Artificial Intelligence in Acute Kidney Injury Prediction: Challenges and Opportunities in Low-Income Settings
Hafida Chelgui, MD
Department of Nephrology, Nefissa Hamoud University Hospital, Algiers, Algeria
Background
Acute kidney injury (AKI) remains a major cause of morbidity and mortality worldwide1. Most cases occur in low- and middle-income countries (LMICs), where delayed diagnosis and limited access to nephrology care worsen outcomes2. Artificial intelligence (AI) tools can predict AKI hours before serum creatinine rises, enabling earlier intervention3,4. However, most existing models are developed and validated in high-income settings, relying on continuous electronic data infrastructures that are rarely available in LMICs, raising concerns about generalizability and equity.
Methods
A narrative review of studies published between 2015 and 2025 identified AI-based AKI prediction models. Articles were assessed for study design, input variables, validation strategies, performance metrics, and applicability to low-resource environments. Contextual clinical insights from North African nephrology practice, including common AKI etiologies such as sepsis and obstetric complications, were incorporated to enhance relevance.
Results
Most AI models rely on large datasets, time-series analyses, and complex algorithms, achieving high predictive performance3–5. However, external validation in LMIC populations is lacking, and model performance may be affected by regional differences in AKI etiology and data availability. Simplified, interpretable models using routinely available clinical variables such as serum creatinine, urine output, blood pressure, age, and sepsis status may still provide clinically meaningful early warning signals in low-resource settings.
Conclusion
AI offers a promising opportunity for earlier AKI detection worldwide. To ensure equitable clinical benefit, models must be contextually adapted, ethically validated, and integrated into routine care through simplified, open-access approaches supported by regional collaborations led by nephrologists in LMICs.
DOI: 10.29245/2767-5149/2026/1.1130 View / Download PdfPhosphate Binder Compliance Study in Patients with End-Stage Kidney Disease
Kathleen M Hill Gallant1, Douglas Jermasek2, Brooks Oppenheimer3, Sheila Doss4
1University of Minnesota-Twin Cities, St. Paul, MN, USA
2Unicycive Therapeutics, Inc., Los Altos, CA, USA
3Reason Research, Philadelphia, PA, USA
4American Nephrology Nurses Association, Pitman, NJ, USA
Introduction: ~600k US end-stage kidney disease patients undergo dialysis, and >43% have serum phosphorus >5.5mg/dL, increasing bone disorder and mortality. Recent studies report phosphate binder (PB) non-adherence rates up to 78%.
Objective: Understanding patient perspectives on PB therapy challenges to improve adherence and outcomes.
Methods: 20-minute online survey was conducted (2/15-5/16/24) with patients from the National Kidney Foundation email list. Eligibility: on dialysis (in-center or home), ≥40 years old, using ≥1 phosphate management treatment, and insured. The survey assessed patient perspectives on daily pill burden, PB-related challenges, non-adherence drivers, and impact of PB attributes on compliance.
Results: 200 patients surveyed. PBs had the highest daily pill requirements (4.8 pills/day) vs. diabetes, high cholesterol, high blood pressure, and depression medications (1.2-2.6 pills or injections/day). Among non-compliant group (≤80% compliant), 58% rated taking PBs as directed as “extremely important,” vs. 67%-100% for other medications. PB non-compliance was ~3-fold higher vs. other medications (37% of patients vs. 12-18%, p≤0.05). Self-reported non-compliant patients were 2.6-times more likely to report uncontrolled phosphate levels. Among 126 patients with <100% compliance, top barriers were forgetting to take PBs, too many pills, and large pill size. Patients were 4- and 2-times more likely to be compliant with fewer and smaller pills, respectively.
Conclusion: PBs had the highest pill burden and lowest compliance. Pill number and size were two of the top barriers. Patients preferred regimens with fewer, smaller pills. Reducing pill burden and enhancing the perceived importance of phosphate control may improve adherence and phosphate management.
DOI: 10.29245/2767-5149/2025/3.1127 View / Download Pdf