Confidence Filtering in Video-Based Gait Assessment: Measurement Error versus Selection Shift

Ranked by how close their title and abstract are to this paper’s. Select some to read them together.

Closest papers

1. Close Another approach to the problem Cited by this paper Not relevant

   EMBC Special Issue: Calibrated Uncertainty for Trustworthy Clinical Gait Analysis Using Probabilistic Multiview Markerless Motion Capture

   Seth Donahue, Irina Djuraskovic, Kunal Shah et al. · 2026 · IEEE Transactions on Biomedical Engineering · cited 5 times · Not summarized yet

   Calibrates probabilistic multiview pose estimates against clinical gold standards, whereas this paper tests whether confidence-based filtering shifts gait summaries.

   Abstract

   <italic>Objective:</italic> This study evaluates the calibration and accuracy of a probabilistic MMMC method. Video-based human movement analysis holds potential for movement assessment in clinical practice and research. However, the clinical implementation and trust of multi-view markerless motion capture (MMMC) require that, in addition to being accurate, these systems produce reliable confidence intervals to indicate how accurate they are for any individual. Building on our prior work utilizing variational inference to estimate estimate biomechanical variables against clinical gold-standards. <italic>Methods:</italic> We analyzed data from 68 participants across two institutions, validati…

2. Close Same question Not relevant

   Improving reliability of movement assessment in Parkinson's disease using computer vision-based automated severity estimation

   Jinyu Xu, Xin Xu, Xudong Guo et al. · 2025 · Journal of Parkinson's Disease · cited 10 times · Not summarized yet

   Develops computer-vision ratings of Parkinson’s motor symptoms, sharing this paper’s focus on video-based clinical movement assessment.

   Abstract

   Background Clinical assessments of motor symptoms rely on observations and subjective judgments against standardized scales, leading to variability due to confounders. Improving inter-rater agreement is essential for effective disease management. Objective We developed an objective rating system for Parkinson's disease (PD) that integrates computer vision (CV) and machine learning to correct potential discrepancies among raters while providing the basis for model performance to gain professional acceptance. Methods A prospective PD cohort (n = 128) were recruited from multi-centers. Motor examination videos were recorded using an android tablet with CV-based software following the MDS-UPDRS …

3. Close Same question Cited by this paper Not relevant

   Clinical gait analysis using video-based pose estimation: Multiple perspectives, clinical populations, and measuring change

   Jan Stenum, Melody Hsu, Alexander Pantelyat et al. · 2023 · medRxiv · cited 111 times · Not summarized yet

   Demonstrates video pose-estimation gait analysis across clinical populations and measures change, the assessment setting examined here.

   Abstract

   Gait dysfunction is common in many clinical populations and often has a profound and deleterious impact on independence and quality of life. Gait analysis is a foundational component of rehabilitation because it is critical to identify and understand the specific deficits that should be targeted prior to the initiation of treatment. Unfortunately, current state-of-the-art approaches to gait analysis (e.g., marker-based motion capture systems, instrumented gait mats) are largely inaccessible due to prohibitive costs of time, money, and effort required to perform the assessments. Here, we demonstrate the ability to perform quantitative gait analyses in multiple clinical populations using only …

4. Close Broader context Not relevant

   Evaluating Temporal Windows and Subject -Specific Fine -Tuning for Freezing of Gait Detection with Classical Machine Learning Models

   Clebson I. S. Silva, R. de Freitas Zampolo, Antônio Pereira · 2025 · Anais do XVII Congresso Brasileiro de Inteligência Computacional · Not summarized yet

   Evaluates machine-learning detection of freezing of gait from temporal windows, a neighboring Parkinson’s movement-analysis task.

   Abstract

   Freezing of Gait (FoG) is a critical motor symptom in Parkinson’s disease and a prime target for wearable-based detection. While global models trained across subjects offer scalability, they may fail to generalize to individuals with distinct gait signatures. This study investigates the effectiveness of classical machine learning models, explores the impact of temporal window size, and evaluates whether subject-specific fine-tuning improves detection performance. Using data from a dataset with 35 subjects performing a rotation-eliciting task, we show that ensemble models with 4–5 s windows achieve F1-scores up to 0.92. The results of the importance analysis of features highlight the role of …

5. Close Broader context Not relevant

   A Dual-Use Framework for Clinical Gait Analysis: Attention-Based Sensor Optimization and Automated Dataset Auditing

   Hamidreza Sadeghsalehi · 2025 · arXiv.org · preprint, not peer reviewed · cited 2 times · Not summarized yet

   Uses attention to optimize gait sensors and audit dataset bias, addressing data-quality concerns in clinical gait modeling.

   Abstract

   Objective gait analysis using wearable sensors and AI is critical for managing neurological and orthopedic conditions. However, models are vulnerable to hidden dataset biases, and task-specific sensor optimization remains a challenge. We propose a multi-stream attention-based deep learning framework that functions as both a sensor optimizer and an automated data auditor. Applied to the Voisard et al. (2025) multi-cohort gait dataset on four clinical tasks (PD, OA, CVA screening; PD vs CVA differential), the model's attention mechanism quantitatively discovered a severe dataset confound. For OA and CVA screening, tasks where bilateral assessment is clinically essential, the model assigned mor…

6. Close Same question Not relevant

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

   S. Rupprechter, Gareth Morinan, Yuwei Peng et al. · 2021 · Italian National Conference on Sensors · cited 77 times · Not summarized yet

   Estimates Parkinson’s gait impairment from video, sharing this paper’s clinical population and computer-vision assessment setting.

   Abstract

   Gait is a core motor function and is impaired in numerous neurological diseases, including Parkinson’s disease (PD). Treatment changes in PD are frequently driven by gait assessments in the clinic, commonly rated as part of the Movement Disorder Society (MDS) Unified PD Rating Scale (UPDRS) assessment (item 3.10). We proposed and evaluated a novel approach for estimating severity of gait impairment in Parkinson’s disease using a computer vision-based methodology. The system we developed can be used to obtain an estimate for a rating to catch potential errors, or to gain an initial rating in the absence of a trained clinician—for example, during remote home assessments. Videos (n=729) were co…

7. Close Review Not relevant

   Reliability and validity of current computer vision based motion capture systems in gait analysis: A systematic review.

   Xing-Ye Cheng, Yiran Jiao, R. Meiring et al. · 2025 · Gait & Posture · cited 41 times · Not summarized yet

   Systematically reviews the reliability, validity, and accuracy factors of pose-estimation gait analysis systems.

   Abstract

   BACKGROUND Traditional instrumented gait analysis (IGA) objectively quantifies gait deviations, but its clinical use is hindered by high cost, lab environment, and complex protocols. Pose estimation algorithm (PEA)-based gait analysis, which infers joint positions from videos, offers an accessible method to detect gait abnormalities and tailor rehabilitation strategies. However, its reliability and validity in gait analysis and algorithmic factors affecting accuracy have not been reviewed. RESEARCH QUESTION This systematic review aims to evaluate the accuracy of PEA-based gait analysis systems and to identify the algorithmic factors impacting their accuracy. METHOD A total of 644 articles we…

8. Close Same method, another problem Cited by this paper Not relevant

   Computer Vision for Gait Assessment in Cerebral Palsy: Metric Learning and Confidence Estimation

   Peijun Zhao, M. Alencastre-Miranda, Zhan Shen et al. · 2024 · IEEE transactions on neural systems and rehabilitation engineering · cited 12 times · Not summarized yet

   Uses pose-based machine learning and confidence estimation to assess motor impairment, applying related tools to cerebral palsy.

   Abstract

   Assessing the motor impairments of individuals with neurological disorders holds significant importance in clinical practice. Currently, these clinical assessments are time-intensive and depend on qualitative scales administered by trained healthcare professionals at the clinic. These evaluations provide only coarse snapshots of a person’s abilities, failing to track quantitatively the detail and minutiae of recovery over time. To overcome these limitations, we introduce a novel machine learning approach that can be administered anywhere including home. It leverages a spatial-temporal graph convolutional network (STGCN) to extract motion characteristics from pose data obtained from monocular…

Prior work it builds on

1. Related Same question Used in depth by this paper Not relevant

   Bridge-Disease Curriculum Transfer Enables Smartphone-Based Balance Assessment in Rare Neurologic Disorders

   E. Bamani, J. Buzzatto, Fang-Qiang Ding et al. · 2026 · IEEE transactions on neural systems and rehabilitation engineering · cited 1 time · Not summarized yet

   Develops smartphone video-based balance assessment for NF2, the rare-disease population also included in this paper.

   Abstract

   Video-based motor assessment could enable scalable assessment of neurological function, but rare-disease applications are constrained by extreme data scarcity and poor generalization from small cohorts. We develop and evaluate a smartphone-based balance-assessment framework in NF2-related schwannomatosis (NF2-SWN), an ultra-rare disorder for which objective balance assessment is clinically valuable yet logistically challenging. At its core, a staged bridge-disease curriculum adapts a skeleton-based spatiotemporal graph model from large-scale action recognition through an intermediate Parkinson’s disease domain to the target NF2-SWN cohort ( ${N}={19}$ ), decomposing one large domain shift in…

2. Related Groundwork for this paper Not relevant

   Using psychometric techniques to improve the Balance Evaluation System’s Test: the mini-BESTest

   F. Franchignoni, F. Horak, M. Godi et al. · 2010 · Journal of Rehabilitation Medicine · cited 1,015 times · Not summarized yet

   Uses psychometric analysis to develop the Mini-BESTest, the clinical outcome whose prediction error this paper evaluates.

   Abstract

   Objective To improve, with the aid of psychometric analysis, the Balance Evaluation System’s Test (BESTest), a tool designed to analyse several postural control systems that may contribute to poor functional balance in adults. Methods We examined performance of the BESTest in a convenience sample of 115 consecutive adult patients with diverse neurological diagnoses and disease severity, referred to rehabilitation for balance disorders. Factor (both explorative and confirmatory) and Rasch analysis were used to process the data in order to produce a new, reduced and coherent balance measurement tool. Results Factor analysis selected 24 out of the 36 original BESTest items likely to represent t…

3. Related Broader context Not relevant

   Selective Regression Under Fairness Criteria

   Abhin Shah, Yuheng Bu, J. Lee et al. · 2021 · International Conference on Machine Learning · cited 45 times · Not summarized yet

   Studies how confidence-based abstention can alter subgroup regression performance, a related selection concern outside gait assessment.

   Abstract

   Selective regression allows abstention from prediction if the confidence to make an accurate prediction is not sufficient. In general, by allowing a reject option, one expects the performance of a regression model to increase at the cost of reducing coverage (i.e., by predicting on fewer samples). However, as we show, in some cases, the performance of a minority subgroup can decrease while we reduce the coverage, and thus selective regression can magnify disparities between different sensitive subgroups. Motivated by these disparities, we propose new fairness criteria for selective regression requiring the performance of every subgroup to improve with a decrease in coverage. We prove that if a…

4. Related Same method, another problem Not relevant

   Interpretable Biomechanical Embeddings for CP Gait: From Clinical Metrics to Learned Representations

   E. B. Beeri, J. Buzzatto, H. Krebs · 2026 · International Conference on Biomedical Robotics and Biomechatronics · cited 1 time · Not summarized yet

   Learns interpretable biomechanical representations from pose data for cerebral-palsy gait assessment, using video-based movement modeling for another population.

   Abstract

   Recent advances in video-based gait analysis have enabled accurate clinical assessment of movement disorders using deep learning. Yet, the interpretability of these models and their correspondence to established biomechanical reasoning remain poorly understood, hindering their integration into clinical practice. This study complements our previous work on diffusion-augmented spatio-temporal graph convolutional networks (BA-STGCN) for gait assessment in children with cerebral palsy (CP). While our earlier research emphasized robustness and predictive accuracy, the present work shifts focus toward interpretability and clinical transparency. We investigate how data-driven spatio-temporal repres…

5. Related Same method, another problem Not relevant

   Diffusion-Augmented Spatiotemporal Graph Convolution for Clinical Gait and Motor Function Assessment

   E. Bamani, J. Buzzatto, H. Krebs · 2026 · IEEE transactions on neural systems and rehabilitation engineering · cited 4 times · Not summarized yet

   Combines skeleton diffusion and graph convolution for cerebral-palsy motor assessment, applying pose-based learning to another clinical population.

   Abstract

   Accurate assessment of gross motor function in children with cerebral palsy (CP) is essential for clinical decision-making, yet current practice is limited by data scarcity, severe class imbalance, and patient heterogeneity. Recent skeleton-based deep learning approaches, such as spatio-temporal graph convolutional networks (STGCN), enable automatic GMFCS prediction from monocular video but are limited in generalizability and fairness. In this work, we propose a unified generative–diagnostic pipeline that integrates a Conditional Skeleton Diffusion Model (CSDM) with a Biomechanically-Aware Spatio-Temporal Graph Convolutional Network (BA-STGCN). The CSDM generates clinically plausible 2D skel…