Related Experiment Video
Updated: Jan 9, 2026
TBase - an Integrated Electronic Health Record and Research Database for Kidney Transplant Recipients
Published on: April 13, 2021
Design and validation of an automated healthcare-integrated biobanking algorithm for identification of advanced
Claudia Fischer1, Boris Betz2, Johannes Stolp2
1Institute of Medical Statistics, Computer and Data Sciences (IMSID), Jena University Hospital - Friedrich Schiller University Jena, Jena, Germany.
Insights
This study developed two algorithms to automatically identify patients with chronic kidney disease (CKD) using electronic health records (EHR) for healthcare-integrated biobanking (HIB). The algorithms demonstrated good performance, enabling efficient sample collection for research.
Area of Science:
- Biomedical Informatics
- Clinical Research
- Biobanking
Background:
- Healthcare-integrated biobanking (HIB) relies on efficient identification of surplus clinical samples.
- Extracting specific patient cohorts, such as those with chronic kidney disease (CKD), from heterogeneous electronic health records (EHR) presents a significant challenge.
- Automated algorithms are crucial for identifying suitable samples in routine clinical practice.
Purpose of the Study:
- To develop and validate HIB-specific algorithms for automated identification of chronic kidney disease (CKD) patients using EHR data.
- To enable targeted sample collection and retrospective cohort assembly for research purposes.
- To establish a reproducible framework combining real-world EHR data, patient consent, and validation methods.
Main Methods:
- Two logistic regression-based CKD algorithms (admissionHIB and historyHIB) were developed using a training cohort (n=785).
- Algorithms were validated on patients from Jena University Hospital (01/2018-04/2020) using a gold-standard cohort (n=162) from manual chart review and a silver-standard cohort (n=1075) generated by a prior validated algorithm.
- Performance was evaluated using metrics including F1-score, precision, recall, and accuracy.
Main Results:
- The admissionHIB and historyHIB algorithms achieved F1-scores of 86% and 91% in the training cohort, respectively.
- In the validation cohort, the algorithms yielded F1-scores of 80% (admissionHIB) and 78% (historyHIB) in the gold-standard cohort, and 83% and 80% in the silver-standard cohort.
- The best-performing automated review algorithm for silver-standard generation achieved 93% recall, precision, and F1-score, and 97% accuracy.
Conclusions:
- The developed HIB-specific CKD algorithms demonstrate robust performance across diverse patient populations.
- These algorithms provide a reproducible framework for leveraging real-world EHR data for biobanking and cohort assembly.
- The study highlights the potential of automated methods to improve efficiency and accuracy in healthcare-integrated biobanking.
Abstract:
Healthcare-integrated biobanking (HIB) describes the collection of surplus samples from clinical routine and requires tailored algorithms for identification of adequate samples. However, identifying patients with specific conditions like chronic kidney disease (CKD) from heterogeneous real-world data remains challenging. This study develops and validates two HIB-specific algorithms for automated CKD identification based on electronic health records (EHR), enabling targeted sample collection and retrospective cohort assembly. Two logistic regression-based CKD algorithms were developed in an existing training cohort (n = 785) with high prevalence of CKD (48 %): the admissionHIB algorithm (based on laboratory values at admission) and the historyHIB algorithm (including additional previous hospital stays). The validation was carried out on patients of Jena University Hospital who gave informed consent to the Broad Consent of the Medical Informatics Initiative (MII) and were admitted between 01/2018 and 04/2020. The validation cohort was divided into a gold-standard cohort (n = 162) defined by manual chart review and a larger silver-standard cohort (n = 1075) generated using a validated algorithm from prior studies. The admissionHIB and historyHIB algorithms achieved F1-scores of 86 % and 91 %, respectively, in the training cohort. The validation cohort had a lower prevalence of CKD (approximately 12 %). Several automated review algorithms were evaluated in the gold-standard cohort, with the best-performing model (93 % recall, precision, and F1-score; 97 % accuracy) selected to generate the silver-standard cohort. Both HIB algorithms yielded F1-scores of 80 % (admissionHIB) and 78 % (historyHIB) in the gold-standard cohort, and 83 % and 80 %, respectively, in the silver-standard cohort. These findings demonstrate good performance of HIB-specific CKD algorithms across heterogeneous patient populations, establishing a reproducible framework combining real-world EHR data, patient consent infrastructure, and silver-standard validation.
Related Concept Videos
01:28Chronic Kidney Disease III: Interprofessional Care
01:25Chronic Kidney Disease I: Introduction
01:30Acute Kidney Injury IV: Diagnostic Studies and Prevention
01:28Drug Dosing in Renal Diseases: Estimation of Glomerular Filtration Rate Based on Serum Creatinine Concentration
01:28Kidney Transplant I: Introduction
01:18Chronic Kidney Disease IV: Nursing Management