Sanad-1.0

Clinical AI Assistant for Medical Diagnosis, Transcription, and Arabic Medical Support

Sanad-1.0 is a fine-tuned clinical AI model built on Google's MedGemma-27B-text-it. Purpose-built for Mediscribe, it provides clinical transcription (dialogue to SOAP notes), primary diagnosis extraction with ICD-10 coding, and ranked differential diagnosis generation. Trained on 551,491 curated medical examples across 15 specialized datasets using a 4-stage progressive QLoRA pipeline.

Specifications

Architecture

 1  Stage 1: Transcription (152,930 examples) - Dialogue to SOAP notes, clinical documentation
 2  Stage 2: Diagnosis (61,920 examples) - Clinical knowledge, diagnostic reasoning, ICD-10
 3  Stage 3: Differential Diagnosis (129,696 examples) - Ranked DDx with chain-of-thought reasoning
 4  Stage 4: Arabic + Reinforcement (179,373 examples) - Bilingual support, existing clinical data

Features

• Clinical transcription: converts doctor-patient conversations into structured SOAP notes and discharge summaries
• Primary diagnosis extraction with ICD-10 classification and clinical reasoning
• Ranked differential diagnosis with probability assessments and reasoning chains
• Chain-of-thought reasoning with transparent <thinking> traces
• Full bilingual capability (English + Arabic) for clinical consultations
• USMLE-level knowledge across 21+ medical specialties
• Structured JSON output for EHR integration
• 128K context window for complete clinical transcripts and multi-visit patient histories
• 4-stage progressive fine-tuning with decreasing learning rates to prevent catastrophic forgetting
• 87.7% MedQA accuracy, surpassing models with 2.5x more parameters

Benchmarks