Page 155 - Emerging Trends and Innovations in Web-Based Applications and Technologies

International Journal of Trend in Scientific Research and Development (IJTSRD) @ www.ijtsrd.com eISSN: 2456-6470
· Resource Usage: The model required reasonable [5] Fati Oiza Ochepa1, John Patrick2, Malik Adeiza Rufai3
resources, making it efficient and practical. and Adamu Isah4 “A Deep Learning Based Multiple
Chronic Disease Detection Model” NOV 2022 | IRE
· Scalability: It handled larger datasets well, maintaining
Journals | Volume 6 Issue 5 | ISSN: 2456-8880
good performance as data increased.
[6] Mohammad Rashedul Islam, Azrin Sultana, Rakibul
 Key Insights : Islam “A comprehensive review for chronic disease
· Results were visualized using graphs like ROC curves
prediction using machine learning algorithms” Journal
and confusion matrices.
of Electrical Systems and Information Technology
· The system proved effective and scalable, offering volume 11,16 July 2024
reliable predictions for chronic diseases. [7] Al Khan “Machine Learning for Chronic Disease
VII. CONCLUSION Prediction”. August 05, 2022, CEOS Public. Health. Res.
Machine learning has made healthcare better by making it 1(1):101
easier and more reliable to diagnose serious diseases like [8] Dibaba Adeba Debal and Tilahun Melak Sitote
2
1*
heart, kidney, cancer, and diabetes. Our study achieved about
“Chronic kidney disease prediction using machine
90% accuracy in predicting these diseases and provides
learning techniques” Debal and Sitote Journal of Big
reports showing the chances of having a disease. This shows
Data (2022) 9:109 https://doi.org/10.1186/s40537-
that our approach is effective and useful. The proposed
022-00657-5
model also generates detailed reports highlighting the
likelihood of disease occurrence, showcasing the reliability [9] Sun Min Oh,1,2 Katherine M. Stefani,3 and Hyeon
and effectiveness of this approach. Chang Kim1, “Development and Application of
Chronic Disease Risk Prediction Models” Jun 13, 2014.
This research paper aims to create a robust and efficient https://doi.org/10.3349/ymj.2014.55.4.853
model for predicting chronic diseases using a combination of
machine learning and deep learning techniques. By [10] Kawsher Rahman1*, Prasanna Pasam2, Srinivas
leveraging both text and image data, the model will provide Addimulam3 and Vineel Mouli Natakam4 “Leveraging
comprehensive insights into patient health, facilitating early AI for Chronic Disease Management: A New Horizon
intervention and improved outcomes. in Medical Research” Volume 9, No 2/2022 Review
Article Malays. j. med. biol. res.
VIII. FUTURE SCOPE
In the future, researchers can try different types of machine [11] Kosarkar, Gopal Sakarkar, Shilpa Gedam (2022), “An
learning methods, like supervised and unsupervised Analytical Perspective on Various Deep Learning
st
techniques, to see which ones work best for predicting Techniques for Deepfake Detection”, 1 International
diseases. This particular research paper can help find models Conference on Artificial Intelligence and Big Data
th
th
that are even more accurate and reliable. Additionally, using Analytics (ICAIBDA), 10 & 11 June 2022, 2456-
larger datasets that include more variety—such as data from 3463, Volume 7, PP. 25-30,
people of different ages, regions, and health conditions—can https://doi.org/10.46335/IJIES.2022.7.8.5
make the model work better for all kinds of patients. By also [12] Usha Kosarkar, Gopal Sakarkar, Shilpa Gedam (2022),
focusing on new ways to measure the model’s performance, “Revealing and Classification of Deepfakes Videos
like checking how well it works in real-life situations, Images using a Customize Convolution Neural
predictions can become more trustworthy and useful for
Network Model”, International Conference on Machine
doctors and patients. th th
Learning and Data Engineering (ICMLDE), 7 & 8
REFERENCES September 2022, 2636-2652, Volume 218, PP. 2636-
[1] Usha Kaushik Kulkarni1, Manjunath B2, Mayur 2652, https://doi.org/10.1016/j.procs.2023.01.237
Hebbar T M3, Meghana M4, Shashank S5, and Tojo [13] Usha Kosarkar, Gopal Sakarkar (2023), “Unmasking
Mathew6 “Chronic Disease Prediction Using Machine Deep Fakes: Advancements, Challenges, and Ethical
Learning” Vol. 10, Issue 6, June 2021 DOI Considerations”, 4 International Conference on
th
10.17148/IJARCCE.2021.10663 Electrical and Electronics Engineering (ICEEE),19 &
th
[2] Kang Adiwijaya, Nur Ghaniaviyanto Ramadhan, Warih 20 August 2023, 978-981-99-8661-3, Volume 1115,
th
Maharani and Alfian Akbar Gozali “Chronic Diseases PP. 249-262, https://doi.org/10.1007/978-981-99-
Prediction Using Machine Learning With Data 8661-3_19
Preprocessing Handling: A Critical review” IEEE [14] Usha Kosarkar, Gopal Sakarkar, Shilpa Gedam (2021),
Access PP(99):1-1: January 2024 “Deepfakes, a threat to society”, International Journal
DOI:10.1109/ACCESS.2024.3406748 of Scientific Research in Science and Technology
[3] Rakibul Islam, Azrin Sultana and Mohammad (IJSRST), 13 October 2021, 2395-602X, Volume 9,
th
Rashedul Islam “A comprehensive review for chronic Issue 6, PP. 1132-1140,
disease prediction using machine learning algorithms” https://ijsrst.com/IJSRST219682
Journal of Electrical Systems and Information [15] Usha Kosarkar, Prachi Sasankar(2021), “ A study for
Technology: July 2024 DOI:10.1186/s43067-024-
Face Recognition using techniques PCA and KNN”,
00150-4
Journal of Computer Engineering (IOSR-JCE), 2278-
[4] Mohamed Elhoseny and Rayan Alanazi “Identification 0661,PP 2-5,
and Prediction of Chronic Diseases Using Machine [16] Usha Kosarkar, Gopal Sakarkar (2024), “Design an
Learning Approach” efficient VARMA LSTM GRU model for identification of
https://doi.org/10.1155/2022/2826127
deep-fake images via dynamic window-based spatio-

IJTSRD | Special Issue on Emerging Trends and Innovations in Web-Based Applications and Technologies Page 145