EUVIMEDEUVIMED entdecken
ValidierungsstudieOpen Access · CC BY 4.0

External validation of a machine learning-based web application for personalized testing of objective functioning using the five-repetition sit-to-stand test

Kenneth Arockia, Massimo Bottini iD, Anita M Klukowska iD, Victor Gabriel El-Hajj iD, Maria Gharios iD, Ali Buwaider iD, Carlo Serra iD, Luca Regli iD, Marc L Schröder, Victor E Staartjes iD

Acta Neurochirurgica · 18.08.2026 · 168 (1)

DOI: 10.1007/s00701-026-07005-z ↗

Kurz gefasst

Validierungsstudie in der Zeitschrift Acta Neurochirurgica, online erschienen am 18.08.2026. Verfasst von Kenneth Arockia und 9 weiteren Autor:innen. Beteiligte Einrichtung: Machine Intelligence in Clinical Neuroscience & Microsurgical Neuroanatomy (MICN) Laboratory, Department of Neurosurgery, Clinical Neuroscience Cente…. Hauptthemen laut MEDLINE: Machine Learning, Internet, Exercise Test. Die Arbeit nennt 20 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: University of Zurich.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Purpose

Simple generalized thresholds for assessing functional impairment in clinical testing are limited, as they fail to consider patient-specific properties such as age, body height, and body mass index. A previously developed machine learning-based model for personalized testing using the five-repetition sit-to-stand (5R-STS) test, that estimates personalized upper limits of normal (ULN) to identify objective functional impairment (OFI) was externally validated to evaluate its performance and generalizability across cohorts.

Methods

Only healthy individuals were included in the study. After the machine learning-based model was applied to this external dataset, expected and observed 5R-STS test times were compared using standardized performance assessment metrics including root mean square error (RMSE), mean absolute error (MAE), and R 2 values. Additionally, a Bland–Altman analysis was performed to assess agreement between observed and expected values. Validation of the expected ULN involved comparing the proportion of individuals exceeding their personalized thresholds with the corresponding proportion based on the generalized threshold. Subgroup analyses by test setting and country of residence were additionally performed, along with a graphical assessment of model performance.

Results

Application of the model to 171 healthy individuals resulted in an RMSE of 2.33 (95% CI: 1.93 to 2.73) seconds, MAE of 1.70 (95% CI: 1.47 to 1.94) seconds, and R 2 of 0.064 (95% CI: -0.25 to 0.15). The Bland–Altman analysis demonstrated a mean bias of -1.1 s. Based on the personalized ULNs, OFI was classified in 17.5% of individuals, compared to 6.4% when using the generalized threshold of 10.4 s. These analyses indicated limited external generalization, with acceptable approximation for some faster and mid-range test times but systematic underestimation of slower test times. Multivariable regression analyses showed that remote testing was independently associated with greater prediction bias and higher odds of personalized ULN exceedance compared with supervised testing (adjusted mean difference: − 0.90 s; adjusted OR: 10.7). Exploratory country-of-residence analyses showed differences across the three largest national subgroups. 130 (76.1%) rated ease of use as excellent, and 145 (84.9%) rated clarity of instructions as excellent. 143 participants (83.6%) indicated that they prefer the 5R-STS over a battery of questionnaires.

Conclusions

In the context of personalized testing, moving toward individually focused precision assessment of patients requires rigorous external validation to ensure the robustness of such applied computational methods. In this external validation, the model demonstrated limited generalization including a systematic underestimation of slower test times and insufficient personalized ULN calibration. These findings indicate that external validity of models derived from single-center data can be limited, underscoring the importance of comprehensive external validation and, potentially, multicenter retraining before clinical implementation.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Machine LearningInternetExercise TestHumansFemaleMaleAdultMiddle AgedReproducibility of ResultsYoung AdultPrecision Medicine

Stichwörter der Autor:innen

External validationFive-repetition sit-to-stand testMachine learningObjective functional testingPersonalized medicinePrecision medicine

Autor:innen und Institutionen

  • Machine Intelligence in Clinical Neuroscience & Microsurgical Neuroanatomy (MICN) Laboratory, Department of Neurosurgery, Clinical Neuroscience Center, University Hospital Zurich, University of Zurich, Frauenklinikstras…
  • Department of Neurosurgery, Medical University of Bialystok, Białystok, Poland.
  • Department of Clinical Neuroscience, Karolinska Institutet, Stockholm, Sweden.
  • Department of Neurosurgery, Medical University of Innsbruck, Innsbruck, Austria.
  • Department of Clinical Neuroscience, Karolinska Institutet, Stockholm, Sweden. victoregon.staartjes@usz.ch.
  • Capio Spine Center Stockholm, Löwenströmska Hospital, Stockholm, Sweden. victoregon.staartjes@usz.ch.

ORCID-Profile: Massimo Bottini, Anita M Klukowska, Victor Gabriel El-Hajj, Maria Gharios, Ali Buwaider, Carlo Serra, Luca Regli, Victor E Staartjes

Förderung

  • University of Zurich

Zitieren

APA

Arockia, K., Bottini, M., Klukowska, A. M., El-Hajj, V. G., Gharios, M., Buwaider, A., Serra, C., Regli, L., Schröder, M. L., & Staartjes, V. E. (2026). External validation of a machine learning-based web application for personalized testing of objective functioning using the five-repetition sit-to-stand test. Acta Neurochirurgica, 168(1). https://doi.org/10.1007/s00701-026-07005-z

Vancouver

Arockia K, Bottini M, Klukowska AM, El-Hajj VG, Gharios M, Buwaider A, et al. External validation of a machine learning-based web application for personalized testing of objective functioning using the five-repetition sit-to-stand test. Acta Neurochirurgica. 2026;168(1). doi:10.1007/s00701-026-07005-z

BibTeX
@article{Arockia2026,
  author = {Arockia, Kenneth and Bottini, Massimo and Klukowska, Anita M and El-Hajj, Victor Gabriel and Gharios, Maria and Buwaider, Ali and Serra, Carlo and Regli, Luca and Schröder, Marc L and Staartjes, Victor E},
  title = {External validation of a machine learning-based web application for personalized testing of objective functioning using the five-repetition sit-to-stand test},
  journal = {Acta Neurochirurgica},
  year = {2026},
  volume = {168},
  number = {1},
  doi = {10.1007/s00701-026-07005-z}
}
Kostenlos starten →