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

## TL;DR

This study compares statistical parametric mapping and explainable machine learning for detecting outliers in plantar pressure data, finding that machine learning performs better while remaining interpretable.

## Contribution

The novel contribution is a human-centered evaluation of SPM and explainable ML for outlier detection in plantar pressure datasets.

## Key findings

- The ML model outperformed SPM in outlier detection (Matthews Correlation Coefficient: ML = 0.96 ± 0.01; SPM = 0.78 ± 0.02).
- Experts found both SPM and SHAP explanations clear and trustworthy, though SPM was perceived as less complex.
- The study highlights the complementary potential of SPM and explainable ML for automated outlier detection in plantar pressure data.

## 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 cross-validation; 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). Experts perceived both SPM and SHAP explanations as clear, useful, and trustworthy, though SPM was assessed less complex. These findings highlight the complementary potential of SPM and explainable ML as approaches for automated outlier detection in plantar pressure data, and underscore the importance of explainability in translating complex model outputs into interpretable insights that can effectively inform decision-making.