Ddxplus: Synthetic Patient Data for Medical Symptom Detection

A large-scale dataset for Automatic Symptom Detection (ASD) and Automatic Diagnosis (AD) systems in the medical domain. Patients are synthesized using a proprietary medical knowledge base and a commercial rule-based AD system, characterized by socio-demographic data, a pathology, and related symptoms and antecedents. The dataset was released by aai530-group6 on Hugging Face in January 2024.

Use Cases

• Training models for Automatic Symptom Detection (ASD) based on synthesized patient symptom profiles.
• Developing Automatic Diagnosis (AD) systems based on rule-synthesized patient pathology data.
• Benchmarking clinical AI systems using synthetic patient socio-demographic and medical history data.

Strengths

• Dataset is described as 'large-scale', suggesting substantial size.
• Patients are synthesized using a proprietary medical knowledge base, implying structured medical logic.
• Includes multiple patient characteristics: socio-demographic data, pathology, symptoms, and antecedents.

Limitations

• Row count, column details, and file formats are unknown, limiting suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• Data is synthetic, which may not fully capture the complexity and noise of real-world clinical data.

Provenance

Source

Synthesized using a proprietary medical knowledge base and a commercial rule-based AD system.

Collection Method

Patients were synthesized, not collected from real-world sources.

Freshness

Last updated 2024-01-22 03:48:18.