Authors :
S. Umar Kalimulla; V. AlekyaSatyasri; K. Srunvitha; S. H. N. V. V. D. S. Sai Charan; A. V Satya Sai Ram; DR. V. Venkateswara Rao
Volume/Issue :
Volume 8 - 2023, Issue 11 - November
Google Scholar :
https://tinyurl.com/mrynph8e
Scribd :
https://tinyurl.com/3y37p62n
DOI :
https://doi.org/10.5281/zenodo.10245792
Abstract :
Diabetes is a prevalent chronic disease
affecting a significant portion of the global population.
Early detection and accurate prediction of diabetes can
play a crucial role in managing the condition and
preventing complications. Machine learning (ML)
techniques have shown promising results in diabetes
prediction based on patient data. In this study, we
propose a user-understandable approach utilizing the
Random Forest classifier algorithm for accurate and
interpretable diabetes prediction. To build our
prediction model, we utilized a comprehensive dataset
comprising various patient attributes, including age,
body mass index (BMI), blood pressure, glucose levels,
and medical history. Pre-processing techniques were
applied to handle missing values and normalize the data,
followed by feature selection to identify the most relevant
attributes for diabetes prediction. The user-
understandable representation of the model facilitated
effective interpretation and communication of the
prediction results. This allows healthcare professionals
to explain the prediction rationale to patients, promoting
shared decision-making and patient engagement.
Diabetes is a prevalent chronic disease
affecting a significant portion of the global population.
Early detection and accurate prediction of diabetes can
play a crucial role in managing the condition and
preventing complications. Machine learning (ML)
techniques have shown promising results in diabetes
prediction based on patient data. In this study, we
propose a user-understandable approach utilizing the
Random Forest classifier algorithm for accurate and
interpretable diabetes prediction. To build our
prediction model, we utilized a comprehensive dataset
comprising various patient attributes, including age,
body mass index (BMI), blood pressure, glucose levels,
and medical history. Pre-processing techniques were
applied to handle missing values and normalize the data,
followed by feature selection to identify the most relevant
attributes for diabetes prediction. The user-
understandable representation of the model facilitated
effective interpretation and communication of the
prediction results. This allows healthcare professionals
to explain the prediction rationale to patients, promoting
shared decision-making and patient engagement.
