Machine learning algorithms using the inflammatory prognostic index for contrast-induced nephropathy in NSTEMI patients

Biomark Med. 2024;18(23):1007-1015. doi: 10.1080/17520363.2024.2422810. Epub 2024 Nov 13.

Abstract

Aim: Inflammatory prognostic index (IPI), has been shown to be related with poor outcomes in cancer patients. We aimed to investigate the predictive role of IPI for contrast-induced nephropathy (CIN) development in non-ST segment elevation myocardial infarction patients using a nomogram and performing machine learning (ML) algorithms.Materials & methods: A total of 178 patients with CIN (+) and 1511 with CIN (-) were included.Results: CIN (+) patients had higher IPI levels, and IPI was independently associated with CIN. A risk prediction nomogram including IPI had a higher predictive ability and good calibration. Naive Bayes and k-nearest neighbors were the best ML algorithms for the prediction of CIN patients.Conclusion: IPI might be used as an easily obtainable marker for CIN prediction using ML algorithms.

Keywords: contrast-induced nephropathy; inflammatory prognostic index; machine learning; nomogram; non-ST segment elevation myocardial infarction.

Plain language summary

[Box: see text].

MeSH terms

  • Aged
  • Algorithms*
  • Contrast Media* / adverse effects
  • Female
  • Humans
  • Inflammation
  • Kidney Diseases / chemically induced
  • Kidney Diseases / diagnosis
  • Machine Learning*
  • Male
  • Middle Aged
  • Nomograms
  • Non-ST Elevated Myocardial Infarction* / diagnosis
  • Non-ST Elevated Myocardial Infarction* / diagnostic imaging
  • Prognosis

Substances

  • Contrast Media