Reliable prediction of outcomes of aneurysmal subarachnoid hemorrhage (aSAH) based on factors available at patient admission may support responsible allocation of resources as well as treatment decisions. Radiographic and clinical scoring systems may help clinicians estimate disease severity, but their predictive value is limited, especially in devising treatment strategies. In this study, we aimed to examine whether a machine learning (ML) approach using variables available on admission may improve outcome prediction in aSAH compared to established scoring systems. Combined clinical and radiographic features as well as standard scores (Hunt & Hess, WFNS, BNI, Fisher, and VASOGRADE) available on patient admission were analyzed using a consecutive single-center database of patients that presented with aSAH (n = 388). Different ML models (seven algorithms including three types of traditional generalized linear models, as well as a tree bosting algorithm, a support vector machine classifier (SVMC), a Naive Bayes (NB) classifier, and a multilayer perceptron (MLP) artificial neural net) were trained for single features, scores, and combined features with a random split into training and test sets (4:1 ratio), ten-fold cross-validation, and 50 shuffles. For combined features, feature importance was calculated. There was no difference in performance between traditional and other ML applications using traditional clinico-radiographic features. Also, no relevant difference was identified between a combined set of clinico-radiological features available on admission (highest AUC 0.78, tree boosting) and the best performing clinical score GCS (highest AUC 0.76, tree boosting). GCS and age were the most important variables for the feature combination. In this cohort of patients with aSAH, the performance of functional outcome prediction by machine learning techniques was comparable to traditional methods and established clinical scores. Future work is necessary to examine input variables other than traditional clinico-radiographic features and to evaluate whether a higher performance for outcome prediction in aSAH can be achieved.

BACKGROUND: Although numerous articles have been published not only on the classification of thoracic outlet syndrome (TOS) but also on diagnostic standards, timing, and type of surgical intervention, there still remains some controversy because of the lack of level 1 evidence. So far, attempts to generate uniform reporting standards have not yielded conclusive results. OBJECTIVE: To systematically review the body of evidence and reach a consensus among neurosurgeons experienced in TOS regarding anatomy, diagnosis, and classification. METHODS: A systematic literature search on PubMed/MEDLINE was performed on February 13, 2021, yielding 2853 results. Abstracts were screened and classified. Recommendations were developed in a meeting held online on February 10, 2021, and refined according to the Delphi consensus method. RESULTS: Six randomized controlled trials (on surgical, conservative, and injection therapies), 4 “guideline” articles (on imaging and reporting standards), 5 observational studies (on diagnostics, hierarchic designs of physiotherapy vs surgery, and quality of life outcomes), and 6 meta-analyses were identified. The European Association of Neurosurgical Societies’ section of peripheral nerve surgery established 18 statements regarding anatomy, diagnosis, and classification of TOS with agreement levels of 98.4 % (±3.0). CONCLUSION: Because of the lack of level 1 evidence, consensus statements on anatomy, diagnosis, and classification of TOS from experts of the section of peripheral nerve surgery of the European Association of Neurosurgical Societies were developed with the Delphi method. Further work on reporting standards, prospective data collections, therapy, and long-term outcome is necessary.

OBJECTIVE: Feasible clinical scores for predicting shunt-dependent hydrocephalus (SDHC) after aneurysmal subarachnoid hemorrhage (aSAH) are scarce. The chronic hydrocephalus ensuing from SAH score (CHESS) was introduced in 2015 and has a high predictive value for SDHC. Although this score is easy to calculate, several early clinical and radiological factors are required. The authors designed the retrospective analysis described here for external CHESS validation and determination of predictive values for the radiographic Barrow Neurological Institute (BNI) scoring system and a new simplified combined scoring system.METHODS: Consecutive data of 314 patients with aSAH were retrospectively analyzed with respect to CHESS parameters and BNI score. A new score, the shunt dependency in aSAH (SDASH) score, was calculated from independent risk factors identified with multivariate analysis.RESULTS: Two hundred twenty-five patients survived the initial phase after the hemorrhage, and 27.1% of these patients developed SDHC. The SDASH score was developed from results of multivariate analysis, which revealed acute hydrocephalus (aHP), a BNI score of ≥ 3, and a Hunt and Hess (HH) grade of ≥ 4 to be independent risk factors for SDHC (ORs 5.709 [aHP], 6.804 [BNI], and 4.122 [HH]; p < 0.001). All 3 SDHC scores tested (CHESS, BNI, and SDASH) reliably predicted chronic hydrocephalus (ORs 1.533 [CHESS], 2.021 [BNI], and 2.496 [SDASH]; p ≤ 0.001). Areas under the receiver operating curve (AUROC) for CHESS and SDASH were comparable (0.769 vs 0.785, respectively; p = 0.447), but the CHESS and SDASH scores were superior to the BNI grading system for predicting SDHC (BNI AUROC 0.649; p = 0.014 and 0.001, respectively). In contrast to CHESS and BNI scores, an increase in the SDASH score coincided with a monotonous increase in the risk of developing SDHC.CONCLUSIONS: The newly developed SDASH score is a reliable tool for predicting SDHC. It contains fewer factors and is more intuitive than existing scores that were shown to predict SDHC. A prospective score evaluation is needed.

Background and purpose: There are numerous grading scales to describe the severity of aneurysmal subarachnoid hemorrhage (aSAH) and to predict outcome. Historically, outcome measures are heterogeneous and the comparability of grading scales is therefore limited. We designed this study to compare radiographic, clinical and combined grading systems in aSAH.Methods: Data from 423 consecutive patients with aSAH were analyzed. Modified Fisher (mFish), Barrow Neurological Institute (BNI), Hunt and Hess (HH), World Federation of Neurosurgical Societies (WFNS), VASOGRADE (VG) and HAIR scores were calculated from clinical and radiographic data or the combination of both. Outcome measures included the development of new cerebral infarction (CI) and functional patient outcome assessed by the modified Rankin scale.Results: Cerebral infarction and unfavorable outcome were predicted by radiographic, clinical and combined measures (each with P ≤ 0.001). Clinical (HH, WFNS) and combined (VG, HAIR) scores had superior predictive power for CI compared with mFish grading but not BNI [area under the curve (AUC)_mFish 0.612, AUC_BNI 0.616, AUC_WFNS 0.672, AUC_HH 0.673, AUC_VG 0.674, AUC_HAIR 0.638]. Predictive performances of clinical gradings (HH, WFNS) for patient outcome were superior to radiographic measures and of similar quality or better than combined systems (AUC_BNI 0.628, AUC_mFish 0.654, AUC_WFNS 0.736, AUC_HH 0.749, AUC_VG 0.711, AUC_HAIR 0.739).Conclusions: Knowledge of the merits and limitations of clinical, radiographic and combined scores is necessary in routine clinical practice. The new combined grading systems (HAIR, VG) showed no superiority compared with the established clinical measures (WFNS, HH) in predicting CI and unfavorable patient outcome.

Thoracic outlet syndrome (TOS) refers to a group of disorders in which there is compression of and/or damage to the neurovascular structures at the thoracic outlet, i.e., at the transition from chest to neck. The incidence of neurogenic thoracic outlet syndrome (nTOS) is estimated to be 2–3 / 100 000 / year, with an estimated prevalence of 10 / 100 000. Patients present with upper extremity sensorimotor symptoms that are often related to movement. The aim of the present article is to highlight the clinical presentation patterns of nTOS and to provide an overview of its diagnosis and treatment. Selective literature search for prospective observational studies and RCTs, including systematic reviews and meta-analyses. There is no multicenter randomized controlled trial available on the treatment of nTOS. Prospective observational studies with a hierarchical study design report a positive effect of physiotherapy in 27–59% of cases. After unsuccessful conservative treatment, up to 56–90% benefit from surgical management. Patients with nTOS are more severely affected compared with those with other forms of TOS and benefit less from transaxillary first rib resection. nTOS patients who underwent supraclavicular decompression without rib resection had excellent surgical outcomes in 27%, good outcomes in 36%, acceptable outcomes in 26%, and poor surgical outcomes in 11% of cases. There is no systematic comparison available of the types of surgical management involved. Also, there is currently no uniform classification available for all medical sub-disciplines. Therefore, interpretation, and comparability of the study results are limited. Although nTOS is the most common form of TOS, studies on its treatment are currently limited in terms of numbers and quality. The type of surgical management varies according to the experience and preference of the surgeon, treating specialty, special anatomic features, and clinical symptoms.

Pain and sensory disturbance in the distribution of the lateral femoral cutaneous nerve in the ventrolateral portion of the thigh is called meralgia paresthetica (MP). The incidence of MP has risen along with the increasing prevalence of obesity and diabetes mellitus and was recently estimated at 32 new cases per 100 000 persons per year. In this review, we provide an overview of current standards and developments in the diagnosis and treatment of MP. This review is based on publications retrieved by a selective literature search, with special attention to meta-analyses, systematic reviews, randomized and controlled trials (RCTs), and prospective observational studies. The diagnosis is mainly based on typical symptoms combined with a positive response to an infiltration procedure. In atypical cases, electrophysiological testing, neurosonography, and magnetic resonance imaging can be helpful in establishing the diagnosis. The literature search did not reveal any studies of high quality. Four prospective observational studies with small case numbers and partly inconsistent results are available. In a meta-analysis of 149 cases, pain relief was described after infiltration in 85% of cases and after surgery in 80%, with 1-38 months of follow-up. In another meta-analysis of 670 cases, there was pain relief after infiltration in 22% of cases, after surgical decompression in 63%, and after neurectomy in 85%. Hardly any data are available on more recent treatment options, such as radiofrequency therapy, spinal cord stimulation, or peripheral nerve stimulation. The state of the evidence is limited in both quantity and quality, corresponding to evidence level 2a for surgical and non-surgical methods. Advances in imaging and neurophysiological testing have made the diagnosis easier to establish. When intervention is needed, good success rates have been achieved with surgery (decompression, neurectomy), and variable success rates with infiltration.