Our AI Safety and Security Process

Introduction

In today’s fast-paced healthcare environment, clinicians are overwhelmed with extensive patient charts- some can be as long as Hamlet (over 30,000 words).  The sheer volume of information makes it challenging to focus on the most critical and pertinent information during patient encounters. Pieces distills and summarizes this information, filling in the gaps for physicians and providing more accurate data.
‍
Ensuring the safety and reliability of these AI-generated summaries is a huge responsibility that we at Pieces take very seriously. We’ve been diligently developing our Pieces Classification Framework for Hallucinatory Error for years to tackle this issue head-on, and are eager to share more in this technical white paper.

Pieces Classification Framework for Hallucinatory Error

While Large Language Models (LLMs) are excellent at summarizing large amounts of data, they come with limitations – most notably, the potential for “hallucinations,” where the AI can generate inaccurate or misleading information. To address this, Pieces developed a risk classification framework to categorize hallucinations by severity.
‍
In this paper, we outline our pioneering classification framework, the “Pieces Framework,” the methodology behind it, and how we mitigate hallucination risks to ensure AI reliably supports healthcare providers.

SafeRead: Our patented clinical document review system

SafeRead is a patented platform designed for Pieces clinicians to review AI-generated content. Our approach combines adversarial AI models with a scalable human-in-the-loop process to monitor for bias, hallucinations, omissions, and quality.