*Disclaimer: All diagnosis and Recommendations provided are for patient's reference. In no way does this software prescribe medicines. Please reach out to a healthcare professional for treatment.
DrugPulse is a groundbreaking initiative that applies machine learning techniques to leverage patient reviews and various attributes for evaluating the effectiveness of different drugs in the treatment of specific medical conditions and recommend the user to take which drugs based on the several factors. This software seeks to harness the vast reservoir of unstructured patient experiences to provide nuanced and data-driven evaluations of pharmaceutical products, thereby revolutionizing decision-making in the healthcare sector.
We were shortlisted among the top 50 projects across the CS Department at the University of Windsor and showcased our innovation to a panel of judges from various renowned industry leaders at the CS Demo Day 2023.
Key-Feature Breakdown:
◦ SYMPTOM-TO-DRUG INSIGHTS:
Seamlessly integrates your input of what you're feeling, predicts potential medical conditions, validates with accuracy, and provides valuable insights into effective medicines based on real-world experiences.
◦ REVIEW-DRIVEN DRUG RECOMMENDATIONS:
Provide your current medical condition and receive tailored drug recommendations based on insightful reviews. A smarter way to explore and understand your treatment options with Review-Driven Drug Recommendations.
◦ DRUG INSIGHT HUB:
Provide the name of the drug you are taking, and unlock a wealth of details about the medication. Gain comprehensive insights into your prescribed drug, empowering you with knowledge and understanding about its uses, effects, and more.
Technologies Used:
◦ pandas, numpy, Python, Plotly, BeautifulSoup
◦ Sklearn, Tensorflow, Pytorch and several algorithms including XGBoost.
◦ mean_squared_error, r2_score, accuracy_score, confusion_matrix,
plot_confusion_matrix
◦ Flask
◦ HTML, CSS, SCSS
