RESUMO
RATIONALE AND OBJECTIVES: We aimed at developing and validating a nomogram and machine learning (ML) models based on radiomics score (Radscore), morphology, and PHASES to predict intracranial aneurysm (IA) rupture. MATERIALS AND METHODS: We collected 440 patients with IAs in our hospital from 2015 to 2023, totaling 475 IAs (214 ruptured and 261 unruptured). A 7:3 random split was utilized to allocate participants into training and testing sets. To optimize the selection of radiomics features extracted from digital subtraction angiography, we employed t-tests and LASSO regression. Subsequently, we built single-factor and multifactor logistic regression (LR) models, alongside a nomogram. Furthermore, we employed four ML algorithms. After a comprehensive evaluation, including area under the curve (AUC), calibration curves, decision curve analysis (DCA), and other metrics, the best model was determined. RESULTS: The AUCs for LR models P (PHASES), M (Morphology), and R (Radscore) in the testing set were 0.859, 0.755, and 0.803, respectively, while those for multifactor models R+M (Radscore and Morphology), R+P (Radscore and PHASES), and R+M+P (Radscore, Morphology, and PHASES) were 0.818, 0.899, and 0.887, respectively. The AUCs of random forest, extreme gradient boosting, gradient boosting machine, and light gradient boosting machine were 0.880, 0.888, 0.891, and 0.892 in testing set, respectively. In the training set, the LR model showed significant differences in AUCs compared with the four ML models (all p < 0.05). However, in the testing set, no statistically significant differences were found between them (all p > 0.05). Both ML models and the nomogram exhibit excellent performance in DCA and calibration curves. CONCLUSION: Nomogram and ML models based on Radscore, morphology, and PHASES show high precision in predicting aneurysm rupture.
RESUMO
BACKGROUND: Intracranial aneurysm (IA) is a common cerebrovascular disease and the leading cause of spontaneous subarachnoid hemorrhage. Recent evidence suggests that gut microbiota is involved in the pathophysiological process of IA through the gut-brain axis. However, the role of gut inflammation in the development of IA has yet to be clarified. Our study aimed to investigate whether fecal calprotectin (FC) level, a sensitive marker of gut inflammation, is correlated with the development of IA and the prognosis of patients with ruptured IA (RIA). METHODS: 182 patients were collected from January 2022 to January 2023, including 151 patients with IA and 31 healthy individuals. 151 IA patients included 109 patients with unruptured IA (UIA) and 42 patients with RIA. The FC level was measured by enzyme-linked immunosorbent assay. Other detailed information was obtained from an electronic medical record system. RESULTS: Compared with healthy controls, the FC levels in patients with IA were increased (P < 0.0001). Patients with RIA had significantly higher FC levels than UIA patients (P < 0.0001). Moreover, the FC level in RIA patients with unfavorable outcomes was higher than in RIA patients with favorable outcomes. Logistic regression analysis showed that the elevated FC level was an independent risk factor for a 3-month poor prognosis in patients with RIA (OR=1.005, 95% CI = 1.000 -1.009, P = 0.044). CONCLUSION: Fecal calprotectin level is significantly elevated in IA patients, especially those with RIA. FC is a novel biomarker of 3-month poor outcomes in RIA patients.
Assuntos
Aneurisma Roto , Aneurisma Intracraniano , Hemorragia Subaracnóidea , Humanos , Aneurisma Intracraniano/complicações , Aneurisma Intracraniano/diagnóstico , Hemorragia Subaracnóidea/etiologia , Aneurisma Roto/etiologia , Biomarcadores , Inflamação/complicaçõesRESUMO
Homocysteine (Hcy) is a sulphur-containing nonessential amino acid derived from the intermediate metabolites of methionine. Methionine is obtained from dietary proteins, such as poultry, meat, eggs, seafood, and dairy products. Abnormalities in Hcy metabolic pathways, deficiencies in dietary methionine, folate, and vitamins B12, B6, and B2 and genetic defects, polymorphisms, or mutations in Hcy metabolism-related enzymes may lead to an increase in plasma Hcy levels. Generally, a plasma Hcy level higher than 10 or 15â µmol/L has been defined as hyperhomocysteinemia (HHcy). An individual with essential hypertension complicated with HHcy is considered to have H-type hypertension (HTH). Currently, HHcy is considered a novel independent risk factor for various cardiovascular diseases. To provide a useful reference for clinicians, the research progress on Hcy, HHcy, and HTH in recent years was systematically reviewed here, with a focus on the source and metabolic pathways of Hcy, plasma Hcy levels and influencing factors, detection methods for plasma Hcy levels, relationship between Hcy concentration and hypertension, pathogenesis of HTH, cardiovascular complications of HTH, and treatment of HTH.