Belgian Health Data Agency’s Post

I'm excited to share another step in my training plan to combine my knowledge of medicine with the amazing world of data! 🌟📊 The intersection of health and data offers incredible opportunities to improve patient outcomes and advance medical research. The adventure is just beginning, and I can't wait to see where this journey takes me! 🚀💡 #Medicine #DataScience #Training #BigData

🚀 Second Task: Disease Prediction from Medical Data 🏥 In my ongoing journey at CodeAlpha , I had the opportunity to work on disease prediction using medical records! 📊 This project involved applying different classification algorithms, performing essential steps like data cleaning, data transformation, and exploring patterns within medical datasets. It has been an amazing experience in predictive analytics, using data to support healthcare decisions and help improve patient outcomes! Github: https://lnkd.in/enCChaQ4 #MachineLearning #Healthcare #DataScience #CodeAlpha

🚀 Excited to share that I have participated in the one day WiDS Datathon 2024 challenge “Equity in Healthcare” organized by the Department of Data Science and Analytics (DSA), Central University of Rajasthan in collaboration with Women in Data Science Community (WiDS) . We trained multiple machine learning models to predict patient metastatic diagnosis periods, refining strategies in handling messy real-world healthcare data to drive actionable insights and advance impactful healthcare outcomes." My experience in the Datathon honed my skills in handling messy real-world data, where I employed various techniques to address data quality issues effectively. Through this process, we gained valuable insights into data preprocessing, feature engineering, model selection, and ensemble techniques, contributing to our understanding and skills in predictive analytics and data science. #Wids2024

A while ago, I conducted an internal research project with Alane Miguelis Falcão Magalhães and Priscila Rubim intending to validate the accuracy of a Two-Sample T-Test in Qlik, comparing it with the medical research gold standard: R. We have done this for T and other hypothesis testing but we prioritized to formally write about our findings in T-Test. Recently, we decided to make this document available to the whole community. I will also mention this during my session at #QlikConnect You can download it on the link below: https://lnkd.in/eFkcbK58 #Qlik #DataScience

Want to learn more about the LOAD Model and Data Journey Models? Sign up to our online learning platform and get free, instant access to "Assessing the socio-technical landscape for change". https://bit.ly/48rbByY #HDRFutures #DataScience #HealthData #HealthResearch

Hello Connections! Completed my third task given by CodSoft. This was a very unique task for me. Task: Iris flower Classification model 🌷 Objectives of task: To train a machine learning model that can learn measurements and accurately classify the Iris flowers into their respective species. Here you can view task details: https://lnkd.in/ena7qZBX CodSoft #datascience #internshipproject

Thrilled to announce that our paper, "Design and Assessment of Representative Hybrid Clinical Trials using Health Recommender System," has been accepted to HealthRecSys @ ACM RecSys 2024! 🎉 Building on the success of our presentations at AMIA 2023 and the Best Poster Award at SCT 2023, this paper utilizes machine learning and causal inference to develop health recommender systems that support clinical trial design. Our ongoing research also explores how LLMs can further aid in optimizing these trial design decisions. Stay tuned for more updates, including access to the paper and code! #HealthRecSys2024 #ACMRecSys2024 #ClinicalTrials #MachineLearning #LLMs #HealthAI

🚀 Thrilled to share my latest project: using #MachineLearning to predict #Diabetes! 📊💉 We dug into a big Diabetes dataset and used ML to forecast outcomes accurately. From sorting data to training models, it's been an amazing journey! ✨ Big thanks to InternPe for the chance! 🙌 Check out our video below! Excited to hear your thoughts! 😀 #DiabetesPrediction #HealthTech #DataScience #AIinHealthcare #MLModels #TechForGood

Learning to analyze MEPS by examples The MEPS datasets from the Agency for Healthcare Research and Quality (AHRQ) were among the most challenging datasets to ingest. There are thousands of variables for each year, and aligning those variables across the years took some effort. Ingesting is one thing, but learning to analyze is another level. Luckily, AHRQ published various examples to learn from on its GitHub [1]. So, I picked one example to validate if my data ingestion worked okay and learn about the data [1]. Let me share one tip. I like to learn by example. Rather than reading tutorials or watching videos, I learn fastest by trying examples. Here are my steps. 1. Pick one example. 2. Don't copy and paste exactly. Tweak the original a little bit and then paste it. 3. Run it - usually, it fails because I tweaked it a bit. 4. Debug it. 5. Repeat till it runs. The original example [1] used 2019 data to examine the number of people who did not receive treatment because they couldn't afford it. Since I ingested multiple years, I changed the example to visualize the trends. The chart below shows my output! I am showing three trends: - Couldn't afford medical care (blue) - Couldn't afford dental care (yellow) - Couldn't afford prescription meds (green) The good news is that these trends are going down! I plan to try a few more examples like this. What do you think of my learning approach? How do you learn new datasets, systems, or languages? I like to tweak and try things - having examples helps me a lot! [1] https://lnkd.in/eJVvuccX #learning #education #opendata #surveydata #meps #healthcareanalytics #healthcaretechnology

Unlock the power of data with LearnAtRISE. Explore courses and gain insights to shape a better world. Enquire Now! #DataScience #LearnAtRISE #Insights