre-defined repository for removing noisy and missing data from the dataset (108); wherein the dataset (108) is bifurcated into a training dataset and a testing dataset;
a feature selection module (118) configured to minimize input variables from the training dataset by using a feature selection technique to improve the prediction of hypothyroid disease;
a training module (120) configured to train machine learning models by using the training dataset;
a prediction module (122) configured to execute the trained machine learning models on the minimized dataset (108) to predict the presence of the hypothyroid disease in a patient; and
an evaluation module (124) configured to evaluate the trained machine learning models by using the testing dataset.
2. The system (100) as claimed in claim 1, wherein the machine learning models are selected from a bagging model, a random forest model, a grad boost model, an ada boost model, or a combination thereof.
3. The system (100) as claimed in claim 1, wherein the trained machine learning models are binary classification models.
4. The system (100) as claimed in claim 1, wherein the feature selection technique is a chi-square test method.
5. The system (100) as claimed in claim 1, wherein the random forest model predicts the presence of the hypothyroid disease in the patient with an accuracy of 99.75%.
6. The system (100) as claimed in claim 1, wherein the grad boost model predicts the presence of the hypothyroid disease in the patient with the accuracy of 98.97%.
7. The system (100) as claimed in claim 1, wherein the ada boost model predicts the presence of the hypothyroid disease in the patient with the accuracy of 96.67%.
8. The system (100) as claimed in claim 1, wherein the bagging model predicts the presence of the hypothyroid disease in the patient with the accuracy of 99.53%.
9. A method (200) for predicting hypothyroid disease using ensemble models, the method (200) comprising steps of:
performing a pre-processing on a dataset (108) collected from a pre-defined repository for removing noisy and missing data from the dataset (108); wherein the dataset (108) is bifurcated into a training dataset and a testing dataset;
minimizing input variables from the training dataset by using a feature selection technique to improve the prediction of hypothyroid disease;
training machine learning models by using the training dataset; and
executing the trained machine learning models on the minimized dataset (108) to predict a presence of the hypothyroid disease in a patient.
10. The method (200) as claimed in claim 9, comprises a step of evaluating the trained machine learning models by using the testing dataset.
Date: December 07, 2023
Place: Noida

Dr. Keerti Gupta
Agent for the Applicant
(IN/PA-1529)