innovation in medicine

Making New Discoveries

There is always exciting research being conducted at PRISMAp labs. Find out more about our exciting research or read one of our many published articles below.

A person injects liquid into vials in a lab

Current Projects


Autonomous Delirium Monitoring and Adaptive Prevention

Delirium prevention in the ICU is often achieved with non-pharmacological approaches, but some methods are difficult to implement due to their dependence on sporadic human observations. ADAPT, the Autonomous Delirium Monitoring and Adaptive Prevention system, will autonomously quantify two indicators of delirium (patient mobility and circadian desynchrony) and predict delirium trajectories, as well as prompt actions that decrease delirium risk factors (e.g., ambient light, nightly disruptions). Successful application of ADAPT would augment clinical decision-making and promote more targeted interventions.

Decorative image of surgeon looking at hologram

CHoRUS (Bridge2ai)

A Patient-Focused Collaborative Hospital Repository Using Standards (CHoRUS) for Equitable AI

While AI in critical care (AICC) has helped improve patient care, AICC research lacks a large generalized dataset, standards that support the exchange and use of health information (interoperability) between sites and researchers, and support from a workforce trained in AI and general public familiar with medical AI. CHoRUS, a multimillion dollar collaboration of 18 top medical research institutions, aims to solve these problems by creating a 100,000 patient dataset from a sample population with varied backgrounds, ethical standards that enable interoperability, and AI education for AICC researchers and the general public.

Clinical hospital employees

Intelligent Intensive Care Unit (I2CU)

Pervasive Sensing and Artificial Intelligence for Augmented Clinical Decision-Making

Although close monitoring and dynamic assessment of patient acuity are key aspects of ICU care, both are limited by time constraints imposed on healthcare providers. Dynamic and precise assessment of patient acuity relies almost exclusively on physicians’ clinical judgement and vigilance, and details indicating patient condition may be partially captured or completely missed by overburdened nurses. We aim to develop deep learning models for sensing, quantifying, and communicating any patient’s condition in an autonomous, precise, and interpretable manner. This tool could enhance clinical workflow and enable early intervention.

ICU staff


Integrating Data, Algorithms, and Clinical Reasoning for Surgical Risk Assessment

IDEALIST could advance the ability of healthcare providers to diagnose diseases by computing the risk of postoperative complications in real-time. Ultimately, the results are expected to improve patient outcomes, decrease hospitalization costs, and reduce lifelong complications. The proposed research is relevant to public health because it can result in enhanced perioperative care workflow and early intervention.

A surgeon reads from a computer tablet in an operating room

Additional Projects

  • Network Analysis of Urinary Molecular Signature Complements Clinical Data to Predict Postoperative Acute Kidney Injury (NavigateAKI)
  • Digital Rehabilitation Environment Augmenting Medical System (DREAMS)

Follow PRISMAP on Twitter for the latest research updates!

Featured Publications

Reinforcement learning in surgery

Patients and physicians make essential decisions regarding diagnostic and therapeutic interventions. These actions should be performed or deferred under time constraints and uncertainty regarding patients’ diagnoses and predicted response to treatment. This may lead to cognitive and judgment errors.

diagram showing reinforcement learning framework and challenges in development of reinforcement learning models

Our Latest Publications