EUVIMEDEUVIMED entdecken
MetaanalyseSystematische ÜbersichtOpen Access · CC BY-NC-ND 4.0

Machine learning‐based prediction models for pressure injury: A systematic review and meta‐analysis

Juhong Pei iD, Xiaojing Guo, Hongxia Tao iD, Yuting Wei, Hongyan Zhang, Yuxia Ma, Lin Han iD

International Wound Journal · 2023-12 · 20 (10) · 4328-4339

DOI: 10.1111/iwj.14280 ↗

Kurz gefasst

Metaanalyse in der Zeitschrift International Wound Journal, online erschienen am 20.06.2023. Verfasst von Juhong Pei und 6 weiteren Autor:innen. Beteiligte Einrichtung: The First Clinical Medical College, School of Nursing, Lanzhou University, Lanzhou, China. Hauptthemen laut MEDLINE: Pressure Ulcer. Die Arbeit wurde bisher 34-mal zitiert (Crossref) und nennt 51 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: National Nature Science Foundation of China, the National scientific research training plan of Gansu Provincial Hospital, Provincial Talent Project of Gansu Province.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Despite the fact that machine learning (ML) algorithms to construct predictive models for pressure injury development are widely reported, the performance of the model remains unknown. The goal of the review was to systematically appraise the performance of ML models in predicting pressure injury. PubMed, Embase, Cochrane Library, Web of Science, CINAHL, Grey literature and other databases were systematically searched. Original journal papers were included which met the inclusion criteria. The methodological quality was assessed independently by two reviewers using the Prediction Model Risk of Bias Assessment Tool (PROBAST). Meta‐analysis was performed with Metadisc software, with the area under the receiver operating characteristic curve, sensitivity and specificity as effect measures. Chi‐squared and I 2 tests were used to assess the heterogeneity. A total of 18 studies were included for the narrative review, and 14 of them were eligible for meta‐analysis. The models achieved excellent pooled AUC of 0.94, sensitivity of 0.79 (95% CI [0.78–0.80]) and specificity of 0.87 (95% CI [0.88–0.87]). Meta‐regressions did not provide evidence that model performance varied by data or model types. The present findings indicate that ML models show an outstanding performance in predicting pressure injury. However, good‐quality studies should be conducted to verify our results and confirm the clinical value of ML in pressure injury development.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Pressure UlcerHumansSensitivity and SpecificityROC CurveMachine LearningSoftware

Stichwörter der Autor:innen

machine learning algorithmmeta-analysispredictive modellingpressure injury

Autor:innen und Institutionen

  • The First Clinical Medical College, School of Nursing, Lanzhou University, Lanzhou, China.
  • School of Nursing, Lanzhou University, Lanzhou, China.
  • Department of Nursing, Gansu Provincial Hospital, Lanzhou, China.

ORCID-Profile: Juhong Pei, Hongxia Tao, Lin Han

Förderung

  • National Nature Science Foundation of China
  • the National scientific research training plan of Gansu Provincial Hospital
  • Provincial Talent Project of Gansu Province
  • National Natural Science Foundation of China

Zitieren

APA

Pei, J., Guo, X., Tao, H., Wei, Y., Zhang, H., Ma, Y., & Han, L. (2023). Machine learning‐based prediction models for pressure injury: A systematic review and meta‐analysis. International Wound Journal, 20(10), 4328-4339. https://doi.org/10.1111/iwj.14280

Vancouver

Pei J, Guo X, Tao H, Wei Y, Zhang H, Ma Y, et al. Machine learning‐based prediction models for pressure injury: A systematic review and meta‐analysis. International Wound Journal. 2023;20(10):4328-4339. doi:10.1111/iwj.14280

BibTeX
@article{Pei2023,
  author = {Pei, Juhong and Guo, Xiaojing and Tao, Hongxia and Wei, Yuting and Zhang, Hongyan and Ma, Yuxia and Han, Lin},
  title = {Machine learning‐based prediction models for pressure injury: A systematic review and meta‐analysis},
  journal = {International Wound Journal},
  year = {2023},
  volume = {20},
  number = {10},
  pages = {4328--4339},
  doi = {10.1111/iwj.14280}
}
Kostenlos starten →