EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Artificial intelligence in preoperative assessment and optimization: a narrative review

Yoann Elmaleh, Yassine Moussali, Richard Boyer

Turkish Journal of Intensive Care · 26.03.2026 · 24 (1) · 1-10

DOI: 10.63729/tjic.2026.683 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Turkish Journal of Intensive Care, online erschienen am 26.03.2026. Verfasst von Yoann Elmaleh und 2 weiteren Autor:innen. Die Arbeit nennt 20 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Preoperative assessment and optimization are pivotal for complex surgical patients, yet traditional scores and clinician-driven workflows may miss subtle risk interactions and modifiable factors. Artificial intelligence (AI), especially machine learning (ML), can leverage large-scale electronic health record (EHR) data to improve risk stratification and support targeted optimization strategies.

Methods

We conducted a narrative review focusing on practical, clinically actionable AI applications in preoperative assessment and optimization, emphasizing recent advances and implementation considerations for high-risk surgical patients.

Results

ML-based preoperative risk models can outperform conventional calculators, exemplified by a gradient-boosted decision-tree model trained on >1.4 million surgical cases that achieved an AUROC of 0.95 for 30-day mortality and exceeded NSQIP performance, with prospective real-world deployment. Automated frailty phenotyping from structured preoperative EHR data (demographics, ASA/acuity, ICD-10/CCS diagnoses, and routine labs) has also been externally validated in older adults and shows strong stepwise associations with adverse outcomes. AI additionally supports preoperative optimization by identifying actionable targets such as anemia risk (supporting early iron/EPO pathways), penicillin allergy delabeling opportunities, and improved detection of risky alcohol use via natural language processing of clinical notes. Successful clinical impact depends on workflow integration, interpretability, and attention to privacy, bias, regulation, and prospective evidence.

Conclusions

AI-enabled preoperative assessment can enhance identification of high-risk patients and systematically surface modifiable factors for optimization, with early evidence of improved predictive performance and feasible integration into point-of-care workflows. Future work should prioritize robust external validation across diverse populations, implementation studies demonstrating patient-centered benefit, and governance frameworks ensuring safety, fairness, and clinician trust.

Zitieren

APA

Elmaleh, Y., Moussali, Y., & Boyer, R. (2026). Artificial intelligence in preoperative assessment and optimization: a narrative review. Turkish Journal of Intensive Care, 24(1), 1-10. https://doi.org/10.63729/tjic.2026.683

Vancouver

Elmaleh Y, Moussali Y, Boyer R. Artificial intelligence in preoperative assessment and optimization: a narrative review. Turkish Journal of Intensive Care. 2026;24(1):1-10. doi:10.63729/tjic.2026.683

BibTeX
@article{Elmaleh2026,
  author = {Elmaleh, Yoann and Moussali, Yassine and Boyer, Richard},
  title = {Artificial intelligence in preoperative assessment and optimization: a narrative review},
  journal = {Turkish Journal of Intensive Care},
  year = {2026},
  volume = {24},
  number = {1},
  pages = {1--10},
  doi = {10.63729/tjic.2026.683}
}
Kostenlos starten →