Interpretability of Input Representations for Gait Classification in Patients after Total Hip Arthroplasty

Abstract

Many machine learning models show black box characteristics and, therefore, a lack of transparency, interpretability, and trustworthiness. This strongly limits their practical application in clinical contexts. For overcoming these limitations, Explainable Artificial Intelligence (XAI) has shown promising results. The current study examined the influence of different input representations on a trained model’s accuracy, interpretability, as well as clinical relevancy using XAI methods. The gait of 27 healthy subjects and 20 subjects after total hip arthroplasty (THA) was recorded with an inertial measurement unit (IMU)-based system. Three different input representations were used for classification. Local Interpretable Model-Agnostic Explanations (LIME) was used for model interpretation. The best accuracy was achieved with automatically extracted features (mean accuracy Macc = 100%), followed by features based on simple descriptive statistics (Macc = 97.38%) and waveform data (Macc = 95.88%). Globally seen, sagittal movement of the hip, knee, and pelvis as well as transversal movement of the ankle were especially important for this specific classification task. The current work shows that the type of input representation crucially determines interpretability as well as clinical relevance. A combined approach using different forms of representations seems advantageous. The results might assist physicians and therapists finding and addressing individual pathologic gait patterns.

Identification of Patients with Sarcopenia Using Gait Parameters Based on Inertial Sensors

“…In recent years, interest in XAI has been increasing owing to its classification accuracy and to features that significantly contributed to classification. Dindorf et al [ 12 ] used the local interpretable model-agnostic explanations (LIME) to understand the features for identifying total hip arthroplasty (THA), and found that the sagittal movement of the hip, knee, and pelvis as well as transversal movement of the ankle were especially important for this specific classification task, as shown in Table 2 .…”

“…In the field of gait analysis, domain knowledge to detect gait parameters remains important for designing the inputs of the model. The explainable artificial intelligence (XAI) method is receiving increased attention as a method used to obtain domain knowledge based on machine learning [ 12 ].…”

A Clinically Interpretable Computer-Vision Based Method for Quantifying Gait in Parkinson’s Disease

“…Studies focusing on classification of PD gait achieved good accuracy, but relied on “black box” systems which are difficult to interpret [ 25 ]. Previous studies focusing on interpretability of gait analysis systems used marker based motion capture systems [ 26 , 27 ], and devices such as inertial measurement units [ 28 ]. However, to our knowledge, no study has focused on interpretability of systems that utilise markerless pose estimation for classification of PD gait.…”

Classification and Automated Interpretation of Spinal Posture Data Using a Pathology-Independent Classifier and Explainable Artificial Intelligence (XAI)

“…This opacity does not comply with the requirements of the European General Data Protection Regulation (GDPR, EU 2016/679) [ 29 ] and strongly limits practical applications in clinical contexts [ 30 ]. Recently, through advances in the application of explainable artificial intelligence (XAI) methods in the biomechanical clinical domain, machine learning is becoming more and more applicable in practical clinical settings [ 31 , 32 ]. XAI offers methods for increasing the trustworthiness and transparency of black box models [ 27 ].…”