Skip to content
DraconiticResearch
Search Sources API
203,948 studies31 sourcesUpdated 31 min ago
Peer-reviewedCC BY 4.0Renal Failure

Comparison of an AI-enabled single-lead ECG monitor and point-of-care testing for detecting intradialytic hypokalemia

  • Wen-Fang Chiang1,2
  • Po-Jen Hsiao1,2,3
  • Kun-Lin Wu1,2,3
  • Ruei-Lin Wang1,2
  • Kun-Yi Lin4
  • Chi-Ming Chu5,6
  • Jenq-Shyong Chan1,2
6 affiliations
  1. 1Division of Nephrology, Department of Internal Medicine, Taoyuan Armed Forces General Hospital, Taoyuan, Taiwan
  2. 2Division of Nephrology, Department of Internal Medicine, Tri-Service General Hospital, National Defense Medical University, Taipei, Taiwan
  3. 3Department of Life Sciences, National Central University, Taoyuan, Taiwan
  4. 4Department of Orthopedic Surgery, Tri-Service General Hospital, National Defense Medical University, Taipei, Taiwan
  5. 5Division of Biostatistics and Medical Informatics, Department of Epidemiology, School of Public Health, National Defense Medical University, Taipei, Taiwan
  6. 6Graduate Institute of Medical Sciences, National Defense Medical University, Taipei, Taiwan
Read full textPDFDOICite

Abstract

Background: Intradialytic hypokalemia is an underrecognized complication of maintenance hemodialysis (MHD). While point-of-care (POC) testing offers rapid biochemical confirmation, it remains limited by its intermittent nature. Artificial intelligence (AI)-enabled electrocardiography (ECG) provides a potential noninvasive alternative for trend monitoring; however, its performance in MHD has not been compared with POC testing against a central laboratory standard.

Methods: This single-center prospective study compared AI-ECG potassium estimation and POC testing during MHD. An algorithm was trained on ECG–potassium pairs from 45 patients (2021–2022) and tested in 29 patients (2023). Concurrent laboratory–POC–ECG pairs enabled direct comparison, using central laboratory assays as the reference standard.

Results: The AI-enabled ECG model achieved high accuracy within the non-hypokalemic range (mean absolute error (MAE) of 0.479 mmol/L), although the predictive variance expanded during hypokalemia (MAE of 1.000 mmol/L). POC testing demonstrated the highest laboratory concordance (MAE 0.201 mmol/L; ρ = 0.977). With respect to hypokalemia screening, the AI-ECG model maintained good discriminatory performance (area under the curve (AUC) of 0.722), which was paired with a high sensitivity (77.9%) and a robust negative predictive value (83.2%). POC testing significantly outperformed the AI-ECG model in diagnostic discrimination (AUC 0.996 vs. 0.722; ΔAUC 0.274; p < 0.0001).

Conclusions: The AI-enabled ECG model demonstrates preliminary screening potential for hypokalemia alongside reliable non-hypokalemic tracking. Although POC testing remains the superior modality for point-in-time analytical precision, AI-enabled ECG offers a noninvasive approach for intradialytic trend monitoring. However, its ability to improve clinical outcomes or safely reduce invasive testing requires formal prospective decision-impact studies.

Related

  1. CO055 | COMPARISON OF VISCOELASTIC COAGULATION MONITOR AND ROTATIONAL THROMBOELASTOMETRY FOR HEMOSTATIC PHENOTYPING AND OUTCOME PREDICTION IN SEPSIS
    Giovanni Gottardi
    Bleeding, Thrombosis and Vascular BiologyPeer-reviewedCC BY-NCFull textCardiovascular medicineDOAJ
  2. Comparison of AI-enabled cardiac chambers volumetry based on non-gated chest CT scans with echocardiography: An AI-CVD study within the Multi-Ethnic Study of Atherosclerosis (MESA)
    Seyed Reza Mirjalili, Kyle Atlas, Anthony P. Reeves +29
    American journal of preventive cardiologyPeer-reviewedCC BY-NC-NDFull textGeneral medicineEurope PMC
  3. Detecting epidemic outbreaks with routine blood tests: A comparison of surveillance methods using COVID-19 simulations and real-world seasonal disease data
    K. A. Klochkov, I. I. Maslova, E. N. Ilina +1
    medRxivPreprintCC BYFull textEpidemiology & public healthmedRxiv
  4. Hypokalemia and New-Onset Diabetes in Heart Failure With Mildly Reduced or Preserved Ejection Fraction
    John W Ostrominski, Henri Lu, Brian L Claggett +16
    Diabetes CarePeer-reviewedCC BY 4.0Full textCardiovascular medicineHAL
  5. The Intradialytic Changes in Cardiac Troponin I—A Systematic Review
    Johan Ferrier Jørgensen, Frans Brandt, Michael Waldhauer Hunderup +1
    Seminars in DialysisPeer-reviewedCC BY-NC-ND 4.0Full textCardiovascular medicinePMC

Cite

BibTeXRIS
BibTeX
@article{chiang2026comparison,
  title = {{Comparison of an AI-enabled single-lead ECG monitor and point-of-care testing for detecting intradialytic hypokalemia}},
  author = {Wen-Fang Chiang and Po-Jen Hsiao and Kun-Lin Wu and Ruei-Lin Wang and Kun-Yi Lin and Chi-Ming Chu and Jenq-Shyong Chan},
  journal = {Renal Failure},
  year = {2026},
  month = oct,
  doi = {10.1080/0886022x.2026.2746815},
  url = {https://doi.org/10.1080/0886022x.2026.2746815},
  note = {CC BY 4.0},
}
RIS
TY  - JOUR
TI  - Comparison of an AI-enabled single-lead ECG monitor and point-of-care testing for detecting intradialytic hypokalemia
AU  - Wen-Fang Chiang
AU  - Po-Jen Hsiao
AU  - Kun-Lin Wu
AU  - Ruei-Lin Wang
AU  - Kun-Yi Lin
AU  - Chi-Ming Chu
AU  - Jenq-Shyong Chan
PY  - 2026
DA  - 2026/10/30
JO  - Renal Failure
DO  - 10.1080/0886022x.2026.2746815
UR  - https://doi.org/10.1080/0886022x.2026.2746815
AB  - Background: Intradialytic hypokalemia is an underrecognized complication of maintenance hemodialysis (MHD). While point-of-care (POC) testing offers rapid biochemical confirmation, it remains limited by its intermittent nature. Artificial intelligence (AI)-enabled electrocardiography (ECG) provides a potential noninvasive alternative for trend monitoring; however, its performance in MHD has not been compared with POC testing against a central laboratory standard.  Methods: This single-center prospective study compared AI-ECG potassium estimation and POC testing during MHD. An algorithm was trained on ECG–potassium pairs from 45 patients (2021–2022) and tested in 29 patients (2023). Concurrent laboratory–POC–ECG pairs enabled direct comparison, using central laboratory assays as the reference standard.  Results: The AI-enabled ECG model achieved high accuracy within the non-hypokalemic range (mean absolute error (MAE) of 0.479 mmol/L), although the predictive variance expanded during hypokalemia (MAE of 1.000 mmol/L). POC testing demonstrated the highest laboratory concordance (MAE 0.201 mmol/L; ρ = 0.977). With respect to hypokalemia screening, the AI-ECG model maintained good discriminatory performance (area under the curve (AUC) of 0.722), which was paired with a high sensitivity (77.9%) and a robust negative predictive value (83.2%). POC testing significantly outperformed the AI-ECG model in diagnostic discrimination (AUC 0.996 vs. 0.722; ΔAUC 0.274; p < 0.0001).  Conclusions: The AI-enabled ECG model demonstrates preliminary screening potential for hypokalemia alongside reliable non-hypokalemic tracking. Although POC testing remains the superior modality for point-in-time analytical precision, AI-enabled ECG offers a noninvasive approach for intradialytic trend monitoring. However, its ability to improve clinical outcomes or safely reduce invasive testing requires formal prospective decision-impact studies.
SN  - 0886-022X
SN  - 1525-6049
ER  -