loading
loading
NIH grant 1R43DK146600-01A1: Personalized Assessment and Care of Kidney Support in Critically Ill Patients(PACKS-ICU)
Institute: {'code': 'DK', 'abbreviation': 'NIDDK', 'name': 'National Institute of Diabetes and Digestive and Kidney Diseases', 'admin_org_id': '12500020', 'admin_funding_url': ''}. PI: Ravindra L. Mehta. Award: $304910.
Start: 2026-08-06T00:00:00.
Project Summary
Acute kidney injury requiring dialysis (AKI-D) is a severe complication of critical illness, contributing to in-
hospital mortality rates exceeding 50%, prolonged ICU stays, high rehospitalization rates and significant
long-term morbidity, including chronic dialysis dependence. This condition imposes an economic burden
of over $10 billion annually in the U.S., with $1.7 billion attributed to avoidable costs from variability in
dialysis application. To address this, DAECOS LLC has developed an AI-driven Clinical Decision Support
System (CDSS) that integrates seamlessly with electronic health records (EHRs) to predict dialysis needs
and improve outcomes. The DAECOS CDSS uses proprietary algorithms validated on over 100,000 ICU
patients across five international centers. It provides real-time, actionable insights to healthcare
providers, enabling early and accurate identification of patients who will benefit from acute dialysis. The
system also identifies distinct patient phenotypes for dynamic risk stratification, optimizing resource
allocation and reducing healthcare costs. In this Phase 1 project, DAECOS will collaborate with the UC
San Diego Center for Health Innovation to refine the algorithm using retrospective data from three UC
San Diego hospitals (Aim 1), deploy the CDSS within UCSD’s EPIC EHR via AWS cloud and FHIR APIs to
enable real-time decision support (Aim 2), and Implement the CDSS in a silent test mode to evaluate its
validity, usability, and workflow integration across teaching/non-teaching settings (Aim 3). The project
will focus on developing a secure, scalable data processing pipeline, integrating heterogeneous data
sources, and designing an intelligent alert system that aligns with ICU workflows. By aligning predictions
with observed utilization rates and optimizing workflows, the CDSS aims to reduce mortality, ICU stays,
progression to chronic dialysis and patient quality of life. Broader impacts include cost savings through
standardized care, efficient resource allocation in overwhelmed ICUs, and a scalable framework for AI-
driven critical care interventions. Successful completion will provide the foundation for designing a
comprehensive SBIR Phase 2 clinical trial, which will further evaluate the CDSS's effectiveness and
potential for widespread implementation in critical care settings.document fetched 2026-08-16 06:34