EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Evaluating automated machine learning platforms for use in healthcare

Ian A Scott iD, Keshia R De Guzman, Nazanin Falconer, Stephen Canaris, Oscar Bonilla, Steven M McPhail, Sven Marxen, Aaron Van Garderen, Ahmad Abdel-Hafez, Michael Barras

JAMIA Open · 08.04.2024 · 7 (2)

DOI: 10.1093/jamiaopen/ooae031 ↗

Kurz gefasst

Fachartikel in der Zeitschrift JAMIA Open, online erschienen am 10.06.2024. Verfasst von Ian A Scott und 9 weiteren Autor:innen. Beteiligte Einrichtung: Centre for Health Services Research, University of Queensland, Brisbane, 4102, Australia. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objective

To describe development and application of a checklist of criteria for selecting an automated machine learning (Auto ML) platform for use in creating clinical ML models. Materials and Methods Evaluation criteria for selecting an Auto ML platform suited to ML needs of a local health district were developed in 3 steps: (1) identification of key requirements, (2) a market scan, and (3) an assessment process with desired outcomes.

Results

The final checklist comprising 21 functional and 6 non-functional criteria was applied to vendor submissions in selecting a platform for creating a ML heparin dosing model as a use case.

Discussion

A team of clinicians, data scientists, and key stakeholders developed a checklist which can be adapted to ML needs of healthcare organizations, the use case providing a relevant example.

Conclusion

An evaluative checklist was developed for selecting Auto ML platforms which requires validation in larger multi-site studies.

Schlagwörter

Stichwörter der Autor:innen

artificial intelligenceautomatedmachine learning

Autor:innen und Institutionen

  • Centre for Health Services Research, University of Queensland, Brisbane, 4102, Australia.
  • Department of Internal Medicine and Clinical Epidemiology, Princess Alexandra Hospital, Brisbane, 4102, Australia.
  • Department of Pharmacy, Princess Alexandra Hospital, Brisbane, 4102, Australia.
  • School of Pharmacy, The University of Queensland, Brisbane, 4102, Australia.
  • Digital Health and Informatics, Metro South Health, Brisbane, 4102, Australia.
  • Australian Centre for Health Services Innovation and Centre for Healthcare Transformation, School of Public Health and Social Work, Queensland University of Technology, Brisbane, 4059, Australia.

ORCID-Profile: Ian A Scott

Zitieren

APA

Scott, I. A., De Guzman, K. R., Falconer, N., Canaris, S., Bonilla, O., McPhail, S. M., Marxen, S., Van Garderen, A., Abdel-Hafez, A., & Barras, M. (2024). Evaluating automated machine learning platforms for use in healthcare. JAMIA Open, 7(2). https://doi.org/10.1093/jamiaopen/ooae031

Vancouver

Scott IA, De Guzman KR, Falconer N, Canaris S, Bonilla O, McPhail SM, et al. Evaluating automated machine learning platforms for use in healthcare. JAMIA Open. 2024;7(2). doi:10.1093/jamiaopen/ooae031

BibTeX
@article{Scott2024,
  author = {Scott, Ian A and De Guzman, Keshia R and Falconer, Nazanin and Canaris, Stephen and Bonilla, Oscar and McPhail, Steven M and Marxen, Sven and Van Garderen, Aaron and Abdel-Hafez, Ahmad and Barras, Michael},
  title = {Evaluating automated machine learning platforms for use in healthcare},
  journal = {JAMIA Open},
  year = {2024},
  volume = {7},
  number = {2},
  doi = {10.1093/jamiaopen/ooae031}
}
Kostenlos starten →