Hybrid Method for Evaluating Feature Importance for Predicting Chronic Heart Diseases | IEEE Conference Publication | IEEE Xplore

Hybrid Method for Evaluating Feature Importance for Predicting Chronic Heart Diseases


Abstract:

Predicting the impact of different factors on the patient’s health is as important as diagnosing diseases, especially when monitoring patients with chronic diseases. To p...Show More

Abstract:

Predicting the impact of different factors on the patient’s health is as important as diagnosing diseases, especially when monitoring patients with chronic diseases. To perform this by Artificial Intelligence (AI) methods, it is recommended to determine the features importance (FI) of data. There are a number of methods to evaluate FI. However, we can see a big variation in their results which is difficult to interpret. To solve this issue, we proposed new method which aim is minimizing the differences. Furthermore, to demonstrate the effectiveness of the proposed method we used the extracted FIs as weights of the weighted KNN and compared performances.
Date of Conference: 28-30 September 2022
Date Added to IEEE Xplore: 14 June 2023
ISBN Information:
Conference Location: Tashkent, Uzbekistan
Citations are not available for this document.

I. Introduction

Using AI algorithms in medicine opens up huge opportunities for the different domain of healthcare. As a consequence, todays, various algorithms of AI are widely used in the direction of disease detection, interpretation and segmentation of medical images as well as classification of diseases [1 –3, 15 –18]. But in healthcare, there are cases when it is more important to determine the factors (drug, food, physical activity etc.) affecting the patient’s condition and to determine the degree of influence of these factors than to diagnose the disease. In particular, the monitoring of chronic diseases is one of this crucial case. Because, in the process of daily monitoring of the patient, it is necessary to determine what factors and to what extent cause its condition to improve or to worsens. To solve such kind of problem, machine learning methods of evaluating the importance of features in the dataset has been used.

Cites in Papers - |

Cites in Papers - IEEE (2)

Select All
1.
Nur E Jannat Hema, Nubras Samayeen Zeest, Mohammad Ratul Mahjabin, Muhammad Nazrul Islam, "An Ensemble-based ML Model to Predict Cardiac Disease", 2024 International Conference on Inventive Computation Technologies (ICICT), pp.214-219, 2024.
2.
Kudratjon Zohirov, "A New Approach to Determining the Active Potential Limit of an Electromyography Signal", 2023 3rd International Conference on Technological Advancements in Computational Sciences (ICTACS), pp.291-294, 2023.

Cites in Papers - Other Publishers (4)

1.
Rashid Nasimov, Nigorakhon Nasimova, Bahodir Mumimov, Adibaxon Usmanxodjayeva, Guzal Sobirova, Akmalbek Abdusalomov, "Development of Fully Synthetic Medical Database Shuffling Method", Internet of Things, Smart Spaces, and Next Generation Networks and Systems, vol.14543, pp.55, 2024.
2.
Tao Lin, Mengyao Fan, "FMI-CAECD: Fusing Multi-Input Convolutional Features with Enhanced Channel Attention for Cardiovascular Diseases Prediction", Sensors, vol.24, no.22, pp.7160, 2024.
3.
Simon Bin Akter, Rakibul Hasan, Sumya Akter, Md. Mahadi Hasan, Tanmoy Sarkar, , 2024.
4.
Zarnigor Tagmatova, Akmalbek Abdusalomov, Rashid Nasimov, Nigorakhon Nasimova, Ali Hikmet Dogru, Young-Im Cho, "New Approach for Generating Synthetic Medical Data to Predict Type 2 Diabetes", Bioengineering, vol.10, no.9, pp.1031, 2023.

References

References is not available for this document.