Digital Innovation for Outpatient Acute Kidney Injury: The Impact of Acute Kidney Injury Detection System (AKIDS) on Kidney Disease Burden

Acute kidney injury (AKI) in hospitalized patients accelerates the progression to end-stage kidney disease (ESKD), but the greater challenge lies in outpatient AKI (AKI_OPT)—a largely overlooked condition due to fragmented data and lack of consensus definitions. AKI can progress to chronic kidney disease and ESKD if the kidney function is not carefully cared for. Taiwan, known as the “dialysis island”, has the world's highest ESKD incidence and prevalence, reflected in an annual health insurance expenditure of NT$58.7 billion. This underscores the urgent need for an innovative way, data-driven intervention.

To address this, Taiwan established the National Health Insurance MediCloud to unsure a cloud-based health information exchange with cross-institution interoperability. Leveraging this infrastructure, CMUH launched the AKI Detection System (AKIDS) in 2017, integrating national and local electronic health records (EHRs) to enable real-time screening of AKI_OPT and nephrotoxic agents use. AKIDS functions as an in-flow clinical service, streamlining kidney care through automatic function summaries, dialysis risk alerts, and a nephrotoxic agent dashboard. It can significantly reduce the time physicians spend gathering data and enables proactive referral and scheduling for high-risk patients.

By embedding algorithms into routine care, AKIDS sets a new benchmark for digital kidney care. Its design supports cross-institutional scalability, and its effectiveness has been validated in real-world clinical trials—demonstrating the transformative potential of smart, data-driven interventions.

Implementation and Monitoring

To solidify the seamless integration of machine-human collaboration and assess clinical effectiveness, we devised a four-stage development plan for AKIDS:

1. Design Stage
   Starting 2017 as part of CMUH's institutional quality improvement program, AKIDS involved the directors from AKI Care, Quality Improvement, Information Technology, and Big Data Center in the early design stage. We created a schema for data exchange between local institutional EHR and the National Health Insurance Cloud. We confirmed the clinical impact of the algorithm-defined AKI_OPT on the Pre-ESKD population at CMUH, revealing patients with AKI_OPT had a 141% and 84% increased risk of one-year and overall all-cause mortality, respectively (Scientific Report; doi:10.1038/s41598-019-54227-6). We further validated the pathological traits of AKI_OPT identified by AKIDS, confirming that AKI biomarkers were indeed elevated in urine samples taken at AKI_OPT diagnosis (European Renal Association 2022; doi.org/10.1093/ndt/gfac068.050).
    
2. Sandbox Stage
   Between December 2017 and May 2020, CMUH implemented AKIDS in the backend of the outpatient Health Information System (HIS) to elucidate the real-world impact of AKI_OPT using the data algorithm to automatically detect unaware AKI_OPT and to screen for over 4,000 nephrotoxic agents (Figure 1). We also introduced a risk stratification system to prevent overwhelming nephrology services, ensuring only AKI_OPT patients with high-risk of progression to ESKD were referred to nephrology clinics (Figure 2). The sandbox stage helped us to understand the real-world burden of unaware AKI_OPT and to ensure the digital infrastructure can work smoothly, which will pave the way for successful hospital-wide deployment.
    
3. Clinical Trial Stage
   From June 2020 to January 2022, despite the COVID-19 pandemic, we effectively executed a randomized clinical trial without hindering the regular clinical operations, to assess the clinical effectiveness of AKIDS. Concurrently, we established the first-of-its-kind biobank to serve as a foundation for future investigations into biomarker identification and drug discovery.
    
4. Implementation Stage
   Starting February 2022, AKIDS has been launched to all appointed outpatients' hospital-wide because of the beneficial effects of decreasing kidney failure observed in the clinical trial.

Accomplishment

Since the sandbox stage, AKIDS has screened for over 600 thousand outpatients in the CMUH, with an average monthly AKI_OPT incidence of 11%. Of patients with AKI_OPT, 23% of them required nephrology care, but only 3% actually received such care before the AKIDS implementation. In addition, patients with AKI_OPT have significantly 16-fold risk of kidney failure and 3-fold risk of death within one year, indicating a huge gap in kidney care (Commun Med. 2025. https://doi.org/10.1038/s43856-025-00836-4). Furthermore, our pragmatic randomized clinical trial has provided solid evidence that for high-risk patients with AKI_OPT, AKIDS implementation exhibited almost 40% reduction in the risk of kidney failure in 1 year (Figure 3). For every 6 patients covered by the AKIDS, 1 patient can be prevented to develop kidney failure. We estimate that the timely diagnosis of AKI_OPT could potentially save at least 31 million USD spent on dialysis every year in Taiwan.

We believe AKIDS exemplifies the future of AI-driven clinical decision support in smart hospitals—proactively identifying silent threats like outpatient AKI, closing the gap in nephrology care, and transforming real-world clinical outcomes. With strong digital infrastructure, validated clinical impact, peer-reviewed publications, and both national and international recognition, AKIDS stands as a scalable and impactful solution to improve kidney health and reduce preventable dialysis burden on a population level.

Journal Article
 

• three publications (Scientific Reports 2023；Communications Medicine 2025；Heliyon 2025)

Awards

2023

• International Hospital Federation Award Quality and Patient Safety Honorary Award

2017​

• Innovative Digital Service Application Award Golden Award

Patents
 

• Taiwan patent (patent No. I755108)

Contact window
 

• Dr. Chin-Chi Kuo, MD, PhD
  Vice Superintendent, Big Data Center, CMUH
  Attending Physician, Division of Nephrology, Department of Internal Medicine, CMUH
  Director & Professor, Department of Biomedical Informatics, College of Medicine, CMU
  025725@tool.caaumed.org.tw