Kerstin Bach

Background: Accurate motor assessment is crucial for diagnosing and monitoring neurological and musculoskeletal disorders. However, traditional manual and semiautomated methods can be subjective, time-consuming, or expensive. Real-time 3D human pose estimation (HPE) is emerging as a low-cost, noninvasive alternative. However, its clinical adoption is limited due to a lack of thorough, standardized evaluation of its accuracy and robustness in real-world clinical settings. Objective: This study aims to introduce a technical pipeline for evaluating the applicability of real-time 3D HPE in simulated clinical rehabilitation settings. Methods: The framework facilitates the evaluation of an HPE model’s spatial and spatiotemporal accuracy, real-time capability, and robustness against simulated common setup errors and camera position variations, using a marker-based motion capture system as a gold-standard baseline. To address the technical challenge of interdataset comparison, the framework includes a morphing model that harmonizes differing joint definitions. Results: Applying the framework to a popular, accessible real-time algorithm (MediaPipe) on 4 healthy participants (N=127,828 frames) showed that simulated underexposure and defocus blur had negligible effects (rank-biserial correlation [RBC] ≤0.02), whereas body segment occlusion (mean-per-joint angular error [MPJAE] increase of 1.5, SD 10 degrees; +24.3%) and insufficient multiocular calibration (MPJAE increase of 7.8, SD 14 degrees; +123.4%, RBC=0.95) significantly degraded tracking accuracy. The framework also showed significant sensitivity to nonfrontal camera placements, both side- and back-facing views (RBC 0.41‐0.49 and bias up to 2.2 degrees/37.1%), relative to stable frontal placements (RBC ≤0.03). The skeleton morphing module reduced Procrustes-aligned mean per joint position error (PA-MPJPE) by 55.29 mm (N=79,423 frames, 57.2% reduction) and its SD by 24.69 mm (N=79,423 frames, 50.7%). Conclusions: This study establishes a technical foundation for the standardized evaluation of markerless tracking for clinical applications, like motor rehabilitation. The morphing model enables interdataset comparison, and the proposed framework facilitates domain-specific interpretation of HPE performance. While further validation on pathological populations is required, this work provides the necessary engineering foundation for future validation studies.

Today, the use of Artificial Intelligence (AI) is rapidly increasing in many areas of society. While model performance on various tasks continue to impress, it does so at the cost of increased model complexity, such that most state-of-the-art AI models are effectively black boxes. Where human-made decisions typically are accompanied by human-understandable explanations detailing the reasoning behind the decision, incorporating advanced AI as part of a decision-making process reduces the transparency of that process significantly. Yet, the ability to explain decisions is essential for there to be understanding and trust. As a response to this, Explainable Artificial Intelligence (XAI) has emerged as a field that aims to provide explanations of model behaviour. Methods categorised as post-hoc are designed to generate explanations for black box models after training, at no cost to model performance. In parallel with this, extensive work has been done in the field of causality to formalise the structure of human-understandable, causal explanations. This work presents a comprehensive literature review of the current state of the subfield of XAI that consist of causality-motivated post-hoc XAI methods. In order to clearly define causal XAI, a causal framework for categorising XAI is introduced, and three types of post-hoc XAI methods are identified: observational methods, internally causal methods and externally causal methods. Finally, externally causal XAI is argued a promising direction for reliable and understandable post-hoc XAI, with the ability to generate counterfactual explanations using a meaningful vocabulary, in line with the definition of counterfactual used in causal theory.

BACKGROUND Accurate motor assessment is crucial for diagnosing and monitoring neurological and musculoskeletal disorders. However, traditional manual and semiautomated methods can be subjective, time-consuming, or expensive. Realtime 3D Human Pose Estimation (HPE) is emerging as a lowcost, noninvasive alternative. However, its clinical adoption is limited due to a lack of thorough, standardized evaluation of its accuracy and robustness in realworld clinical settings. OBJECTIVE This study introduces a technical pipeline for evaluating the applicability of realtime 3D HPE in simulated clinical rehabilitation settings. METHODS The framework facilitates the evaluation of an HPE model's spatial and spatiotemporal accuracy, realtime capability, and robustness against simulated common setup errors and camera position variations, using a marker-based motion capture system as a gold-standard baseline. To address the technical challenge of inter-dataset comparison, the framework includes a morphing model that harmonizes differing joint definitions. RESULTS Applying the framework to an exemplary state-of-the-art algorithm (Mediapipe) demonstrated the pipeline's sensitivity to image distortions. The metrics showed that simulated underexposure and blur had negligible effects, whereas body segment occlusion and insufficient multiocular calibration significantly degraded tracking accuracy. Additionally, the framework showed significant sensitivity to specific camera placements (sagittal views), in contrast to more stable frontal views. CONCLUSIONS This study establishes a technical foundation for the standardized evaluation of markerless tracking for clinical applications, like motor rehabilitation. The morphing model enables inter-dataset comparison, and the proposed framework facilitates domain-specific interpretation of HPE performance. While further validation on pathological populations is required, this work provides the necessary engineering foundation for future validation studies.

Counterfactual explanations provide intuitive insights into AI model decisions by showing minimal changes needed to alter predictions. However, generating plausible counterfactuals for multivariate time series remains challenging due to complex temporal dependencies, inter-channel correlations, and the need to preserve physiologically realistic patterns, particularly in safety-critical domains like healthcare. This paper presents a novel framework for generating plausible counterfactual explanations for multivariate time series classification, demonstrated on 12-lead ECG data. Our approach employs a hierarchical perturbation strategy guided by permutation-based feature importance, operating at both segment and channel levels to handle temporal dependencies and channel correlations inherent in time series. By anchoring counterfactuals to existing instances from the target class, we enrich plausibility while maintaining minimal modifications. Our evaluation demonstrates significant improvements over the baseline method: 98% validity (vs. 65%), 43% reduction in required modifications, and 75% improvement in proximity to original instances. This work contributes: (I) a perturbation-based explanation approach combining instance-based and importance-guided generation for time series, (II) comprehensive evaluation metrics tailored for multivariate time series, and (III) empirical validation on medical data where interpretability is crucial for clinical adoption.

We developed the SupportPrim PT clinical decision support system (CDSS) using the artificial intelligence method case-based reasoning to support personalised musculoskeletal pain management. The aim of this study was to evaluate the effectiveness of the CDSS for patients in physiotherapy practice. A cluster randomised controlled trial was conducted in primary care in Norway. We randomised 44 physiotherapists to (1) use the CDSS alongside usual care or (2) usual care alone. The CDSS provided personalised treatment recommendations based on a case base of 105 patients with positive outcomes. During the trial, the case-based reasoning system did not have an active learning capability; therefore, the case base size remained the same throughout the study. We included 724 patients presenting with neck, shoulder, back, hip, knee, or complex pain (CDSS; n = 358, usual care; n = 366). Primary outcomes were assessed with multilevel logistic regression using self-reported Global Perceived Effect (GPE) and Patient-Specific Functional Scale (PSFS). At 12 weeks, 165/298 (55.4%) patients in the intervention group and 176/321 (54.8%) in the control group reported improvement in GPE (odds ratio, 1.18; confidence interval, 0.50-2.78). For PSFS, 173/290 (59.7%) patients in the intervention group and 218/310 (70.3%) in the control group reported clinically important improvement in function (odds ratio, 0.41; confidence interval, 0.20-0.85). No significant between-group differences were found for GPE. For PSFS, there was a significant difference favouring the control group, but this was less than the prespecified difference of 15%. We identified several study limitations and recommend further investigation into artificial intelligence applications for managing musculoskeletal pain.

Background: Self-management is endorsed in clinical practice guidelines for the care of musculoskeletal pain. In a randomized clinical trial, we tested the effectiveness of an artificial intelligence–based self-management app (selfBACK) as an adjunct to usual care for patients with low back and neck pain referred to specialist care. Objective: This study is a process evaluation aiming to explore patients’ engagement and experiences with the selfBACK app and specialist health care practitioners’ views on adopting digital self-management tools in their clinical practice. Methods: App usage analytics in the first 12 weeks were used to explore patients’ engagement with the SELFBACK app. Among the 99 patients allocated to the SELFBACK interventions, a purposive sample of 11 patients (aged 27-75 years, 8 female) was selected for semistructured individual interviews based on app usage. Two focus group interviews were conducted with specialist health care practitioners (n=9). Interviews were analyzed using thematic analysis. Results: Nearly one-third of patients never accessed the app, and one-third were low users. Three themes were identified from interviews with patients and health care practitioners: (1) overall impression of the app, where patients discussed the interface and content of the app, reported on usability issues, and described their app usage; (2) perceived value of the app, where patients and health care practitioners described the primary value of the app and its potential to supplement usual care; and (3) suggestions for future use, where patients and health care practitioners addressed aspects they believed would determine acceptance. Conclusions: Although the app’s uptake was relatively low, both patients and health care practitioners had a positive opinion about adopting an app-based self-management intervention for low back and neck pain as an add-on to usual care. Both described that the app could reassure patients by providing trustworthy information, thus empowering them to take actions on their own. Factors influencing app acceptance and engagement, such as content relevance, tailoring, trust, and usability properties, were identified. Trial Registration: ClinicalTrials.gov NCT04463043; https://clinicaltrials.gov/study/NCT04463043

In eXplainable Artificial Intelligence (XAI), instance-based explanations have gained importance as a method for illuminating complex models by highlighting differences or similarities between the samples and their explanations. The evaluation of these explanations is crucial for assessing their quality and effectiveness. However, the quantitative evaluation of instance-based explanation methods reveals inconsistencies and variations in terminology and metrics. Addressing this, our survey provides a unified notation for instance-based explanation evaluation metrics for instance-based explanations with a particular focus on counterfactual explanations. Further, it explores associated trade-offs, identifies areas for improvement, and offers a practical Python toolkit, CEval. Key contributions include a comprehensive survey of quantitative evaluation metrics, facilitating practical counterfactual evaluation with the package, and providing insights into explanation evaluation limitations and future directions.