R01DK126933
Project Grant
Overview
Grant Description
Using Machine Learning for Early Recognition and Personalized Treatment of Acute Kidney Injury - Project Summary
Acute Kidney Injury (AKI) occurs in up to 20% of hospitalized patients and is associated with increased risk of readmission, morbidity, and mortality. The estimated annual cost of AKI care in the US is over 10 billion dollars, and with the incidence rising, these costs will continue to increase.
The current gold standards for diagnosing AKI, creatinine and urine output, are often delayed in their recognition of tubular injury. Prior work on AKI has typically focused on patients who have already developed AKI based on these standards, and interventions at this late time point have had mixed success. In contrast, emerging data suggest that intervening earlier can improve outcomes. Therefore, it is critical to optimize the early detection of AKI in hospitalized patients.
We have previously developed a machine learning tool to identify patients at high risk of severe (Stage 2 or greater) AKI more than a day earlier than clinically apparent using structured electronic health record (EHR) data. Although more accurate than prior methods, it suffers from a high rate of false positives, which limits its value in clinical practice.
There is a large amount of valuable information that is stored in unstructured free-text fields (e.g., clinical notes) that could be utilized using natural language processing (NLP) within advanced deep learning neural network models that could significantly improve the detection of early AKI. Furthermore, there are established and emerging kidney injury biomarkers that could be combined with EHR-based models to improve accuracy even further.
Finally, it remains unclear what interventions will have the best chance of decreasing the risk for developing severe AKI in high-risk patients. A better understanding of which interventions are of greatest benefit to specific patients is critical for improving the outcomes of patients at risk of AKI.
The objective of this project is to develop novel tools to improve the identification and treatment of patients at high risk of AKI using a large, multicenter cohort.
In Aim 1, we will use NLP and deep learning algorithms to develop a model to predict severe AKI across four health systems.
In Aim 2, we will silently run the best-performing model developed in Aim 1 in real-time to identify high-risk patients. Manual retrospective chart review will be performed on a cohort of the highest risk patients to determine both the proportion of patients who receive guideline-based care as well as the association between receipt of guideline-based care and outcomes. We will also identify novel phenotypes of patients who are particularly helped or harmed by specific guideline-based interventions.
Finally, in Aim 3, we will collect kidney injury biomarkers in the highest-risk patients to determine the added value of biomarkers to EHR-based models alone.
Our proposal will provide clinicians with new tools to identify patients at risk of AKI earlier and more accurately. It will also provide evidence for which interventions are most likely to improve patient outcomes. This will result in earlier, more personalized care for patients at high risk of AKI, which will lead to decreased costs, morbidity, and mortality.
Acute Kidney Injury (AKI) occurs in up to 20% of hospitalized patients and is associated with increased risk of readmission, morbidity, and mortality. The estimated annual cost of AKI care in the US is over 10 billion dollars, and with the incidence rising, these costs will continue to increase.
The current gold standards for diagnosing AKI, creatinine and urine output, are often delayed in their recognition of tubular injury. Prior work on AKI has typically focused on patients who have already developed AKI based on these standards, and interventions at this late time point have had mixed success. In contrast, emerging data suggest that intervening earlier can improve outcomes. Therefore, it is critical to optimize the early detection of AKI in hospitalized patients.
We have previously developed a machine learning tool to identify patients at high risk of severe (Stage 2 or greater) AKI more than a day earlier than clinically apparent using structured electronic health record (EHR) data. Although more accurate than prior methods, it suffers from a high rate of false positives, which limits its value in clinical practice.
There is a large amount of valuable information that is stored in unstructured free-text fields (e.g., clinical notes) that could be utilized using natural language processing (NLP) within advanced deep learning neural network models that could significantly improve the detection of early AKI. Furthermore, there are established and emerging kidney injury biomarkers that could be combined with EHR-based models to improve accuracy even further.
Finally, it remains unclear what interventions will have the best chance of decreasing the risk for developing severe AKI in high-risk patients. A better understanding of which interventions are of greatest benefit to specific patients is critical for improving the outcomes of patients at risk of AKI.
The objective of this project is to develop novel tools to improve the identification and treatment of patients at high risk of AKI using a large, multicenter cohort.
In Aim 1, we will use NLP and deep learning algorithms to develop a model to predict severe AKI across four health systems.
In Aim 2, we will silently run the best-performing model developed in Aim 1 in real-time to identify high-risk patients. Manual retrospective chart review will be performed on a cohort of the highest risk patients to determine both the proportion of patients who receive guideline-based care as well as the association between receipt of guideline-based care and outcomes. We will also identify novel phenotypes of patients who are particularly helped or harmed by specific guideline-based interventions.
Finally, in Aim 3, we will collect kidney injury biomarkers in the highest-risk patients to determine the added value of biomarkers to EHR-based models alone.
Our proposal will provide clinicians with new tools to identify patients at risk of AKI earlier and more accurately. It will also provide evidence for which interventions are most likely to improve patient outcomes. This will result in earlier, more personalized care for patients at high risk of AKI, which will lead to decreased costs, morbidity, and mortality.
Awardee
Funding Goals
(1) TO PROMOTE EXTRAMURAL BASIC AND CLINICAL BIOMEDICAL RESEARCH THAT IMPROVES THE UNDERSTANDING OF THE MECHANISMS UNDERLYING DISEASE AND LEADS TO IMPROVED PREVENTIONS, DIAGNOSIS, AND TREATMENT OF DIABETES, DIGESTIVE, AND KIDNEY DISEASES. PROGRAMMATIC AREAS WITHIN THE NATIONAL INSTITUTE OF DIABETES AND DIGESTIVE AND KIDNEY DISEASES INCLUDE DIABETES, DIGESTIVE, ENDOCRINE, HEMATOLOGIC, LIVER, METABOLIC, NEPHROLOGIC, NUTRITION, OBESITY, AND UROLOGIC DISEASES. SPECIFIC PROGRAMS AREAS OF INTEREST INCLUDE THE FOLLOWING: (A) FOR DIABETES, ENDOCRINE, AND METABOLIC DISEASES AREAS: FUNDAMENTAL AND CLINICAL STUDIES INCLUDING THE ETIOLOGY, PATHOGENESIS, PREVENTION, DIAGNOSIS, TREATMENT AND CURE OF DIABETES MELLITUS AND ITS COMPLICATIONS, NORMAL AND ABNORMAL FUNCTION OF THE PITUITARY, THYROID, PARATHYROID, ADRENAL, AND OTHER HORMONE SECRETING GLANDS, HORMONAL REGULATION OF BONE, ADIPOSE TISSUE, AND LIVER, ON FUNDAMENTAL ASPECTS OF SIGNAL TRANSDUCTION, INCLUDING THE ACTION OF HORMONES, COREGULATORS, AND CHROMATIN REMODELING PROTEINS, HORMONE BIOSYNTHESIS, SECRETION, METABOLISM, AND BINDING, AND ON HORMONAL REGULATION OF GENE EXPRESSION AND THE ROLE(S) OF SELECTIVE RECEPTOR MODULATORS AS PARTIAL AGONISTS OR ANTAGONISTS OF HORMONE ACTION, AND FUNDAMENTAL STUDIES RELEVANT TO METABOLIC DISORDERS INCLUDING MEMBRANE STRUCTURE, FUNCTION, AND TRANSPORT PHENOMENA AND ENZYME BIOSYNTHESIS, AND BASIC AND CLINICAL STUDIES ON THE ETIOLOGY, PATHOGENESIS, PREVENTION, AND TREATMENT OF INHERITED METABOLIC DISORDERS (SUCH AS CYSTIC FIBROSIS). (B) FOR DIGESTIVE DISEASE AND NUTRITION AREAS: GENETICS AND GENOMICS OF THE GI TRACT AND ITS DISEASES, GENETICS AND GENOMICS OF LIVER/PANCREAS AND DISEASES, GENETICS AND GENOMICS OF NUTRITION, GENETICS AND GENOMICS OF OBESITY, BARIATRIC SURGERY, CLINICAL NUTRITION RESEARCH, CLINICAL OBESITY RESEARCH, COMPLICATIONS OF CHRONIC LIVER DISEASE, FATTY LIVER DISEASE, GENETIC LIVER DISEASE, HIV AND LIVER, CELL INJURY, REPAIR, FIBROSIS AND INFLAMMATION IN THE LIVER, LIVER CANCER, LIVER TRANSPLANTATION, PEDIATRIC LIVER DISEASE, VIRAL HEPATITIS AND INFECTIOUS DISEASES, GASTROINTESTINAL AND NUTRITION EFFECTS OF AIDS, GASTROINTESTINAL MUCOSAL AND IMMUNOLOGY, GASTROINTESTINAL MOTILITY, BASIC NEUROGASTROENTEROLOGY, GASTROINTESTINAL DEVELOPMENT, GASTROINTESTINAL EPITHELIAL BIOLOGY, GASTROINTESTINAL INFLAMMATION, DIGESTIVE DISEASES EPIDEMIOLOGY AND DATA SYSTEMS, NUTRITIONAL EPIDEMIOLOGY AND DATA SYSTEMS, AUTOIMMUNE LIVER DISEASE, BILE, BILIRUBIN AND CHOLESTASIS, BIOENGINEERING AND BIOTECHNOLOGY RELATED TO DIGESTIVE DISEASES, LIVER, NUTRITION AND OBESITY, CELL AND MOLECULAR BIOLOGY OF THE LIVER, DEVELOPMENTAL BIOLOGY AND REGENERATION, DRUG-INDUCED LIVER DISEASE, GALLBLADDER DISEASE AND BILIARY DISEASES, EXOCRINE PANCREAS BIOLOGY AND DISEASES, GASTROINTESTINAL NEUROENDOCRINOLOGY, GASTROINTESTINAL TRANSPORT AND ABSORPTION, NUTRIENT METABOLISM, PEDIATRIC CLINICAL OBESITY, CLINICAL TRIALS IN DIGESTIVE DISEASES, LIVER CLINICAL TRIALS, OBESITY PREVENTION AND TREATMENT, AND OBESITY AND EATING DISORDERS. (C) FOR KIDNEY, UROLOGIC AND HEMATOLOGIC DISEASES AREAS: STUDIES OF THE DEVELOPMENT, PHYSIOLOGY, AND CELL BIOLOGY OF THE KIDNEY, PATHOPHYSIOLOGY OF THE KIDNEY, GENETICS OF KIDNEY DISORDERS, IMMUNE MECHANISMS OF KIDNEY DISEASE, KIDNEY DISEASE AS A COMPLICATION OF DIABETES, EFFECTS OF DRUGS, NEPHROTOXINS AND ENVIRONMENTAL TOXINS ON THE KIDNEY, MECHANISMS OF KIDNEY INJURY REPAIR, IMPROVED DIAGNOSIS, PREVENTION AND TREATMENT OF CHRONIC KIDNEY DISEASE AND END-STAGE RENAL DISEASE, IMPROVED APPROACHES TO MAINTENANCE DIALYSIS THERAPIES, BASIC STUDIES OF LOWER URINARY TRACT CELL BIOLOGY, DEVELOPMENT, PHYSIOLOGY, AND PATHOPHYSIOLOGY, CLINICAL STUDIES OF BLADDER DYSFUNCTION, INCONTINENCE, PYELONEPHRITIS, INTERSTITIAL CYSTITIS, BENIGN PROSTATIC HYPERPLASIA, UROLITHIASIS, AND VESICOURETERAL REFLUX, DEVELOPMENT OF NOVEL DIAGNOSTIC TOOLS AND IMPROVED THERAPIES, INCLUDING TISSUE ENGINEERING STRATEGIES, FOR UROLOGIC DISORDERS,RESEARCH ON HEMATOPOIETIC CELL DIFFERENTIATION, METABOLISM OF IRON OVERLOAD AND DEFICIENCY, STRUCTURE, BIOSYNTHESIS AND GENETIC REGULATION OF HEMOGLOBIN, AS WELL AS RESEARCH ON THE ETIOLOGY, PATHOGENESIS, AND THERAPEUTIC MODALITIES FOR THE ANEMIA OF INFLAMMATION AND CHRONIC DISEASES. (2) TO ENCOURAGE BASIC AND CLINICAL RESEARCH TRAINING AND CAREER DEVELOPMENT OF SCIENTISTS DURING THE EARLY STAGES OF THEIR CAREERS. THE RUTH L. KIRSCHSTEIN NATIONAL RESEARCH SERVICE AWARD (NRSA) FUNDS BASIC AND CLINICAL RESEARCH TRAINING, SUPPORT FOR CAREER DEVELOPMENT, AND THE TRANSITION FROM POSTDOCTORAL BIOMEDICAL RESEARCH TRAINING TO INDEPENDENT RESEARCH RELATED TO DIABETES, DIGESTIVE, ENDOCRINE, HEMATOLOGIC, LIVER, METABOLIC, NEPHROLOGIC, NUTRITION, OBESITY, AND UROLOGIC DISEASES. (3) TO EXPAND AND IMPROVE THE SMALL BUSINESS INNOVATION RESEARCH (SBIR) PROGRAM. THE SBIR PROGRAM AIMS TO INCREASE AND FACILITATE PRIVATE SECTOR COMMERCIALIZATION OF INNOVATIONS DERIVED FROM FEDERAL RESEARCH AND DEVELOPMENT, TO ENHANCE SMALL BUSINESS PARTICIPATION IN FEDERAL RESEARCH AND DEVELOPMENT, AND TO FOSTER AND ENCOURAGE PARTICIPATION OF SOCIALLY AND ECONOMICALLY DISADVANTAGED SMALL BUSINESS CONCERNS AND WOMEN-OWNED SMALL BUSINESS CONCERNS IN TECHNOLOGICAL INNOVATION. (4) TO UTILIZE THE SMALL BUSINESS TECHNOLOGY TRANSFER (STTR) PROGRAM. THE STTR PROGRAM INTENDS TO STIMULATE AND FOSTER SCIENTIFIC AND TECHNOLOGICAL INNOVATION THROUGH COOPERATIVE RESEARCH AND DEVELOPMENT CARRIED OUT BETWEEN SMALL BUSINESS CONCERNS AND RESEARCH INSTITUTIONS, TO FOSTER TECHNOLOGY TRANSFER BETWEEN SMALL BUSINESS CONCERNS AND RESEARCH INSTITUTIONS, TO INCREASE PRIVATE SECTOR COMMERCIALIZATION OF INNOVATIONS DERIVED FROM FEDERAL RESEARCH AND DEVELOPMENT, AND TO FOSTER AND ENCOURAGE PARTICIPATION OF SOCIALLY AND ECONOMICALLY DISADVANTAGED SMALL BUSINESS CONCERNS AND WOMEN-OWNED SMALL BUSINESS CONCERNS IN TECHNOLOGICAL INNOVATION.
Grant Program (CFDA)
Awarding / Funding Agency
Place of Performance
Chicago,
Illinois
606375418
United States
Geographic Scope
Single Zip Code
Related Opportunity
Analysis Notes
Amendment Since initial award the total obligations have increased 441% from $621,756 to $3,362,045.
University Of Chicago was awarded
AI-Predict: Early AKI Detection & Treatment Optimization
Project Grant R01DK126933
worth $3,362,045
from the National Institute of Diabetes and Digestive and Kidney Diseases in August 2021 with work to be completed primarily in Chicago Illinois United States.
The grant
has a duration of 5 years and
was awarded through assistance program 93.847 Diabetes, Digestive, and Kidney Diseases Extramural Research.
The Project Grant was awarded through grant opportunity NIH Research Project Grant (Parent R01 Clinical Trial Not Allowed).
Status
(Ongoing)
Last Modified 7/25/25
Period of Performance
8/1/21
Start Date
7/31/26
End Date
Funding Split
$3.4M
Federal Obligation
$0.0
Non-Federal Obligation
$3.4M
Total Obligated
Activity Timeline
Subgrant Awards
Disclosed subgrants for R01DK126933
Transaction History
Modifications to R01DK126933
Additional Detail
Award ID FAIN
R01DK126933
SAI Number
R01DK126933-3826411490
Award ID URI
SAI UNAVAILABLE
Awardee Classifications
Private Institution Of Higher Education
Awarding Office
75NK00 NIH National Institute of Diabetes and Digestive and Kidney Diseases
Funding Office
75NK00 NIH National Institute of Diabetes and Digestive and Kidney Diseases
Awardee UEI
ZUE9HKT2CLC9
Awardee CAGE
5E688
Performance District
IL-01
Senators
Richard Durbin
Tammy Duckworth
Tammy Duckworth
Budget Funding
Federal Account | Budget Subfunction | Object Class | Total | Percentage |
---|---|---|---|---|
National Institute of Diabetes and Digestive and Kidney Diseases, National Institutes of Health, Health and Human Services (075-0884) | Health research and training | Grants, subsidies, and contributions (41.0) | $1,377,232 | 100% |
Modified: 7/25/25