Work

Dynamic isolation forest for anomaly detection in post-PCI myocardial infarction patients

Year: 2026

Type: article

Abstract: Patients with myocardial infarction require continuous monitoring of multiple laboratory parameters after percutaneous coronary intervention (PCI), but assessment of their dynamic changes and of whether they deviate from the typical recovery trajectory still relies largely on clinical experience, and objective methods remain lacking. This study included 183 patients with myocardial infarction who underwent PCI, constructed fixed three-time-point windows, used blinded expert review as the reference, compared dynamic isolation forest (DIF) with other unsupervised methods, and conducted an external supportive prognostic analysis in MIMIC-IV. The results showed that DIF had the best agreement with expert ratings (Spearman's ρ = 0.585; Kendall's τ = 0.452), with an AUC of 0.859, and overall outperformed the other methods; the MIMIC-IV analysis showed that higher DIF anomaly scores were associated with an increased risk of death. DIF can be used to identify abnormal recovery windows after PCI that deviate from the typical recovery trajectory and may have potential for risk stratification, although its clinical utility still requires further validation.

Source: Scientific Reports

DOI: 10.1038/s41598-026-54390-7

Authors: Yu Zhang, Shan Gao, He Xu, Yuan Liu, Yaqiong Guo, XueLing Wei

Institution: Northwest Minzu University

Language: English

Topic: Anomaly Detection Techniques and Applications

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

SDG: Good health and well-being

Open Access status: gold

Estimated APC paid: $2,690