METHOD FOR DIAGNOSING DIABETES

Abstract

ABSTRACT A method (100) for diagnosing diabetes, the method (100) comprising the steps of receiving, via a data input module, a plurality of health indicators from a user, pre-processing the plurality of health indicators by managing missing data, encoding categorical variables, and standardizing numerical data to prepare the pre-processed data for analysis, training one or more machine learning models on the pre-processed health indicators, evaluating the performance of each of the trained machine learning models based on one or more evaluation metrics, to determine at least one of the one or more machine learning models with the highest accuracy for diabetes classification and displaying, via a user interface, a diabetes classification result to the user based on the at least one of the one or more machine learning models with the highest evaluation metric. <>

Specification

Description:FIELD OF THE DISCLOSURE
[0001] This invention generally relates to a field of diabetes and in particular relates to a method diagnosing diabetes based on patient driven data.
BACKGROUND

[0002] The subject matter discussed in the background section should not be assumed to be prior art merely as a result of its mention in the background section. Similarly, a problem mentioned in the background section or associated with the subject matter of the background section should not be assumed to have been previously recognized in the prior art. The subject matter in the background section merely represents different approaches, which in and of themselves may also correspond to implementations of the claimed technology.
[0003] Traditionally, diabetes diagnosis has relied on physical tests, including fasting blood sugar levels, glucose tolerance tests, and glycated hemoglobin (A1C) measurements. These conventional approaches often require lab-based testing, specialized equipment, and trained personnel, which can de , Claims:1. A method (100) for diagnosing diabetes, the method (100) comprising the steps of:
receiving, via a data input module, a plurality of health indicators from a user;
pre-processing the plurality of health indicators by managing missing data, encoding categorical variables, and standardizing numerical data to prepare the pre-processed data for analysis;
training one or more machine learning models on the pre-processed health indicators;
evaluating the performance of each of the trained machine learning models based on one or more evaluation metrics, to determine at least one of the one or more machine learning models with the highest accuracy for diabetes classification; and
displaying, via a user interface, a diabetes classification result to the user based on the at least one of the one or more machine learning models with the highest evaluation metric.

2. The method (100) as claimed in claim 1, wherein the health indicators include blood pressure, cholesterol levels, BMI, smoking status, demographic de

Documents