Stroke Prediction using Optimization and Exploratory Data Analysis

Kaur, Ravneet; Hambarde, Kaustubh; George, Reuben; Hussain, Arwa; Gomkar, Chaitanya; Sonawani, Shilpa

doi:10.1109/iatmsi56455.2022.10119295

Cited by 1 publication

(4 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The Exploratory data analysis on the Stroke Prediction Dataset employed a comprehensive approach to unveil insights into potential stroke risk factors and their predictive significance [19]. The initial step in this analysis involved univariate analysis, which focused on examining individual variables within the dataset to understand their distributions and inherent characteristics [26].…”

Section: Resultsmentioning

confidence: 99%

“…The Exploratory data analysis on the Stroke Prediction Dataset employed a multifaceted approach to uncover insights into stroke risk factors and their potential predictive value [19]. Initially, descriptive statistics were computed to summarize the dataset's numerical and categorical variables, providing a foundational understanding of their distributions and central tendencies [22].…”

Section: Figure 1 Visualization Of Missing Values In the Datasetmentioning

confidence: 99%

“…Exploratory data analysis offers a powerful means of uncovering patterns and relationships within complex datasets, providing valuable insights into disease etiology and epidemiology [18]. Exploratory data analysis systematically explores variables such as hypertension, BMI, cardiovascular disease, and average glucose levels to uncover patterns and relationships contributing to stroke onset [19]. Visualization techniques like histograms, scatter plots, and box plots facilitate the identification of distributions and trends within the data [20].…”

Section: Introductionmentioning

confidence: 99%

“…Visualization techniques like histograms, scatter plots, and box plots facilitate the identification of distributions and trends within the data [20]. Moreover, correlation analysis enables quantification of the relationships between different risk factors and stroke incidence [19].…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Critical Exploratory Data Analysis on Stroke Prediction Dataset

Ariful Furqon,

Najwa,

Zarkasi

et al. 2024

JKT

View full text Add to dashboard Cite

Stroke is a significant global health concern, requiring an in-depth understanding of the complex factors contributing to its occurrence. Age, body mass index (BMI), and average glucose levels are critical factors in stroke etiology. This study employed exploratory data analysis techniques to investigate the relationships between variables in a stroke prediction dataset. The research methodology included (1) dataset description, (2) data preprocessing, (3) exploratory data analysis, and (4) interpretation. Descriptive statistical analysis provided insights into the dataset's composition and variability, while data preprocessing techniques handled missing values and facilitated feature extraction. Based on exploratory data analysis, significant relationships were found between age, hypertension, heart disease, average glucose levels, and stroke. However, BMI showed a less significant role in stroke. These findings contribute to a better understanding of the factors contributing to stroke risk and may aid in developing more effective prevention strategies.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Figure 1 Visualization Of Missing Values In the Datasetmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations