Alejandro García-Rudolph

Background: Aggressive behavior after stroke is common and linked to poorer outcomes, yet prior studies have not translated this knowledge into operational benchmarks that guide planning (time‐limited risk windows, realistic goals, discharge timelines) during postacute rehabilitation. Objective: To quantify service benchmarks after the first electronic health record (EHR)‐documented aggression and map them to a standardized, time‐boxed response: event rates and short‐horizon risks (30/60 days), functional/length‐of‐stay (LOS) gaps in clinical units, and practical targets for planning. Design: Retrospective observational cohort with prespecified 1:1 propensity‐matched sensitivity analysis. Setting: Single tertiary neurorehabilitation hospital (postacute, inpatient). Patients: Adults with first‐ever ischemic or hemorrhagic stroke admitted ≤3 months post stroke between 2005 and 2023 ( N = 1683). Aggression was flagged at the first qualifying EHR annotation; 317 (18.8%) had more than one episode. Outcome Measure(s): Incidence densities (per 1000 patient‐days) and derived 30‐/60‐day risks for first aggression, urinary tract infection, and falls; between‐group differences in LOS and motor Functional Independence Measure (mFIM) outcomes (gain, efficiency, effectiveness) summarized as median differences (Hodges–Lehmann). Results: Across 111,945 patient‐days, first‐aggression incidence was 2.83/1000 (95% CI: 2.53–3.16), implying 8.1% 30‐day and 15.6% 60‐day risks. Compared with nonaggressive patients, the aggressive group had higher urinary tract infection rates (rate ratio 1.92, 95% confidence interval [CI]: 1.43–2.57) and falls (rate ratio 1.28, 95% CI: 1.00–1.63). Functional gaps (median differences, Hodges–Lehmann) favored the nonaggressive group: LOS was longer (+17.9 days, 95% CI +13.8 to +22.0), mFIM efficiency and effectiveness were lower in the full cohort; in the matched subset (317 vs. 317), Hodges–Lehmann differences persisted (eg, LOS +9.8 days, 95% CI +4.1 to +15.2). Conclusions: A single EHR‐documented aggression provides a planning signal: event rates and 30‐/60‐day risks justify a 60‐day precaution window, and scaled gaps support realistic goal setting (mFIM) and discharge date updates. These benchmarks offer a framework for bedside counseling, service targets, and audit; multicenter validation is warranted.

Introduction: Social risk is a relevant operational category in health social work because it focuses on individual-level conditions associated with poorer health outcomes that may be amenable to intervention. Although numerous social screening tools have been developed in recent years, uncertainty remains as to which instruments specifically assess this construct, which domains they cover, and the extent to which they can be used in complex clinical settings. This review aimed to identify and describe structured instruments for assessing social risk in adults, analyze their characteristics, and examine their potential applicability to health social work and neurorehabilitation. Methods: A systematic review was conducted in accordance with Joanna Briggs Institute guidance and the PRISMA 2020 statement. The initial search was conducted in Dialnet, PsycINFO, and PubMed in September 2025. During peer review, the searches were updated in the same databases and expanded to Scopus, Web of Science, and CINAHL on 11 July 2026. Reports in English or Spanish describing structured tools used with adults in clinical, healthcare, or community settings were included. A two-stage selection process was applied, first to reports and then to tools. Only tools whose primary construct was social risk and that covered at least two domains were retained. Data were synthesized using descriptive, categorical, and comparative analyses. Methodological quality was assessed using the relevant Joanna Briggs Institute critical appraisal tools, and potential applicability was examined in terms of content coverage, operational characteristics, and the available evidence on validity and reliability. Results: Seventy-five reports were included, and 48 tools were identified, of which 10 met the eligibility criteria. Four were developed in Spain, five in the United States, and one in Singapore. The instruments showed considerable heterogeneity in target population, intended clinical use, structure, administration time, and measurement properties. Content analysis identified 23 domains. Housing instability was the most frequently represented domain, followed by mobility and income. PRAPARE had the broadest coverage, encompassing 15 domains. Five instruments reported at least one reliability estimate, although the evidence was uneven and, in several cases, limited to previously validated items or components. None of the instruments had been developed or validated specifically for adults with acquired neurological disabilities. Discussion: The findings confirm conceptual and operational fragmentation in the measurement of social risk. The tools may support risk identification and the systematic collection of information, but their usefulness depends on the fit between the target population, intended purpose, and context of use. In neurorehabilitation, architectural barriers and the need for support with basic activities of daily living were underrepresented. Conclusions: The identified tools may complement professional social work assessment and social diagnosis in healthcare, but they should not be used in isolation or directly transferred to populations other than those for which they were developed. These findings provide a basis for the future adaptation, development, and validation of social risk assessment tools specifically designed for neurorehabilitation.

Recent literature demonstrates widespread interest in the use of Large Language Models (LLMs) for simplifying medical information across multiple domains. In radiology, several studies explored the...

Purpose: To identify and characterize latent trajectories of depression using growth mixture modeling (GMM) applied to irregularly timed assessments spanning up to 20 years post-injury, examine baseline rehabilitation variables significantly associated with trajectory membership, and determine predictors of sustained depressive burden. Methods: This retrospective observational cohort study included adults with traumatic or non-traumatic spinal cord injury admitted for inpatient rehabilitation within 3 months post-injury (2005–2023), with follow-up extending until May 2025. Depressive symptoms were assessed using the Hospital Anxiety and Depression Scale (HADS-D) at admission, discharge, and follow-up, totaling 3,258 assessments (n = 679 patients). GMM identified latent trajectories while accommodating irregularly spaced assessments. Predictors of trajectory membership were analyzed through multivariable regression with quantified model discrimination. Results: A 3-class GMM solution provided optimal fit (entropy=0.75). Most participants (81.6%) followed a stable low-depression trajectory (Class 1). A borderline depression trajectory (Class 2; 8.4%) remained persistently elevated, while a probable depression trajectory (Class 3; 10.0%) displayed delayed worsening peaking at 5–7 years post-injury. Class 3 included a significantly higher proportion of non-traumatic injuries (63%) and females (44.1%), with most patients (85.3%) showing no depressive symptoms during rehabilitation, but later exhibiting a marked increase in depressive burden. Logistic regression predicting Class 2 achieved good discrimination (AUC=0.81; 95% CI, 0.65–0.97), identifying baseline depressive symptoms, tetraplegia, female sex, and primary level of education as significant predictors. Conclusions: Irregularly sampled follow-ups revealed distinct depression trajectories, including delayed-onset risk. Findings emphasize early rehabilitation-based screening and long-term monitoring to target follow-up and psychological support.

Objective: We examined whether GPT-4o, a widely used large language model (LLM), could produce age- and education-appropriate versions of complex pediatric traumatic brain injury case descriptions, while preserving clinical accuracy and emotional tone. Methods: Five cases were adapted into four audience scenarios. Text complexity was assessed via Flesch–Kincaid (FKS), Gunning Fog, and SMOG indices. Clinical human experts rated text fidelity and emotional appropriateness on a 3-point scale. Results: Original texts showed very high complexity (FKS 18.2–20.5), equivalent to 18–20 years of education. Adaptations for parents with high school education were often over-simplified (FKS 4.75–7.1), while versions for 12-year-olds were well-matched (FKS ~5–6). Texts for 8-year-olds had FKS scores of 4.0–6.8 (above grade 2–3 targets) and reduced fidelity (scores 1–2). Emotional tone was consistently rated appropriate across all audiences. Conclusion: Clinicians may use LLMs to draft explanations, but must carefully review and tailor them.

Digital Twins (DTs) have transitioned from theory to reality, with growing applications in healthcare. Data generated by technologies (e.g. rehabilitation robots), essential for DT implementation, though widely produced in clinical settings, remains untapped in DT stroke rehabilitation, highlighting a gap compared to broader healthcare use. We conducted a scoping review to i) define DT rehabilitation objectives, their input data, generation methods and user involvement; ii) analyze mechanisms underpinning DT models and outputs; iii) map key stakeholders driving innovation; iv) identify desirable properties for DT studies from broader healthcare literature and map them to stroke rehabilitation DT studies. Following PRISMA-ScR guidelines, PubMed, Scopus, Web of Science and Google Scholar were searched for studies including only empirical data. Full-text reviews were conducted by three reviewers through repeated calibration. Sixteen studies were included, addressing five rehabilitation objectives: upper-limb (10), gait (3), and engagement, mental health, and general/planning (1 each). Patient sample sizes varied widely, with one retrospective study including 1,216 patients, while 15 studies involved 54 patients in total (median = 1).We identified 16 DTs mechanisms (e.g. variational autoencoders, Hill muscle models) and outcomes (e.g. exoskeleton control, upper-limb exercise delivery, gait torque estimation, impaired hand-mobility quantification). Academic institutions conducted 12 studies, Europe contributed 8 studies across 6 countries. Of 25 desirable properties identified, 8 (e.g. reproducible algorithms) showed high adoption, while 15 (e.g. cost-effectiveness, clinical integration) showed low/very low adoption by included studies. DTs in stroke rehabilitation show promise, though challenges remain (e.g. patient involvement, scalability).

Sleep quality critically influences recovery in neurological patients, yet its longitudinal monitoring during hospitalization remains limited. Nursing narrative notes offer an underutilized resource to track sleep trajectories objectively across time. To propose and apply a formal pipeline that integrates structured clinical data and unstructured nursing annotations to monitor sleep trajectories during post-acute inpatient neurorehabilitation, relying exclusively on free-to-use software tools and without increasing nursing workload. A total of 17,039 nighttime nursing annotations were extracted and categorized into four sleep quality states. Two expert raters manually labeled a training set of 2,000 annotations (κ = 0.84). A random forest classifier achieved 0.93 sensitivity and 0.94 specificity and was used to classify the remaining notes. Sleep sequences were constructed and clustered using sequence analysis (TraMineR) and hierarchical clustering (AGNES, Ward's method). The obtained clusters (silhouette = 0.40) were compared using non-parametric statistics across clinical, functional, and social variables in a cohort of 303 post-acute consecutive neurorehabilitation inpatients. Four distinct sleep trajectory clusters were identified, each characterized by unique functional and socio-environmental profiles. The first group (n = 102; 33.7%) combined high functional independence, strong social support, stable economy, short hospitalization, and favorable sleep quality. The second group (n = 76; 25.1%) presented moderate functional independence, precarious economic conditions, and the highest proportion of poor sleep quality. The third group (n = 76; 25.1%) exhibited severe functional impairment, long hospitalization, poor housing conditions, but paradoxically the highest proportion of good sleep quality. The fourth group (n = 49; 16.2%) showed profound disability, relatively favorable socio-economic conditions, and predominance of intermediate sleep quality, likely influenced by medication. Distinctive sets of social and functional keywords emerged for each cluster. This pipeline identified clinically meaningful sleep profiles from nursing notes, highlighting functional and social determinants' role in shaping neurorehabilitation sleep trajectories.

Inpatients undergoing stroke rehabilitation experience high malnutrition rates, requiring strict dietary management. However, manual and time-pressured dietary provision can cause errors in diet composition, highlighting the need for innovation. Therefore, we aimed to evaluate whether GPT-4o can accurately identify dietary errors in hospital-based stroke rehabilitation menus, analyze differences in AI vs. expert rationale for decisions, and explore AI's potential role in clinical workflows through a structured collaboration framework. A TRIPOD-compliant validation study analyzing 264 hospital-based menus designed for stroke rehabilitation inpatients requiring specialized diets (e.g., dysphagia, diabetes). GPT-4o's dietary compliance classifications were assessed using a structured 0-error, 1-error, and 2+ error framework, with expert dietitians as ground-truth in a rehabilitation hospital nutrition department, where expert dietitians selected menus from existing clinical practices for inpatients on specialized diets. AI-expert agreement, overall accuracy, sensitivity, and specificity in dietary error classification were assessed. AI vs. expert justifications were analyzed thematically to identify differences in decision rationale. Cohen's Kappa (95% CI) measured inter-rater reliability. Overall accuracy, sensitivity, and specificity were calculated using a 3 × 3 confusion matrix, comparing AI classifications (0-error, 1-error, 2+ error) to the expert-labeled ground truth. Thematic analysis categorized AI vs. expert justifications for flagged dietary errors. Out of 264 menus (1,000+ food items), 26 (9.8%) had discrepancies. Among these, 57.7% (15 cases) were PAS-based dysphagia diets, followed by diabetic (19.2%, 5 cases) and allergen-related (15.4%, 4 cases) diets. The remaining two cases involved low-sodium and low-fat diets. Cohen's Kappa: 0.892 (95% CI: 0.845-0.939, p < 0.001). 0-errors: Sensitivity 94.3%, specificity 100%; 1-error: Sensitivity 86.2%, specificity 96.6%; 2+-errors: Sensitivity 97.8%, specificity 92.6%. Thematic analysis revealed GPT-4o followed strict rule-based interpretations, whereas dietitians incorporated patient tolerance and food preparation considerations. GPT-4o demonstrated high accuracy but over-flagged violations, supporting its role as a prescreening tool with expert collaboration.

Study design Hospital-based retrospective epidemiological research. Objectives To describe the epidemiological and demographic characteristics of patients with traumatic spinal cord injury (TSCI) in Catalonia from 1972–2022. Setting Neurological university hospital in Catalonia. Methods All patients diagnosed with TSCI admitted to the hospital from 1972–2022 were retrospectively reviewed. Etiology categories, neurological level of injury, American Spinal Injury Association Impairment Scale (AIS), Functional Independence Measure (FIM), and crude incidence rates were analyzed. Results A total of 3092 individuals with TSCI met the criteria. The crude annual incidence rate was 0.94/100,000 inhabitants. Mean age rose significantly over the years, from 27.7 (SD = 10.9) during 1972–1981 to 41.8 (SD = 17.1) during 2012–2022. The proportion of females constantly increased during 1982–2022 (18.4−23.1%). Etiologies were traffic accidents (51.8%), falls (22.0%), sports (9.8%), work-related (9.1%), suicide attempts (4.6%) and violence (2.7%). The proportion of traffic accidents dropped from 62.4% during 1982–1991 to 37.5% during 2012–2022, whereas falls increased from 14.5% during 1982–1991 to 26.0% during 2012–2022. Suicide attempts was the only etiology constantly increasing during 1972–2022 from 1–8% and with highest proportion of females (55.9%). Thoracic injuries dropped from 57.9% (1972–1981) to 38.3% (2012–2022), while cervical injuries constantly increased up to 48.8% in 2012–2022 with AIS A cases dropping and AIS D increasing. During 2002–2022, the etiologies with highest proportion of poor motor FIM at admission were sports (68.9%) and falls (63.1%). Conclusions Our results suggest the need on prevention strategies specially addressing falls and female suicide attempts.