{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/ef73feb437f4405ab6588a08e113efde\" frameborder=\"0\" width=\"1280\" height=\"960\" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>","height":960,"width":1280,"provider_name":"Loom","provider_url":"https://www.loom.com","thumbnail_height":960,"thumbnail_width":1280,"thumbnail_url":"https://cdn.loom.com/sessions/thumbnails/ef73feb437f4405ab6588a08e113efde-52998c9ac7ad40c0.gif","duration":291.2949,"title":"Cardiovascular Disease Prediction Insights 📊","description":"Hi everyone, in this video, I presented my final project on Cardiovascular Disease Prediction, showcasing a dashboard that visualizes key data from our dataset. I discussed the prevalence of cardiovascular disease (CVD) in relation to factors like blood pressure, age, and BMI, noting that nearly 80% of individuals in high-risk groups have CVD. I also explored the correlation of these factors with CVD status and tested various machine learning models, finding that the one-hot random forest and gradient boosted tree models performed best. I encourage you to watch the entire video for a deeper understanding and to consider how these findings might impact our approach to health assessments. Thank you!"}