EUVIMEDEUVIMED entdecken
Crossref

Reproducibility and class-level audit of wellbeing classification in the DigitalExposome dataset

Özel Sebetci iD

Technology and Health Care · 17.11.2026

DOI: 10.1177/09287329261509125 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Technology and Health Care, online erschienen am 17.11.2026. Verfasst von Özel Sebetci. Beteiligte Einrichtung: Department of Computer Technologies, Aydın Adnan Menderes University, Aydın, Türkiye. Die Arbeit nennt 21 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Repeated observations and missing participant and time metadata can complicate interpretation of wellbeing classification results from public sensor datasets.

Objective

To assess reproducibility and split sensitivity of wellbeing classification on the released DigitalExposome CSV.

Methods

We reconstructed an initially submitted 30-sample, 15-sample-stride windowed Random Forest (RF) analysis and compared matched 70/30 file-order and unstratified random row splits. Ten random seeds quantified partition variability. We recalculated class-level metrics and ran a deduplicated, 30-row positional-embargo sensitivity analysis. The CSV contains no participant identifiers or timestamps.

Results

The file-order RF holdout gave Macro F1 = 0.8515; random splits yielded mean Macro F1 = 0.9772 (SD = 0.0014). Reconstructed windows yielded accuracy = 0.7887, Macro F1 = 0.7632, and weighted F1 = 0.7549. Recalculated recall was 0.205 for wellbeing level 2. The deduplicated sensitivity analysis produced Macro F1 values of 0.128–0.162 across examined split fractions and leaf settings.

Conclusion

Scores were sensitive to split procedure and repeated feature vectors. Because row chronology and participant membership cannot be recovered, these results do not estimate future-time or participant-independent performance and do not establish clinical utility.

Schlagwörter

Stichwörter der Autor:innen

DigitalExposomeduplicate observationsevaluation protocolrandom forestreproducibilityself-reported wellbeingsensor data

Autor:innen und Institutionen

  • Department of Computer Technologies, Aydın Adnan Menderes University, Aydın, Türkiye.

ORCID-Profile: Özel Sebetci

Zitieren

APA

Sebetci, Ö. (2026). Reproducibility and class-level audit of wellbeing classification in the DigitalExposome dataset. Technology and Health Care. https://doi.org/10.1177/09287329261509125

Vancouver

Sebetci Ö. Reproducibility and class-level audit of wellbeing classification in the DigitalExposome dataset. Technology and Health Care. 2026. doi:10.1177/09287329261509125

BibTeX
@article{Sebetci2026,
  author = {Sebetci, Özel},
  title = {Reproducibility and class-level audit of wellbeing classification in the DigitalExposome dataset},
  journal = {Technology and Health Care},
  year = {2026},
  doi = {10.1177/09287329261509125}
}
Kostenlos starten →