A 6-month prognostic nomogram incorporating hemoglobin level for intracerebral hemorrhage in younger adults

Deep learning survival model predicts outcome after intracerebral hemorrhage from initial CT scan

BACKGROUND

Predicting functional impairment after intracerebral hemorrhage (ICH) provides valuable information for planning of patient care and rehabilitation strategies. Current prognostic tools are limited in making long term predictions and require multiple expert-defined inputs and interpretation that make their clinical implementation challenging. This study aimed to predict long term functional impairment of ICH patients from admission non-contrast CT scans, leveraging deep learning models in a survival analysis framework.

METHODS

We used the admission non-contrast CT scans from 882 patients from the Massachusetts General Hospital ICH Study for training, hyperparameter optimization, and model selection, and 146 patients from the Yale New Haven ICH Study for external validation of a deep learning model predicting functional outcome. Disability (modified Rankin scale [mRS] > 2), severe disability (mRS > 4), and dependent living status were assessed via telephone interviews after 6, 12, and 24 months. The prediction methods were evaluated by the c-index and compared with ICH score and FUNC score.

RESULTS

Using non-contrast CT, our deep learning model achieved higher prediction accuracy of post-ICH dependent living, disability, and severe disability by 6, 12, and 24 months (c-index 0.742 [95% CI -0.700 to 0.778], 0.712 [95% CI -0.674 to 0.752], 0.779 [95% CI -0.733 to 0.832] respectively) compared with the ICH score (c-index 0.673 [95% CI -0.662 to 0.688], 0.647 [95% CI -0.637 to 0.661] and 0.697 [95% CI -0.675 to 0.717]) and FUNC score (c-index 0.701 [95% CI- 0.698 to 0.723], 0.668 [95% CI -0.657 to 0.680] and 0.727 [95% CI -0.708 to 0.753]). In the external independent Yale-ICH cohort, similar performance metrics were obtained for disability and severe disability (c-index 0.725 [95% CI -0.673 to 0.781] and 0.747 [95% CI -0.676 to 0.807], respectively). Similar AUC of predicting each outcome at 6 months, 1 and 2 years after ICH was achieved compared with ICH score and FUNC score.

CONCLUSION

We developed a generalizable deep learning model to predict onset of dependent living and disability after ICH, which could help to guide treatment decisions, advise relatives in the acute setting, optimize rehabilitation strategies, and anticipate long-term care needs.

Prognostic analysis and risk assessment based on RNA editing in hepatocellular carcinoma

Hepatocellular carcinoma (HCC) is a leading cause of cancer-related mortality, and prognosis assessment is crucial for guiding treatment decisions. In this study, we aimed to develop a personalized prognostic model for HCC based on RNA editing. RNA editing is a post-transcriptional process that can affect gene expression and, in some cases, play a role in cancer development. By analyzing RNA editing sites in HCC, we sought to identify a set of sites associated with patient prognosis and use them to create a prognostic model. We gathered RNA editing data from the Synapse database, comprising 9990 RNA editing sites and 250 HCC samples. Additionally, we collected clinical data for 377 HCC patients from the Cancer Genome Atlas (TCGA) database. We employed a multi-step approach to identify prognosis-related RNA editing sites (PR-RNA-ESs). We assessed how patients in the high-risk and low-risk groups, as defined by the model, fared in terms of survival. A nomogram was developed to predict the precise survival prognosis of HCC patients and assessed the prognostic model's utility through a receiver operating characteristic (ROC) analysis and decision curve analysis (DCA). Our analysis identified 33 prognosis-related RNA editing sites (PR-RNA-ESs) associated with HCC patient prognosis. Using a combination of LASSO regression and cross-validation, we constructed a prognostic model based on 13 PR-RNA-ESs. Survival analysis demonstrated significant differences in the survival outcomes of patients in the high-risk and low-risk groups defined by this model. Additionally, the differential expression of the 13 PR-RNA-ESs played a role in shaping patient survival. Risk-prognostic investigations further distinguished patients based on their risk levels. The nomogram enabled precise survival prognosis prediction. Our study has successfully developed a highly personalized and accurate prognostic model for individuals with HCC, leveraging RNA editing data. This model has the potential to revolutionize clinical evaluation and medical management by providing individualized prognostic information. The identification of specific RNA editing sites associated with HCC prognosis and their incorporation into a predictive model holds promise for improving the precision of treatment strategies and ultimately enhancing patient outcomes in HCC.

Anemia and Optimal Transfusion Thresholds in Brain-Injured Patients: A Narrative Review of the Literature

Anemia is a highly prevalent condition that may compromise oxygen delivery to vital organs, especially among the critically ill. Although current evidence supports the adoption of a restrictive transfusion strategy and threshold among the nonbleeding critically ill patient, it remains unclear whether this practice should apply to the brain-injured patient, given the predisposition to cerebral ischemia in this patient population, in which even nonprofound anemia may exert a detrimental effect on clinical outcomes. The purpose of this review is to provide an overview of the pathophysiological changes related to impaired cerebral oxygenation in the brain-injured patient and to present the available evidence on the effect of anemia and varying transfusion thresholds on the clinical outcomes of patients with acute brain injury.

Serum cold-inducible RNA-binding protein (CIRP) levels as a prognostic indicator in patients with acute ischemic stroke

Background

Acute ischemic stroke (AIS) is the leading cause of morbidity and mortality among cerebrovascular diseases. While animal studies have suggested a correlation between cold-inducible RNA-binding protein (CIRP) serum levels and the severity and prognosis of cerebral infarction, there has been a lack of research exploring this association in humans with cerebral infarction.

Materials and methods

A total of 148 patients diagnosed with AIS within 7 days from symptom onset were included in this study. Comprehensive information regarding the patients' basic demographics, medical history, clinical parameters, the severity of cerebral infarction, and serum CIRP levels was collected. Follow-up data were obtained through telephonic interviews or by reviewing clinical notes for 3 months after the patients were discharged to assess the functional outcomes of treatment.

Results

The findings of this study demonstrated a significant increase in serum CIRP levels during the early stages of AIS, followed by a gradual decline after 3 days. Significant differences were observed in the serum CIRP levels between the 1-day group and the 4-7 day group (P < 0.0047), as well as between the 2-3 day group and the 4-7 day group (P < 0.0006). Moreover, a significant positive correlation was observed between the serum CIRP levels and the severity of cerebral infarction. Higher serum CIRP levels were associated with more severe National Institutes of Health Stroke Scale scores (P < 0.05) and larger cerebral infarction volumes (P < 0.05). Furthermore, patients with higher serum CIRP levels exhibited poorer modified Rankin scale scores (P < 0.05). These findings indicate that serum CIRP serves as an essential pro-inflammatory mediator and a valuable biomarker for assessing brain injury in patients with AIS.

Conclusion

The findings of this study suggest an elevation in serum CIRP levels among patients with AIS. These levels are positively correlated with the severity of AIS and serve as indicators of a poor prognosis. Therefore, CIRP could serve as a target for early clinical intervention while managing AIS, and further research should explore serum CIRP levels as prognostic indicators in AIS.