KIT | KIT-Bibliothek | Impressum | Datenschutz

Human-centered evaluation of statistical parametric mapping and explainable machine learning for outlier detection in plantar pressure data

Dindorf, Carlo ; Dully, Jonas; Simon, Steven; Perchthaler, Dennis; Becker, Stephan; Ehmann, Hannah; Heitmann, Kjell; Stetter, Bernd ORCID iD icon 1; Diers, Christian; Fröhlich, Michael
1 Institut für Sport und Sportwissenschaft (IfSS), Karlsruher Institut für Technologie (KIT)

Abstract:

Plantar pressure mapping is essential in clinical diagnostics and sports science, yet large heterogeneous datasets often contain outliers from technical errors or procedural inconsistencies. Statistical Parametric Mapping (SPM) provides interpretable analyses but is sensitive to alignment and its capacity for robust outlier detection remains unclear. This study compares an SPM approach with an explainable machine learning (ML) approach to establish transparent quality-control pipelines for plantar pressure datasets. Data from multiple centers were annotated by expert consensus and enriched with synthetic outliers resulting in 798 valid samples and 2000 outliers. We evaluated (i) a non-parametric, registration-dependent SPM approach and (ii) a convolutional neural network (CNN), explained using SHapley Additive exPlanations (SHAP). Performance was assessed via nested crossvalidation; explanation quality via a semantic differential survey with domain experts. The ML model reached high accuracy and outperformed SPM, which misclassified clinically meaningful variations and missed true outliers (Matthews Correlation Coefficient: ML = 0.96 ± 0.01; SPM = 0.78 ± 0.02). ... mehr


Verlagsausgabe §
DOI: 10.5445/IR/1000189772
Veröffentlicht am 20.01.2026
Cover der Publikation
Zugehörige Institution(en) am KIT Institut für Sport und Sportwissenschaft (IfSS)
Publikationstyp Zeitschriftenaufsatz
Publikationsjahr 2026
Sprache Englisch
Identifikator ISSN: 2045-2322
KITopen-ID: 1000189772
Erschienen in Scientific Reports
Verlag Nature Research
Band 16
Heft 1
Seiten Art.-Nr.: 1326
Vorab online veröffentlicht am 11.01.2026
Nachgewiesen in Web of Science
OpenAlex
KIT – Die Universität in der Helmholtz-Gemeinschaft
KITopen Landing Page