All Case Studies
Healthcare

Ping An

China's largest insurer built a 440M-user AI healthcare platform achieving 98% diagnostic accuracy

AI Transformation ProgramAI Pilot ProgramAI Governance Retainer
440M+
Registered Users
~98%
AI Diagnostic Accuracy
52%
Cost Reduction

The Challenge

Ping An, China's largest insurer and a Fortune Global 500 company, recognized that China's healthcare system suffered from a profound urban-rural access divide. While tier-one cities hosted world-class hospitals, rural communities often lacked basic diagnostic capabilities. The company sought to build an AI-powered digital healthcare ecosystem that could bridge this gap, extending specialist-calibre clinical decision support to hundreds of millions of users across the country's vast geographic and socioeconomic spectrum.

Building such a platform required overcoming significant technical and regulatory challenges. Heterogeneous data quality across China's fragmented hospital information systems, with varying EHR standards and diagnostic coding practices, complicated the construction of nationally representative training datasets. The National Health Commission's evolving medical-AI governance framework required that any AI-assisted diagnostic recommendation carry explicit disclaimers and maintain complete audit trails linking algorithmic outputs to licensed physician confirmations, demanding continuous adaptation of validation and deployment protocols.

The Approach

Ping An built Good Doctor (Ping An Health), an AI-powered telehealth platform that connects patients with AI-augmented clinical decision support and remote specialist consultation. The platform's proprietary medical AI model, Ping An Medical Master, was trained on data from over 1.44 billion cumulative consultations and six world-leading medical databases, enabling it to cover thousands of disease conditions with multi-modal analysis of symptoms, lab results, medical imaging, and clinical history.

The platform deployed a multi-modal triage engine combining natural-language symptom descriptions, medical image analysis, and structured vital-sign inputs to generate diagnostic hypotheses ranked by clinical urgency. Phased rollout commenced with dermatological and ophthalmological conditions where image-based assessment achieved high specialist-concordance rates, building clinician trust before expanding to more complex differential-diagnosis scenarios. A comprehensive service network was established covering 50,000 in-house and contracted doctors across 29 specialties, linking 105,000 health service providers, 235,000 pharmacies, and 4,000 hospitals.

In 2025, Ping An launched the Ping An Xin Yi AI Doctor Assistant, a generative AI and digital human-powered service providing 24/7 access to AI-assisted medical consultations. This system ensures every AI-generated recommendation undergoes real-time review by a licensed physician, maintaining clinical safety while dramatically improving accessibility. AI integration reduced average service costs per family doctor user by approximately 52% while improving operational efficiency by roughly 50%, enabling the platform to scale affordably across underserved regions.

Results

440M+
Registered Users
Over 440 million registered users as of mid-2022, making it the world's largest digital healthcare platform (Ping An Good Doctor company filings)
~98%
AI Diagnostic Accuracy
AI-assisted consultations achieved approximately 98% accuracy rate, trained on data from 1.44 billion cumulative consultations (H1 2025 interim results)
52%
Cost Reduction
AI integration reduced average service cost per family doctor user by approximately 52% while improving operational efficiency by ~50% (H1 2025 interim results)

This is an industry case study based on publicly available information. Ping An is not a Pertama Partners client.

Want results like these for your organization?

We help enterprises across Southeast Asia design and deliver AI transformation programs. Let’s talk about what’s possible for your team.