METHODS: In contrast, ViTs have demonstrated proficiency in capturing global signal patterns. In light of these observations, we propose a novel approach to enhance AD risk assessment. Our proposition involves a hybrid architecture, merging the strengths of CNNs and ViTs to compensate for their respective feature extraction limitations. Our proposed Dual-Branch Feature Fusion Network (DBN) leverages both CNN and ViT components to acquire texture features and global semantic information from EEG signals. These elements are pivotal in capturing dynamic electrical signal changes in the cerebral cortex. Additionally, we introduce Spatial Attention (SA) and Channel Attention (CA) blocks within the network architecture. These attention mechanisms bolster the model's capacity to discern abnormal EEG signal patterns from the amalgamated features. To make well-informed predictions, we employ a two-factor decision-making mechanism. Specifically, we conduct correlation analysis on predicted EEG signals from the same subject to establish consistency.
RESULTS: This is then combined with results from the Clinical Neuropsychological Scale (MMSE) assessment to comprehensively evaluate the subject's susceptibility to AD. Our experimental validation on the publicly available OpenNeuro database underscores the efficacy of our approach. Notably, our proposed method attains an impressive 80.23% classification accuracy in distinguishing between AD, Frontotemporal dementia (FTD), and Normal Control (NC) subjects.
DISCUSSION: This outcome outperforms prevailing state-of-the-art methodologies in EEG-based AD prediction. Furthermore, our methodology enables the visualization of salient regions within pathological images, providing invaluable insights for interpreting and analyzing AD predictions.
METHODS: A prospective-retrospective cohort of 985 patients was identified from the APASL-ACLF Research Consortium (AARC) database and the Chinese Study Group. Complications of ACLF (ascites, infection, hepatorenal syndrome, hepatic encephalopathy, upper gastrointestinal bleeding) as well as cirrhosis and the current main prognostic models were measured for their predictive ability for 28- or 90-day mortality.
RESULTS: A total of 709 patients with HBV-ACLF as defined by the AARC criteria were enrolled. Among these HBV-ACLF patients, the cirrhotic group showed significantly higher mortality and complications than the non-cirrhotic group. A total of 36.1% and 40.1% of patients met the European Association for the Study of Liver (EASL)-Chronic Liver Failure consortium (CLIF-C) criteria in the non-cirrhotic and cirrhotic groups, respectively; these patients had significantly higher rates of mortality and complications than those who did not satisfy the CLIF-C criteria. Furthermore, among patients who did not meet the CLIF-C criteria, the cirrhotic group exhibited higher mortality and complication rates than the non-cirrhotic group, without significant differences in organ failure. The Tongji prognostic predictor model score (TPPMs), which set the number of complications as one of the determinants, showed comparable or superior ability to the Chinese Group on the Study of Severe Hepatitis B-ACLF score (COSSH-ACLFs), APASL-ACLF Research Consortium score (AARC-ACLFs), CLIF-C organ failure score (CLIF-C OFs), CLIF-C-ACLF score (CLIF-C-ACLFs), Model for End-Stage Liver Disease score (MELDs) and MELD-sodium score (MELD-Nas) in HBV-ACLF patients, especially in cirrhotic HBV--ACLF patients. Patients with two (OR 4.70, 1.88) or three (OR 8.27, 2.65) complications had a significantly higher risk of 28- or 90-day mortality, respectively.
CONCLUSION: The presence of complications is a major risk factor for mortality in HBV-ACLF patients. TPPM possesses high predictive ability in HBV-ACLF patients, especially in cirrhotic HBV-ACLF patients.
METHODS: Prospectively collected data of ACLF patients from APASL-ACLF Research Consortium (AARC) was analyzed for 30-day outcomes. The models evaluated at days 0, 4, and 7 of presentation for 30-day mortality were: AARC (model and score), CLIF-C (ACLF score, and OF score), NACSELD-ACLF (model and binary), SOFA, APACHE-II, MELD, MELD-Lactate, and CTP. Evaluation parameters were discrimination (c-indices), calibration [accuracy, sensitivity, specificity, and positive/negative predictive values (PPV/NPV)], Akaike/Bayesian Information Criteria (AIC/BIC), Nagelkerke-R2, relative prediction errors, and odds ratios.
RESULTS: Thirty-day survival of the cohort (n = 2864) was 64.9% and was lowest for final-AARC-grade-III (32.8%) ACLF. Performance parameters of all models were best at day 7 than at day 4 or day 0 (p 12 had the lowest 30-day survival (5.7%).
CONCLUSIONS: APASL-ACLF is often a progressive disease, and models assessed up to day 7 of presentation reliably predict 30-day mortality. Day-7 AARC model is a statistically robust tool for classifying risk of death and accurately predicting 30-day outcomes with relatively lower prediction errors. Day-7 AARC score > 12 may be used as a futility criterion in APASL-ACLF patients.