Get in Touch
We can help with Generative AI Integrations, Solutions Architecture, DevOps, Healthcare Wellness Apps
Send emailFrequently Asked Questions
The Start and Q&A chats and wellness/education reports are powered by an AI model from Anthropic called Claude Sonnet 4.5. This model is guided by a written set of ethical principles, ensuring safe and reliable interactions. This approach emphasizes transparency, helpfulness, and harmlessness. The data stored is both HIPAA-and-GDPR-compliant. That means personal identifiable information (PII) is removed, stored, and compartmented separately from sensitive medical data.
The heartcheckapp has been designed so that the input (prompts) are strickly controlled to ensure the model's ethical use and accuracy.
System prompts (guardrails) ensure that the model's responses remain within the limited scope of the app's wellness/education healthcare mandate.
The heartcheckapp is compliant with the evolving landscape of AI regulations, including the General Data Protection Regulation (GDPR) compliance guidelines and the EU AI Act.
The heartcheckapp uses Amazon Comprehend Medical, a HIPAA-eligible natural language processing (NLP) service that leverages machine learning, to quickly and accurately extract protected health information (PHI) from uploaded medical reports. The PHI from uploaded documents is anonymized and stored securely and separately from the medical data.
In addition, Anthropic's Sonnet Claude 4.5 extracts Personal Identifiable Information (PII) and PHI from wellnesss reports.
Yes. The start chat asks the customer to send a greeting in their prefered language, and responds by sending a welcome message in that language. The agents continue to communicate in this language as the customer transitions to the question and answer chat.
The wellness report is also sent in the customer's preferred language.
No. the heartcheckapp does NOT provide clinical risk assessments or offer treatment recommendations. Instead, it produces a wellness report that summarizes information the customer provides during chat sessions and via document uploads.
The following wellness banner appears at the top of every chat: "Educational only — not a medical device. This chat does not provide diagnosis, treatment, or medical decision support. If you have symptoms such as chest pain, trouble breathing, severe weakness, or confusion, call emergency services 112 (EU), 911 (USA) now or seek urgent care. For personal medical questions, contact a licensed clinician."