everythingpossible/123RF
 

AI In Healthcare Use Case #6: Pieces Technologies

  • 18 June 2019
  • Sam Mire

This interview is part of our new AI in Healthcare series, where we interview the world's top thought leaders on the front lines of the intersections between AI and healthcare.

In this interview, we speak with Patrick Conner, Director of Marketing, Product Marketing & Communications at Pieces Technologies with analysis from Komli-Kofi Atsina, M.D., Medical Director and contribution from Laurie Barenblat, M.S., Impact Consultant for Pieces Technologies, and Ruben Amarasingham, M.D, M.B.A, and CEO of Pieces Technologies (consultation by Patrick Conner). They help us understand how their company is using AI to transform healthcare, and what the future of the healthcare industry holds.

1. What’s the story behind Pieces Tech? Why and how did you begin?

PC: In 2009, Ruben Amarasingham, M.D., M.B.A, founded PCCI as part of the Parkland Health & Hospital System, one of the country’s leading public hospital institutions, and led an innovative mission-driven research team in building software and algorithms to characterize and alert care providers to the sometimes-hidden clinical and social determinant risks of the patients they were treating.

In 2010, Dr. Amarasingham treated a patient who changed his entire perspective on the challenge of addressing social determinants of health, leading him to consider how his software could not only identify social determinant risks, but also connect patients to community resources that could help them address these risks in concert with the health system. Dr. Amarasingham realized that “even if we identify the critical risks, it doesn’t matter if we have no plan or capability to address them. We need to build networks of community organizations that can work mutually with our health systems to improve the status of our patients and clients.”

The continued software development was immensely successful at Parkland and ultimately resulted in $50 million dollars in grant funding to study various aspects of development, implementation, and outcomes. In 2016, due to a burgeoning demand for this technology and connected services, Dr. Amarasingham used his research and clinical observations as a physician, administrator, and researcher at Parkland Health to create Pieces Technologies, Inc. The Pieces Technologies family has grown to over 45 full-time employees who continue to operationalize and harden the software in order to spread commercially across the country.

Pieces Technologies operates in seven states and growing, and is a leader in the mission to address social determinants of health for the betterment of community health.

2.  Please describe your use case and how Pieces Tech uses artificial intelligence:

RA: Pieces Decision Sciences (DS) platform is a cloud-based software platform that improves the quality and cost of care by applying key algorithms at every step of a patient’s care in real-time. The platform can be bi-directionally integrated with the electronic medical record (EMR) or other non-EMR systems and incorporates multiple data types, including structured, unstructured, and imaging data. The system interprets this data using a wide variety of algorithms to provide support for core decision-making tasks across a growing library of clinical and operational situations. Pieces Technologies has found that clinical, operational, and population health problems can be optimized by applying five categories of real-time algorithms. The algorithm categories can be broadly categorized as: Identification algorithms, Prediction algorithms, Activation algorithms, Monitoring algorithms, and Learning or Review algorithms. Pieces DS applies these algorithms at every stage of a patient’s care.

We use artificial intelligence to predict patients at risk for adverse outcomes, machine learning with clinical human augmentation to ensure the highest model accuracy, and proprietary natural language processing technology to surface insights from unstructured data such as free text progress notes and dictated notes. The Pieces platform supports the care team across the entire journey – in the health system and in the community.

3. Could you share a specific customer/user that benefits from what you offer? What has your service done for them?

LB: A large regional health system reduced readmission rates by implementing Pieces DS, which uses AI to rapidly identify at-risk patients in the EMR. This hospital utilized Pieces’ All-Cause Readmission Risk (ACRR) model to identify its target population of high and very high-risk patients. The hospital then used a Pieces algorithm running Natural Language Processing (NLP) and machine learning on clinical notes to identify and track the patients in those higher risk groups who had pre-discharge follow-up appointments. Thirty-seven percent of patients across both risk groups had pre-discharge follow-up appointments, and those patients showed 9 percent and 12 percent lower all-cause 30-day readmission rates, respectively, compared to patients with no indication of pre-discharge follow-up appointments. Combined, the two groups showed an 8 percent lower all-cause readmission rate. Moreover, very high-risk patients with pre-discharge follow-up appointments had 17% lower readmissions within seven days.

The hospital also found benefit in using the Pieces algorithms to identify additional components that affect higher-risk patients, namely socioeconomic and environmental factors, or the social determinants of health (SDoH). Analysis showed that patients experiencing one or more SDoH had significantly higher 30-day readmission rates (37 percent high risk, 19 percent very high risk). In addition, among the patients who had pre-discharge follow-up appointments, there was a nearly 20 percent higher readmission rate for those experiencing at least one SDoH compared to those who were not.

The combination of leveraging Pieces AI predictive models to identify and monitor elevated risk patients, along with the hospital system’s dedication to integrating the new data into their daily workflows, enabled the hospital system to effectively reduce risks and improve outcomes.

 

About Sam Mire

Sam is a Market Research Analyst at Disruptor Daily. He's a trained journalist with experience in the field of disruptive technology. He’s versed in the impact that blockchain technology is having on industries of today, from healthcare to cannabis. He’s written extensively on the individuals and companies shaping the future of tech, working directly with many of them to advance their vision. Sam is known for writing work that brings value to industry professionals and the generally curious – as well as an occasional smile to the face.

Comments

COMMUNITY