Post-stroke Survivors Research Articles

Genetic Variations and Altered Blood mRNA Level of Circadian Genes and BDNF as Risk Factors of Post-Stroke Cognitive Impairment Among Eastern Indians.

Post-stroke cognitive impairment (PSCI) is a clinical outcome in around 30% of post-stroke survivors. BDNF is a major gene in this regard. It is regulated by circadian rhythm. The circadian genes are correlated with stroke timings at molecular level. However, studies suggesting the role of these on susceptibility to PSCI are limited. We aim here to determine: (a) genetic risk variants in circadian clock genes, BDNF and (b) dysregulation in expression level of CLOCK, BMAL1, and BDNF that may be associated with PSCI. BDNF (rs6265G/A, rs56164415C/T), CLOCK (rs1801260T/C, rs4580704G/C), and CRY2 (rs2292912C/G) genes variants were genotyped among 119 post-stroke survivors and 292 controls from Eastern part of India. In addition, we analyzed their gene expression in Peripheral blood Mononuclear cells (PBMC) from 15 PSCI cases and 12 controls. The mRNA data for BDNF was further validated by its plasma level through ELISA (n = 38). Among the studied variants, only rs4580704/CLOCK showed an overall association with PSCI (P = 0.001) and lower Bengali Mini-Mental State Examination (BMSE) score. Its 'C' allele showed a correlation with attention deficiency. The language and memory impairments showed association with rs6265/BDNF, while the 'CC' genotype of rs2292912/CRY2 negatively influenced language and executive function. A significant decrease in gene expression for CLOCK and BDNF in PBMC (influenced by specific genotypes) of PSCI patients was observed than controls. Unlike Pro-BDNF, plasma-level mBDNF was also lower in them. Our results suggest the genetic variants in CLOCK, CRY2, and BDNF as risk factors for PSCI among eastern Indians. At the same time, a lowering expression of CLOCK and BDNF genes in PSCI patients than controls describes their transcriptional dysregulation as underlying mechanism for post-stroke cognitive decline.

Understanding the Effect of Counterfactual Explanations on Trust and Reliance on AI for Human-AI Collaborative Clinical Decision Making

Artificial intelligence (AI) is increasingly being considered to assist human decision-making in high-stake domains (e.g. health). However, researchers have discussed an issue that humans can over-rely on wrong suggestions of the AI model instead of achieving human AI complementary performance. In this work, we utilized salient feature explanations along with what-if, counterfactual explanations to make humans review AI suggestions more analytically to reduce overreliance on AI and explored the effect of these explanations on trust and reliance on AI during clinical decision-making. We conducted an experiment with seven therapists and ten laypersons on the task of assessing post-stroke survivors' quality of motion, and analyzed their performance, agreement level on the task, and reliance on AI without and with two types of AI explanations. Our results showed that the AI model with both salient features and counterfactual explanations assisted therapists and laypersons to improve their performance and agreement level on the task when 'right' AI outputs are presented. While both therapists and laypersons over-relied on 'wrong' AI outputs, counterfactual explanations assisted both therapists and laypersons to reduce their over-reliance on 'wrong' AI outputs by 21% compared to salient feature explanations. Specifically, laypersons had higher performance degrades by 18.0 f1-score with salient feature explanations and 14.0 f1-score with counterfactual explanations than therapists with performance degrades of 8.6 and 2.8 f1-scores respectively. Our work discusses the potential of counterfactual explanations to better estimate the accuracy of an AI model and reduce over-reliance on 'wrong' AI outputs and implications for improving human-AI collaborative decision-making.

Ankle stiffness asymmetry is associated with balance function in individuals with chronic stroke

Ankle joint is one of important contributors on balance in stroke survivors. This study aimed to investigate the relationships of ankle stiffness symmetry ratios along the talocrural and subtalar axes with clinical balance measures and weight distribution during quiet standing in ambulatory chronic post-stroke survivors. The clinical trials involved 15 ambulatory elderly with chronic post-stroke hemiparesis and 15 healthy controls. Ankle stiffness was evaluated during non-weight-bearing isokinetic passive biaxial ankle movements, and ankle stiffness symmetry ratios between paretic and non-paretic ankle stiffness (SR: Inversion/Eversion SRIE & Dorsi-/Plantarflexion SRDP) were measured. A certified physiotherapist evaluated the Berg Balance Scale (BBS) and weight-distribution ratio (WDR) on bilateral force plates during quiet standing. Correlation coefficients, the factor analysis, and Pearson linear multiple regression were assessed with measured parameters. Correlation coefficients showed significances in-betweens; BBS and SRDP (r = −0.543, p = 0.022), WDR and SRIE (r = −0.667, p = 0.004), SRIE and SRDP (r = −0.604, p = 0.011). The exploratory factor analysis suggested four extracted factors; (1) Balance & Gait, (2) Stroke, (3) Symmetry and (4) Dimension. The first and second factors include general and pathological characteristics in stoke participants respectively. The third factor is associated with symmetrical characteristics explaining up to 99.9% of the variance. Multiple regression analysis showed ankle stiffness ratios predict BBS up to 60% of variance. The biaxial ankle stiffness ratio is a useful clinical variable that assesses balance function, in ambulatory chronic stroke survivors.

Applying the ICF codes, flag model and C-OAR-SE in the development of return-to-work assessment scale for stroke survivors.

The Return-to-Work Assessment Scale (RAS) was developed in 2021 by Ibikunle et al. to assess return-to-work among post-stroke survivors. The aim of this study was to describe how the conceptual (flag model and ICF) and theoretical framework (C-OAR-SE) were used in developing the RAS. The development of the RAS consisted of three phases: (i) Initial item generation (ii) Face and content validity (iii) Psychometric testing. With each phase embracing the flag model, international classification of functioning, disability and health (ICF) and the C-OAR-SE an acronym for the six aspects of the theory: 'C' [construct definition], 'OAR' [object representation, attribute classification, and rater entity identification], and 'SE' [selection of item type and answer scale, as well as, enumeration]. A triangulated approach drawn on three separate theories and models. Phase one was developed by using the flag model which provided the semi-structured open ended questions that materialized into the draft instrument while phases two and three were developed using the ICF and the C-OAR-SE. The scale consists of two sections, A and B. Section A comprises general information about post-stroke survivors, which would not be scored, while section B includes three parts that are important to consider when deciding to return-to-work. An instrument called RAS was developed, an excellent, internally consistent, as well as reliable tool that has demonstrated good group and structural validity.

Alberta Stroke Program Early CT Score can Predict Severity of Spasticity and Functional Outcome in Ischemic Stroke Survivors.

Post-stroke spasticity is common and an early predictor of the severity of spasticity can help track recovery trajectory helping to modify rehabilitation plans. We explored the utility of the Alberta Stroke Program Early CT Score (ASPECTS) to predict functional motor capacity in patients after acute ischemic stroke. One hundred and one patients (mean age of 58.6 ± 7.6 years; M:F = 72: 29) with the first documented acute ischemic stroke were followed up for three to twelve months after the stroke. Cerebral lesions within the territory of the middle cerebral artery were evaluated using the ASPECTS. Spasticity was assessed using the Modified Ashworth Score (MAS) and walking with Timed Up and Go test (TUG). The associations between severity of spasticity and size/extent of infarct as derived from ASPECTS and between spasticity and functional walking in post-stroke survivors were analyzed. Among the patients studied, 61.3% (n = 62) had infarct in the region of supply of the left middle cerebral artery (MCA) and 38.7% (n = 39) had infarct in the region supplied by the right MCA. Three percent (n = 3) had a low ASPECTS, 53.6% (n = 54) had an intermediate score and 44.4% (n = 44) had a high score. The majority of patients with no to mild spasticity had high ASPECTS. Worse spasticity was significantly associated with low ASPECTS (P = 0.001). High scores in Timed Up and Go test (TUG) were associated with low ASPECTS (P < 0.001). Patients with high ASPECTS had the propensity to have subcortical infarcts (P < 0.001) when compared to those with moderate ASPECTS, who had a mix of cortical and subcortical infarcts. ASPECTS at admission in patients with acute ischemic stroke is a good predictor of post-stroke spasticity and functional walking. Low ASPECTS is associated with higher spasticity and lower functional walking status on follow-up after stroke.

Functional Performance and Community Reintegration of Chronic Post-stroke Survivors in Eastern India

Introduction: Stroke is the primary cause of functional dependency in daily activities leading to disability of the individual. It becomes an economic burden for the person and society. Post-stroke management in rehabilitation gives more emphasis on improving functional performance. The improvement in functional activities of post-stroke survivors makes them independent in their daily activities at home but, still an impediment exists to participate in society and reintegrating into the community. The objective of the study is to find the association of community reintegration with the functional performance of one-year post-stroke survivors in eastern India and to compare their functional independence, community reintegration, and participation in instrumental daily living activities between stroke affection side and stroke subtype of the study group.&#x0D; Materials and Methods: A cross-sectional observational study was carried out on post-stroke survivors between 30 and 60 years of age without sex barrier. Ninety-four patients (mean age 54.38±12.06) were recruited for the study. The outcome was measured by the community integration questionnaire (CIQ), Lawton instrumental activities of daily living (LIADL), and functional independence measure (FIM).&#x0D; Results: Spearman rank order correlation was used and found a significant positive correlation persists between FIM to CIQ as the r=0.565 (P=0.01, 95% CI, -0.40%-0.70%) and LIADL to CIQ r=0.687 (P=0.01, 95% CI, -0.55%-0.79%) FIM to LIADL r=0.532 (P=0.01, 95% CI,&#x0D; -0.36%-0.67%). Mann-Whitney U test was done to compare FIM, LIADL, and CIQ between stroke affection side (right vs left) and stroke sub-type (ischemic vs haemorrhagic), and no significant difference was found.&#x0D; Conclusion: Functional independence, instrumental activities of daily living, and community reintegration are associated with each other. Hence, community reintegration should be incorporated into stroke rehabilitation to maintain a meaningful life as a part of society and family.

Assessing Depression and its Correlates Among Post-stroke Survivors with Aphasia in Sri Lanka

Assessing Depression and its Correlates Among Post-stroke Survivors with Aphasia in Sri Lanka

Impaired Upper Limb Motor Function in Post-stroke Patients and Its Impact on Trunk Control and Mobility: A Cross-sectional Study

Objectives: This study aims to investigate the impact of impaired upper limb motor function on trunk control and mobility in chronic post-stroke survivors so that the upper limb function should be enhanced as a core component of rehabilitation. Methods: This analytical cross-sectional study was conducted from March 2021 to August 2021 at the Rehabilitation Center for the Physically Disabled in Peshawar, Pakistan. A total of 166 chronic stroke patients in the age range of 35 to 70 years and greater than 6 months post-stroke were included. To assess the impaired upper extremity, the Fugl-Meyer assessment upper extremity scale was used, and the trunk control and mobility were checked through functional reach test and timed up and go test, respectively. Results: Among 166 stroke survivors having upper extremity impairment, 109(65.7%) participants’ upper extremity was severely affected. Mobility levels measured through the timed up and go test were categorized and scored; accordingly, the participants showed a low risk of 22(13.3%), moderate 32(19.3%), high 72(43.4%), and very high risk of falls of 40(24%). Among 166 patients, 147(88.6%) had no trunk control which resulted in 8 times greater fall risk in 65(39.2%) participants. Thus, upper limb impairment is significantly associated with impaired trunk control and mobility (P=0.001). Discussion: This study found about one-third of stroke survivors have a risk of falling, two-thirds have upper extremity impairment, and two-thirds have no trunk control. This study showed a significant reduction in mobility level, balance, and posture balance in stroke survivors having upper extremity impairment. These findings suggest that stroke survivors with upper extremity impairment may use therapeutic intervention to minimize falls and enhance postural balance and trunk control.

Relationship of Cognitive Ability and Self-Confidence in Driving Activities among Post-Stroke Survivors

Evidence on cognitive abilities and driving activity's self-confidence associated with difficulty in performing driving among post-stroke patients is still insufficient. Therefore, the cross-sectional study was conducted to investigate the association between post-stroke survivors' cognitive abilities and driving activity's self-confidence among post-stroke patients. The findings indicated a significant association (p&lt;0.05) between cognitive ability with age and driving status. Moreover, driving status shows a significant association (p &lt;0.05) with self-confidence. Therefore, an occupational therapist must conduct an off-road evaluation identifying an individual's cognitive capacity and self-confidence associated with the post-stroke patient's driving performance.

The Effectiveness of Mirror Therapy in Stroke Patients: A Systematic Review

Backgrounds : Stroke is a global problem and the second cause of death in the world. Purpose : To find out the effectiveness of giving mirror therapy in stroke patients. Methods : There are five databases used, namely Science Direct, SAGE Journal, Emerald, ProQuest and PubMed to search for mirror therapy and post-strokes. The inclusion criteria used are for publications for the last 5 years from 2017 to 2022, full-text articles and in English, according to the title, and RCT research or experimental studies. Results : of the total 7 articles submitted for this systematic review after quality assessment, this included 3 randomized controlled trials and 4 experimental studies. All muscle strength studies in post-stroke patients after being given mirror interventions experienced an increase in muscles in parts of the body that experienced hemiperation, thereby increasing independence in patients. From the results of all studies, it was found that the optimal time in starting the therapy is in the chronic stage, and the therapeutic dose is given with the same intensity (at least five sessions per week) and duration (at least 30 minutes to 90 minutes). Conclusion : mirror therapy proved to be an effective and viable approach to rehabilitate post-stroke survivors in acute, sub-acute, and chronic phases of the stroke, despite the long-term effects.

Effect of Breather on Multidimensional Outcomes in Post-Stroke Survivors

Effect of Breather on Multidimensional Outcomes in Post-Stroke Survivors

Design, development, and evaluation of an interactive personalized social robot to monitor and coach post-stroke rehabilitation exercises.

Socially assistive robots are increasingly being explored to improve the engagement of older adults and people with disability in health and well-being-related exercises. However, even if people have various physical conditions, most prior work on social robot exercise coaching systems has utilized generic, predefined feedback. The deployment of these systems still remains a challenge. In this paper, we present our work of iteratively engaging therapists and post-stroke survivors to design, develop, and evaluate a social robot exercise coaching system for personalized rehabilitation. Through interviews with therapists, we designed how this system interacts with the user and then developed an interactive social robot exercise coaching system. This system integrates a neural network model with a rule-based model to automatically monitor and assess patients' rehabilitation exercises and can be tuned with individual patient's data to generate real-time, personalized corrective feedback for improvement. With the dataset of rehabilitation exercises from 15 post-stroke survivors, we demonstrated our system significantly improves its performance to assess patients' exercises while tuning with held-out patient's data. In addition, our real-world evaluation study showed that our system can adapt to new participants and achieved 0.81 average performance to assess their exercises, which is comparable to the experts' agreement level. We further discuss the potential benefits and limitations of our system in practice.

Effectiveness of Virtual Rehabilitation Versus Therapeutic Exercises in the Balance Training of Lower Limb Among Post-Stroke Patients

Background: Stroke is the major source of death and disability and leads to impaired balance in post-stroke patients. Balance training is one of the main components of stroke rehabilitation. Virtual rehabilitation is gaining more popularity as it engages the patients attention in training. Objective: To evaluate the effects of virtual rehabilitation versus therapeutic exercises to improve the balance in patients with stroke. Methods: This randomized controlled trial conducted at Abdullah Hospital, Lalamusa from August to December 2022. The sample size of 30 participants was randomly divided into two groups virtual therapy group versus therapeutic exercises group, after taking their informed consent. Participants were recruited through the non-probability purposive sampling, between the age of 35 to 55 years, post-stroke survivors after 3 months and were able to stand up with or without assistive devices. Participants with auditory or visual dysfunction, a history of deep venous thrombosis, lower limb amputation, severe receptive or expressive aphasia, significant cognitive impairments and unstable hypertension were excluded. The data was collected from the patients by using Berg Balance Scale (BSS) at three different time frames: baseline, mid-intervention and post-intervention. The Shapiro-Wilk test was applied to calculate the normality of the data. For descriptive analysis, quantitative variables were calculated by mean and standard deviation whereas, for qualitative variables, frequency and percentages were used. To find significance an independent sample t-test was applied for between-group analysis and two-way repeated measure ANOVA was used to measure within-group analysis. Results: Both groups improved their balance after six months of intervention. Comparative analysis showed a significant improvement with p-value≤0.05 in both groups. The mean and standard deviation after six weeks of intervention in the virtual training group was 55.4±0.82 and the therapeutic exercise group was 54.47±1.3. This showed that the virtual rehabilitation group had improved balance in patients with stroke. Conclusion: Virtual rehabilitation was found to be effective in improving the balance of patients with stroke. It not only improves balance but also engages the patient in the treatment protocol. This rehabilitation is effective for the balance training of post-stroke patients.

AGREE: A Compliant-Controlled Upper-Limb Exoskeleton for Physical Rehabilitation of Neurological Patients

In this work, we introduce the AGREE exoskeleton, a robotic device designed to assist in upper-limb physical rehabilitation for post-stroke survivors. We detail the exoskeleton design at the mechatronic, actuation, and control levels. The AGREE exoskeleton features a lightweight and adaptable mechanical design, which can be used with both the right and left arm, supporting three active degrees-of-freedom at the shoulder and one at the elbow. The device embodies a spring-pulley anti-gravity system to minimize torque requirements and has torque sensors on each joint for safe and smooth interaction with the user. The AGREE control system, which employs a loadcell-based impedance control method, offers various modes of human-robot interaction, such as passive-assisted, active-assisted, and active-resistive exercises. Results from our experimental characterization demonstrate that the exoskeleton is capable of both compliant and rigid behavior, providing a wide range of haptic impedance and transparent behavior to both user-generated and therapist-generated forces. Our findings indicate that the AGREE exoskeleton may be a viable option for safely assisting patients with neurological conditions.

Cross-cultural translation, adaptation, and validation of the stroke-specific quality of life (SSQOL) scale 2.0 into Amharic language

BackgroundThe stroke-specific quality of life 2.0 (SSQOL 2.0) scale is a valid, reliable instrument which has been widely used as a patients reported outcome measure among stroke survivors. However, the SSQOL scale has not been validated and used in any Ethiopian language. This study aimed to translate, culturally adapt, and test the psychometric properties of the SSQOL scale 2.0 in Amharic, which is the official and working language with about 34 million (23%) speakers in Ethiopia.MethodsThe adapted English version of the SSQOL 2.0 scale was translated into Amharic and then back-translated to English. An expert committee translated and created a final Amharic version of SSQOL (SSQOL-AM) scale. Pre-field testing (pilot and cognitive debriefing) was conducted with 15 post-stroke subjects. The SSQOL-Am was administered to 245 stroke survivors from four referral hospitals to determine the psychometric properties. Cronbach’s alpha and Intra-class correlation coefficient were used to calculate the internal consistency and test–retest reliability, spearman’s correlation for the convergent validity of the SSQOL-Am scale. The Standard Error of Measurement (SEM), Minimum Detectable Change (MDC), Bland Altman Limit of Agreement (LOA), Confirmatory Factor Analysis, and Exploratory Factor Analysis were also determined.ResultsThe SSQOL-Am demonstrated excellent test–retest reliability (ICC = 0.93), internal consistency (Cronbach’s alpha = 0.96), SEM 0.857, MDC 1.94, and good LOA. As postulated, the mobility domain of the tool demonstrated a significantly strong correlation with the physical function domain of the SF-36 (rho = 0.70, p < 0.001).ConclusionsThe SSQOL-Am is a valid and reliable outcome measure. The tool can be used in both clinical practice and research purposes with Amharic speaking post-stroke survivors.

Brain-computer interface combined with mental practice and occupational therapy enhances upper limb motor recovery, activities of daily living, and participation in subacute stroke.

We investigated the effects of brain-computer interface (BCI) combined with mental practice (MP) and occupational therapy (OT) on performance in activities of daily living (ADL) in stroke survivors. Participants were randomized into two groups: experimental (n = 23, BCI controlling a hand exoskeleton combined with MP and OT) and control (n = 21, OT). Subjects were assessed with the functional independence measure (FIM), motor activity log (MAL), amount of use (MAL-AOM), and quality of movement (MAL-QOM). The box and blocks test (BBT) and the Jebsen hand functional test (JHFT) were used for the primary outcome of performance in ADL, while the Fugl-Meyer Assessment was used for the secondary outcome. Exoskeleton activation and the degree of motor imagery (measured as event-related desynchronization) were assessed in the experimental group. For the BCI, the EEG electrodes were placed on the regions of FC3, C3, CP3, FC4, C4, and CP4, according to the international 10-20 EEG system. The exoskeleton was placed on the affected hand. MP was based on functional tasks. OT consisted of ADL training, muscle mobilization, reaching tasks, manipulation and prehension, mirror therapy, and high-frequency therapeutic vibration. The protocol lasted 1 h, five times a week, for 2 weeks. There was a difference between baseline and post-intervention analysis for the experimental group in all evaluations: FIM (p = 0.001, d = 0.56), MAL-AOM (p = 0.001, d = 0.83), MAL-QOM (p = 0.006, d = 0.84), BBT (p = 0.004, d = 0.40), and JHFT (p = 0.001, d = 0.45). Within the experimental group, post-intervention improvements were detected in the degree of motor imagery (p < 0.001) and the amount of exoskeleton activations (p < 0.001). For the control group, differences were detected for MAL-AOM (p = 0.001, d = 0.72), MAL-QOM (p = 0.013, d = 0.50), and BBT (p = 0.005, d = 0.23). Notably, the effect sizes were larger for the experimental group. No differences were detected between groups at post-intervention. BCI combined with MP and OT is a promising tool for promoting sensorimotor recovery of the upper limb and functional independence in subacute post-stroke survivors.

Balance Rehabilitation through Robot-Assisted Gait Training in Post-Stroke Patients: A Systematic Review and Meta-Analysis.

Balance impairment is a common disability in post-stroke survivors, leading to reduced mobility and increased fall risk. Robotic gait training (RAGT) is largely used, along with traditional training. There is, however, no strong evidence about RAGT superiority, especially on balance. This study aims to determine RAGT efficacy on balance of post-stroke survivors. PubMed, Cochrane Library, and PeDRO databases were investigated. Randomized clinical trials evaluating RAGT efficacy on post-stroke survivor balance with Berg Balance Scale (BBS) or Timed Up and Go test (TUG) were searched. Meta-regression analyses were performed, considering weekly sessions, single-session duration, and robotic device used. A total of 18 trials have been included. BBS pre-post treatment mean difference is higher in RAGT-treated patients, with a pMD of 2.17 (95% CI 0.79; 3.55). TUG pre-post mean difference is in favor of RAGT, but not statistically, with a pMD of -0.62 (95%CI - 3.66; 2.43). Meta-regression analyses showed no relevant association, except for TUG and treatment duration (β = -1.019, 95% CI - 1.827; -0.210, p-value = 0.0135). RAGT efficacy is equal to traditional therapy, while the combination of the two seems to lead to better outcomes than each individually performed. Robot-assisted balance training should be the focus of experimentation in the following years, given the great results in the first available trials. Given the massive heterogeneity of included patients, trials with more strict inclusion criteria (especially time from stroke) must be performed to finally define if and when RAGT is superior to traditional therapy.

Evidence-based improvement of gait in post-stroke patients following robot-assisted training: A systematic review.

The recovery of walking after stroke is a priority goal for recovering autonomy. In the last years robotic systems employed for Robotic Assisted Gait Training (RAGT) were developed. However, literature and clinical practice did not offer standardized RAGT protocol or pattern of evaluation scales. This systematic review aimed to summarize the available evidence on the use of RAGT in post-stroke, following the CICERONE Consensus indications. The literature search was conducted on Pubmed, Cochrane library and PEDro, including studies with the following criteria: 1) adult post-stroke survivors with gait disability in acute/subacute/chronic phase; 2) RAGT as intervention; 3) any comparators; 4) outcome regarding impairment, activity, and participation; 5) both primary studies and reviews. Sixty-one articles were selected. Data about characteristics of patients, level of disability, robotic devices used, RAGT protocols, outcome measures, and level of evidence were extracted. It is possible to identify robotic devices that are more suitable for specific phase disease and level of disability, but we identified significant variability in dose and protocols. RAGT as an add-on treatment seemed to be prevalent. Further studies are needed to investigate the outcomes achieved as a function of RAGT doses delivered.

Machine Learning Techniques for the Prediction of Functional Outcomes in the Rehabilitation of Post-Stroke Patients: A Scoping Review

Stroke is one of the main causes of long-term disabilities, increasing the cost of national healthcare systems due to the elevated costs of rigorous treatment that is required, as well as personal cost because of the decreased ability of the patient to work. Traditional rehabilitation strategies rely heavily on individual clinical data and the caregiver’s experience to evaluate the patient and not in data extracted from population data. The use of machine learning (ML) algorithms can offer evaluation tools that will lead to new personalized interventions. The aim of this scoping review is to introduce the reader to key directions of ML techniques for the prediction of functional outcomes in stroke rehabilitation and identify future scientific research directions. The search of the relevant literature was performed using PubMed and Semantic Scholar online databases. Full-text articles were included if they focused on ML in predicting the functional outcome of stroke rehabilitation. A total of 26 out of the 265 articles met our inclusion criteria. The selected studies included ML approaches and were directly related to the inclusion criteria. ML can play a key role in supporting decision making during pre- and post-treatment interventions for post-stroke survivors, by utilizing multidisciplinary data sources.

Development and Rasch Validation of an Observational Assessment Tool of Upper Limb Functional Impairment in Stroke Survivors: Functional Assessment Test for Upper Limb

ObjectiveTo develop and validate a quick observational clinical tool, the Functional ASsessment Test for Upper Limb (FAST-UL), for the evaluation of upper limb impairment in goal-directed functional-oriented motor tasks after stroke. DesignObservational, cross-sectional, psychometric study. SettingInpatient and outpatient rehabilitation clinic. ParticipantsA total of 188 post-stroke survivors (mean age 65.2±17.7 years, 61% men, 48% with ischemic stroke and 66% in the sub-acute phase; N=188). InterventionsNot applicable. Main Outcome MeasuresPrincipal component analysis and Rasch analysis through a Partial Credit Model were used to assess the structure and psychometric properties of the 5 items of the FAST-UL (Hand to Mouth [HtM], Reach to Target, Prono-Supination, Grasp and Release, and Pinch and Release [PaR]). ResultsThe Cronbach's α equal to 0.96 was indicative of an acceptable internal consistency; the reliability, as measured through the Person Separation Reliability equal to 0.87, was good. The FAST-UL tool was unidimensional. All the FAST-UL items were found to fit well the Rasch measurement model. The easiest to perform FAST-UL item was the HtM movement while the most difficult was the PaR movement. ConclusionsThe FAST-UL is a quick, easy-to-administer observational assessment tool of upper limb motor impairment in post-stroke survivors with good item-level psychometric properties.