Predictive Modeling and Integrated Risk Assessment of Postoperative Mortality and Pneumonia in Traumatic Brain Injury Patients through Clustering and Machine Learning: Retrospective Study.

This study harnessed machine learning to forecast postoperative mortality (POM) and postoperative pneumonia (PPN) among surgical traumatic brain injury (TBI) patients. Our analysis centered on the following key variables: Glasgow Coma Scale (GCS), midline brain shift (MSB), and time from injury to emergency room arrival (TIE). Additionally, we introduced innovative clustered variables to enhance predictive accuracy and risk assessment. Exploring data from 617 patients spanning 2012 to 2022, we observed that 22.9% encountered postoperative mortality, while 30.0% faced postoperative pneumonia (PPN). Sensitivity for POM and PPN prediction, before incorporating clustering, was in the ranges of 0.43-0.82 (POM) and 0.54-0.76 (PPN). Following clustering, sensitivity values were 0.47-0.76 (POM) and 0.61-0.77 (PPN). Accuracy was in the ranges of 0.67-0.76 (POM) and 0.70-0.81 (PPN) prior to clustering and 0.42-0.73 (POM) and 0.55-0.73 (PPN) after clustering. Clusters characterized by low GCS, small MSB, and short TIE exhibited a 3.2-fold higher POM risk compared to clusters with high GCS, small MSB, and short TIE. In summary, leveraging clustered variables offers a novel avenue for predicting POM and PPN in TBI patients. Assessing the amalgamated impact of GCS, MSB, and TIE characteristics provides valuable insights for clinical decision making.

Outcome Analysis of External Neurolysis in Posture-Induced Compressive Peroneal Neuropathy and the Utility of Magnetic Resonance Imaging in the Treatment Process.

OBJECTIVE: We aimed to analyze the effectiveness of external neurolysis on the common peroneal nerve (CPN) in patients with posture-induced compressive peroneal neuropathy (PICPNe). Further, we aimed to examine the utility of magnetic resonance imaging (MRI) in assessing the severity of denervation status and predicting the postoperative prognosis. METHODS: We included 13 patients (eight males and five females) with foot drop who underwent CPN decompression between 2018 and 2020. We designed a grading system for assessing the postoperative functional outcome. Additionally, we performed MRI to evaluate the denervation status of the affected musculature and its effect on postoperative recovery. RESULTS: The median time to surgery was 3 months. The median preoperative ankle dorsiflexion and eversion grades were both 3, while the average functional grade was 1. Posterior crural intermuscular septum was the most common cause of nerve compression, followed by deep tendinous fascia and anterior crural intermuscular septum. There was a significant postoperative improvement in the median postoperative ankle dorsiflexion and eversion grades and average postoperative functional (4, 5, and 2.38, respectively). Preoperative ankle eversion was significantly correlated with denervation status. Additionally, the devernation status on MRI was positively correlated with the outcome favorability. However, denervation atrophy led to a less favorable outcome. CONCLUSION: Among patients with intractable PICPNe despite conservative management, surgical intervention could clinically improve motor function and functional ability. Additionally, MRI examination of the affected muscle could help diagnose CPNe and assess the postoperative prognosis.

Anatomical Variants of "Short Head of Biceps Femoris Muscle" Associated with Common Peroneal Neuropathy in Korean Populations : An MRI Based Study.

OBJECTIVE: In Asians, kneeling and squatting are the postures that are most often induce common peroneal neuropathy. However, we could not identify a compatible compression site of the common peroneal nerve (CPN) during hyper-flexion of knees. To evaluate the course of the CPN at the popliteal area related with compressive neuropathy using magnetic resonance imaging (MRI) scans of healthy Koreans. METHODS: 1.5-Tesla knee MRI scans were obtained from enrolled patients and were retrospectively reviewed. The normal populations were divided into two groups according to the anatomical course of the CPN. Type I included subjects with the CPN situated superficial to the lateral gastocnemius muscle (LGCM). Type II included subjects with the CPN between the short head of biceps femoris muscle (SHBFM) and the LGCM. We calculated the thickness of the SHBFM and posterior elongation of this muscle, and the LGCM at the level of femoral condyles. In type II, the length of popliteal tunnel where the CPN passes was measured. RESULTS: The 93 normal subjects were included in this study. The CPN passed through the "popliteal tunnel" formed between the SHBFM and the LGCM in 36 subjects (38.7% type II). The thicknesses of SHBFM and posterior portions of this muscle were statistically significantly increased in type II subjects. The LGCM thickness was comparable in both groups. In 78.8% of the "popliteal tunnel", a length of 21 mm to <40 mm was measured. CONCLUSION: In Korean population, the course of the CPN through the "popliteal tunnel" was about 40%, which is higher than the Western results. This anatomical characteristic may be helpful for understanding the mechanism of the CPNe by posture.