EUVIMEDEUVIMED entdecken
ValidierungsstudieOpen Access

A Risk Prediction Model (CMC-AKIX) for Postoperative Acute Kidney Injury Using Machine Learning: Algorithm Development and Validation

Ji Won Min iD, Jae-Hong Min iD, Se-Hyun Chang iD, Byung Ha Chung iD, Eun Sil Koh iD, Young Soo Kim iD, Hyung Wook Kim iD, Tae Hyun Ban iD, Seok Joon Shin iD, In Young Choi iD, Hye Eun Yoon iD

Journal of Medical Internet Research · 2025

DOI: 10.2196/62853 ↗

Kurz gefasst

Validierungsstudie in der Zeitschrift Journal of Medical Internet Research, 2025. Verfasst von Ji Won Min und 10 weiteren Autor:innen. Beteiligte Einrichtung: Department of Internal Medicine, Bucheon St. Mary's Hospital, College of Medicine, The Catholic University of Korea, Seoul, Republic of Korea. Hauptthemen laut MEDLINE: Acute Kidney Injury, Machine Learning, Postoperative Complications, Algorithms. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 51 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Postoperative acute kidney injury (AKI) is a significant risk associated with surgeries under general anesthesia, often leading to increased mortality and morbidity. Existing predictive models for postoperative AKI are usually limited to specific surgical areas or require external validation.

Objective

We proposed to build a prediction model for postoperative AKI using several machine learning methods.

Methods

We conducted a retrospective cohort analysis of noncardiac surgeries from 2009 to 2019 at seven university hospitals in South Korea. We evaluated six machine learning models: deep neural network, logistic regression, decision tree, random forest, light gradient boosting machine, and naïve Bayes for predicting postoperative AKI, defined as a significant increase in serum creatinine or the initiation of renal replacement therapy within 30 days after surgery. The performance of the models was analyzed using the area under the curve (AUC) of the receiver operating characteristic curve, accuracy, precision, sensitivity (recall), specificity, and F1-score.

Results

Among the 239,267 surgeries analyzed, 7935 cases of postoperative AKI were identified. The models, using 38 preoperative predictors, showed that deep neural network (AUC=0.832), light gradient boosting machine (AUC=0.836), and logistic regression (AUC=0.825) demonstrated superior performance in predicting AKI risk. The deep neural network model was then developed into a user-friendly website for clinical use.

Conclusions

Our study introduces a robust, high-performance AKI risk prediction system that is applicable in clinical settings using preoperative data. This model’s integration into a user-friendly website enhances its clinical utility, offering a significant step forward in personalized patient care and risk management.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Acute Kidney InjuryMachine LearningPostoperative ComplicationsAlgorithmsHumansRetrospective StudiesMaleFemaleMiddle AgedRepublic of KoreaRisk AssessmentAgedRisk FactorsROC CurveNeural Networks, Computer

Stichwörter der Autor:innen

South Koreaacute kidney injuryanesthesiaartificial intelligencecohort analysisdeep neural networksdigital healthgeneral surgeryhospitallogistic regressionmachine learningmorbiditymortalitypatient carepostoperative care

Autor:innen und Institutionen

  • Department of Internal Medicine, Bucheon St. Mary's Hospital, College of Medicine, The Catholic University of Korea, Seoul, Republic of Korea.
  • School of Information, University of California, Berkley, CA, United States.
  • Department of Medical Informatics, College of Medicine, The Catholic University of Korea, Seoul, Republic of Korea.
  • Department of Internal Medicine, Seoul St. Mary's Hospital, College of Medicine, The Catholic University of Korea, Seoul, Republic of Korea.
  • Department of Internal Medicine, Yeouido St. Mary's Hospital College of Medicine, The Catholic University of Korea, Seoul, Republic of Korea.
  • Department of Internal Medicine, Uijeongbu St. Mary's Hospital, College of Medicine, The Catholic University of Korea, Seoul, Republic of Korea.

ORCID-Profile: Ji Won Min, Jae-Hong Min, Se-Hyun Chang, Byung Ha Chung, Eun Sil Koh, Young Soo Kim, Hyung Wook Kim, Tae Hyun Ban, Seok Joon Shin, In Young Choi, Hye Eun Yoon

Zitieren

APA

Min, J. W., Min, J. H., Chang, S. H., Chung, B. H., Koh, E. S., Kim, Y. S., Kim, H. W., Ban, T. H., Shin, S. J., Choi, I. Y., & Yoon, H. E. (2025). A Risk Prediction Model (CMC-AKIX) for Postoperative Acute Kidney Injury Using Machine Learning: Algorithm Development and Validation. Journal of Medical Internet Research. https://doi.org/10.2196/62853

Vancouver

Min JW, Min JH, Chang SH, Chung BH, Koh ES, Kim YS, et al. A Risk Prediction Model (CMC-AKIX) for Postoperative Acute Kidney Injury Using Machine Learning: Algorithm Development and Validation. Journal of Medical Internet Research. 2025. doi:10.2196/62853

BibTeX
@article{Min2025,
  author = {Min, Ji Won and Min, Jae-Hong and Chang, Se-Hyun and Chung, Byung Ha and Koh, Eun Sil and Kim, Young Soo and Kim, Hyung Wook and Ban, Tae Hyun and Shin, Seok Joon and Choi, In Young and Yoon, Hye Eun},
  title = {A Risk Prediction Model (CMC-AKIX) for Postoperative Acute Kidney Injury Using Machine Learning: Algorithm Development and Validation},
  journal = {Journal of Medical Internet Research},
  year = {2025},
  doi = {10.2196/62853}
}
Kostenlos starten →