2022
DOI: 10.1016/j.health.2022.100032
|View full text |Cite
|
Sign up to set email alerts
|

A predictive analytics approach for stroke prediction using machine learning and neural networks

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

2
31
0
1

Year Published

2022
2022
2024
2024

Publication Types

Select...
5
3
2

Relationship

1
9

Authors

Journals

citations
Cited by 107 publications
(34 citation statements)
references
References 13 publications
2
31
0
1
Order By: Relevance
“…Furthermore, the models trained on reduced feature set also consumed less computational time i.e only 3.86 iterations per second(it/s) using CVD and 15.52 iterations per second(it/s) using framingham dataset. We have also validated our findings by comparing our work with other published proposals [41,42] where same datasets were used with full feature set and the obtained accuracy results were less or equal to the results that we obtained using reduced feature set. Overall, the experimental results proved that the performance of the ML models increased significantly by using only the relevant features.…”
Section: Classification Results Using Full Feature Setsupporting
confidence: 77%
“…Furthermore, the models trained on reduced feature set also consumed less computational time i.e only 3.86 iterations per second(it/s) using CVD and 15.52 iterations per second(it/s) using framingham dataset. We have also validated our findings by comparing our work with other published proposals [41,42] where same datasets were used with full feature set and the obtained accuracy results were less or equal to the results that we obtained using reduced feature set. Overall, the experimental results proved that the performance of the ML models increased significantly by using only the relevant features.…”
Section: Classification Results Using Full Feature Setsupporting
confidence: 77%
“…As explained in [19], the authors proposed a comprehensive assessment of patient characteristics in the digital health record. They used systematic analysis to look at various features.…”
Section: Literature Reviewmentioning
confidence: 99%
“…Sistem klasifikasi dan diagnosis pada suatu penyakit dengan menggunakan algoritma Jaringan Syaraf Tiruan (JST) sebagai salah satu cabang Artificial Intelligence (AI) direkomendasikan oleh Najeeb Abbas A. dkk. [8], yang melakukan penelitian tentang keandalan JST perambatan balik sebagai salah satu metode klasifikasi dengan tingkat akurasi tinggi [9].…”
Section: Tinjauan Literaturunclassified