• Pieces self-drafted more than 1 million inpatient clinical summaries in real-time with a very low hallucination rate of <.001
• This latest milestone is one of many industry firsts for the healthcare AI firm
• The AI system is currently in use by doctors, nurses, and case managers across a range of disciplines with time savings from 30 minutes to 2 hours per user per shift

DALLAS, Aug. 9, 2023 /PRNewswire/ — Pieces Technologies Inc., a healthcare AI firm based in Dallas, announced today that its enterprise AI software for hospitals, Pieces, has generated more than 1 million autonomously written clinical summaries which have been used broadly in real-world inpatient clinical environments. The Pieces “working summary” was generated in real-time for more than 72,000 hospitalized patients across a range of clinical disciplines as diverse as internal medicine and surgical subspecialties, organ transplantation, multi-specialty ICUs, labor and delivery, and pediatrics. Pieces reached the milestone within 7 months of going live, and with an industry leading “severe hallucination rate” of less than 0.1%. In contrast, some studies have reported that as many as 10% of patient medical records contain serious factual errors. Four years in the making, Pieces employs a combination of contextual modeling, collaborative and adversarial AI, human-in-the-loop supervision and automated clinical prompt engineering to achieve the low hallucination rate, which it contractually guarantees through its Pieces SafeRead program.

“The Pieces system is remarkable and really showcases the power of AI for real world healthcare” says Dr. Nicholas S. Desai, Chief Medical Officer & Chief Quality Officer, Houston Methodist Sugar Land. “This has not been an overnight development. The Pieces team iterated and customized their AI in response to our clinical and administrative feedback, and the response from our users on the ground has been exceptional, and is further reinforced by the low percentage of edits the clinicians have made to these automated bespoke AI generated clinical working summaries. This is just scratching the surface of what Pieces’ clinical generative AI tools will help us accomplish here at Houston Methodist to maximize provider and staff efficiency while aiding in providing operational transparency on the patient’s hospital journey.”

The Pieces working summary and associated clinical predictive models are currently being used by doctors, nurses, care managers, and administrators in real-world, live production inpatient environments for clinical and case management handoffs, multidisciplinary rounds, discharge planning, and hospital-wide efforts to reduce excess length of stay and readmission rates. The software will soon go-live for pediatric hospital environments. Separately, Pieces automated clinical documentation improvement and 3-way patient communication will be released later this year. Pieces customizes the Generative AI output according to customer specific needs.

“Self-drafting 1 million summaries that doctors and nurses can – and have – relied upon in real-time is perhaps Pieces’ most significant clinical and technical accomplishment in 7 years” says Ruben Amarasingham, MD, CEO of Pieces. “What I’m most proud of is the exceedingly low error rate, which itself is improving rapidly. We are on track to achieve a severe hallucination rate of less than 1 error in 1 million summaries generated.”

This AI milestone, the first in the United States for live inpatient clinical environments, demonstrates that safe applied clinical generative AI holds enormous possibilities for healthcare delivery. The Pieces hallucination guarantee and commitment to the NIST framework underscores the company’s focus on safety, transparency, accountability and maximum human oversight.

About Pieces Technologies
Pieces Technologies, Inc. is a leading healthcare artificial intelligence R&D company that applies generative AI technology to support and augment healthcare teams. Using cloud-based AI with clinically-based natural language processing (NLP) and generation, predictive modeling, and physician-supervised machine learning, the company offers solutions that streamline clinician workflows and improve patient outcomes. Pieces AI Solutions augment and support care teams by delivering clinical and administrative insights seamlessly within the EHR. For more information or to request a demo, visit www.piecestech.com.

View original content to download multimedia:https://www.prnewswire.com/news-releases/pieces-technologies-achieves-a-major-milestone-1-million-autonomously-written-inpatient-clinical-summaries-301896907.html

SOURCE Pieces Technologies