No abstract

No abstract

To confirm whether machine learning algorithms (MLA) can achieve an effective risk stratification of dying within 7 days after basal ganglia hemorrhage (BGH). We collected patients with BGH admitted to Sichuan Provincial People’s Hospital between August 2005 and August 2021. We developed standard ML-supervised models and fusion models to assess the prognostic risk of patients with BGH and compared them with the classical logistic regression model. We also use the SHAP algorithm to provide clinical interpretability. 1383 patients with BGH were included and divided into the conservative treatment group (CTG) and surgical treatment group (STG). In CTG, the Stack model has the highest sensitivity (78.5%). In STG, Weight-Stack model achieves 58.6% sensitivity and 85.1% specificity, and XGBoost achieves 61.4% sensitivity and 82.4% specificity. The SHAP algorithm shows that the predicted preferred characteristics of the CTG are consciousness, hemorrhage volume, prehospital time, break into ventricles, brain herniation, intraoperative blood loss, and hsCRP were also added to the STG. XGBoost, Stack, and Weight-Stack models combined with easily available clinical data enable risk stratification of BGH patients with high performance. These ML classifiers could assist clinicians and families to identify risk states timely when emergency admission and offer medical care and nursing information.

Objective A meta-analysis was conducted to analyze the incidence of typical and atypical headaches and outcomes following various treatments in patients with Chiari I malformation. Background Headache is the most common symptom of Chiari malformation, which can be divided into typical and atypical subgroups to facilitate management. Much controversy surrounds the etiology, prevalence and optimal therapeutic approach for both types of headaches. Method We identified relevant studies published before 30 July 2022, with an electronic search of numerous literature databases. The results of this study were reported according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses statement. Result A total of 1913 Chiari malformation type I CIM patients were identified, 78% of whom presented with headache, within this group cephalgia was typical in 48% and atypical in 29% of patients, and migraine was the most common type of atypical headache. The ratio of typical/atypical headaches with international classification of headache disorders diagnosis was 1.53, and without international classification of headache disorders diagnosis was 1.56, respectively. The pooled improvement rates of typical headaches following conservative treatment, extradural decompression and intradural decompression were 69%, 88%, and 92%, respectively. The corresponding improvement rates for atypical headaches were 70%, 57.47%, and 69%, respectively. The complication rate in extradural decompression group was significantly lower than in intradural decompression group (RR, 0.31; 95% CI: 0.06–1.59, I2 = 50%, P = 0.14). Low reoperation rates were observed for refractory headaches in extradural decompression and intradural decompression groups (1%). Conclusion The International Classification of Headache Disorders can assist in screening atypical headaches. extradural decompression is preferred for typical headaches, while conservative therapy is optimal for atypical headaches. A definite correlation exists between atypical headaches and Chiari Malformation Type I patients with higher prevalence than in the general population. Importantly, decompression is effective in relieving headaches in this particular patient population.

No abstract