Hand (New York, N.Y.) · 2026
Predictive Modeling of Sensory Recovery Following Peripheral Nerve Injury: Evaluating the Combined Influence of Surgical, Biological, and Social Factors.
СтатьяНазвание и аннотация: Перевод в очереди
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…
Ошибки и ограничения
История · было → стало
Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.
Rizvanović Bryce F, Jenkins Danna, Mueller Madeline K, Ferguson Alexandra M, Nuelle Julia A V
Аннотация
BACKGROUND: Recovery from peripheral nerve injuries (PNI) is influenced by a range of biological, social, and clinical factors. However, the relative contributions of these domains to sensory recovery remain unclear. The objective of this study is to evaluate the predictive value of biological, social, and injury/surgical factors on sensory recovery after PNI, using logistic regression modelsMethods:A retrospective review of 169 patients who underwent upper extremity peripheral nerve reconstruction between May 2013 and May 2023 was conducted. Functional sensory recovery was measured using static 2-point discrimination (2pD) at 6 months postsurgery. Predictor variables were categorized into 3 domains: biological (eg, age and comorbidities), social (eg, insurance status and formal rehabilitation participation), and surgical (eg, nerve injured, gap length, and timing to surgery). Separate logistic regression models were developed for each domain, followed by a combined model incorporating all variables. Model performance was assessed using accuracy, area under the receiver operating characteristic (ROC) curve (AUC), and confusion matrix analysis.
RESULTS: The Injury/Surgical model yielded the highest standalone accuracy (82.4%) and ROC AUC (0.85) among domain-specific models. The Combined model demonstrated superior overall performance with an ROC AUC of 0.92 and accuracy of 85.3%. Key predictive features included age, gap length, injury-to-evaluation interval, formal occupational therapy participation, Area Deprivation Index, current smoker, and history of alcohol use.
CONCLUSIONS: Recovery from PNI is most strongly influenced by injury-specific and surgical characteristics. However, the integration of social and biological factors can enhance predictive performance. Multidimensional modeling frameworks may inform preoperative counseling, surgical planning, and postoperative care.
RESULTS: The Injury/Surgical model yielded the highest standalone accuracy (82.4%) and ROC AUC (0.85) among domain-specific models. The Combined model demonstrated superior overall performance with an ROC AUC of 0.92 and accuracy of 85.3%. Key predictive features included age, gap length, injury-to-evaluation interval, formal occupational therapy participation, Area Deprivation Index, current smoker, and history of alcohol use.
CONCLUSIONS: Recovery from PNI is most strongly influenced by injury-specific and surgical characteristics. However, the integration of social and biological factors can enhance predictive performance. Multidimensional modeling frameworks may inform preoperative counseling, surgical planning, and postoperative care.