A predictive analytics approach for stroke prediction using machine learning and neural networks
The negative impact of stroke in society has led to concerted efforts to improve the management and diagnosis of stroke. With an increased synergy between technology and medical diagnosis, caregivers create opportunities for better patient management by systematically mining and archiving the patien...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2022-11-01
|
| Series: | Healthcare Analytics |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2772442522000090 |
| _version_ | 1811187208704491520 |
|---|---|
| author | Soumyabrata Dev Hewei Wang Chidozie Shamrock Nwosu Nishtha Jain Bharadwaj Veeravalli Deepu John |
| author_facet | Soumyabrata Dev Hewei Wang Chidozie Shamrock Nwosu Nishtha Jain Bharadwaj Veeravalli Deepu John |
| author_sort | Soumyabrata Dev |
| collection | DOAJ |
| description | The negative impact of stroke in society has led to concerted efforts to improve the management and diagnosis of stroke. With an increased synergy between technology and medical diagnosis, caregivers create opportunities for better patient management by systematically mining and archiving the patients’ medical records. Therefore, it is vital to study the interdependency of these risk factors in patients’ health records and understand their relative contribution to stroke prediction. This paper systematically analyzes the various factors in electronic health records for effective stroke prediction. Using various statistical techniques and principal component analysis, we identify the most important factors for stroke prediction. We conclude that age, heart disease, average glucose level, and hypertension are the most important factors for detecting stroke in patients. Furthermore, a perceptron neural network using these four attributes provides the highest accuracy rate and lowest miss rate compared to using all available input features and other benchmarking algorithms. As the dataset is highly imbalanced concerning the occurrence of stroke, we report our results on a balanced dataset created via sub-sampling techniques. |
| first_indexed | 2024-04-11T13:58:16Z |
| format | Article |
| id | doaj.art-9c7f9d41aa0d4cc8b47b2ea0bf706c21 |
| institution | Directory Open Access Journal |
| issn | 2772-4425 |
| language | English |
| last_indexed | 2024-04-11T13:58:16Z |
| publishDate | 2022-11-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Healthcare Analytics |
| spelling | doaj.art-9c7f9d41aa0d4cc8b47b2ea0bf706c212022-12-22T04:20:11ZengElsevierHealthcare Analytics2772-44252022-11-012100032A predictive analytics approach for stroke prediction using machine learning and neural networksSoumyabrata Dev0Hewei Wang1Chidozie Shamrock Nwosu2Nishtha Jain3Bharadwaj Veeravalli4Deepu John5ADAPT SFI Research Centre, Dublin, Ireland; School of Computer Science, University College Dublin, Ireland; Corresponding author at: School of Computer Science, University College Dublin, Ireland.Beijing University of Technology, Beijing, China; Beijing-Dublin International College, Beijing, ChinaNational College of Ireland, Dublin, IrelandADAPT SFI Research Centre, Dublin, IrelandDepartment of Electrical and Computer Engineering, National University of Singapore, SingaporeSchool of Electrical and Electronic Engineering, University College Dublin, IrelandThe negative impact of stroke in society has led to concerted efforts to improve the management and diagnosis of stroke. With an increased synergy between technology and medical diagnosis, caregivers create opportunities for better patient management by systematically mining and archiving the patients’ medical records. Therefore, it is vital to study the interdependency of these risk factors in patients’ health records and understand their relative contribution to stroke prediction. This paper systematically analyzes the various factors in electronic health records for effective stroke prediction. Using various statistical techniques and principal component analysis, we identify the most important factors for stroke prediction. We conclude that age, heart disease, average glucose level, and hypertension are the most important factors for detecting stroke in patients. Furthermore, a perceptron neural network using these four attributes provides the highest accuracy rate and lowest miss rate compared to using all available input features and other benchmarking algorithms. As the dataset is highly imbalanced concerning the occurrence of stroke, we report our results on a balanced dataset created via sub-sampling techniques.http://www.sciencedirect.com/science/article/pii/S2772442522000090predictive analyticsmachine learningneural networkelectronic health recordsstroke |
| spellingShingle | Soumyabrata Dev Hewei Wang Chidozie Shamrock Nwosu Nishtha Jain Bharadwaj Veeravalli Deepu John A predictive analytics approach for stroke prediction using machine learning and neural networks Healthcare Analytics predictive analytics machine learning neural network electronic health records stroke |
| title | A predictive analytics approach for stroke prediction using machine learning and neural networks |
| title_full | A predictive analytics approach for stroke prediction using machine learning and neural networks |
| title_fullStr | A predictive analytics approach for stroke prediction using machine learning and neural networks |
| title_full_unstemmed | A predictive analytics approach for stroke prediction using machine learning and neural networks |
| title_short | A predictive analytics approach for stroke prediction using machine learning and neural networks |
| title_sort | predictive analytics approach for stroke prediction using machine learning and neural networks |
| topic | predictive analytics machine learning neural network electronic health records stroke |
| url | http://www.sciencedirect.com/science/article/pii/S2772442522000090 |
| work_keys_str_mv | AT soumyabratadev apredictiveanalyticsapproachforstrokepredictionusingmachinelearningandneuralnetworks AT heweiwang apredictiveanalyticsapproachforstrokepredictionusingmachinelearningandneuralnetworks AT chidozieshamrocknwosu apredictiveanalyticsapproachforstrokepredictionusingmachinelearningandneuralnetworks AT nishthajain apredictiveanalyticsapproachforstrokepredictionusingmachinelearningandneuralnetworks AT bharadwajveeravalli apredictiveanalyticsapproachforstrokepredictionusingmachinelearningandneuralnetworks AT deepujohn apredictiveanalyticsapproachforstrokepredictionusingmachinelearningandneuralnetworks AT soumyabratadev predictiveanalyticsapproachforstrokepredictionusingmachinelearningandneuralnetworks AT heweiwang predictiveanalyticsapproachforstrokepredictionusingmachinelearningandneuralnetworks AT chidozieshamrocknwosu predictiveanalyticsapproachforstrokepredictionusingmachinelearningandneuralnetworks AT nishthajain predictiveanalyticsapproachforstrokepredictionusingmachinelearningandneuralnetworks AT bharadwajveeravalli predictiveanalyticsapproachforstrokepredictionusingmachinelearningandneuralnetworks AT deepujohn predictiveanalyticsapproachforstrokepredictionusingmachinelearningandneuralnetworks |