Kidney Week

Abstract: TH-PO465

Role of Advanced Imaging Metrics in Predicting Outcomes in Patients Affected with Polycystic Kidney Disease

Session Information

• Cystic Kidney Diseases: Clinical Assessment and Therapeutic Directions
  October 24, 2024 | Location: Exhibit Hall, Convention Center
  Abstract Time: 10:00 AM - 12:00 PM

Category: Genetic Diseases of the Kidneys

• 1201 Genetic Diseases of the Kidneys: Cystic

Authors

• Kline, Timothy L., Mayo Foundation for Medical Education and Research, Rochester, Minnesota, United States

Timothy L. Kline, MS, PhD

• Gregory, Adriana, Mayo Foundation for Medical Education and Research, Rochester, Minnesota, United States

Adriana Gregory, MS

• Cohen, Aaron, Indiana University, Bloomington, Indiana, United States

Aaron Cohen, MSc

• Ables, Erin, Indiana University, Bloomington, Indiana, United States

Erin Ables, MA

• Chebib, Fouad T., Mayo Clinic in Florida, Jacksonville, Florida, United States

Fouad T. Chebib, MD, FASN

• Landsittel, Doug, University at Buffalo, Buffalo, New York, United States

Doug Landsittel, PhD

• Torres, Vicente E., Mayo Foundation for Medical Education and Research, Rochester, Minnesota, United States

Vicente E. Torres, MD, PhD

• Harris, Peter C., Mayo Foundation for Medical Education and Research, Rochester, Minnesota, United States

Peter C. Harris, PhD

• Rahbari-Oskoui, Frederic F., Emory University, Atlanta, Georgia, United States

Frederic F. Rahbari-Oskoui, MD, MS, FASN

• Chapman, Arlene B., University of Chicago Division of the Biological Sciences, Chicago, Illinois, United States

Arlene B. Chapman, MD

• Mrug, Michal, The University of Alabama at Birmingham Division of Nephrology, Birmingham, Alabama, United States

Michal Mrug, MD

• Yu, Alan S.L., The University of Kansas Medical Center, Kansas City, Kansas, United States

Alan S.L. Yu, MBChB

Background

The CRISP and HALT-A studies have provided significant longitudinal data on patients affected with ADPKD. This study utilized this data to compare advanced imaging metrics with a model built upon clinical information for predicting kidney health outcomes.

Methods

A cohort of 582 patients from the CRISP and HALT-A studies were included, all of whom had complete data for the following ‘base model’ variables: age, sex, serum creatinine, BMI, diastolic BP, hemoglobin, and CO2. Using the T2-weighted coronal sequences, standard imaging metrics such as total kidney volume (TKV) were measured. Additionally, from these same series, advanced imaging metrics were calculated using a previously developed AI-based tool, including total kidney cyst volume (TKCV), total cyst number (TCN), renal parenchyma volume (RPV), and cyst parenchyma surface area (CPSA). Statistical analyses were performed to compare the predictive power of these advanced imaging metrics with the base model, as well as explore their incorporation into the model.

Results

The analysis demonstrated that individual advanced imaging metrics (TKCV, TCN, RPV, CPSA) were comparable to the base model in predicting kidney health outcomes (see Table). The analysis demonstrated that individual advanced imaging metrics (TKCV, TCN, RPV, CPSA) were 1) comparable to the entire base model for prognosis of kidney failure, 2) were statistically significant and led to improvements in predicted risk when added to the base model.

Conclusion

Advanced imaging metrics offer valuable insights into kidney structure in PKD patients. Their individual predictive power for kidney health outcomes is on par with a multivariable model (i.e. the base model) and also their addition to the base model further improves the model’s predictive potential. Further research is needed to explore the potential of these imaging techniques in clinical practice and their ability to predict long-term outcomes in PKD patients.

Funding

• NIDDK Support