Build Your Own

LLM agnostic platform.
‍Unmatched clinical reasoning capabilities.

Try the Playground
Try the Playground
Contact Sales

Mendel is the first AI platform designed for clinical data and clinical reasoning.

This is today's AI stack: LLMs

  • Pre-trained LLM on proprietary clinical data
  • RAG (retrieval augmented generation)
  • Knowledge graphs
LLM + knowledge graph

The Mendel platform

Designed for the complexity of today's precision medicine
Horizontal stack of LLM + Hypergraph

Pre-trained LLM

Trained on the world’s largest corpus of labeled clinical data

Clinical Knowledge Hypergraph

Leverages a proprietary ontology and architecture to represent the complexity for precision medicine

Computation engine

That can traverse enterprise scale hypergraph in milliseconds

Superior. Proven.

Our neurosymbolic approach provides unparalleled clinical reasoning capabilities with exceptional economies of scale, delivering trustworthy answers at a scope that current solutions can't achieve.
Table of comparing Hypercube, ChatGPT4, and LLAMA on F1, Processing Time, and ~ Cost Per Query.
F1
Processing Time
~ Cost per Query
Hypercube
70.36%
12 milliseconds
$0.01
Chat GPT4
40.54%
4.38 hours
$128
LLAMA-2
34.53%
7.02 hours
$9.30

Examples of Custom Creations with Hypercube

EMR to EDC icon
EMR to EDC
Site identification icon
Site-identification
UI screen with patient data icon. Notification bell at the top.
Commercial Alerts
Custom NLP & LLM icon
Custom NLP & LLM
Revolutionizing clinical data with hypercube
Unstructured data icon

Unravel unstructured data

Mendel platform couples the Hypergraph with a constellation of language models pre-trained on 100s of millions of clinical records labeled by clinical experts. It performs tasks like:

  • Optical character recognition

  • Document classification

  • Natural language processing

Hypercube icon

Reasoning ready copilots

The platform comes with pre-built copilots for complex tasks like cohort retrieval, chart reviews, and more. It also enables data teams at life sciences to design their own applications, leveraging the most advanced clinical reasoning capabilities offered by Mendel’s platform.

LLM icon

LLM agnostic. Turn any LLM into a clinically smart LLM.

You can leverage Mendel's ready-to-use constellations of pre-trained models right out of the box. Alternatively, the platform supports a diverse array of large language models, including Anthropic's Claude, OpenAI's GPT-3.5 and GPT-4, as well as open-source models like Meta's LLaMA and Mistral's Mixtral.

Case Studies and Publications

Transforming Unstructured Pathology Data
Read
→
Mendel Unveils Groundbreaking Neuro-Symbolic AI System Outperforming GPT-4 for Automatic Cohort Retreival in New Study
Read
→
Improving Clinical Trial Participant Prescreening With Artificial Intelligence (AI): A Comparison of the Results of AI Assisted vs Standard Methods in 3 Oncology Trials
Read
→
View Success Stories

Got a question?

What makes your search actually work?
We combine large language modeling with a proprietary hypergraph that captures the complexity of precision medicine. This setup achieves a near-physician-level understanding of data, with advanced algorithms enabling fast and cost-effective hypergraph traversal.
What is a Hypergraph vs. a Knowledge graph?
A hypergraph is a generalization of a graph, allowing edges to connect any number of vertices. Knowledge graphs are typically based on simple graph, limiting the representation of complex relationships.
Why can’t I build my own Hypergraph?
Building a clinical Hypergraph requires extensive domain expertise, large-scale data curation, and complex algorithmic development. It is a time-consuming and resource-intensive process that most organizations may find challenging to undertake independently.
Are hypergraphs slow?
Not necessarily. Our Hypergraph technology utilizes innovative algorithms and data structures specifically designed for efficient hypergraph analysis, enabling quick traversal and querying even with a large number of nodes and relationships.
Who are the experts behind the Hypergraph?
Our Hypergraph is developed by a team of AI scientists and clinical experts who have worked together for years to curate knowledge and build a scalable solution tailored to the unique challenges of the clinical domain.
What ontology are you using?
We have developed a proprietary ontology called the “Generative Ontology” that combines principles of generative grammar and ontology to create a scalable and adaptable system for modeling the clinical domain.
Can I trust the logic?
Yes, our Hypergraph is expert-curated and open, allowing clinical teams to audit the logic. The underlying language models are trained on actual medical data and records, not just internet data.
Is this a rule-based system?
No, our platform combines both symbolic reasoning (through the Hypergraph) and machine learning (through language models) to achieve a more comprehensive and flexible approach to clinical reasoning, going beyond traditional rule-based systems.
View All FAQs

Get started with the
Mendel platform today

Try the Playground
Contact Sales