Image Courtesy of IMBD.

The TV show “House” served as the main source of inspiration for our group’s data science project, HEALTHhOUSE, a machine learning model that predicts most likely diseases based on a pattern of symptoms. The plan for our predictive model is to assist users in identifying potential illnesses more efficiently, mirroring Dr. House and his medical teams' diagnostic prowess.

• Shanara Hawkins @ShanaraTech
• Emmanuel Presley @EmanPresley
• Ivette Reese @Ivette12345
• Jon Unger @Ungernator12

We Collaborated as a group to implement all the major components and competencies of Data Science. On the data engineering side, we began by choosing a topic that would deepend our understanding with developing machine learning models. We decided on Healthcare since we could incorporate the TV series "House" into our slide deck and presentational narrative. Next, we searched through Kaggle for datasets discussing symptoms, diseases, and demographics. Given the limited number of open datasets that included our list of criteria in one file, we were challenged with locating and comparing multiple datasets discussing the same diseases and symptoms. We found two datasets matching the criteria to meet our projects goals. Disease Prediction Using Machine Learning and [Disease Prediction through Symptoms] https://www.kaggle.com/datasets/usamag123/disease-prediction-through-symptoms/code) Finally, we prepocessed and cleaned our datasets, queried the data, built a full-stack web application, linking our machine learning model, Tableau Visualizations, an About Us page, and created an engaging and informative slide deck presentation HEALTHhOUSE Slide Deck Presentation

Data is everywhere. The amount of data points at our disposal for consideration and analysis is expansive, immeasurable, and uniquely complex. Technology has proven to be a powerful tool assisting clinicians in determining a patient’s probability of acquiring specific health conditions and diseases. The likelihood that one will experience either an illness, sickness, or other medical condition is inevitable. With this in mind, our group selected healthcare as our topic of interest to explore how predictive analytics could be used to accurately determine which disease a person would likely have given the symptoms they selected in the algorithm. Data science influences advancements, and innovations, creating meaningful changes based on reliable outcomes that lead to a better quality of life. As progress in machine learning algorithms continues and new technologies emerge, concurrently, we can also ensure improvements in efficacy, validity, and accuracy. Predictive modeling working in tandem with personalized medicine has its advantages such as empowering healthcare practitioners to deliver targeted treatment and interventions that will enhance patient healthcare outcomes and satisfaction. Using tools like HEALTHhOUSE's Disease Discovery Tool would be a wise investment offering quick and easy health checks from the comfort of your home. After all, your health is your wealth! You can access our analytics PDF report, HEALTHhOUSE: A dISEASE Discovery Tool to learn more about the datasets, our ETL process, Machine Learning and Tableau dashboard creation, limitation, bias, Implications, and Works Cited. Stay Healthy!

• Python/Jupyter Notebook
• Pandas Library
• Machine Learning/AI
• Model Helper
• Tableau
• Flask API
• VSCODE
• JSON
• JavaScript
• Plotly and/or Leaflet
• HTML
• JS/CSS

1. Click on this linkto be redirected to our Home page.
2. Next, you'll find the following three titles that serve as additional links to other sections in our project: Machine Learning, Tableau, and About Us.
3. HEALTHhOUSE Machine Learning
   • Here, you can acess our machine learning model titled, HEALTHhOUSE:A DISEASE DISCOVERY TOOL.
   • Instructions on how to use the discovery tool is included below the title.
4. Tableau
   • Here, you will find our data visualizations and dashboard created from the patterns and trends discovered from a detailed examination comparing and contrasting insights uncovered in the datasets
5. About Us: We Are NOT Doctors.
   • Meet each of our group project contributors. Fun Bios and Pics included.

We would like to extend a special shout out to our Professor and our outstanding TA for their invaluable support and guidance in tackling complex webpage coding, database integration, and assisting us with troubleshooting crucial functions for our HEALTHhouse Dashboard, Recommender tool, and Webpages to function appropriately. Their unwavering commitment during our journey as Data Scientists has been nothing short of inspiring. Many thanks to you both!

1. Southern Methodist University Data Science CAPE Instructional Staff
   • Professor: Alexander Booth @ABoothInTheWild
   • Assistant Teaching Professor: Sherhone Grant @SherhoneGrantDS