Effectiveness and efficiency of aquatic therapy on independence in activities of daily living and mobility in post-acute spinal cord injury: A matched case-control study.

BACKGROUND AND PURPOSE: Aquatic therapy (AT), though potentially effective, lacks studies on clinical efficacy in patients with spinal cord injury (SCI). A recent study analyzing interviews with rehabilitation professionals on its clinical application reported that the scarce evidence of AT benefits was one of the actual barriers to its successful integration into clinical practice. We seek to provide evidence by comparing independence in activities of daily living (ADLs) and functional ambulation capacity in patients following rehabilitation which included AT and matched controls who followed rehabilitation without AT (non-AT). METHODS: Functional Independence Measure (FIM), Spinal Cord Independence Measure (SCIM-III), Walking Index for Spinal Cord Injury (WISCI-II) and its minimal clinically important difference (WISCI-II/MCID) were assessed. The AT group followed the Halliwick concept. We performed nonparametric nearest-neighbor k:1 matching for age, time since injury to admission, FIM at admission, level of injury (paraplegia/tetraplegia), completeness and cause of injury (traumatic, non-traumatic). The rehabilitation program comprised four daily hours of intensive treatment from the multidisciplinary team. Both groups received the same total number of rehabilitation hours at the same specialized clinical center and were admitted to follow inpatient rehabilitation within 2 months after injury. RESULTS: A total of 29 patients with SCI who followed AT (admitted between 2017 and 2023) were compared to historical matches selected from 551 inpatients with SCI (admitted between 2014 and 2023). For k = 1, the groups showed no significant differences in gains, efficiency, or effectiveness in FIM and SCIM-III; significant differences were observed in WISCI-II gain (p = 0.018) and WISCI-II efficiency (p = 0.046) in favor of the AT group; the proportion of patients achieving WISCI-II/MCID was significantly higher for the AT group (75.9% vs. 48.3%) (p = 0.030). These results were confirmed for k = 2. CONCLUSION: The AT group performed similarly in independence for performing ADLs and significantly better in ambulation than the matched historical controls.

Multi-task learning for predicting quality-of-life and independence in activities of daily living after stroke: a proof-of-concept study.

A health-related (HR) profile is a set of multiple health-related items recording the status of the patient at different follow-up times post-stroke. In order to support clinicians in designing rehabilitation treatment programs, we propose a novel multi-task learning (MTL) strategy for predicting post-stroke patient HR profiles. The HR profile in this study is measured by the Barthel index (BI) assessment or by the EQ-5D-3L questionnaire. Three datasets are used in this work and for each dataset six neural network architectures are developed and tested. Results indicate that an MTL architecture combining a pre-trained network for all tasks with a concatenation strategy conditioned by a task grouping method is a promising approach for predicting the HR profile of a patient with stroke at different phases of the patient journey. These models obtained a mean F1-score of 0.434 (standard deviation 0.022, confidence interval at 95% [0.428, 0.44]) calculated across all the items when predicting BI at 3 months after stroke (MaS), 0.388 (standard deviation 0.029, confidence interval at 95% [0.38, 0.397]) when predicting EQ-5D-3L at 6MaS, and 0.462 (standard deviation 0.029, confidence interval at 95% [0.454, 0.47]) when predicting the EQ-5D-3L at 18MaS. Furthermore, our MTL architecture outperforms the reference single-task learning models and the classic MTL of all tasks in 8 out of 10 tasks when predicting BI at 3MaS and has better prediction performance than the reference models on all tasks when predicting EQ-5D-3L at 6 and 18MaS. The models we present in this paper are the first models to predict the components of the BI or the EQ-5D-3L, and our results demonstrate the potential benefits of using MTL in a health context to predict patient profiles.

Evaluating AI Models: Performance Validation Using Formal Multiple-Choice Questions in Neuropsychology.

High-quality and accessible education is crucial for advancing neuropsychology. A recent study identified key barriers to board certification in clinical neuropsychology, such as time constraints and insufficient specialized knowledge. To address these challenges, this study explored the capabilities of advanced Artificial Intelligence (AI) language models, GPT-3.5 (free-version) and GPT-4.0 (under-subscription version), by evaluating their performance on 300 American Board of Professional Psychology in Clinical Neuropsychology-like questions. The results indicate that GPT-4.0 achieved a higher accuracy rate of 80.0% compared to GPT-3.5's 65.7%. In the "Assessment" category, GPT-4.0 demonstrated a notable improvement with an accuracy rate of 73.4% compared to GPT-3.5's 58.6% (p = 0.012). The "Assessment" category, which comprised 128 questions and exhibited the highest error rate by both AI models, was analyzed. A thematic analysis of the 26 incorrectly answered questions revealed 8 main themes and 17 specific codes, highlighting significant gaps in areas such as "Neurodegenerative Diseases" and "Neuropsychological Testing and Interpretation."

Community integration after spinal cord injury rehabilitation: Predictors and causal mediators.

CONTEXT/OBJECTIVE: Community integration (CI) is a crucial rehabilitation goal after spinal cord injury (SCI). There is a pressing need to enhance our understanding of the factors associated with CI for individuals with traumatic or non-traumatic etiologies, with the latter being notably understudied. Accordingly, our research explores the associations and potential mediators influencing CI across these populations. SETTING: Specialized neurological rehabilitation center. PARTICIPANTS: Community-dwelling individuals who were admitted as inpatients within 3 months post-injury (n = 431, 51.9% traumatic, 48.1% non-traumatic), assessed in relation to community integration within 1-3 years after discharge. OUTCOME MEASURE: Community Integration Questionnaire (CIQ). Covariates: American Spinal Injury Association Impairment Scale (AIS), Functional Independence Measure (FIM) and Hospital Anxiety and Depression Scale (HADS). RESULTS: Multiple linear regression yielded age, B AIS grade, educational level (< 6 years and <12 years), time since injury to admission, length of stay, HADS-depression at discharge, total FIM at discharge and three social work interventions (support in financial, legal and transportation services) as significant predictors of total CIQ score (Adjusted R2 = 41.4). Multiple logistic regression identified age, traumatic etiology, educational level (< 6 years and <12 years), length of stay, HADS depression at discharge, total FIM at discharge and one social work intervention (transportation support) as significant predictors of good community integration, AUC (95% CI): 0.82 (0.75-0.89), Sensitivity:0.76, Specificity:0.73. We identified motor FIM at discharge and motor FIM efficiency as causal mediators of total CIQ. CONCLUSIONS: We identified modifiable factors during rehabilitation-functional independence, depression, and social work interventions-that are associated with CI.

Falls characteristics experienced by working-age adults during inpatient post-stroke rehabilitation and their impact on length of stay, discharge functional status, ambulation and destination.

BACKGROUND: In-hospital falls are frequent post-stroke medical complications and will remain of concern because it may not be possible to prevent all of them. We aimed to i) compare admission clinical and sociodemographic characteristics between fallers and non-fallers ii) determine falls characteristics iii) compare length of stay (LOS), discharge functional independence, ambulation and destination between fallers and non-fallers. METHODS: A matched case-control study, comparing individuals (n = 302) who fell during inpatient post-acute rehabilitation, matched (on time to admission, age and motor Functional Independence Measure (mFIM)) to individuals (n = 302) who didn´t fall, admitted within 3 months post-injury to a center between 2008 and 2023. Ambulation was assessed using the Functional Ambulation Category (FAC). RESULTS: Mean age at admission was 50±8 years. No baseline differences were seen between groups in the proportion of patients with aphasia, diabetes, dyslipidemia, hypertension, neglect, atrial fibrillation, dysphagia, dominant side affected, medication for depression, FAC assessment, body mass index and educational level. A first-fall in the first week was experienced by 22.2 % and in the first three weeks by 54.3 %. Most falls occurred at the patients' room (75.1 %) mostly due to distractions (55.3 %) and transferring without help (32.4 %) with 18 % occurring in the bathroom, fallers were alone in 68.6 % of the cases. Fallers had an 8-day longer mean LOS compared to non-fallers, yet there were no differences in discharge mFIM or FAC scores. While non-fallers had a higher proportion of poor mFIM outcomes (28.5 % vs. 17.9 %) and no ambulation (20.7 % vs. 12.4 %), fallers showed greater mFIM gains (26 vs. 22 points). Discharge destinations were similar across both groups. CONCLUSIONS: Despite no baseline differences, fallers experienced longer stays with comparable independence and ambulation scores at discharge. Most falls occurred in patients' rooms during unsupervised activities. Preventive recommendations have been provided to address these risks and enhance patient safety.

Precision nutrition impact on metabolic health and quality of life in aging population after a 3-month intervention: A randomized intervention.

OBJECTIVES: Innovative precision dietary procedures are required to promote healthy aging. This study aimed to evaluate the effects of a personalised strategy based on the inclusion of individualised foods and digital tools on overall health status and quality of life within a follow-up of 3 months in older adults with overweight or obesity. METHODS: 127 men and women aged between 50 and 80 years with overweight/obesity participated in the study-between January 2020 and September 2020 at the Center for Nutrition Research-University of Navarra and IMDEA-ALIMENTACIÓN-and were randomly assigned to a usual-care group (standard recommendations) or precision group (precision nutrition strategy based on the inclusion of individualised foods and a mobile application). Anthropometry, body fat percentage, biochemical parameters, diet, and quality of life (SF-36 Health Survey) were assessed at baseline and after 3 months. RESULTS: Both strategies were found to improve overall metabolic health; however, the precision approach demonstrated significantly better outcomes. The precision strategy reduced body weight at 3 months (-4.3 kg; p < 0.001) with significant improvements in body fat percentage, blood pressure and general metabolic health (glycated haemoglobin; alanine aminotransferase; aspartate aminotransferase; hepatic steatosis index) in comparison with the standard recommendations. The precision approach significantly enhanced the quality of life (SF-36) of individuals, with additional improvements in emotional well-being (p = 0.024) and vitality (p = 0.008). Adherence to the Mediterranean diet was significantly associated with a higher quality of life and vitality. CONCLUSION: These results support the benefit of precision nutrition approaches for promoting healthy aging and emotional well-being, enhancing the quality of life in aging populations, during the COVID-19 pandemic.

Epidemiology of pediatric spinal trauma with neurological deficits in Catalonia: a 36-year experience.

PURPOSE: Existing literature on pediatric traumatic spinal cord injury (PTSCI) demonstrates large variations in characteristics, incidence, time-periods and etiology, worldwide. Epidemiological studies addressing injuries to the total spine, conducted in Southern European regions are remarkably scarce; therefore we aimed to investigate long-term trends analyzing etiology, fracture location and type, single or multiple fractures, associated lesions and neurological status in Catalonia, Spain. METHODS: We conducted a retrospective observational study. We analyzed post-acute patients after PTSCI, aged 0-17, admitted with neurological deficits between 1986 and 2022 to a specialized hospital in Catalonia. Neurological deficits were assessed using the American Spinal Injury Association Impairment Scale (AIS). RESULTS: Two hundred and forty nine children were included, 174 (69.9%) boys and 75 (30.1%) girls; mean age was 13.9 years (range, 2 months to 17 years). Two hundred and four children (82%) had ≥ 1 spinal fractures, 66 (26.5%) dislocations and 8 (3.2%) SCIWORA. Fractures were multilevel contiguous in 108 (43.4%) cases. Fracture types comprised 81 vertebral compactions (32.5%), 22 burst fractures (8.8%), 7 odontoid (2.8%) and 4 tear-drops (1.6%). There were ≥ 1 associated lesions in 112 cases (45%): in limbs in 23 cases (9.2%), thorax or abdomen in 59 (23.7%) and skull or face in 81 (32.5%). In 44 cases (39% of the 112) there were multiple lesions. Locations comprised cervical spine in 105 cases (42%), thoracic spine in 124 (49%), lumbar spine in 18 (7%), and sacrum in 2 (0.8%). Road traffic accidents (RTAs) were the main etiology (62.2%) over the whole period. However, from 2016 onwards, RTAs dropped below the rate of falls and sports injuries. The most common sites for injury in those aged 9 years or older were in the cervical (41.1%) and thoracic (50.7%) regions. Those aged 8 or under were far more likely to sustain a complete SCI (80.0%) or an accompanying traumatic brain injury (45.0%) likely due to higher numbers of pedestrian versus car RTAs. A significant peak in the occurrence of cases during 2006-2010 (20.1%) was identified with an absolute drop immediately after, during 2011-2015 (8.8%). A marked shift in trend is observed between 2016-2022 regarding age of injuries (an increase in 9 years or older), etiology (increase in falls and sports versus RTA), AIS grade (increase in incomplete lesions AIS B-D versus AIS A), severity (increase in tetraplegia versus paraplegia) and location (increase in cervical versus lumbar and thoracic injuries). CONCLUSIONS: A shift in trend is observed in the past 7 years regarding age of injuries (increase in those older than 9), etiology (increase in falls and sports versus RTA), AIS grade (increase in incomplete lesions AIS B-D versus AIS A), severity (increase in tetraplegia versus paraplegia) and location (increase in cervical). LEVEL OF EVIDENCE: IV.

Predictors of social risk for post-ischemic stroke reintegration.

After stroke rehabilitation, patients need to reintegrate back into their daily life, workplace and society. Reintegration involves complex processes depending on age, sex, stroke severity, cognitive, physical, as well as socioeconomic factors that impact long-term outcomes post-stroke. Moreover, post-stroke quality of life can be impacted by social risks of inadequate family, social, economic, housing and other supports needed by the patients. Social risks and barriers to successful reintegration are poorly understood yet critical for informing clinical or social interventions. Therefore, the aim of this work is to predict social risk at rehabilitation discharge using sociodemographic and clinical variables at rehabilitation admission and identify factors that contribute to this risk. A Gradient Boosting modelling methodology based on decision trees was applied to a Catalan 217-patient cohort of mostly young (mean age 52.7), male (66.4%), ischemic stroke survivors. The modelling task was to predict an individual's social risk upon discharge from rehabilitation based on 16 different demographic, diagnostic and social risk variables (family support, social support, economic status, cohabitation and home accessibility at admission). To correct for imbalance in patient sample numbers with high and low-risk levels (prediction target), five different datasets were prepared by varying the data subsampling methodology. For each of the five datasets a prediction model was trained and the analysis involves a comparison across these models. The training and validation results indicated that the models corrected for prediction target imbalance have similarly good performance (AUC 0.831-0.843) and validation (AUC 0.881 - 0.909). Furthermore, predictor variable importance ranked social support and economic status as the most important variables with the greatest contribution to social risk prediction, however, sex and age had a lesser, but still important, contribution. Due to the complex and multifactorial nature of social risk, factors in combination, including social support and economic status, drive social risk for individuals.

Pressure ulcers acquired during inpatient rehabilitation after spinal cord injury, characterization and predictors: A 15-years' experience.

BACKGROUND: Most studies focus on the risk factors associated with the development of pressure ulcers (PUs) during acute phase or community care for individuals with spinal cord injury (SCI). OBJECTIVES: This study aimed to i) compare clinical and demographic characteristics of inpatients after SCI with PUs acquired during rehabilitation vs inpatients without PUs and ii) evaluate an existing PU risk assessment tool iii) identify first PU predictors. METHODS: Individuals (n = 1,135) admitted between 2008 and 2022 to a rehabilitation institution within 60 days after SCI were included. Admission Functional Independence Measure (FIM), American Spinal Injury Association Impairment Scale (AIS) and mEntal state, Mobility, Incontinence, Nutrition, Activity (EMINA) were assessed. Kaplan-Meier curves and Cox proportional hazards models were fitted. RESULTS: Overall incidence of PUs was 8.9%. Of these, 40.6% occurred in the first 30 days, 47.5% were sacral, 66.3% were Stage II. Patients with PUs were older, mostly with traumatic injuries (67.3%), AIS A (54.5%), lower FIM motor (mFIM) score and mechanical ventilation. We identified specific mFIM items to increase EMINA specificity. Adjusted Cox model yielded sex (male), age at injury, AIS grade, mFIM and diabetes as PUs predictors (C-Index = 0.749). CONCLUSION: Inpatients can benefit from combined assessments (EMINA + mFIM) and clinical features scarcely addressed in previous studies to prevent PUs.

Return to work within a year after first stroke: blue and white collar workers comparison, predictors and causal mediation assessed during inpatient rehabilitation.

BACKGROUND: Most research focuses around impairments in body function and structure, with relatively only a small number exploring their social impact. OBJECTIVES: 1) compare characteristics for individuals who before stroke were blue collar vs. white collar workers 2) identify clinical, functional, and job-related factors associated with return to work within 1 year after discharge 3) identify specific ADL individual items (assessed at rehabilitation discharge) as return to work predictors and 4) identify return to work causal mediators. METHODS: Retrospective observational cohort study, analyzing adult patients with stroke admitted to rehabilitation between 2007 and 2021, including baseline Barthel Index (BI) and return to work assessments between 2008 and 2022. Kaplan-Meier survival curves and Cox proportional hazards were applied. Causal mediation analyses using 1000-bootstrapped simulations were performed. RESULTS: A total of 802 individuals were included (14.6% returned to work), 53.6% blue-collar and 46.4% white-collar. Blue-collar workers showed significantly higher proportion of ischemic stroke, diabetes, dyslipidemia, and hypertension.Individuals not returning to work presented a higher proportion of blue collar, dominant side affected, aphasia, lower BI scores, and larger length of stay (LOS). Multivariable Cox proportional hazards identified age at injury, aphasia, hypertension, and total discharge BI score (C-Index = 0.74). Univariable Cox models identified three independent BI items at all levels of independence: bathing (C-Index = 0.58), grooming (C-Index = 0.56) and feeding (C-Index = 0.59). BI efficiency (gain/LOS) was a causal mediator. CONCLUSION: Blue collar workers showed higher proportion of risk factors and comorbidities. Novel factors, predictors, and a return to work mediator were identified.

Effectiveness and efficiency of telerehabilitation on functionality after spinal cord injury: A matched case-control study.

BACKGROUND: Telerehabilitation in spinal cord injury (teleSCI) is a growing field that can improve access to care and health outcomes in patients with spinal cord injury (SCI). The clinical effectiveness of teleSCI is not known. OBJECTIVES: To compare independence in activities of daily living and mobility capacity in patients following teleSCI and matched controls undergoing traditional rehabilitation. DESIGN: Matched case-control study. SETTING: TeleSCI occurring in home setting (cases) versus traditional rehabilitation on inpatient unit (controls). PARTICIPANTS: Forty-two consecutive patients with SCI followed with teleSCI were compared to 42 historical rehabilitation inpatients (controls) matched for age, time since injury to rehabilitation admission, level of injury (paraplegia/tetraplegia), complete or incomplete injury, and etiology (traumatic/nontraumatic). The teleSCI group (n = 42) was also compared to the complete cohort of historical controls (n = 613). INTERVENTIONS: The teleSCI group followed home-based telerehabilitation (3.5 h/day, 5 days/week, 67 days average duration) and historical controls followed in-person rehabilitation. MAIN OUTCOME MEASURE(S): The Functional Independence Measure (FIM), the Spinal Cord Independence Measure (SCIM) and the Walking Index for Spinal Cord Injury (WISCI). We formally compared gains, efficiency and effectiveness. International Standards for Neurological Classification of Spinal Cord Injury and the American Spinal Injury Association Impairment Scale (AIS) were used. RESULTS: The teleSCI group (57.1% nontraumatic, 71.4% paraplegia, 73.8% incomplete, 52.4% AIS grade D) showed no significant differences compared with historical controls in AIS grades, neurological levels, duration, gains, efficiency and effectiveness in FIM, SCIM, or WISCI, although the teleSCI cohort had significantly higher admission FIM scores compared with the complete cohort of historical controls. CONCLUSIONS: TeleSCI may provide similar improvements in mobility and functional outcomes as traditional rehabilitation in medically stable patients (predominantly with paraplegia and motor incomplete SCI) when provided with appropriate support and equipment.

Tele-rehabilitation on independence in activities of daily living after stroke: A Matched Case-Control Study.

OBJECTIVES: To compare independence in activities of daily living (ADLs) in post-acute patients with stroke following tele-rehabilitation and matched in-person controls. MATERIALS AND METHODS: Matched case-control study. A total of 35 consecutive patients with stroke who followed tele-rehabilitation were compared to 35 historical in-person patients (controls) matched for age, functional independence at admission and time since injury to rehabilitation admission (<60 days). The tele-rehabilitation group was also compared to the complete cohort of historical controls (n=990). Independence in ADLs was assessed using the Functional Independence Measure (FIM) and the Barthel Index (BI). We formally compared FIM and BI gains calculated as discharge score - admission scores, efficiency measured as gains / length of stay and effectiveness defined as (discharge score-admission score)/ (maximum score-admission score). We analyzed the minimal clinically important difference (MCID) for FIM and BI. RESULTS: The groups showed no significant differences in type of stroke (ischemic or hemorrhagic), location, severity, age at injury, length of stay, body mass index, diabetes, dyslipidemia, hypertension, aphasia, neglect, affected side of the body, dominance or educational level. The groups showed no significant differences in gains, efficiency nor effectiveness either using FIM or Barthel Index. We identified significant differences in two specific BI items (feeding and transfer) in favor of the in-person group. No differences were observed in the proportion of patients who achieved MCID. CONCLUSIONS: No significant differences were seen between total ADL scores for tele-rehabilitation and in-person rehabilitation. Future research studies should analyze a combined rehabilitation approach that utilizes both models.

Inpatient Rehabilitation Falls: Comparing Patients With Traumatic Brain Injury Versus Patients With Stroke.

BACKGROUND: Cognitively impaired neurological rehabilitation inpatients are at an increased risk for falls; yet, little is known regarding fall risk of different groups, such as stroke versus traumatic brain injury. OBJECTIVES: To determine if rehabilitation patients' fall characteristics differ for patients with stroke versus patients with traumatic brain injury. METHODS: This retrospective observational cohort study evaluates inpatients with stroke or traumatic brain injury admitted to a rehabilitation center in Barcelona, Spain, between 2005 and 2021. We assessed independence in daily activities with the Functional Independence Measure. We compared fallen versus nonfallen patients' features and examined the association between time to first fall and risk using Cox proportional hazards models. RESULTS: A total of 1,269 fall events were experienced by 898 different patients with traumatic brain injury ( n = 313; 34.9%) and stroke ( n = 585; 65.1%). A higher proportion of falls for patients with stroke occurred while performing rehabilitation activities (20.2%-9.8%), whereas falls were significantly higher for patients with traumatic brain injury during the night shift. Fall timing revealed completely different behaviors (stroke vs. traumatic brain injury), for example, an absolute peak at 6 a.m. due to young male traumatic patients. Nonfallen patients ( n = 1,363; 78.2%) were younger, with higher independence in daily activities scores, and having a larger time since injury to admission; all three were significant fall predictors. CONCLUSIONS: Patients with traumatic brain injury and stroke showed different fall behaviors. Knowledge of fall patterns and characteristics in the inpatient rehabilitation setting can help design management protocols to mitigate their risk.

Predicting models for arm impairment: External validation of the Scandinavian models and identification of new predictors in post-acute stroke settings.

BACKGROUND: Post-stroke arm impairment at rehabilitation admission as predictor of discharge arm impairment was consistently reported as extremely useful. Several models for acute prediction exist (e.g. the Scandinavian), though lacking external validation and larger time-window admission assessments. OBJECTIVES: (1) use the 33 Fugl-Meyer Assessment-Upper Extremity (FMA-UE) individual items to predict total FMA-UE score at discharge of patients with ischemic stroke admitted to rehabilitation within 90 days post-injury, (2) use eight individual items (seven from the Scandinavian study plus the top predictor item from objective 1) to predict mild impairment (FMA-UE≥48) at discharge and (3) adjust the top three models from objective 2 with known confounders. METHODS: This was an observational study including 287 patients (from eight settings) admitted to rehabilitation (2009-2020). We applied regression models to candidate predictors, reporting adjusted R2, odds ratios and ROC-AUC using 10-fold cross-validation. RESULTS: We achieved good predictive power for the eight item-level models (AUC: 0.70-0.82) and for the three adjusted models (AUC: 0.85-0.88). We identified finger mass flexion as new item-level top predictor (AUC:0.88) and time to admission (OR = 0.9(0.9;1.0)) as only common significant confounder. CONCLUSION: Scandinavian item-level predictors are valid in a different context, finger mass flexion outperformed known predictors, days-to-admission predict discharge mild arm impairment.

Long-term trajectories of community integration: identification, characterization, and prediction using inpatient rehabilitation variables.

BACKGROUND: Community integration (CI) is often regarded as the foundation of rehabilitation endeavors after stroke; nevertheless, few studies have investigated the relationship between inpatient rehabilitation (clinical and demographic) variables and long-term CI. OBJECTIVES: To identify novel classes of patients having similar temporal patterns in CI and relate them to baseline features. METHODS: Retrospective observational cohort study analyzing (n = 287) adult patients with stroke admitted to rehabilitation between 2003 and 2018, including baseline Functional Independence Measure (FIM) at discharge, follow-ups (m = 1264) of Community Integration Questionnaire (CIQ) between 2006 and 2022. Growth mixture models (GMMs) were fitted to identify CI trajectories, and baseline predictors were identified using multivariate logistic regression (reporting AUC) with 10-fold cross validation. RESULTS: Each patient was assessed at 2.7 (2.2-3.7), 4.4 (3.7-5.6), and 6.2 (5.4-7.4) years after injury, 66% had a fourth assessment at 7.9 (6.8-8.9) years. GMM identified three classes of trajectories.Lowest CI (n=105, 36.6%): The lowest mean total CIQ; highest proportion of dysphagia (47.6%) and aphasia (46.7%), oldest at injury, largest length of stay (LOS), largest time to admission, and lowest FIM.Highest CI (n=63, 21.9%): The highest mean total CIQ, youngest, shortest LOS, highest education (27% university) highest FIM, and Intermediate CI (n=119, 41.5%): Intermediate mean total CIQ and FIM scores. Age at injury OR: 0.89 (0.85-0.93), FIM OR: 1.04 (1.02-1.07), hypertension OR: 2.86 (1.25-6.87), LOS OR: 0.98 (0.97-0.99), and high education OR: 3.05 (1.22-7.65) predicted highest CI, and AUC was 0.84 (0.76-0.93). CONCLUSION: Novel clinical (e.g. hypertension) and demographic (e.g. education) variables characterized and predicted long-term CI trajectories.

Long-term prediction of functional independence using adjusted and unadjusted single items of the functional independence measure (FIM) at discharge from rehabilitation.

CONTEXT: Being able to survive in the long-term independently is of concern to patients with spinal cord injury (SCI), their relatives, and to those providing or planning health care, especially at rehabilitation discharge. Most previous studies have attempted to predict functional dependency in activities of daily living within one year after injury. OBJECTIVES: (1) build 18 different predictive models, each model using one FIM (Functional Independence Measure) item, assessed at discharge, as independent predictor of total FIM score at chronic phase (3-6 years post-injury) (2) build three different predictive models, using in each model an item from a different FIM domain with the highest predictive power obtained in objective (1) to predict "good" functional independence at chronic phase and (3) adjust the 3 models from objective (2) with known confounding factors. METHODS: This observational study included 461 patients admitted to rehabilitation between 2009 and 2019. We applied regression models to predict total FIM score and "good" functional independence (FIM motor score ≥ 65) reporting adjusted R2, odds ratios, ROC-AUC (95% CI) tested using 10-fold cross-validation. RESULTS: The top three predictors, each from a different FIM domain, were Toilet (adjusted R2 = 0.53, Transfers domain), Toileting (adjusted R2 = 0.46, Self-care domain), and Bowel (adjusted R2 = 0.35, Sphincter control domain). These three items were also predictors of "good" functional independence (AUC: 0.84-0.87) and their predictive power increased (AUC: 0.88-0.93) when adjusted by age, paraplegia, time since injury, and length of stay. CONCLUSIONS: Discharge FIM items accurately predict long-term functional independence.

Falls During Inpatient Rehabilitation After Spinal Cord Injury: Characterization, Clock-Hour Visualization, and Time to Event Predictors.

OBJECTIVES: To (1) determine fall characteristics (eg, cause, location, witnesses) of inpatients with spinal cord injury (SCI) and whether they were different for ambulatory persons vs wheelchair users; (2) visualize the total number of daily falls per clock-hour for different inpatients' features (eg, cause of injury, age); (3) compare clinical and demographic characteristics of inpatients who experienced a first fall event vs inpatients who did not experience such event; and (4) identify first fall event predictors. DESIGN: Retrospective observational cohort study. SETTING: Institution for inpatient neurologic rehabilitation. PARTICIPANTS: Persons with SCI (N=1294) admitted to a rehabilitation facility between 2005 and 2022. INTERVENTIONS: Not applicable. MAIN OUTCOME MEASURES: Functional independence measure (FIM), Hospital Anxiety and Depression Scale (HADS), American Spinal Injury Association Impairment Scale (AIS), and Spinal Cord Independence Measure (SCIM) at admission. Kaplan-Meier survival curves and Cox proportional hazards models were used. RESULTS: A total of 502 fall events were experienced by 369 ambulatory inpatients (19.8%) and wheelchair users (80.2%) in 63.9% of cases being alone, with cause, situation, and location significantly different in both groups. Clock-hour visualizations revealed an absolute peak at 12 AM (complete or incomplete injuries, with paraplegia or tetraplegia) but a relative peak at 9 AM mainly including incomplete patients with paraplegia. Of the (n=1294) included patients, 16.8% experienced at least 1 fall. Fallen patients reported higher levels of HADS depression, lower total SCIM, and longer time since injury to admission, with no differences in age, sex, educational level, FIM (quasi-significant), and AIS grade. Multivariable Cox proportional hazards identified time since injury to admission and AIS grade D as significant predictors of first fall event. CONCLUSIONS: Falls identification, characterization, and clock-hour visualization can support decisions for mitigation strategies specifically addressed to inpatients with SCI. Fall predictors were identified as a first step for future research.

Understanding and Predicting Cognitive Improvement of Young Adults in Ischemic Stroke Rehabilitation Therapy.

Accurate early predictions of a patient's likely cognitive improvement as a result of a stroke rehabilitation programme can assist clinicians in assembling more effective therapeutic programs. In addition, sufficient levels of explainability, which can justify these predictions, are a crucial requirement, as reported by clinicians. This article presents a machine learning (ML) prediction model targeting cognitive improvement after therapy for stroke surviving patients. The prediction model relies on electronic health records from 201 ischemic stroke surviving patients containing demographic information, cognitive assessments at admission from 24 different standardized neuropsychology tests (e.g., TMT, WAIS-III, Stroop, RAVLT, etc.), and therapy information collected during rehabilitation (72,002 entries collected between March 2007 and September 2019). The study population covered young-adult patients with a mean age of 49.51 years and only 4.47% above 65 years of age at the stroke event (no age filter applied). Twenty different classification algorithms (from Python's Scikit-learn library) are trained and evaluated, varying their hyper-parameters and the number of features received as input. Best-performing models reported Recall scores around 0.7 and F1 scores of 0.6, showing the model's ability to identify patients with poor cognitive improvement. The study includes a detailed feature importance report that helps interpret the model's inner decision workings and exposes the most influential factors in the cognitive improvement prediction. The study showed that certain therapy variables (e.g., the proportion of memory and orientation executed tasks) had an important influence on the final prediction of the cognitive improvement of patients at individual and population levels. This type of evidence can serve clinicians in adjusting the therapeutic settings (e.g., type and load of therapy activities) and selecting the one that maximizes cognitive improvement.

Clinical Prediction Rule Validation for Ambulation Outcome After Traumatic Spinal Cord Injury in a Spanish Population.

BACKGROUND: Predicting the ability to walk after traumatic spinal cord injury is of utmost importance in the clinical setting. Nevertheless, only a small fraction of predictive models are evaluated on their performance by other authors using external data. The Dutch Clinical Prediction Rule for long-term walking ability was developed and validated using neurological assessments performed within 15 days postinjury. However, in reality, this assessment is most often performed between 11 and 55 days. When considering a longer time from injury to neurological assessments, the Dutch Clinical Prediction Rule has only been externally validated for patients after non-traumatic spinal cord injury. OBJECTIVE: We aimed to validate the Dutch Clinical Prediction Rule with neurological assessment performed within 3-90 days after traumatic spinal cord injury, using (a) the Dutch Clinical Prediction Rule logistic regression coefficients (Equation 1); (b) the Dutch Clinical Prediction Rule weighted coefficients (Equation 2); and (c) the reestimated (using a Spanish population) weighted coefficients (Equation 3). METHODS: We conducted a retrospective (STROBE-compliant) study involving 298 adults with traumatic spinal cord injury admitted to a hospital between 2010 and 2019 in Spain. The Spinal Cord Independence Measure item-12 was used for walking assessment. RESULTS: Using Equation 1, the model yielded 86.2% overall classification accuracy, 94.5% sensitivity, and 83.4% specificity (area under the curve [AUC] = 0.939, 95% confidence interval [CI]: 0.915-0.965; p < .001).Using Equation 2 yielded 86.2% overall classification accuracy, 93.2% sensitivity, and 83.9% specificity (AUC = 0.9392, 95% CI: 0.914-0.964; p < .001).Using Equation 3 yielded 86.9% overall classification accuracy, 68.9% sensitivity, and 92.8% specificity (AUC = 0.939, 95% CI: 0.914-0.964; p < .001). CONCLUSIONS: This study validates the Dutch Clinical Prediction Rule in a Spanish traumatic spinal cord injury population with assessments performed up to 90 days postinjury with similar performance, using the original coefficients and including a reestimation of the coefficients.