About Our AI

Fight Health Insurance uses AI to help you draft health insurance appeal letters. Our AI is a tool to assist you — it is not a replacement for professional medical or legal advice. You should always review and customize any generated appeal before submitting it.

How It Works

When you submit a denial or chat with our system, we use fine-tuned medical language models (like MedGemma) to draft an appeal letter tailored to your situation. We run multiple AI models in parallel. Our system also searches PubMed for relevant medical literature to strengthen your appeal with citations.

Training & Data

We generate synthetic training examples from publicly available state appeal decisions from California, and other states, and use those examples to fine-tune our models. These public decisions describe the diagnosis, treatment, denial reason, and outcome of real appeals, but contain no private patient information. No real patient appeal letters are used in training.

We fine-tune using LoRA (Low-Rank Adaptation), an efficient technique that adapts a small fraction of model parameters while preserving the base model's "knowledge." After fine-tuning, we quantize the models to reduce their size and power consumption while maintaining quality. In general generating an appeal uses less power than playing a video game on a modern PC.

We update which base models we use as better open language models become available.

For more details on how we handle your data, see our Terms of Service. You can also request deletion of your data at any time.

Sustainability

We care about the environmental impact of running AI. A few things we do:

• Low-power inference: Our models are quantized so they run on a single GPU, consuming a fraction of the energy that large cloud-hosted models require.
• Solar powered when possible: During the day, our inference servers run on solar power. We aim to shift compute to daylight hours when solar generation is available.
• Efficient serving: We use vLLM, a high-throughput inference engine that maximizes the work done per watt.

Open Source

Fight Health Insurance is mostly open source. You can find our code on GitHub. We believe transparency is especially important when AI is involved in healthcare.

Limitations

AI-generated appeals are a starting point, not a finished product. Our models can make mistakes, hallucinate citations, or miss important details about your specific situation. Always:

• Review the generated appeal carefully before sending it.
• Verify any cited medical literature or regulations.
• Add personal details about your medical history that the AI does not know.
• Consult a healthcare professional or attorney if your situation is complex.