Functional Independence Measure Motor Score Research Articles

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

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). 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. 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. 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). Inpatients can benefit from combined assessments (EMINA + mFIM) and clinical features scarcely addressed in previous studies to prevent PUs.

469 Recovery Rate of Motor Function During Rehabilitation After Traumatic Cervical Spinal Cord Injury Predicts Functional Status at Years 1 and 5 After Surgery: A Multicenter, Longitudinal Cohort Study

INTRODUCTION: Traumatic spinal cord injury (SCI) is a devastating condition. Early surgical decompression and rehabilitative efforts in cervical SCI patients has been shown to improve neurological outcomes. METHODS: A longitudinal, retrospective cohort study was conducted from the multicenter Spinal Cord Injury Model Systems (SCIMS) database on patients with motor Functional Independence Measure (FIM) scores at admission to and discharge from rehabilitation, year 1, and year 5. Patients who underwent surgical decompression with neurological levels of injury limited to the cervical region and those with American Spinal Injury Association (ASIA) Impairment Scale (AIS) grades of A and B were included. The FIM score was utilized to calculate changes in motor FIM scores over each respective time period. Multivariate logistical regression was performed to identify longitudinal predictors associated with functional independence. RESULTS: A total of 351 patients met the inclusion criteria. The change in motor FIM score during the inpatient rehab period was a significant predictor of achieving FI at 1 and 5 years (year 1: aOR = 15.6, 95% CI 3.94-77.6, p < 0.0001; year 5: aOR = 28.0, 95% CI 6.13-173.6, p < 0.0001). For patients not achieving FI at year 1, the change in motor FIM score during inpatient rehab was a greater predictor of FI at year 5 (aOR = 64.7, 95% CI 5.15-1717.3, p = 0.0004). CONCLUSIONS: Inpatient rehabilitation efforts may lead to greater long-term functional status and carry emphasized importance for patients who do not attain functional independence by year 1.

Association of phasae angle dynamics with sarcopenia and activities of daily living in osteoporotic fracture patients.

This study aimed to determine whether changes in phase angle during rehabilitation are associated with clinical outcomes such as activities of daily living (ADL), skeletal muscle index (SMI), and strength in patients with osteoporotic fractures. This retrospective observational study included patients with osteoporotic fractures admitted to convalescent rehabilitation wards. Changes in phase angle were defined as the difference between the phase angle values at discharge and on admission. The primary outcome was the Functional Independence Measure Motor (FIM-motor) score at discharge. The secondary outcomes were SMI and handgrip strength at discharge. We used multivariate analysis to adjust for confounding factors and examine the association between changes in the phase angle and outcomes. We analyzed a total of 115 patients (97 women, mean age 81.0 ± 10.0 years), with a median change in phase angle of 0.0° during hospitalization. We observed increased phase angles in 49 patients (43%), with a median increase of 0.2°. Multiple regression analysis showed that changes in phase angle were independently associated with FIM-motor score at discharge (β = 0.238, P = 0.027). Changes in phase angle were not significantly associated with SMI (β = 0.059, P = 0.599) or handgrip strength (β = -0.032, P = 0.773) at discharge. An increased phase angle during rehabilitation was positively associated with ADL improvement in patients with osteoporotic fractures. These findings may help clinicians make informed decisions regarding patient care and treatment strategies for better outcomes.

Post-hip-fracture knee pain in older adults prolongs their hospital stays: A retrospective analysis using propensity score matching.

Post-hip-fracture knee pain (PHFKP) occurs in ∼28%-37% of patients and contributes to a prolonged length of hospital stay (LOS). Analyses of LOS prolongation due to PHFKP have been limited to univariate analyses that do not consider important confounding factors. After adjusting for important confounding factors, we investigated whether the presence or absence of PHFKP makes a difference in LOS in patients with hip fractures. We conducted a retrospective review of the medical records of patients who had undergone postoperative rehabilitation after surgery for a hip fracture. Demographic and clinical information, discharge parameters, and PHFKP development information were collected from the medical records. Using propensity score matching, we performed a two-group comparison of LOS, the functional independence measure (FIM) motor score (FIMm), FIMm gain, and FIMm effectiveness in patients with and without PHFKP. Six variables were included in the calculation of propensity scores: age, sex, body mass index, fracture type, American Society of Anesthesiologists physical status, and independence in activities of daily living at discharge. One-way analysis of variance was used to examine the details of the relationships between LOS and (i) the time of PHFKP development and (ii) pain intensity. We analyzed the cases of 261 patients, of whom 87 (33.3%) developed PHFKP. In propensity score matching, 80 patients were each matched to a patient in the PHFKP or non-PHFKP group. After propensity score matching, a between-group comparison revealed that the PHFKP group had a longer LOS (+11days) than the non-PHFKP group, and there were no differences in FIMm gain or FIMm effectiveness. The timing of PHFKP development and pain intensity were not related to the LOS. Even after adjusting for confounders, the development of PHFKP was found to prolong LOS. Clinicians should be aware of possible LOS prolongation in hip fracture patients with PHFKP.

Is the isokinetic strength of nonparetic lower limb related to fatigue in stroke survivors? A cross-sectional study.

The study aimed to investigate the correlation between nonparetic knee muscle strength and fatigue in a cohort of stroke survivors. Thirty-two stroke survivors (17 females, 15 males; median age 62 (interquartile range [IQR] 51-69), (min: 45, max: 81) years were recruited in this cross-sectional study between January 2012 and September 2012. Sociodemographic, clinical, and stroke-related parameters were recorded. All participants underwent an isokinetic measurement of the nonparetic knee flexion and extension. Functional independence measure, functional ambulation category, and Mini-Mental State Examination scores were used to evaluate the functional status, ambulation, and mental status of the patients. Anxiety, depression, and fatigue severity were measured using the Hospital Anxiety and Depression Scale and fatigue severity scale (FSS), respectively. The median duration of stroke was 3.1 (IQR: 2.5-6.5) months. Stroke survivors with reduced muscle strength were older and had lower motor and total functional independence measure scores than those with normal strength (p=0.026, p=0.034, and p=0.034, respectively). There were more patients with lower functional ambulation category scores in the group with reduced muscle strength (p=0.023). Peak torque values of knee flexors at 60°/sec and 180°/sec correlated negatively with FSS (r= -0.360, p=0.043 and r= -0.452, p=0.009, respectively). There was also a negative correlation between the work of knee extensor and flexors at 180°/sec and FSS (r= -0.398, p=0.024 and r= -0.451, p=0.010, respectively). Anxiety and depression scores were not significantly correlated with fatigue. The lower strength of nonparetic knee extensor muscles was related to greater disability and worse ambulatory scores. The lower strength of knee flexor muscles and the work of both knee muscles in the nonparetic limb were related to higher fatigue levels in stroke survivors. Therefore, fatigue management and strengthening of both knee flexor and extensor muscles in the nonparetic limb is emphasized during stroke rehabilitation.

Association between oral health status and functional independence measure on admission in convalescent hospitalized patients

BackgroundOral health management has become increasingly important for acute inpatients. Older patients often require extended periods of medical care, and oral health management is necessary in the convalescent period following the acute period. During the convalescent period, oral health management remains unclear as convalescent hospitals have limited dental resources, and effective dental care must be provided if the objective of hospitalization is to improve life functions. This study aimed to clarify the relationship between daily functioning and oral health status at the time of admission to a convalescent hospital to aid in improving daily functioning in the convalescent period.MethodsWe included patients admitted to the rehabilitation department of a specific convalescent hospital from January to December 2021. A total of 375 patients were included in the study, with complete data records. At admission, we gathered information from the medical records, including the patient’s age, sex, primary disease, Charlson Comorbidity Index, Mini Nutritional Assessment Short-Form (MNA-SF), Functional Oral Intake Scale (FOIS), Functional Independence Measure (FIM), number of teeth, and Oral Health Assessment Tool (OHAT). Statistical analysis was conducted using SPSS Ver. 27, with a significance level of 5%.ResultsThe mean age of the 375 participants (189 men and 186 women) was 75.0 ± 12.1 years (range, 42–97 years), and over 80% were > 65 years. About 30% of major diseases could be attributed to strokes and fractures, followed by spinal cord and spine diseases. In non-stroke patients, multiple regression analysis using FIM motor, FIM cognitive, and FIM and OHAT total scores as objective variables showed that higher total scores of MNA-SF, FOIS, and lower modified Rankin Scale and OHAT were significantly associated with better FIMs. Lower OHAT scores were significantly associated with lower FOIS and MNA-SF scores, male sex, having fewer teeth, and poor dietary patterns.ConclusionsThe convalescent period is an opportune time to provide intensive dental care due to the generally stable condition and extended hospital stay. Our results suggest that oral health management, such as dysphagia rehabilitation and denture treatment, is important for maintaining and improving independence, a key objective of convalescent rehabilitation, and malnutrition improvement.

Prognostic Value of Dysphagia for Activities of Daily Living Performance and Cognitive Level after Stroke.

The purpose of this study was to examine the association between baseline dysphagia and the improvement of activities of daily living performance and cognitive level among inpatients after stroke. This was a retrospective cohort study of patients undergoing convalescent rehabilitation after stroke. Dysphagia was assessed using the Food Intake LEVEL Scale. Outcomes were the motor and cognitive scores of the Functional Independence Measure (FIM) at discharge. Multiple regression analysis was performed to examine the association between dysphagia at admission and these outcomes. There were 499 participants with a median age of 74 years. A multiple regression analysis was carried out after adjusting for potential confounders including age and sex. Dysphagia at admission was independently and negatively associated with motor (β=-0.157, P<0.001) and cognitive (β=-0.066, P=0.041) FIM scores at discharge. Baseline dysphagia in patients after stroke was negatively associated with improvement in performance of activities of daily living and cognitive level.

Applicability of the Diagnostic Criteria for Sarcopenic Obesity Defined by ESPEN/EASO Criteria in Acutely Admitted Patients with Stroke: Prevalence and Association with Outcomes.

Few reports have described sarcopenic obesity in patients with stroke. This study aimed to investigate the prevalence of sarcopenic obesity, as defined by the European Society for Clinical Nutrition and Metabolism (ESPEN) and European Association for the Study of Obesity (EASO) consensus statement, in patients with acute stroke and to determine whether it was associated with improved physical function at discharge. This retrospective cohort study was conducted from May 2020 to November 2021 in patients with acute stroke. Sarcopenic obesity was determined using the ESPEN and EASO consensus statement. The main outcome was physical function based on the Functional Independence Measure motor score at discharge. Multiple regression analysis was conducted to evaluate the association between sarcopenic obesity and the Functional Independence Measure motor score. This study included 276 patients (182 men; mean age, 72.4 y). Sarcopenic obesity screened for obesity with body mass index >27.5 was found in 11 (4%) patients. Multiple regression analysis revealed that sarcopenic obesity screened for obesity with body mass index >27.5 was not significantly associated with the Functional Independence Measure motor score at discharge (β=0.038; 95% confidence interval: -0.046, 0.123; p=0.369). This study revealed a prevalence rate of 4% for sarcopenic obesity diagnosed by the ESPEN and EASO criteria and showed that sarcopenic obesity was not statistically associated with activities of daily living at acute discharge in patients with stroke.

Machine Learning Web Application for Predicting Functional Outcomes in Patients With Traumatic Spinal Cord Injury Following Inpatient Rehabilitation.

Accurately predicting functional outcomes in patients with spinal cord injury (SCI) helps clinicians set realistic functional recovery goals and improve the home environment after discharge. The present study aimed to develop and validate machine learning (ML) models to predict functional outcomes in patients with SCI and deploy the models within a web application. The study included data from the Japan Association of Rehabilitation Database from January 1, 1991, to December 31, 2015. Patients with SCI who were admitted to an SCI center or transferred to a participating post-acute rehabilitation hospital after receiving acute treatment were enrolled in this database. The primary outcome was functional ambulation at discharge from the rehabilitation hospital. The secondary outcome was the total motor Functional Independence Measure (FIM) score at discharge. We used binary classification models to predict whether functional ambulation was achieved, as well as regression models to predict total motor FIM scores at discharge. In the training dataset (70% random sample) using demographic characteristics and neurological and functional status as predictors, we built prediction performance matrices of multiple ML models and selected the best one for each outcome. We validated each model's predictive performance in the test dataset (the remaining 30%). Among the 4181 patients, 3827 were included in the prediction model for the total motor FIM score. The mean (standard deviation [SD]) age was 50.4 (18.7) years, and 3211 (83.9%) patients were male. There were 3122 patients included in the prediction model for functional ambulation. The CatBoost Classifier and regressor models showed the best performances in the training dataset. On the test dataset, the CatBoost Classifier had an area under the receiver operating characteristic curve of 0.8572 and an accuracy of 0.7769 for predicting functional ambulation. Likewise, the CatBoost Regressor performed well, with an R2 of 0.7859, a mean absolute error of 9.2957, and a root mean square error of 13.4846 for predicting the total motor FIM score. The final models were deployed in a web application to provide functional predictions. The application can be found at http://3.138.174.54:8501. In conclusion, our prediction models developed using ML successfully predicted functional outcomes in patients with SCI and were deployed in an open-access web application.

The Association between Oral Health Management and the Functional Independence Measure Scores at the Time of Admission of Inpatients to a Convalescent Hospital.

Many older patients admitted to convalescent hospitals present with impaired oral function, which is an important function of daily life. This study aimed to investigate the actual status of the oral healthcare needs of inpatients in a convalescent hospital and to clarify the relationship between the level of independence at admission and the oral function. The participants were 147 patients (94 males, 53 females, mean age: 74.6 ± 13.1 years) who received dental visits during their stay at a convalescent hospital. Information regarding general and oral health was extracted from medical records. Most patients were found to have low Functional Independence Measure motor scores, and approximately 70% had some form of oral intake, but approximately 80% had nutritional problems. The mean number of present and functional teeth were 16.6 and 20.8, respectively, and 65% of patients lost molar occlusal support. Multiple regression analysis showed significant positive correlations of high functional independence measure with age, eating status, nutritional status, and the number of functional teeth. This implied that oral health management is important for patients in a convalescent hospital and that enhancing oral health may be related to improved eating textures and better nutritional status.

A data-driven approach to categorize patients with traumatic spinal cord injury: cluster analysis of a multicentre database.

Conducting clinical trials for traumatic spinal cord injury (tSCI) presents challenges due to patient heterogeneity. Identifying clinically similar subgroups using patient demographics and baseline injury characteristics could lead to better patient-centered care and integrated care delivery. We sought to (1) apply an unsupervised machine learning approach of cluster analysis to identify subgroups of tSCI patients using patient demographics and injury characteristics at baseline, (2) to find clinical similarity within subgroups using etiological variables and outcome variables, and (3) to create multi-dimensional labels for categorizing patients. Retrospective analysis using prospectively collected data from a large national multicenter SCI registry. A method of spectral clustering was used to identify patient subgroups based on the following baseline variables collected since admission until rehabilitation: location of the injury, severity of the injury, Functional Independence Measure (FIM) motor, and demographic data (age, and body mass index). The FIM motor score, the FIM motor score change, and the total length of stay were assessed on the subgroups as outcome variables at discharge to establish the clinical similarity of the patients within derived subgroups. Furthermore, we discussed the relevance of the identified subgroups based on the etiological variables (energy and mechanism of injury) and compared them with the literature. Our study also employed a qualitative approach to systematically describe the identified subgroups, crafting multi-dimensional labels to highlight distinguishing factors and patient-focused insights. Data on 334 tSCI patients from the Rick Hansen Spinal Cord Injury Registry was analyzed. Five significantly different subgroups were identified (p-value ≤0.05) based on baseline variables. Outcome variables at discharge superimposed on these subgroups had statistically different values between them (p-value ≤0.05) and supported the notion of clinical similarity of patients within each subgroup. Utilizing cluster analysis, we identified five clinically similar subgroups of tSCI patients at baseline, yielding statistically significant inter-group differences in clinical outcomes. These subgroups offer a novel, data-driven categorization of tSCI patients which aligns with their demographics and injury characteristics. As it also correlates with traditional tSCI classifications, this categorization could lead to improved personalized patient-centered care.

The impact of body mass index changes on traumatic brain injury patients’ outcomes during hospitalization

PurposeObesity is a complex multifactorial disease with increasing prevalence worldwide. The present study was conducted, since there were different results on the effect of obesity on the prognosis of patients with moderate and severe brain trauma, and the issue was less investigated. MethodsThe present descriptive-analytical study was conducted in 2 hospitals, Al-Zahra and Kashani in year 2022. Patients with Glasgow coma scale (GCS) score of 9 – 12 (moderate concussion) and patients with a GCS score of < 8 (severe concussion) who consented to participate in the study were included in the study. Patients who died; had serious injuries related to the chest, abdomen, pelvis, spine, and organs, in addition to the concussion; had a part of their body amputated during the same incident; received medications; or had diseases which caused obesity like diabetes were excluded from the study. Patients’ height and weight were extracted for calculating the body mass index (BMI). Their functional independences were measured at admission and discharge according to the Glasgow outcome scale-extended (GOSE) scale. All the data were analyzed in SPSS 26. ResultsThis study examined a total of 287 traumatic brain injury (TBI) patients (251 with moderate concussion and 36 with severe concussion). In total, 91 (36.3%) patients with moderate TBI had a lower BMI, and 14 (38.9%) patients with severe TBI had a constant BMI. There was a significant difference between the mean changes of BMI and the GOSE, functional independence measure (FIM) motor (p = 0.006), FIM cognitive (p = 0.023), and FIM total scores (p = 0.002) in patients with severe TBI; however, significant difference was found only between the mean changes of BMI, GOSE and FIM motor scores (p = 0.001) in patients with moderate TBI. ConclusionBMI is a risk factor affecting treatment results in patients with TBI, which should be controlled.

Clinical efficacy of assessment of swallowing ability for pneumonia and other assessment tools for occurrence and mortality from pneumonia among older inpatients in a long-term care hospital

BackgroundAspiration pneumonia is an important condition in elderly patients and detecting dysphagia early can help clinicians identify patients with a high risk of aspiration pneumonia. We previously reported the usefulness of the Assessment of Swallowing Ability for Pneumonia (ASAP) in predicting the occurrence of and mortality from pneumonia in patients in acute care hospitals; however, there are very few reports on the utility of this screening test for patients in stable condition. MethodsElderly patients in stable condition (n = 133) without pneumonia were prospectively enrolled. Associations between ASAP, Functional Independence Measure (FIM), Controlling Nutrition Status (CONUT), and Charlson Co-morbidity Index (CCI) scores and occurrence of/mortality from pneumonia during hospitalization were evaluated. ResultsThe occurrence of pneumonia was observed in 27 (20.3%) patients, and 18 (13.5%) died during hospitalization. Multivariate analysis showed that low ASAP score and low FIM motor were independent predictors for the occurrence of pneumonia, and low ASAP score was an independent predictor for mortality from pneumonia. Areas under the curve for ASAP, FIM motor, FIM cognition, and CONUT scores were 0.895 (95% confidence interval [CI], 0.829–0.960), 0.913 (95% CI, 0.860–0.968), 0.841 (95% CI, 0.761–0.921), and 0.753 (95% CI, 0.649–0.858), respectively, for occurrence, and 0.881 (95% CI, 0.807–0.955), 0.904 (95% CI, 0.860–0.949), 0.829 (95% CI, 0.727–0.931), 0.746 (95% CI, 0.617–0.874), respectively, for mortality. ConclusionThe ASAP and FIM motor are useful for predicting the occurrence of and mortality from pneumonia in elderly inpatients in long-term care hospitals.

Predictors of patient length of stay post stroke rehabilitation.

There is little research on length of hospital stay (LOS) in patients post stroke in South African rehabilitation facilities. As LOS is an important indicator of cost-of-care, this information may be useful to all stakeholders. To determine the predictors of hospital LOS in patients post stroke rehabilitation. A retrospective file review of 243 patients. Patient functional ability was measured using the Functional Independence Measure (FIM). Predictors of LOS were determined with multiple regression analysis. The median admission and discharge FIM scores were 43 (range: 16-119) and 75 (range: 16-120) points respectively. The median LOS was 43 (range: 3-112) days. Predictors of LOS were premorbid psychiatric conditions, impaired speech, requiring oxygen support, the development of pneumonia and admission FIM motor score, with admission FIM motor score being the strongest individual predictor of LOS (41%). Admission FIM score had an influence on patient outcomes and LOS. Patients with higher admission FIM motor scores may be able to participate in rehabilitation better and thus have shorter LOS. Being able to predict LOS on admission allows facility administrators to manage bed occupancy, human and clinical resources in post stroke rehabilitation.

Physical functioning factors predicting a return home after stroke rehabilitation: A systematic review and meta-analysis.

This systematic review and meta-analysis sought to identify the physical functioning factors associated with home discharge after inpatient stroke rehabilitation. A search of PubMed, Embase, CINHAL, The Cochrane Library (Trials), Web of Science, and PEDro were conducted up until May 2023. Two independent reviewers selected studies for population (patients with stroke), predictive factors (physical functioning), outcome (discharge destination), setting (inpatient rehabilitation), and study designs (observational and experimental studies). Predictive factors were identified among assessments of the "body function" and "activity" components of the International Classification of Functioning. Methodological quality was assessed with the Newcastle-Ottawa Scale. The findings used quantitative and narrative syntheses. Meta-analyses were performed with the inverse variance method and the random-effects model using included studies with sufficient data. Forty-five studies were included with 204,787 participants. Included studies assessed the association of independence in activities of daily living, walking, rolling, transferring, and balance on admission with a probability of returning home. Motor (odds ratio = 1.23, 95% confidence interval: 1.12-1.35, p < .001) and total (odds ratio = 1.34, 95% confidence interval: 1.14-1.57, p < .001) Functional Independence Measure scores on admission were significantly associated with home discharge in meta-analyses. Additionally, included studies showed that independence in motor activities, such as sitting, transferring, and walking, and scores above thresholds for the Functional Independence Measure and Berg Balance Scale on admission were associated with discharge destination. This review showed that higher independence in activities of daily living on admission is associated with home discharge after inpatient stroke rehabilitation.

Rehabilitation after Hip Fracture Surgery Improves Physical and Cognitive Function in Patients with or Without Sarcopenia.

Sarcopenia is a prevalent risk factor for falls and fractures, and it affects the physical function and mortality of older people. The present study was performed to assess the prevalence of sarcopenia in patients who underwent rehabilitation after hip fracture surgery and to examine the association of sarcopenia with physical and cognitive function outcomes. This case-control study involved 132 patients who were admitted to a convalescent rehabilitation ward at a single hospital after surgical treatment of hip fractures from April 2018 to March 2020. The skeletal muscle mass index was examined using whole-body dual-energy X-ray absorptiometry. The Asian Working Group for Sarcopenia 2019 diagnostic criteria were applied on admission. We compared the walking speed, Mini-Mental State Examination (MMSE) score, and Functional Independence Measure (FIM) score between the sarcopenia group and non-sarcopenia group on admission and on discharge. The prevalence of sarcopenia was 59.8%. In the non-sarcopenia group, the walking speed, MMSE score, FIM total score, FIM motor score, and FIM cognitive score were significantly lower on admission than those on discharge (P < .05). In the sarcopenia group, the walking speed, MMSE score, FIM total score, and FIM motor score were significantly lower on admission than those on discharge (P < .05); there was no significant difference in the FIM cognitive score between admission and discharge. On both admission and discharge, the MMSE score, FIM total score, FIM motor score, and FIM cognitive score were significantly better in the non-sarcopenia group than those in the sarcopenia group. After postoperative rehabilitation of hip fractures in patients with and without sarcopenia, physical and cognitive function outcomes on discharge were significantly better than those on admission. Patients with sarcopenia had significantly worse physical and cognitive function outcomes than patients without sarcopenia both on admission and on discharge.

Improvement of predictive accuracies of functional outcomes after subacute stroke inpatient rehabilitation by machine learning models.

Stepwise linear regression (SLR) is the most common approach to predicting activities of daily living at discharge with the Functional Independence Measure (FIM) in stroke patients, but noisy nonlinear clinical data decrease the predictive accuracies of SLR. Machine learning is gaining attention in the medical field for such nonlinear data. Previous studies reported that machine learning models, regression tree (RT), ensemble learning (EL), artificial neural networks (ANNs), support vector regression (SVR), and Gaussian process regression (GPR), are robust to such data and increase predictive accuracies. This study aimed to compare the predictive accuracies of SLR and these machine learning models for FIM scores in stroke patients. Subacute stroke patients (N = 1,046) who underwent inpatient rehabilitation participated in this study. Only patients' background characteristics and FIM scores at admission were used to build each predictive model of SLR, RT, EL, ANN, SVR, and GPR with 10-fold cross-validation. The coefficient of determination (R2) and root mean square error (RMSE) values were compared between the actual and predicted discharge FIM scores and FIM gain. Machine learning models (R2 of RT = 0.75, EL = 0.78, ANN = 0.81, SVR = 0.80, GPR = 0.81) outperformed SLR (0.70) to predict discharge FIM motor scores. The predictive accuracies of machine learning methods for FIM total gain (R2 of RT = 0.48, EL = 0.51, ANN = 0.50, SVR = 0.51, GPR = 0.54) were also better than of SLR (0.22). This study suggested that the machine learning models outperformed SLR for predicting FIM prognosis. The machine learning models used only patients' background characteristics and FIM scores at admission and more accurately predicted FIM gain than previous studies. ANN, SVR, and GPR outperformed RT and EL. GPR could have the best predictive accuracy for FIM prognosis.

Predictors Of Outcome In ICH Patients Initially Admitted To The ICU Who Are Transferred To Inpatient Rehab (P5-7.002)

<h3>Objective:</h3> Assess factors associated with good functional outcomes after ICH requiring ICU admission. <h3>Background:</h3> Intracerebral hemorrhage (ICH) is associated with high mortality, with patients requiring intensive care unit (ICU) admission having worse outcomes. However, current scores are limited in their ability to predict functional outcomes. <h3>Design/Methods:</h3> We collected data using a prospectively maintained registry of stroke patients admitted to 5 inpatient rehabs (IR)s in our hospital system between 1/2018 to 6/2019. We performed predictive modeling with RIDGE regression analysis to predict the rehab discharge motor functional independence measure (FIM). Variables used to perform predictive modeling included age, ICU length of stay (LOS), concurrent IVH, ICH expansion, decompressive surgery, laterality of ICH, symptom onset to rehab admission, rehab admission motor FIM score, initial NIHSS, and total therapy days. <h3>Results:</h3> We identified 166 patients with ICH admitted to IR, of which a significant number (51%) were initially admitted to the ICU. After excluding patients with incomplete variables, 61 patients were included in the model. The median age was 59[47–71] years, and 44% were female. The median initial NIHSS was 12 [5–18], and the length of stay in the ICU was 6 [3–10] days. 34 (55.7%) of the patient had IVH, and 7 (11.5%) had hematoma expansion. 7 (11.5%) needed decompressive surgery. The median admit motor FIM score was 24 [17–36], and after a median of 14 [14–14] days in IR, the median discharge motor FIM score more than doubled to 58 [46–69]. Our predictive model had an r-squared of 0.65. Decompressive surgery patients had better scores by 4 points than patients without decompressive surgery. As therapy days increase by one day, discharge motor FIM scores increase by approximately 2 points. <h3>Conclusions:</h3> Our model can satisfactorily predict rehab discharge motor FIM. However, additional factors involved in the process will be explored to improve the model. <b>Disclosure:</b> Dr. Ahmad has nothing to disclose. Dr. Tariq has nothing to disclose. Christin Silos has nothing to disclose. Ms. Hernandez has nothing to disclose. Ms. Contreras has nothing to disclose. Dr. Savitz has nothing to disclose.

Potentially Preventable Readmissions After Acute Inpatient Rehabilitation.

The aim of the study is to identify causes and risk factors for potentially preventable readmissions of patients discharged from an inpatient rehabilitation facility. Our hospital billing database was used to identify patients discharged from our inpatient rehabilitation facility between 2013 and 2018 and experienced a potentially preventable readmission within 90 days ( n = 75). Retrospective chart review was completed to obtain clinical data. Of the patients discharged from the inpatient rehabilitation facility who did not experience a potentially preventable readmission, a group of age- and sex-matched controls ( n = 75) was randomly selected. The two study groups were compared using univariate and multivariate analyses. Our study found that individuals who discharged from acute inpatient rehabilitation were more likely to be readmitted with a potentially preventable readmission if they have a greater number of comorbidities, were admitted initially with a spinal cord injury, or have lower admission or discharge Functional Independence Measure motor scores. The most common potentially preventable readmission diagnoses were sepsis, renal failure, respiratory problems, and urinary tract infection. Identifying patients with the common causes for potentially preventable readmissions, in addition to the noted risk factors, is an important consideration for inpatient rehabilitation discharge planning.

The impact of dementia on rehabilitation outcomes following hip fracture.

To compare clinical outcomes between patients for whom their participation in inpatient rehabilitation was and was not impacted by dementia through matching patients reporting dementia (dementia group) with those not reporting dementia (non-dementia group). Prospectively collected data held by the Australasian Rehabilitation Outcome Centre (AROC) were analyzed for patients aged 65 years or older receiving inpatient rehabilitation in public hospitals in Australia following a hip fracture and discharged between July 1, 2014, and June 30, 2019. Patients reported as having dementia impacting their rehabilitation program were matched to patients not reporting dementia based on age, admission motor Functional Independence Measure (FIM) score, and accommodation prior to rehabilitation. The matched cohorts were compared in relation to clinical outcomes (motor and cognitive FIM improvement, FIM efficiency, length of stay, and discharge destination) following participation in hospital-based rehabilitation using univariate analysis. Patients with dementia had significantly lower cognitive FIM scores on commencing rehabilitation (17.6 and 26.9, respectively, P < 0.001) and their median length of stay was 2 days shorter than those without dementia (21 and 23 days, respectively, P < 0.001). Relative change in FIM score and FIM efficiency (per week) were lower in the dementia group [relative FIM score change of dementia vs non-dementia, respectively, 26.2% vs. 44.0% (P < 0.001) and FIM efficiency, 6.5 vs. 8.9 (P < 0.001)]. Discharge destination between the two groups was statistically different, with 35.7% of patients with dementia being discharged to residential aged care facilities (RACFs) compared to 21.7% of those without dementia (P < 0.001). More patients with dementia had carers in their private residence in the post-rehabilitation phase, 82.2% vs. 57.6% (P < 0.001). Patients with dementia who sustain a fractured hip benefit from inpatient rehabilitation, although their clinical outcomes are not as good as those without dementia. FIM change and FIM efficiency were lower in the dementia group. Length of stay in the hospital for patients with dementia was shorter due to earlier recognition for the need for placement in either an RACF or at home with carer support. Theneed for placement in an RACF or carer support in a private residence was significantly greater in the dementia group.