ADAlexis Dorier

Alexis Dorier

*This is an algorithmically generated author record based on publicly available information.

Alexis Dorier has a total of 27 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Towards automated joint detection in sleep studies: bridging clinical insight and artificial intelligence

    by Alexis Dorier, Pietro-Luca Ratti, Mkael Symmonds, Timothy Quinnell, Gary Dennis, Christine Lo, Michele T Hu, Mauricio Villarroel

    Study objectives: To develop and evaluate artificial intelligence methods for detecting upper-body joint positions from video recordings of individuals during sleep, providing a foundation for future automated, video-based analysis of sleep movements that extends beyond conventional sensor-based methods. Methods: We developed HypnoPose and tested five different model configurations. We pretrained each variant on a public body pose dataset and evaluated on a sleep pose dataset comprising 4419 annotated frames from 198 video segments depicting movement across 74 participants (10 RBD, 4 PD, 9 healthy controls, 51 referred for vPSG screening) recorded in clinical and home settings. We manually annotated each frame with 13 body joints, visibility flags, and head orientation. We evaluated model performance against state-of-the-art pose estimators using precision (mAP) and recall (mAR) metrics based on Object Keypoint Similarity (OKS). Results: HypnoPose achieved the highest performance (mAP: 0.088, AP@0.5: 0.326) in the sleep domain, doubling baseline HigherHRNet results (mAP: 0.041, AP@0.5: 0.165) and outperforming gold-standard architectures. It showed 40%–120% relative mAP improvement for occluded joints, enhancing detection of the head, shoulders, and elbows. Home recordings showed higher precision than clinic data (mAP 0.14 vs 0.07). Within clinic recordings, NREM stages outperform Wake (mAP 0.11–0.13 vs 0.06). Conclusions: We present a proof-of-concept for detecting upper-body joint positions from sleep images, even when blankets occlude the person. Our method improves relative precision by 115% compared to standard models. While absolute performance remains modest, this work establishes a first step toward clinically applicable, video-based pose estimation during sleep. Future work should integrate contextual priors and expand annotated sleep datasets. Statement of Significance Video polysomnography (vPSG) is the gold standard for assessing sleep-related disorders. It is resource-intensive, requires specialist expertise for setup and interpretation, and may not capture typical sleep due to the presence of multiple sensors and the laboratory environment. In some populations, such as individuals with REM sleep behavior disorder (RBD), vPSG can be challenging, and clinically relevant behaviors may not occur during a single recording night. At-home recordings provide greater environmental validity but are often constrained by nonstandard camera positioning and suboptimal lighting. This study introduces a benchmark for automated, frame-wise upper-body pose estimation, to identify anatomical joint positions during sleep. While tools for detecting periodic limb movements and REM sleep without atonia already exist, there remains a critical need for objective, scalable methods to quantify complex movements seen in disorders such as RBD, NREM parasomnias, and sleep-related epilepsies. This work lays the foundation for future automated, noncontact movement analysis that complements existing vPSG workflows, reduces manual review time, and supports accessible monitoring of sleep behavior in both clinical and home environments.

  • A Stand-Alone Augmented Reality Intervention for Chronic Pain Using Embodied Systolic Stimulation

    by Oliver A Kannape, Jonathan Pierret, Robert Leeb, Sylvain Cardin, Fabien Bourban, Skander Mensi, Yann Lebrun, Nicolas Merlini, Alexis Dorier, Vincent Moriot, et al.

    Chronic pain presents a tremendous personal, societal, and financial burden. Treatment options are often limited to managing symptoms as opposed to treating the causes, and the consequences of pharmacological treatments can be immensely harmful as evidenced by the on-going opioid epidemic. Virtual Reality interventions and digital therapeutics provide a new tool for therapists but are currently limited to pain-distraction or digitizing traditional approaches that are similarly focused on pain management. However, recent research suggests that potentially neurorestorative, non-pharmacological treatments are conceivable using personalized, embodied, multimodal feedback. In particular, i) providing visual feedback of the affected body part, ii) increasing its embodiment using multisensory stimulation, and iii) timing stimulation to the systole of the ECG cycle have been linked with analgesic effects in induced acute and chronic pain. Based on these findings and methods, we here propose a stand-alone solution that aims to provide neurorestorative feedback for individuals suffering from chronic pain by visualizing interoceptive signals and mapping them onto the patients affected body part using Augmented Reality, tapping into the three aforementioned principles. Our initial findings indicate the feasibility, acceptance, and stimulus adherence of the device and intervention, whose efficacy will be evaluated in an upcoming randomized controlled clinical trial.


  • Open Access

    Autoencoder as a New Method for Maintaining Data Privacy While Analyzing Videos of Patients With Motor Dysfunction: Proof-of-Concept Study

    by Marcus D'Souza, Caspar E P Van Munster, Jonas F Dorn, Alexis Dorier, Christian P Kamm, Saskia Steinheimer, Frank Dahlke, Bernard M J Uitdehaag, Ludwig Kappos, Matthew Johnson

    Background: In chronic neurological diseases, especially in multiple sclerosis (MS), clinical assessment of motor dysfunction is crucial to monitor the disease in patients. Traditional scales are not sensitive enough to detect slight changes. Video recordings of patient performance are more accurate and increase the reliability of severity ratings. When these recordings are automated, quantitative disability assessments by machine learning algorithms can be created. Creation of these algorithms involves non–health care professionals, which is a challenge for maintaining data privacy. However, autoencoders can address this issue. Objective: The aim of this proof-of-concept study was to test whether coded frame vectors of autoencoders contain relevant information for analyzing videos of the motor performance of patients with MS. Methods: In this study, 20 pre-rated videos of patients performing the finger-to-nose test were recorded. An autoencoder created encoded frame vectors from the original videos and decoded the videos again. The original and decoded videos were shown to 10 neurologists at an academic MS center in Basel, Switzerland. The neurologists tested whether the 200 videos were human-readable after decoding and rated the severity grade of each original and decoded video according to the Neurostatus-Expanded Disability Status Scale definitions of limb ataxia. Furthermore, the neurologists tested whether ratings were equivalent between the original and decoded videos. Results: In total, 172 of 200 (86.0%) videos were of sufficient quality to be ratable. The intrarater agreement between the original and decoded videos was 0.317 (Cohen weighted kappa). The average difference in the ratings between the original and decoded videos was 0.26, in which the original videos were rated as more severe. The interrater agreement between the original videos was 0.459 and that between the decoded videos was 0.302. The agreement was higher when no deficits or very severe deficits were present. Conclusions: The vast majority of videos (172/200, 86.0%) decoded by the autoencoder contained clinically relevant information and had fair intrarater agreement with the original videos. Autoencoders are a potential method for enabling the use of patient videos while preserving data privacy, especially when non–health-care professionals are involved.


  • Open Access

    Autoencoder as a New Method for Maintaining Data Privacy While Analyzing Videos of Patients With Motor Dysfunction: Proof-of-Concept Study (Preprint)

    by Marcus D'Souza, Caspar E P Van Munster, Jonas F Dorn, Alexis Dorier, Christian P Kamm, Saskia Steinheimer, Frank Dahlke, Bernard M J Uitdehaag, Ludwig Kappos, Matthew Johnson

    BACKGROUND In chronic neurological diseases, especially in multiple sclerosis (MS), clinical assessment of motor dysfunction is crucial to monitor the disease in patients. Traditional scales are not sensitive enough to detect slight changes. Video recordings of patient performance are more accurate and increase the reliability of severity ratings. When these recordings are automated, quantitative disability assessments by machine learning algorithms can be created. Creation of these algorithms involves non–health care professionals, which is a challenge for maintaining data privacy. However, autoencoders can address this issue. OBJECTIVE The aim of this proof-of-concept study was to test whether coded frame vectors of autoencoders contain relevant information for analyzing videos of the motor performance of patients with MS. METHODS In this study, 20 pre-rated videos of patients performing the finger-to-nose test were recorded. An autoencoder created encoded frame vectors from the original videos and decoded the videos again. The original and decoded videos were shown to 10 neurologists at an academic MS center in Basel, Switzerland. The neurologists tested whether the 200 videos were human-readable after decoding and rated the severity grade of each original and decoded video according to the Neurostatus-Expanded Disability Status Scale definitions of limb ataxia. Furthermore, the neurologists tested whether ratings were equivalent between the original and decoded videos. RESULTS In total, 172 of 200 (86.0%) videos were of sufficient quality to be ratable. The intrarater agreement between the original and decoded videos was 0.317 (Cohen weighted kappa). The average difference in the ratings between the original and decoded videos was 0.26, in which the original videos were rated as more severe. The interrater agreement between the original videos was 0.459 and that between the decoded videos was 0.302. The agreement was higher when no deficits or very severe deficits were present. CONCLUSIONS The vast majority of videos (172/200, 86.0%) decoded by the autoencoder contained clinically relevant information and had fair intrarater agreement with the original videos. Autoencoders are a potential method for enabling the use of patient videos while preserving data privacy, especially when non–health-care professionals are involved.