This page demonstrates an experimental AI Agent interacting with a symbolic expert system implemented in Prolog.
This page is not a medical user interface and is not intended for clinicians to enter symptoms. The real expert system and its UI are located at: http://64.225.98.129:9060/
Reading the documentation and exploring the UI at port 9060 is recommended before using this sandbox.
Port 9060 hosts the real expert system. The system is implemented entirely in Prolog.
Disease descriptions can be explored here: http://64.225.98.129:9060/review
The current page (port 9061) is only a sandbox demonstrating how an AI agent could interact with the expert system.
This sandbox does not contain the expert system.
Instead, it simulates how external software (for example a hospital application) might send a clinical note to an agent that interacts with the expert system.
Clinical note
(simulated hospital software)
↓
Agent (port 9061)
phenotype normalization
↓
MCP request
task: diagnose
↓
Prolog reasoning engine
(port 9060)
↓
Candidate rare diseases
Phenotype normalization is one of the major challenges in medical informatics.
Hospitals typically rely on standardized terminology systems such as:
Mapping clinical text to standardized phenotypes is a complex task and cannot be fully solved in a small demonstration system.
The agent returns a structured JSON output intended for software systems.
{
"phenotypes": [
"Myopia",
"Hyperventilation"
],
"candidate_diseases": [
"biotinidase_deficiency",
"fructose_1_6_bisphosphatase_deficiency",
"holocarboxylase_synthetase_deficiency",
"retinal_ciliopathy_due_to_mutation_in_usher_gene"
]
}
The form below simulates a clinical note sent by external software. For example, entering "Patient reports difficulty seeing distant objects and fast breathing" will generate the machine-readable output shown above.