Related Experiment Video
Updated: Mar 18, 2026
Traumatic Peripheral Nerve Injury in Mice
Published on: March 25, 2022
Predictive Modeling of Sensory Recovery Following Peripheral Nerve Injury: Evaluating the Combined Influence of
Bryce F Rizvanović1, Danna Jenkins1, Madeline K Mueller1
1University of Missouri, Columbia, USA.
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.
