Search

Hepatocellular carcinoma (HCC) remains a global health challenge with high mortality rates, largely due to late diagnosis and suboptimal efficacy of current therapies. With the imperative need for more reliable, non-invasive diagnostic tools and novel therapeutic strategies, this study focuses on the discovery and application of novel genetic biomarkers for HCC using explainable artificial intelligence (XAI). Despite advances in HCC research, current biomarkers like Alpha-fetoprotein (AFP) exhibit limitations in sensitivity and specificity, necessitating a shift towards more precise and reliable markers. This paper presents an innovative multi-model XAI and a probabilistic causal inference framework to identify and validate key genetic biomarkers for HCC prognosis. Our methodology involved analyzing clinical and gene expression data to identify potential biomarkers with prognostic significance. The study utilized robust AI models validated against extensive gene expression datasets, demonstrating not only the predictive accuracy but also the clinical relevance of the identified biomarkers through explainable metrics. The findings highlight the importance of biomarkers such as TOP3B, SSBP3, and COX7A2L, which were consistently influential across multiple models, suggesting their role in improving the predictive accuracy for HCC prognosis beyond AFP. Notably, the study also emphasizes the relevance of these biomarkers to the Hispanic population, aligning with the larger goal of demographic-specific research. The application of XAI in biomarker discovery represents a significant advancement in HCC research, offering a more nuanced understanding of the disease and laying the groundwork for improved diagnostic and therapeutic strategies. [ABSTRACT FROM AUTHOR]

With the emergence of artificial intelligence, deep learning techniques have been widely deployed in forecasting stock markets. However, existing deep-learning-based models for news-based forecasts of stock trends are mostly black-box and difficult to explain. The procedure by which how final predictions are made within models keeps unknown, making it hard to interpret why one prediction should be better than the other. To provide explanations on predictions, this paper proposes to inject causal inference into model procedures and causally interpret predictions. We first generate a causal graph from financial news, and then integrate the information in the causal graph into a neural network model for stock trend prediction. Moreover, in order to better extract keywords from financial news we introduce a novel keyword extraction method named Distinguishable Word Filtering by Kolmogorov–Smirnov Test (DWF-KST). The experiment results on five financial datasets demonstrate that not only our proposed model explicitly provides an interpretation of prediction results, but also outperforms the state-of-art methods. the achieved results boost predictions of S&P 500 2-category from 89.7% to 97.4%, 3-category from 77.4% to 82.5%, and 5-category from 61.5% to 71.6%. For the other two indexes, the performances of Dow index improve from 86.2% to 90.2% and Nasdaq index improve from 76.4% to 78.9%. • We propose a method for stock trend prediction. • We use causal inference based on unstructured data. • Improve the interpretability of DL-based stock prediction models. • We propose DWF-KST for keyword selection in financial news. [ABSTRACT FROM AUTHOR]