Research

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.

someone injecting liquid into vials in a lab

Current Projects

  • Motion Analysis of Delirium in the Intensive Care Unit (ICU)
  • Intelligent ICU of the Future
  • Integrating Data, Algorithms and Clinical Reasoning for Surgical Risk Assessment (IDEALIST)
  • Automated Algorithm Identifies and Communicates Risk of Acute Kidney Injury among Health Care Providers and Patients (AKI-EPIC)
  • Network Analysis of Urinary Molecular Signature Complements Clinical Data to Predict Postoperative Acute Kidney Injury (NavigateAKI) clinicaltrials.gov
  • Digital Rehabilitation Environment Augmenting Medical System (DREAMS) clinicaltrials.gov

Follow PRISMAp on Twitter for the latest research updates!

Featured Publications

Human Activity Recognition Using Inertial, Physiological, and Environmental Sensors

This survey focuses on critical role of machine learning in developing Human Activity Recognition applications based on inertial sensors in conjunction with physiological and environmental sensors.

diagram showing a person with a walker

Discovery and Validation of Urinary Molecular Signature of Early Sepsis

The first ever study to use urinary cellular gene expression to study sepsis. Researchers identified alterations in gene expression unique to systemic and kidney-specific pathophysiologic processes using whole-genome analyses of RNA isolated from the urinary cells of sepsis patients.

diagram of kidney

Clinical Trajectories of Acute Kidney Injury in Surgical Sepsis: A Prospective Observational Study 

Among critically ill surgical sepsis patients, persistent AKI and the absence of renal recovery are associated with distinct early and sustained immunologic and endothelial biomarker signatures and decreased long-term physical function and survival.

graph showing survival probability versus months after sepsis onset

Audiovisual Modules to Enhance Informed Consent in the ICU: A Pilot Study

Audiovisual modules may improve knowledge and comprehension of commonly performed ICU procedures among critically ill patients and caregivers who have no healthcare background.

Critical Care Explorations journal cover

Extended vertical lists for temporal pattern mining from multivariate time series

In this paper, the problem of mining complex temporal patterns in the context of multivariate time series is considered. A new method called the Fast Temporal Pattern Mining with Extended Vertical Lists.

graph showing pattern length versus computational time

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

Older adults demonstrate biomarker evidence of the persistent inflammation, immunosuppression and catabolism syndrome (PICS) after sepsis

CONCLUSION: Older (versus young) and older CCI (versus older RAP) patient subgroups demonstrate early biomarker evidence of the underlying pathobiology of PICS.

Deep Multi-Modal Transfer Learning for Augmented Patient Acuity Assessment in the Intelligent ICU

Accurate prediction and monitoring of patient health in the intensive care unit can inform shared decisions regarding appropriateness of care delivery, risk-reduction strategies, and intensive care resource use. Traditionally, algorithmic…

Building an Artificial Intelligence-Competent Surgical Workforce

No abstract

Optimizing predictive strategies for acute kidney injury after major vascular surgery

CONCLUSION: In predicting acute kidney injury after major vascular surgery, machine learning approaches that incorporate dynamic intraoperative data had greater accuracy, discrimination, and precision than models using either preoperative data…