Halil Ismail Helvaci, Justin Huber, Jihye Bae
et al.
To empower the iterative assessments involved during a person's rehabilitation, automated assessment of a person's abilities during daily activities requires temporally precise segmentation of fine-grained actions in therapy videos. Existing temporal action segmentation (TAS) models struggle to capture sub-second micro-movements while retaining exercise context, blurring rapid phase transitions and limiting reliable downstream assessment of motor recovery. We introduce Multi-Membership Temporal Attention (MMTA), a high-resolution temporal transformer for fine-grained rehabilitation assessment. Unlike standard temporal attention, which assigns each frame a single attention context per layer, MMTA lets each frame attend to multiple locally normalized temporal attention windows within the same layer. We fuse these concurrent temporal views via feature-space overlap resolution, preserving competing local contexts near transitions while enabling longer-range reasoning through layer-wise propagation. This increases boundary sensitivity without additional depth or multi-stage refinement. MMTA supports both video and wearable IMU inputs within a unified single-stage architecture, making it applicable to both clinical and home settings. MMTA consistently improves over the Global Attention transformer, boosting Edit Score by +1.3 (Video) and +1.6 (IMU) on StrokeRehab while further improving 50Salads by +3.3. Ablations confirm that performance gains stem from multi-membership temporal views rather than architectural complexity, offering a practical solution for resource-constrained rehabilitation assessment.
Emily A Brinck, Chelsea E Brehmer, Catherine A Anderson
et al.
Background The number of older working-age adults with disabilities (OWAD) seeking services from State Vocational Rehabilitation Agencies (SVRAs) has increased as individuals remain in the workforce longer and experience disability later in life. However, VR research and practice have largely focused on new employment acquisition rather than employment retention, particularly for individuals approaching retirement age. Objective This study examined differences in VR service utilization, employment outcomes, and expenditures between employment retention and job acquisition pathways for OWAD. Method Secondary analysis of Rehabilitation Services Administration (RSA-911) data from PY 2017–2023 was conducted for individuals ages 50–69 who received VR services and exited the program. Outcomes were compared by age group and employment status using descriptive and inferential analyses. Results The proportion of VR applicants ages 50–69 increased steadily, reaching nearly one-third of all applicants by 2023. Older adults were more likely to be employed at IPE development and to exit VR in competitive integrated employment with lower expenditures needed for job retention. Conclusion Retention-focused strategies emphasizing early intervention, accommodations, and employer engagement may improve employment outcomes of older workers while containing costs, supporting a shift in VR approaches.
Background: Prolonged and frequent use of high-heeled footwear has been associated with musculoskeletal maladaptation and impairments. These include calf tightness, reduced ankle dorsiflexion range of motion (ROM), and altered gait mechanics. Over time, these changes may compromise the functional mobility of the lower extremity.
Objective: to compare the instrument-assisted soft tissue mobilization and dynamic oscillatory stretch technique on ankle ROM and Lower Extremity Functions among high-heeled users.
Method: This single-blinded, randomized Controlled Trial was carried out at Begam Akhtar Memorial Trust Safari Hospital from August 2023 to January 2024. A total of n=54 females aged between 20-40 years with <17 degrees dorsiflexion, wearing high heels of at least 2 inches, for 5 hours/day, for more than 3 days/week, and > one year included in the study. The sample was divided into group A, which received Graston mobilization (IASTM), and group B received the dynamic oscillatory stretch technique (DOST) for gastrocnemius and soleus muscles. For lower limb functions, ankle ROM goniometer and Pain were assessed through lower extremity functional status, goniometer, and numeric pain rating scale.at baseline and after the 12th session.
Results: The Results showed significant improvement (p<0.001) in the IASTM group as compared to the DOST group with respect to ankle ROM, pain reduction, and LEFS showed equal (p=0.303) improvements for both groups.
Conclusions: IASTM is more effective than DOST in improving ankle ROMs and decreasing pain in female high heel users. However, both techniques showed similar improvements in lower extremity functional status.
Clinical trial registry: NCT06086600
Vocational rehabilitation. Employment of people with disabilities
Nizar Alsharif, Theyazn H. H. Aldhyani, Mansour Ratib Mohammad Obeidat
et al.
Behavioral observations have traditionally served as the foundation for diagnosing autism spectrum disorder (ASD). However, these conventional diagnostic methods often present challenges, including potential inaccuracies and significant time demands. The integration of technological screening tools and machine learning algorithms with standard behavioral observations has the potential to enhance the assessment and diagnostic processes for ASD, leading to more efficient and accurate outcomes. Accurate and reliable classification of ASD is essential in medical diagnosis. In this study, the performance of the random forest (RF) and K-nearest neighbors methods was evaluated for ASD detection using a public dataset. This dataset, collected from the Kaggle repository, includes 704 samples of adult autism screening, with 20 attributes designated for future research, especially in identifying key autistic symptoms and refining ASD categorization. The dataset features 10 behavioral traits (AQ-10-Adult) and 10 personal characteristics that have proven effective in distinguishing ASD patients from controls in behavioral science. Data preprocessing involved encoding, feature selection, and data partitioning. The RF model achieved a high accuracy of 99.29%. Our findings illustrate the efficacy of the proposed RF model in accurately diagnosing ASD through comprehensive data analysis and performance metrics. This approach facilitates a more rapid identification of the condition, thereby enhancing the overall detection of ASD.
Vocational rehabilitation. Employment of people with disabilities
Omid Shahani, Ali Shamsi Majelan, Nahid Khoshraftar Yazdi
Objectives: This study determines whether feedback during exercise can improve balance in people with chronic ankle instability (CAI). Using feedback is a method to increase attention and willingness to perform an activity, which can be applied in various ways, including visual, audio, and sensory.
Methods: This research was semi experimental and practical. The sample of the current research was 30 male athletes aged 20 to 25 years with CAI. The participants were purposefully selected and then separated into two groups proprioceptive exercise with feedback and proprioceptive exercise without feedback. In the pre-test, they were evaluated using the stork balance test in two states, eyes open and closed for static and one-leg jump stabilization for dynamic balance. The athletes then performed proprioceptive training for 24 sessions over 8 weeks. Then, in the post-test, the desired variables were re-evaluated. The paired sample t-test and analysis of covariance were used to analyze the data. Significance was considered at the level of 0.05 and analysis was done in the SPSS software, version 27.
Results: Both exercise modalities exhibited a notable disparity in pre-test and post-test outcomes. However, comparative between the cohorts revealed a significant distinction in static balance performance under conditions of eyes closed versus eyes open (P=0.040 and P=0.033) and in dynamic balance (P=0.019).
Discussion: Using feedback while doing exercises is helpful and leads to improved balance. Visual feedback gives the athletes a better understanding of the situation at the moment so that they can perform their best against what they see. Also, using vision compared to other senses creates more confidence in people to maintain the situation. Combining feedback with proprioceptive exercises in rehabilitation has an additive effect on improving the residual effects of injury.
Medicine, Vocational rehabilitation. Employment of people with disabilities
Sinh Phuong Nguyen, Hoang The Tran, Duc Dang Nguyen
et al.
This study aimed to examine caregivers’ perceptions, practices, and challenges regarding rehabilitation services for people with disabilities, with a focus on identifying factors influencing their decisions to bring care recipients for formal rehabilitation. A cross-sectional study was conducted in rural Thai Nguyen Province, Vietnam. Data were collected from 214 primary caregivers using a structured questionnaire covering demographics, caregiving roles, and rehabilitation-related perceptions. A pilot study was conducted to refine the tool, and data were collected via face-to-face interviews by a trained team. Statistical analyses included descriptive statistics, chi-square tests, and stepwise logistic regression to identify key predictors of care-seeking behaviors. Results showed that 92% of caregivers perceived rehabilitation as necessary or very necessary. Female caregivers were more likely to provide care at home (95.3%), while male caregivers were more likely to utilize hospital-based services (73.5%) and to bring care recipients for rehabilitation overall (79.4% vs. 67.1%). Logistic regression revealed that female caregivers were significantly less likely than males to bring people with disabilities in for care (OR = 0.34, <i>p</i> = 0.02). Longer caregiving duration was associated with a reduced likelihood of seeking care (OR = 0.96 per year, <i>p</i> < 0.001), whereas caregivers of individuals with mobility needs (OR = 3.15, <i>p</i> < 0.001) and social integration needs (OR = 2.12, <i>p</i> = 0.05) were significantly more likely to seek care. These findings highlight gender-based differences and caregiving dynamics that influence access to rehabilitation. To enhance rehabilitation outcomes and support caregiver engagement, targeted policies are needed to address gender roles, caregiving fatigue, and the specific needs of care recipients.
Vocational rehabilitation. Employment of people with disabilities
Desta Debalkie Atnafu, Femke Bannink Mbazzi, Mezgebu Yitayal
et al.
Background: People with disabilities on average experience health care barriers, poorer health and higher mortality.
Objectives: This study aims to review and synthesise life expectancy (LE) and years of life lost (YLL) comparing people with disabilities to those without in low and middle-income countries (LMICs).
Method: A systematic review was conducted across six databases. Longitudinal studies with a comparator group that measured LE in or YLL between people with and without disabilities in LMICs were eligible for inclusion. Two reviewers independently assessed study eligibility, extracted data and assessed the risk of bias. Meta-analyses were undertaken using R 4.3.3. The study assessed heterogeneity with I2 and publication bias with a funnel plot. Sub-group and meta-regression analyses were performed, and the risk of bias was evaluated.
Results: Twelve full-text articles were included in this meta-analysis. The pooled mean LE was lower in people with disabilities (57.98 years; 95% confidence intervals [CI]: 53.40–62.95) compared with people without disabilities (70.86 years; 95% CI: 64.06–78.38). The overall weighted years of YLL in people with disabilities was 15.84 years (95% CI: 11.1–22.61). There was no significant difference in YLL between men (16.33 years; 95% CI: 11.49–23.21) and women (13.7 years; 95% CI: 8.45–22.22).
Conclusion: The average LE in people with disabilities was substantially lower compared to those without disabilities in LMICs. This inequity highlights that health systems and public health efforts are failing to meet the needs of people with disabilities and must be improved to become more inclusive.
Contribution: The study emphasises the need for inclusive policies and robust research in the health system to address health disparities.
Vocational rehabilitation. Employment of people with disabilities, Communities. Classes. Races
Artificial intelligence (AI) is reshaping the labor market by changing the task content of occupations. This study investigates the impact of AI development on the emergence of new work, employment, and wages in the United States from 2015 to 2022. I develop innovative methods to measure occupational and industry exposure to AI technologies that substitute labor (automation AI ) or enhance workers' output (augmentation AI), and to identify new work (i.e., new job titles). To address endogeneity, I use instrumental variable estimators, leveraging AI development in countries with limited economic ties to the United States. The findings indicate that automation AI negatively impacts new work, employment, and wages in low-skilled occupations, while augmentation AI fosters the emergence of new work and raises wages for high-skilled occupations. These results suggest that AI may contribute to rising wage inequality.
Victor Li, Naveenraj Kamalakannan, Avinash Parnandi
et al.
Vision-language models (VLMs) have demonstrated remarkable performance across a wide range of computer-vision tasks, sparking interest in their potential for digital health applications. Here, we apply VLMs to two fundamental challenges in data-driven stroke rehabilitation: automatic quantification of rehabilitation dose and impairment from videos. We formulate these problems as motion-identification tasks, which can be addressed using VLMs. We evaluate our proposed framework on a cohort of 29 healthy controls and 51 stroke survivors. Our results show that current VLMs lack the fine-grained motion understanding required for precise quantification: dose estimates are comparable to a baseline that excludes visual information, and impairment scores cannot be reliably predicted. Nevertheless, several findings suggest future promise. With optimized prompting and post-processing, VLMs can classify high-level activities from a few frames, detect motion and grasp with moderate accuracy, and approximate dose counts within 25% of ground truth for mildly impaired and healthy participants, all without task-specific training or finetuning. These results highlight both the current limitations and emerging opportunities of VLMs for data-driven stroke rehabilitation and broader clinical video analysis.
Rehabilitation exoskeletons have shown promising results in promoting recovery for stroke patients. Accurately and timely identifying the motion intentions of patients is a critical challenge in enhancing active participation during lower limb exoskeleton-assisted rehabilitation training. This paper proposes a Dual-Channel Attentive Fusion Network (DCAF-Net) that synergistically integrates pre-movement surface electromyography (sEMG) and inertial measurement unit (IMU) data for lower limb intention prediction in stroke patients. First, a dual-channel adaptive channel attention module is designed to extract discriminative features from 48 time-domain and frequency-domain features derived from bilateral gastrocnemius sEMG signals. Second, an IMU encoder combining convolutional neural network (CNN) and attention-based long short-term memory (attention-LSTM) layers is designed to decode temporal-spatial movement patterns. Third, the sEMG and IMU features are fused through concatenation to enable accurate recognition of motion intention. Extensive experiment on 11 participants (8 stroke subjects and 3 healthy subjects) demonstrate the effectiveness of DCAF-Net. It achieved a prediction accuracies of 97.19% for patients and 93.56% for healthy subjects. This study provides a viable solution for implementing intention-driven human-in-the-loop assistance control in clinical rehabilitation robotics.
People with disabilities (PwD) experience disproportionately high levels of discrimination and hate online, particularly in India, where entrenched stigma and limited resources intensify these challenges. Large language models (LLMs) are increasingly used to identify and mitigate online hate, yet most research on online ableism focuses on Western audiences with Western AI models. Are these models adequately equipped to recognize ableist harm in non-Western places like India? Do localized, Indic language models perform better? To investigate, we adopted and translated a publicly available ableist speech dataset to Hindi, and prompted eight LLMs--four developed in the U.S. (GPT-4, Gemini, Claude, Llama) and four in India (Krutrim, Nanda, Gajendra, Airavata)--to score and explain ableism. In parallel, we recruited 175 PwD from both the U.S. and India to perform the same task, revealing stark differences between groups. Western LLMs consistently overestimated ableist harm, while Indic LLMs underestimated it. Even more concerning, all LLMs were more tolerant of ableism when it was expressed in Hindi and asserted Western framings of ableist harm. In contrast, Indian PwD interpreted harm through intention, relationality, and resilience--emphasizing a desire to inform and educate perpetrators. This work provides groundwork for global, inclusive standards of ableism, demonstrating the need to center local disability experiences in the design and evaluation of AI systems.
Juan Camilo Mansilla, Normand Boucher, François Routhier
Access to transport is key to people’s movement in cities, their social participation, and personal development. People with mobility disabilities (PMDs) face additional barriers when using public transport. The objective of this study is to identify the dilemmas that PMDs face in their daily mobility practices and their coping strategies, in particular the ways in which these dilemmas and strategies are influenced by both personal and environmental characteristics. We conducted ethnographic research, utilizing narrative interviews, life stories, focus groups, and participant observations. Our aim was to analyse multiple experiences of mobility in situations of disability in Quebec City, Canada. This study engages the following research question: how do PMDs navigate their social environment, considering the impact of personal, social, and physical landscape factors on their mobility strategies? Depending on the accessibility of fixed-route public buses and the availability of public paratransit services, what are the dilemmas that PMDs face and how do they shape their mobility strategies? Using the three-dimensional model of narrative analysis, we present a narrative ethnography of participants’ dilemmas and strategies about their experiences on public transport. Five dilemmas are examined. Through this methodology, we propose to extend the study of “constellations of mobility” by including the notion of strategies as an experiential outcome between personal and physical landscape factors, practices, and meanings of mobility. This offers new research perspectives both in disability and mobility studies and in the understanding of urban accessibility experiences in situations of disability.
Vocational rehabilitation. Employment of people with disabilities
Dario Onfiani, Marco Caramaschi, Luigi Biagiotti
et al.
In this paper, we address the development of a robotic rehabilitation system for the upper limbs based on collaborative end-effector solutions. The use of commercial collaborative robots offers significant advantages for this task, as they are optimized from an engineering perspective and ensure safe physical interaction with humans. However, they also come with noticeable drawbacks, such as the limited range of sizes available on the market and the standard control modes, which are primarily oriented towards industrial or service applications. To address these limitations, we propose an optimization-based design method to fully exploit the capability of the cobot in performing rehabilitation tasks. Additionally, we introduce a novel control architecture based on an admittance-type Virtual Fixture method, which constrains the motion of the robot along a prescribed path. This approach allows for an intuitive definition of the task to be performed via Programming by Demonstration and enables the system to operate both passively and actively. In passive mode, the system supports the patient during task execution with additional force, while in active mode, it opposes the motion with a braking force. Experimental results demonstrate the effectiveness of the proposed method.
Kayleigh Schoorl, Tamara Pinos Cisneros, Albert Ali Salah
et al.
Rehabilitation exercises performed by children with cerebral palsy are tedious and repetitive. To make them more engaging, we propose to use an exergame approach, where an adaptive application can help the child remain stimulated and interested during exercises. In this paper, we describe how the mobile phone sensors can be used to classify wrist movements of the user during the rehabilitation exercises to detect if the user is performing the correct exercise and illustrate the use of our approach in an actual mobile phone application. We also show how an adaptive difficulty system was added to the application to allow the system to adjust to the user. We present experimental results from a pilot with healthy subjects that were constrained to simulate restricted wrist movements, as well as from tests with a target group of children with cerebral palsy. Our results show that wrist movement classification is successfully achieved and results in improved interactions.
Blind people use artificial intelligence-enabled visual assistance technologies (AI VAT) to gain visual access in their everyday lives, but these technologies are embedded with errors that may be difficult to verify non-visually. Previous studies have primarily explored sighted users' understanding of AI output and created vision-dependent explainable AI (XAI) features. We extend this body of literature by conducting an in-depth qualitative study with 26 blind people to understand their verification experiences and preferences. We begin by describing errors blind people encounter, highlighting how AI VAT fails to support complex document layouts, diverse languages, and cultural artifacts. We then illuminate how blind people make sense of AI through experimenting with AI VAT, employing non-visual skills, strategically including sighted people, and cross-referencing with other devices. Participants provided detailed opportunities for designing accessible XAI, such as affordances to support contestation. Informed by disability studies framework of misfitting and fitting, we unpacked harmful assumptions with AI VAT, underscoring the importance of celebrating disabled ways of knowing. Lastly, we offer practical takeaways for Responsible AI practice to push the field of accessible XAI forward.
To promote empathy with people that have disabilities, we propose a multi-sensory interactive experience that allows sighted users to embody having a visual impairment whilst using assistive technologies. The experiment involves blindfolded sighted participants interacting with a variety of sonification methods in order to locate targets and place objects in a real kitchen environment. Prior to the tests, we enquired about the perceived benefits of increasing said empathy from the blind and visually impaired (BVI) community. To test empathy, we adapted an Empathy and Sympathy Response scale to gather sighted people's self-reported and perceived empathy with the BVI community from both sighted (N = 77) and BVI people (N = 20) respectively. We re-tested sighted people's empathy after the experiment and found that their empathetic and sympathetic responses (N = 15) significantly increased. Furthermore, survey results suggest that the BVI community believes the use of these empathy-evoking embodied experiences may lead to the development of new assistive technologies.
The online privacy and security of the disabled community is a complex field that has implications for every user who navigates web services. While many disciplines have separately researched the disabled population and their online privacy and security concerns, the overlap between the two is very high but under-researched. Moreover, a complex relationship exists between the disabled population and web services where the interaction depends on several web service developmental factors, including usability and accessibility. To this aid, we explored this intersection of privacy and security of web services as perceived by the disabled community through previous studies by conducting a detailed systematic literature review and analysis of 63 articles. Our findings encompassed several topics, including how the disabled population navigates around authentication interfaces, online privacy concerns, universal design practices, and how security methods such as CAPTCHAs can be improved to become more accessible and usable for people of all needs and abilities. We further discuss the gap in the current research, including solutions such as the universal implementation of inclusive privacy and security tools and protocols.
Kumar Srinivas Bobba, Kartheeban K, Vamsi Krishna Sai Boddu
et al.
As able-bodied people, we often take our vision for granted. For people who are visually impaired, however, their disability can have a significant impact on their daily lives. We are developing proprietary headgear that will help visually impaired people navigate their surroundings, identify objects and people, read text, and avoid obstacles. The headgear will use a combination of computer vision, distance estimation with ultrasonic sensors, voice recognition, and voice assistants to provide users with real-time information about their environment. Users will be able to interact with the headgear through voice commands, such as ''What is that?'' to identify an object or ''Navigate to the front door'' to find their way around. The headgear will then provide the user with a verbal description of the object or spoken navigation instructions. We believe that this headgear has the potential to make a significant difference in the lives of visually impaired people, allowing them to live more independently and participate more fully in society.
David R. Strauser, Chelsea E. Brehmer, P. Rumrill
et al.
BACKGROUND: Individuals with disabilities experience disruptions in life participation at the onset or exacerbation of a disability. The multiple dimensions of functioning impacted go beyond the symptoms of a disabling condition and assessing an individual’s level of functioning is a critical first step of a strengths-based rehabilitation approach. With functioning playing an important role in the vocational rehabilitation process, it would be important to have an assessment tool that can be used to measure an individual’s level of functioning. OBJECTIVE: The purpose of this study was to examine the psychometric properties of the Illinois Brief Functioning Inventory (IBFI), a scale developed to measure the multi-dimensional nature of functioning as it relates to vocational rehabilitation, career development, and employment of people with disabilities. METHODS: Factor analysis, including exploratory factor analysis (EFA) and confirmatory factor analysis (CFA), was used to determine and validate the underlying dimension of IBFI. RESULTS: Overall, the study findings indicate strong psychometrics for a 26-item instrument comprised of five meaningful subscales identifying functioning across physical, cognitive, and emotional dimensions. CONCLUSION: The results of this study provide initial psychometric support regarding the IBFI as an instrument that can be used to identify an individual’s current level of functioning.