RESUMO
OBJECTIVE: The aims of this scoping review were to summarize the evidence regarding sex, racial, ethnic, geographic, and socioeconomic disparities in post-acute rehabilitation following total hip arthroplasty (THA) and knee arthroplasty (TKA). METHODS: Literature searches were conducted in Ovid MEDLINE, EMBASE, CINAHL, Web of Science, and PEDro. Studies were included if they were original research articles published 1993 or later; used data from the US; included patients after THA and/or TKA; presented results according to relevant sociodemographic variables, including sex, race, ethnicity, geography, or socioeconomic status; and studied utilization of post-acute rehabilitation as an outcome. RESULTS: Twelve studies met the inclusion criteria. Five examined disparities in inpatient rehabilitation and found that Black patients and women experience longer lengths of stay after arthroplasty, and women are less likely than men to be discharged home after inpatient THA rehabilitation. Four studies examined data from skilled nursing facilities and found that insurance type and dual eligibility impact length of stay and rates of community discharge but found conflicting results regarding racial disparities in skilled nursing facility utilization after TKA. Five studies examined home health data and noted that rural agencies provide less care after TKA. Results regarding racial disparities in home health utilization after arthroplasty were conflicting. Six studies of outpatient rehabilitation noted geographic differences in timing of outpatient rehabilitation but mixed results regarding race differences in outpatient rehabilitation. CONCLUSION: Current evidence indicates that sex, race, ethnicity, geography, and socioeconomic status are associated with disparities in post-acute rehabilitation use after arthroplasty. IMPACT: Rehabilitation providers across the post-acute continuum should be aware of disparities in the population of patients after arthroplasty and regularly assess social determinants of health and other factors that may contribute to disparities. Customized care plans should ensure optimal timing and amount of rehabilitation is provided, and advocate for patients who need additional care to achieve the desired functional outcome.
RESUMO
BACKGROUND: The rehabilitation of a patient who had a stroke requires precise, personalized treatment plans. Natural language processing (NLP) offers the potential to extract valuable exercise information from clinical notes, aiding in the development of more effective rehabilitation strategies. OBJECTIVE: This study aims to develop and evaluate a variety of NLP algorithms to extract and categorize physical rehabilitation exercise information from the clinical notes of patients who had a stroke treated at the University of Pittsburgh Medical Center. METHODS: A cohort of 13,605 patients diagnosed with stroke was identified, and their clinical notes containing rehabilitation therapy notes were retrieved. A comprehensive clinical ontology was created to represent various aspects of physical rehabilitation exercises. State-of-the-art NLP algorithms were then developed and compared, including rule-based, machine learning-based algorithms (support vector machine, logistic regression, gradient boosting, and AdaBoost) and large language model (LLM)-based algorithms (ChatGPT [OpenAI]). The study focused on key performance metrics, particularly F1-scores, to evaluate algorithm effectiveness. RESULTS: The analysis was conducted on a data set comprising 23,724 notes with detailed demographic and clinical characteristics. The rule-based NLP algorithm demonstrated superior performance in most areas, particularly in detecting the "Right Side" location with an F1-score of 0.975, outperforming gradient boosting by 0.063. Gradient boosting excelled in "Lower Extremity" location detection (F1-score: 0.978), surpassing rule-based NLP by 0.023. It also showed notable performance in the "Passive Range of Motion" detection with an F1-score of 0.970, a 0.032 improvement over rule-based NLP. The rule-based algorithm efficiently handled "Duration," "Sets," and "Reps" with F1-scores up to 0.65. LLM-based NLP, particularly ChatGPT with few-shot prompts, achieved high recall but generally lower precision and F1-scores. However, it notably excelled in "Backward Plane" motion detection, achieving an F1-score of 0.846, surpassing the rule-based algorithm's 0.720. CONCLUSIONS: The study successfully developed and evaluated multiple NLP algorithms, revealing the strengths and weaknesses of each in extracting physical rehabilitation exercise information from clinical notes. The detailed ontology and the robust performance of the rule-based and gradient boosting algorithms demonstrate significant potential for enhancing precision rehabilitation. These findings contribute to the ongoing efforts to integrate advanced NLP techniques into health care, moving toward predictive models that can recommend personalized rehabilitation treatments for optimal patient outcomes.
