AI-Powered Assistant for Patients with End-Stage Cancer
- GitHub Repository
- Created On
- Updated On
- The AI-Powered Assistant for Patients With End-Stage Cancer application is made to support patients dealing with end-stage cancer. It gives helpful information focusing on managing symptoms, choices for comfort care, help for emotional needs, and planning for the end of life. It utilizes OpenAI's GPT-4 AI model for natural language processing. The program uses the Philter Python library to remove personal information (e.g., Personally Identifiable Information, Protected Health Information) from the chat messages and files users upload.
- Symptom Management Guidance: The assistant provides information on common symptoms experienced in end-stage cancer and suggests non-pharmacological interventions for relief.
- Comfort Care Options: It presents various comfort care options, including palliative care services, to alleviate physical and emotional distress.
- Emotional Support: The assistant offers resources for emotional and psychological support, connecting patients with counseling services, support groups, or providing coping strategies.
- End-of-Life Planning: It assists in the planning process for end-of-life care, discussing advance directives, living wills, and healthcare power of attorney.
- Complexity of Medical Information: While the app aims to simplify information for the patients while retaining accuracy and thoroughness, it may
- Information Accuracy: While the app aims to provide accurate and accessible information, it can sometimes make mistakes and miss nuances.
- Data Privacy: When the authors of the paper "Protected Health Information filter (Philter): accurately and securely de-identifying free-text clinical notes" evaluated the Philter library, it removed 99.4% of PHI in the clinical notes. While impressive, it is not perfect and can sometimes miss edge cases.
The efficacy of the application in assisting end-stage cancer patients relies on the advanced capabilities of the GPT-4 model, which has been trained on a diverse range of texts for comprehensive understanding and generation of human-like text. User feedback and iterative improvements are crucial for enhancing the application's performance.
I'm Venkata Chengalvala, the main developer of this app. As an AI consultant for Health Universe, I port high-quality peer-reviewed AI models helpful to clinicians, patients, and/or researchers to Health Universe's platform. I have a Bachelor of Science in Molecular, Cellular, and Developmental Biology (MCDB) and Computer Science from the University of Michigan-Ann Arbor. During my education, I engaged in medical research, co-authoring a literature review on tumor-derived exosomes, cited by 30+ people so far: https://www.sciencedirect.com/science/article/pii/S2211383521001398.
I developed this app to help end-stage cancer patients make informed decisions about their care, including when to stop treatment, palliative/hospice care options, and symptom management. A key feature of this app is the commitment to user privacy, using the Philter library to deidentify personal information (PHI and PII) within the chat messages.
Your insights and feedback on this app are greatly appreciated. If you have any thoughts or feedback on this app, feel free to leave a comment below.