AI hybrid survival assessment for advanced heart failure patients with renal dysfunction

Ge Zhang, Zeyu Wang, Zhuang Tong, Zhen Qin, Chang Su, Demin Li, Shuai Xu, Kaixiang Li, Zhaokai Zhou, Yudi Xu, Shiqian Zhang, Ruhao Wu, Teng Li, Youyang Zheng, Jinying Zhang (), Ke Cheng () and Junnan Tang ()
Additional contact information
Ge Zhang: The First Affiliated Hospital of Zhengzhou University
Zeyu Wang: The First Affiliated Hospital of Zhengzhou University
Zhuang Tong: The First Affiliated Hospital of Zhengzhou University
Zhen Qin: The First Affiliated Hospital of Zhengzhou University
Chang Su: The First Affiliated Hospital of Zhengzhou University
Demin Li: The First Affiliated Hospital of Zhengzhou University
Shuai Xu: The First Affiliated Hospital of Zhengzhou University
Kaixiang Li: The First Affiliated Hospital of Zhengzhou University
Zhaokai Zhou: The First Affiliated Hospital of Zhengzhou University
Yudi Xu: The First Affiliated Hospital of Zhengzhou University
Shiqian Zhang: The First Affiliated Hospital of Zhengzhou University
Ruhao Wu: The First Affiliated Hospital of Zhengzhou University
Teng Li: The First Affiliated Hospital of Zhengzhou University
Youyang Zheng: The First Affiliated Hospital of Zhengzhou University
Jinying Zhang: The First Affiliated Hospital of Zhengzhou University
Ke Cheng: New York City
Junnan Tang: The First Affiliated Hospital of Zhengzhou University

Nature Communications, 2024, vol. 15, issue 1, 1-21

Abstract: Abstract Renal dysfunction (RD) often characterizes the worse course of patients with advanced heart failure (AHF). Many prognosis assessments are hindered by researcher biases, redundant predictors, and lack of clinical applicability. In this study, we enroll 1736 AHF/RD patients, including data from Henan Province Clinical Research Center for Cardiovascular Diseases (which encompasses 11 hospital subcenters), and Beth Israel Deaconess Medical Center. We developed an AI hybrid modeling framework, assembling 12 learners with different feature selection paradigms to expand modeling schemes. The optimized strategy is identified from 132 potential schemes to establish an explainable survival assessment system: AIHFLevel. The conditional inference survival tree determines a probability threshold for prognostic stratification. The evaluation confirmed the system’s robustness in discrimination, calibration, generalization, and clinical implications. AIHFLevel outperforms existing models, clinical features, and biomarkers. We also launch an open and user-friendly website www.hf-ai-survival.com , empowering healthcare professionals with enhanced tools for continuous risk monitoring and precise risk profiling.

Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.nature.com/articles/s41467-024-50415-9 Abstract (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:nat:natcom:v:15:y:2024:i:1:d:10.1038_s41467-024-50415-9

Ordering information: This journal article can be ordered from
https://www.nature.com/ncomms/

DOI: 10.1038/s41467-024-50415-9

Access Statistics for this article

Nature Communications is currently edited by Nathalie Le Bot, Enda Bergin and Fiona Gillespie

More articles in Nature Communications from Nature
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().