1 / 7

Thyroid Detection using Machine Learning

https://projectgurukul.org/thyroid-detection-using-machine-learning/

Sudhanshi
Télécharger la présentation

Thyroid Detection using Machine Learning

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Thyroid Detection using Machine Learning In this article, we will discuss Thyroid Detection Using Machine Learning. With this Machine Learning Project.

  2. Hypo Thyroid Disease Incidences of thyroid illness have increased recently. One of the most crucial roles in controlling metabolism belongs to the thyroid gland. Two of the most prevalent disorders caused by thyroid gland irregularities are hyperthyroidism and hypothyroidism. Each year, a substantial number of patients are identified as having thyroid conditions such as hypothyroidism and hyperthyroidism. Levothyroxine (T4) and triiodothyronine (T3) are produced by the thyroid gland, and both hypothyroidism and hyperthyroidism can result from a lack of thyroid hormones. In the literature, a variety of methods are suggested for diagnosing thyroid illness. In order to appropriately treat the patient at the appropriate time, save lives, and reduce medical costs, a proactive thyroid disease diagnosis is important.

  3. Machine learning and deep learning techniques are used to forecast thyroid diagnosis in the early stages and identify the different types of thyroid disease, such as hypothyroidism and hyperthyroidism. This is possible because of technological breakthroughs in data processing and computation. Technologies like data mining, big data, image and video processing, and parallel computing have gotten advanced, and this has benefited the healthcare industry. Applications for data mining in health care include early disease detection and diagnosis, virus outbreak forecasting, drug development, and testing, health care data management, patient-specific medication recommendations, etc. Healthcare experts work to recognize diseases in their earliest stages so that patients can receive the correct care and the condition can be cured quickly and cheaply. One of the illnesses that affect a major portion of people worldwide is thyroid disease. The American Thyroid Association, the foremost professional organization in the world, estimates that 20 million Americans suffer from a thyroid condition. One in twelve Americans may receive a thyroid problem diagnosis at some point in their lives. According to these figures, thyroid-related illness should not be taken lightly. It would be ideal to use cutting-edge technologies to improve medical procedures for identifying and treating thyroid disorders. Projectgurukul

  4. Choosing Model Machine Learning has offered a number of methods for classifying and detecting thyroid illness. For instance, Garcia utilized the machine learning methods RF, LR, GBM, SVM, and deep neural networks to forecast the highly likely molecules which are the starting of the thyroid hormone balance (DNN). For additional testing in the early stages of thyroid illness, the molecules’ early prediction is useful. For the purpose of conducting the research, the molecular events were gathered from ToxCast databases. According to research, thyroid peroxidase (TPO) and thyroid hormone receptor (TR), with F1 scores of 0.83 and 0.81, respectively, had the best predictive performance. The researchers used feature selection methods and image processing techniques.

  5. Decision Tree Algorithm Decision Tree is going to be a really great choice for this project. When the response variable is categorical, a decision tree is utilized. Decision trees are based on tree-like structures that describe the categorization process based on input features. The Decision Tree can take any type of input variable like discrete, continuous, and even a graph. The steps for implementing the Decision Tree are: 1. 2. Create a tree using the input features of the nodes. Choose a feature to forecast the result from the input feature with the best information gain. Each attribute in each tree node is calculated to determine which node has the biggest information gain. Repeat step 2 to create a subtree by using the feature which is not used in the above nodes. 3. 4. Projectgurukul

  6. KNN KNN is another supervised learning algorithm. KNN aids in the resolution of classification and regression issues. KNN is a sluggish prediction method. It works on the idea that related things are located close to one another. Similar data points are frequently found close together. It assists in categorizing fresh work using similarity metrics. The KNN algorithm collects all the records and categorizes them based on how similar they are. A structure resembling a tree is used to calculate the distance between the spots. The algorithm locates the nearest data points in the training data set, or the new data point’s nearest neighbors, to create a forecast. Here, K is always a positive integer and stands for “number of close neighbors”. The value of the neighbor is picked from a range of classes. Most definitions of proximity use the Euclidean concept of distance. The following equation describes the Euclidean distance between two points P and Q, i.e., P (p1, p2,…. Pn) and Q (q1, q2,…. Qn):

  7. Summary In this Machine Learning project, we develop a hypo Thyroid Disease detection using the Decision Tree and KNN Classifier. We hope you have learned something new from this project. Projectgurukul

More Related