Related Experiment Video
Updated: Jul 4, 2026

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
Published on: August 16, 2020
Machine learning progressive CKD risk prediction model is associated with CKD-mineral bone disorder.
Joseph Aoki1, Omar Khalid1, Cihan Kaya1
1Sonic Healthcare USA, 12357A - A Riata Trace Parkway, Suite 210, Austin, TX 78727, USA.
Machine learning accurately predicts chronic kidney disease (CKD) progression and identifies associated CKD-mineral bone disorder (CKD-MBD). This study highlights under-testing for CKD-MBD and links predictive analytics to early detection of this complication.
Area of Science:
- Nephrology
- Biochemistry
- Artificial Intelligence
Background:
- Chronic kidney disease (CKD) progression is a significant health concern.
- CKD-mineral bone disorder (CKD-MBD) is a critical, under-recognized complication.
- The association between predictive models for CKD progression and CKD-MBD is not well understood.
Purpose of the Study:
- To assess real-world laboratory testing utilization for CKD-MBD.
- To evaluate the association between a machine learning-based CKD risk classifier (PCRC) and CKD-MBD.
- To investigate the utility of predictive analytics in identifying CKD-MBD.
Main Methods:
- A retrospective cohort study of 330,238 US outpatients over 5 years.
- Analysis of laboratory testing data for eGFR, UACR, PTH, calcium, and phosphate.
- Evaluation of PCRC categorization against biochemical markers of CKD-MBD.
Main Results:
- Significant under-utilization of UACR, phosphate, and PTH testing was observed.
- PCRC-predicted CKD progression was associated with increased phosphate and PTH levels (P < 0.01).
- These biochemical changes are consistent with CKD-MBD.
Conclusions:
- There is a notable under-utilization of laboratory tests for CKD-MBD.
- PCRC-predicted CKD progression is linked to CKD-MBD, potentially years before clinical manifestation.
- This study is the first to link predictive analytics for CKD progression with CKD-MBD, offering potential for improved risk stratification and treatment.
Related Concept Videos
Drug Dosing in Renal Diseases: Estimation of Glomerular Filtration Rate Based on Serum Creatinine Concentration
Acute Kidney Injury IV: Diagnostic Studies and Prevention
Chronic Kidney Disease I: Introduction
Chronic Kidney Disease II: Clinical Manifestations
Chronic Kidney Disease III: Interprofessional Care
Chronic Kidney Disease IV: Nursing Management

