| Disease | Task | Open-source Model | Accuracy Before Fine-tuning | Accuracy After Fine-tuning |
|---|---|---|---|---|
| Alzheimer disease | Predict Alzheimer disease | Llama3.1-8B | >90% | >90% |
| Frontotemporal dementia | Predict frontotemporal dementia | Llama3.1-8B | >90% | >90% |
| Lewy body dementia | Predict Lewy body dementia | Llama3.1-8B | >30% | >90% |
| Creutzfeldt-Jakob disease | Predict Creutzfeldt-Jakob disease | Llama3.1-8B | >50% | >90% |
| Mild cognitive impairment | Predict mild cognitive impairment | Llama3.1-8B | >90% | >90% |
| Ischemic stroke | Predict ischemic stroke | Llama3.1-8B | >80% | >90% |
| Parkinson disease | Predict Parkinson disease | Llama3.1-8B | >90% | >90% |
| Lung cancer | Predict lung cancer | Llama3.1-8B | >80% | >90% |
| Breast cancer | Predict breast cancer | Llama3.1-8B | >90% | >90% |
To eliminate the upfront development cost barrier for clinical teams, we have fine-tuned the smaller Llama3.1-8B (8 billion parameters) model for an expanding list of diseases and made them available for free. The model's baseline prediction accuracy—prior to fine-tuning—ranges widely, from 20% to 100%. However, after fine-tuning with synthetic patient data, the fine-tuned Llama3.1-8B model consistently achieves over 90% accuracy in predicting target diseases across various patient cases. Accuracy is calculated based on the top-2 predicted disease scores using synthetic patient datasets.
We invite clinical teams to evaluate these pre-clinically validated LLMs in real-world clinical settings and contribute to publishing real-world evidence on the responsible use of generative AI to improve care delivery and patient outcomes. Please feel free to reach out with any questions about using the LLMs in GenAI research (see a list of ideas here).
If our pre-built fine-tuned LLMs for diseases or healthcare tasks do not meet your specific needs, please contact us. We can create custom fine-tuned Llama3.1-8B models tailored to your requirements for free. For well-funded clinical teams, the mid-size Llama3.1-70B model (70 billion parameters) offers another option for high-accuracy fine-tuning.
To remove technical barriers for clinical teams, our free fine-tuned LLMs are supported by technical services for effective deployment, operation, and further fine-tuning with your local patient data in doctor-controlled environments. Through this cross-disciplinary collaboration, you can conduct LLM clinical evaluation studies more efficiently and publish papers sooner, without worrying about the complexities of fine-tuning your LLMs. The Llama3.1-8B model can run and train on a single GPU server, making it an affordable option for most research projects. This ensures that every clinical team has the opportunity to conduct LLM studies and contribute to advancing predictive healthcare. Additionally, we can assist you in developing GenAI research plans and publishing findings in peer-reviewed journals. Our LLM Operation Services are available via an annual subscription. For collaboration details, please contact us (login required).