Medical-LLM-Medium

**Medical LLM - Medium**

Trained on diverse medical texts, this model excels in summarizing, answering complex clinical questions, and transforming clinical notes, patient encounters, and medical reports into concise summaries.

Its question-answering capability ensures context-specific responses, enhancing decision-making.

For physicians, this tool offers a quick grasp of a patient history, aiding timely decisions.

Optimized for Retrieval-Augmented Generation (RAG), the model integrates with healthcare databases, EHRs, and PubMed to boost response quality.

For enhanced patient care, we offer clinical de-identification for secure data processing, medical speech-to-text for accurate transcriptions, and a medical chatbot to facilitate patient interaction.

**Benchmarks and other characteristics:**
- Achieves 86.31% average on OpenMed benchmarks, surpassing GPT-4 (82.85%) and Med-PaLM-2 (84.08%)
- Medical genetics: 95%; performance in professional medicine: 94.85%
- Clinical knowledge comprehension 89.81% and college biology mastery 93.75%
- Achieves 58.9% average on standard LLM benchmarks
- Balance of specialized medical knowledge and language understanding - 70.93% on GPT4 All benchmark
- Achieves 75.54% performance in medical MCQAs and 79.4% on PubMedQA

**Performance metrics:**

**Medical LLM - Medium** model was evaluated using a chat-based completion workflow across two representative subtasks: Question Answering and Summarization. Both benchmarks were executed against the same dataset of 100 documents, processed in five invocations with 20 documents per request, ensuring consistent workload characteristics across tests.

The experiments were conducted under a **GPU_MEDIUM_8** configuration using four NVIDIA A10 GPUs with a combined memory capacity of 192 GB, and with the model configured for long-context inference (maximum context length tested of 16K tokens; supports 128K ).

Under identical infrastructure and model settings:

- **Question Answering workload** achieved an average of 115 tokens per second
- **Summarization workload** achieved an average of 25 tokens per second

See this table for approximate [memory calculations required](https://nlp.johnsnowlabs.com/docs/en/LLMs/medical_llm#medical-llms-offering) to use this model.

**Additional Model Information**

- [John Snow Labs New Suite of Medical Language Models Advance Industry Benchmarks](https://www.johnsnowlabs.com/john-snow-labs-new-suite-of-medical-language-models-advance-industry-benchmarks/)
- [Measuring the Benefits of Healthcare Specific Large Language Models](https://www.nlpsummit.org/measuring-the-benefits-of-healthcare-specific-large-language-models/)

**How to run this model**:

1. Acquire a John Snow Labs Pay As You Go (PAYG) license from [Sales]([e-mail])
2. Import this listing.
3. See the attached notebook to deploy and use the model.

**Vendor support**
For any assistance, please reach out to [e-mail]

This model comes with optimized CPU and GPU builds. You can select which one to deploy via the notebook.