Skip to content

La1xuan/HealAI_MacHack2023

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

42 Commits
 
 
 
 
 
 
 
 

Repository files navigation

🫀HealAI (MacHacks 2023)

Demo Video

The AI-powered tool that our team has created is designed to help patients better understand their physical injuries and take the necessary treatments to maintain their well-being. The tool works by allowing patients to input their symptoms into the system, which then uses advanced algorithms to analyze the information and provide recommendations for treatments based on those symptoms. This can help patients quickly and easily identify any potential injuries and take steps to address them, leading to better health outcomes and improved quality of life.

How we built it

The tool was built using SKLearn trained on a large dataset of physical injuries and their corresponding treatments. We used classification, model selection and preprocessing techniques to understand and analyze the symptoms entered by the patient and match them with relevant treatments. We also used TKinter to create a desktop application that also serves as the graphical user interface.

Challenges we ran into

  • Reaching 80% accuracy was our most difficult challenge
  • Preprocessing the data to remove any irrelevant information and standardize the symptom descriptions was critical and challenging to implement for the model's performance.
  • One of the challenges was finding a high-quality dataset that accurately reflected the relationship between physical injuries and treatments.

Accomplishments that we're proud of

We are proud of developing a tool that can quickly and accurately provide patients with relevant treatments based on their symptoms.

What we learned

We gained valuable experience in AI and machine learning, particularly in regards to NLP tasks and using machine learning models to classify text data.

What's next for HealAI

In the future, we hope to expand the tool's capabilities by adding additional symptoms and treatments, and incorporating more advanced NLP techniques to improve the model's accuracy and ability to understand more complex symptom descriptions. We also plan to integrate the tool into existing healthcare systems to make it even more accessible to patients.

References:

Machine Learning in Healthcare:

https://pubmed.ncbi.nlm.nih.gov/35273459/

https://github.com/ https://jupyter.org/try

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Languages