Search

Background: Ischemic stroke is a common and serious disease with economic and healthcare burdens. Predicting the unfavorable discharge outcome of patients is essential for formulating appropriate treatment strategies and providing personalized care. Therefore, this study aims to establish and validate a prediction model based on machine learning methods to accurately predict the discharge outcome of ischemic stroke patients, providing valuable information for clinical decision making. Methods: The derivation data consisted of 964 patients from Guangdong Provincial People's Hospital and was used for training and internal validation. A favourable discharge outcome was defined as a National Institutes of Health Stroke Scale score of ≤1 or a decrease of ≥8 points compared to the admission score. A predictive model was created based on 88 medical characteristics gathered during the patient's initial admission, using nine machine learning algorithms. The model's predictive performance was compared using various evaluation metrics. The final model's feature importance was ranked and explained using the Shapley additive explanation method. Findings: The random forest model demonstrated the greatest discriminative ability among the nine machine learning models. We created an interpretable random forest model by ranking and reducing the features based on their importance, which included eight features. In internal validations, the final model accurately predicted the discharge outcomes of ischemic stroke with AUC values of 0.903 and has been translated into a convenient tool to facilitate its utility in clinical settings. Conclusions: Our explainable ML model was not only successfully developed to accurately predict discharge outcomes in patients with ischemic stroke and it mitigated the concern of the “black-box” issue with an undirect interpretation of the ML technique.

Objective: To explore the genetic basis for a pedigree affected with Marfan syndrome (MFS)., Methods: Clinical data of the patients was collected. With genomic DNA extracted from peripheral blood samples, potential mutation was detected by targeted exome sequencing. Candidate variants were validated by Sanger sequencing and bioinformatic analysis., Results: Targeted exome sequencing and Sanger sequencing revealed a missense c.649T to C(p.Trp217Arg) variant in the exon 7 of FBN1 gene, which was unreported previously. Bioinformatics analysis suggested that the variant can cause amino acid replacement and affect the structure and function of fibrillin-1., Conclusion: A novel missense variant of the FBN1 gene was identified, which probably underlies the autosomal dominant MFS in this pedigree.

Background: The lymphocyte to monocyte ratio (LMR), a novel systematic biomarker of inflammation, has been reported to be associated with the progression and prognosis of many malignant cancers. However, the relationship between LMR and survival outcome of urological cancers (UCs) remains controversial. Herein, we conducted a meta-analysis to identify the prognostic value of pretreatment LMR in patients with UCs., Methods: A literature search was performed in PubMed, Web of Science, Embase, Cochrane Library, Cochrane Central Register of Controlled Trials, Scopus, and CINAHL databases up to July 2018. The pooled hazard ratios (HRs) and odds ratios (ORs) with corresponding 95% confidence intervals (CIs) were calculated to evaluate the association of LMR with survival outcome and clinicopathological characteristics in UCs., Results: A total of 17 articles containing 5552 patients were included in our study. The synthesized analysis showed that elevated pretreatment LMR level could predict favorable overall survival (OS) of UCs patients (pooled HR = 0.82, 95%CI: 0.77-0.87). Additionally, the decreased LMR level was correlated with tumor stage (OR = 1.72, 95%CI: 1.15-2.55), lymph node metastasis (OR = 1.46, 95%CI:1.06-1.99), grade (OR = 1.79, 95%CI:1.41-2.27), tumor size (OR = 2.21, 95%CI:1.81-2.68) and necrosis (OR = 1.71, 95%CI:1.36-2.16)., Conclusion: The high pretreatment LMR was associated with favorable prognosis, and could be a potential prognostic biomarker in patients with UCs., (Copyright © 2018 Elsevier GmbH. All rights reserved.)