Kidney Week

Abstract: FR-PO0016

Intradialytic Arterial Oxygen Saturation Instability and Its Association with Clinical Characteristics in Patients on Maintenance Hemodialysis

Session Information

• Artificial Intelligence and Digital Health at the Bedside
  November 07, 2025 | Location: Exhibit Hall, Convention Center
  Abstract Time: 10:00 AM - 12:00 PM

Category: Artificial Intelligence, Digital Health, and Data Science

• 300 Artificial Intelligence, Digital Health, and Data Science

Authors

• Nandorine Ban, Andrea, Renal Research Institute, New York, New York, United States

Andrea Nandorine Ban, MS, MSc

• Desai, Priya, Renal Research Institute, New York, New York, United States

Priya Desai, MPH

• Kotanko, Peter, Renal Research Institute, New York, New York, United States

Peter Kotanko, MD, FASN

• Usvyat, Len A., Renal Research Institute, New York, New York, United States

Len A. Usvyat, PhD

• Zhang, Hanjie, Renal Research Institute, New York, New York, United States

Hanjie Zhang, PhD

Background

Intradialytic hypoxemia is common yet underrecognized in hemodialysis (HD) and may contribute to adverse outcomes. Sleep apnea, marked by intermittent saw-tooth patterns (STP) of arterial oxygen saturation (SaO₂), may cause hypoxemia. This study examined the association between frequent intradialytic SaO₂ instability and patient characteristics.

Methods

We analyzed SaO₂ data from a large U.S. HD cohort monitored with the Crit-Line device (Fresenius Medical Care) from Jan 2021 to July 2023. Intradialytic SaO₂ was recorded every 10 seconds. A one-dimensional convolutional neural network (Zhang, BMC Nephrology, 2025) was used to identify STP in five-minute intervals (Figure 1). Based on patient-level STP frequency, we categorized subjects into three groups: <5%, 5–29%, and ≥30%. Patient demographics and clinical parameters were compared across groups using unadjusted ANOVA and chi-squared tests.

Results

We analyzed 3,162,834 HD sessions from 37,256 in-center patients (Table 1). STP rate was significantly associated with male sex, diabetes, congestive heart failure, body weight and intradialytic blood pressure decline (all P-values < 0.001).

Conclusion

Frequent intradialytic SaO₂ instability is associated with distinct clinical characteristics. Understanding the etiology of STP and their association with hard outcomes warrants further analysis.

Figure 1: Intradialytic SaO₂ during dialysis. STP segments shown in orange; non-STP in purple.

Table 1: Patient characteristics stratified by STP rate. Continuous variables reported as mean ± standard deviation, categorical variables as proportions.

Funding

• Commercial Support – Renal Research Institute LLC, a wholly owned subsidiary of Fresenius Medical Care Holdings Inc.

Digital Object Identifier (DOI)

• doi: 10.1681/ASN.2025afbb79g9