Outlier Detection in Plantar Pressure: Human-Centered Comparison of Statistical Parametric Mapping and Explainable Machine Learning

2025-09-26

AI Summary

Outliers in plantar pressure data—often arising from technical errors or procedural inconsistencies—pose challenges for robust detection and clinical interpretability, where conventional Statistical Parametric Mapping (SPM) exhibits limitations. Method: We developed a transparent, reproducible quality control pipeline integrating SHAP-explained convolutional neural networks with nonparametric registration-based SPM, evaluated via human-centered comparative analysis. Using multicenter real-world data and controlled synthetic outliers, we assessed detection performance and explanation quality under nested cross-validation and expert semantic-difference surveys. Contribution/Results: Machine learning models achieved significantly higher accuracy; SPM frequently misclassified clinically meaningful biomechanical variation as outliers and failed to detect true anomalies. Both methods yielded expert-validated explanations, yet SPM required lower domain expertise for interpretation. This work highlights the complementary value of explainable AI and classical statistical approaches, establishing a novel paradigm for biomechanical data quality control.

Technology Category

Machine Learning: Calibration & Uncertainty QuantificationData Mining & Knowledge Management: Anomaly/Outlier DetectionNatural Language Processing: Safety and Robustness

Application Category

Responsible Web: Machine-in-the-loop, human agency and autonomyEconomics, Online Markets and Human Computation: Data quality aspects of human-annotated datasetsUser Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization

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 anomalies 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. 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.

Problem

• Comparing SPM and explainable ML for outlier detection
• Evaluating plantar pressure data quality control methods
• Assessing transparent anomaly identification in clinical biomechanics

Innovation

• CNN with SHAP for explainable outlier detection
• Statistical Parametric Mapping for interpretable analysis
• Comparing registration-dependent SPM with neural network