Characterization of signature trends across the spectrum of non-alcoholic fatty liver disease using deep learning method

A data-driven approach to decode metabolic dysfunction-associated steatotic liver disease

Metabolic dysfunction-associated steatotic liver disease (MASLD), defined by the presence of liver steatosis together with at least one out of five cardiometabolic factors, is the most common cause of chronic liver disease worldwide, affecting around one in three people. Yet the clinical presentation of MASLD and the risk of progression to cirrhosis and adverse clinical outcomes is highly variable. It, therefore, represents both a global public health threat and a precision medicine challenge. Artificial intelligence (AI) is being investigated in MASLD to develop reproducible, quantitative, and automated methods to enhance patient stratification and to discover new biomarkers and therapeutic targets in MASLD. This review details the different applications of AI and machine learning algorithms in MASLD, particularly in analyzing electronic health record, digital pathology, and imaging data. Additionally, it also describes how specific MASLD consortia are leveraging multimodal data sources to spark research breakthroughs in the field. Using a new national-level 'data commons' (SteatoSITE) as an exemplar, the opportunities, as well as the technical challenges of large-scale databases in MASLD research, are highlighted.

Object detection: A novel AI technology for the diagnosis of hepatocyte ballooning

Metabolic dysfunction-associated fatty liver disease (MAFLD) has reached epidemic proportions worldwide and is the most frequent cause of chronic liver disease in developed countries. Within the spectrum of liver disease in MAFLD, steatohepatitis is a progressive form of liver disease and hepatocyte ballooning (HB) is a cardinal pathological feature of steatohepatitis. The accurate and reproducible diagnosis of HB is therefore critical for the early detection and treatment of steatohepatitis. Currently, a diagnosis of HB relies on pathological examination by expert pathologists, which may be a time-consuming and subjective process. Hence, there has been interest in developing automated methods for diagnosing HB. This narrative review briefly discusses the development of artificial intelligence (AI) technology for diagnosing fatty liver disease pathology over the last 30 years and provides an overview of the current research status of AI algorithms for the identification of HB, including published articles on traditional machine learning algorithms and deep learning algorithms. This narrative review also provides a summary of object detection algorithms, including the principles, historical developments, and applications in the medical image analysis. The potential benefits of object detection algorithms for HB diagnosis (specifically those combined with a transformer architecture) are discussed, along with the future directions of object detection algorithms in HB diagnosis and the potential applications of generative AI on transformer architecture in this field. In conclusion, object detection algorithms have huge potential for the identification of HB and could make the diagnosis of MAFLD more accurate and efficient in the near future.

Hepatic SPARC Expression Is Associated with Inflammasome Activation during the Progression of Non-Alcoholic Fatty Liver Disease in Both Mice and Morbidly Obese Patients

The severity of non-alcoholic fatty liver disease (NAFLD) ranges from simple steatosis to steatohepatitis, and it is not yet clearly understood which patients will progress to liver fibrosis or cirrhosis. SPARC (Secreted Protein Acidic and Rich in Cysteine) has been involved in NAFLD pathogenesis in mice and humans. The aim of this study was to investigate the role of SPARC in inflammasome activation, and to evaluate the relationship between the hepatic expression of inflammasome genes and the biochemical and histological characteristics of NAFLD in obese patients. In vitro studies were conducted in a macrophage cell line and primary hepatocyte cultures to assess the effect of SPARC on inflammasome. A NAFLD model was established in SPARC knockout (SPARC-/-) and SPARC+/+ mice to explore inflammasome activation. A hepatic RNAseq database from NAFLD patients was analyzed to identify genes associated with SPARC expression. The results were validated in a prospective cohort of 59 morbidly obese patients with NAFLD undergoing bariatric surgery. Our results reveal that SPARC alone or in combination with saturated fatty acids promoted IL-1β expression in cell cultures. SPARC-/- mice had reduced hepatic inflammasome activation during the progression of NAFLD. NAFLD patients showed increased expression of SPARC, NLRP3, CASP1, and IL-1β. Gene ontology analysis revealed that genes positively correlated with SPARC are linked to inflammasome-related pathways during the progression of the disease, enabling the differentiation of patients between steatosis and steatohepatitis. In conclusion, SPARC may play a role in hepatic inflammasome activation in NAFLD.

Deep Learning Techniques with Genomic Data in Cancer Prognosis: A Comprehensive Review of the 2021-2023 Literature

Deep learning has brought about a significant transformation in machine learning, leading to an array of novel methodologies and consequently broadening its influence. The application of deep learning in various sectors, especially biomedical data analysis, has initiated a period filled with noteworthy scientific developments. This trend has majorly influenced cancer prognosis, where the interpretation of genomic data for survival analysis has become a central research focus. The capacity of deep learning to decode intricate patterns embedded within high-dimensional genomic data has provoked a paradigm shift in our understanding of cancer survival. Given the swift progression in this field, there is an urgent need for a comprehensive review that focuses on the most influential studies from 2021 to 2023. This review, through its careful selection and thorough exploration of dominant trends and methodologies, strives to fulfill this need. The paper aims to enhance our existing understanding of applications of deep learning in cancer survival analysis, while also highlighting promising directions for future research. This paper undertakes aims to enrich our existing grasp of the application of deep learning in cancer survival analysis, while concurrently shedding light on promising directions for future research in this vibrant and rapidly proliferating field.

Prognosis and personalized treatment prediction in lung adenocarcinoma: An in silico and in vitro strategy adopting cuproptosis related lncRNA towards precision oncology

Background: There is a rapid increase in lung adenocarcinomas (LUAD), and studies suggest associations between cuproptosis and the occurrence of various types of tumors. However, it remains unclear whether cuproptosis plays a role in LUAD prognosis. Methods: Dataset of the TCGA-LUAD was treated as training cohort, while validation cohort consisted of the merged datasets of the GSE29013, GSE30219, GSE31210, GSE37745, and GSE50081. Ten studied cuproptosis-related genes (CRG) were used to generated CRG clusters and CRG cluster-related differential expressed gene (CRG-DEG) clusters. The differently expressed lncRNA that with prognosis ability between the CRG-DEG clusters were put into a LASSO regression for cuproptosis-related lncRNA signature (CRLncSig). Kaplan-Meier estimator, Cox model, receiver operating characteristic (ROC), time-dependent AUC (tAUC), principal component analysis (PCA), and nomogram predictor were further deployed to confirm the model's accuracy. We examined the model's connections with other forms of regulated cell death, including apoptosis, necroptosis, pyroptosis, and ferroptosis. The immunotherapy ability of the signature was demonstrated by applying eight mainstream immunoinformatic algorithms, TMB, TIDE, and immune checkpoints. We evaluated the potential drugs for high risk CRLncSig LUADs. Real-time PCR in human LUAD tissues were performed to verify the CRLncSig expression pattern, and the signature's pan-cancer's ability was also assessed. Results: A nine-lncRNA signature, CRLncSig, was built and demonstrated owning prognostic power by applied to the validation cohort. Each of the signature genes was confirmed differentially expressed in the real world by real-time PCR. The CRLncSig correlated with 2,469/3,681 (67.07%) apoptosis-related genes, 13/20 (65.00%) necroptosis-related genes, 35/50 (70.00%) pyroptosis-related genes, and 238/380 (62.63%) ferroptosis-related genes. Immunotherapy analysis suggested that CRLncSig correlated with immune status, and checkpoints, KIR2DL3, IL10, IL2, CD40LG, SELP, BTLA, and CD28, were linked closely to our signature and were potentially suitable for LUAD immunotherapy targets. For those high-risk patients, we found three agents, gemcitabine, daunorubicin, and nobiletin. Finally, we found some of the CRLncSig lncRNAs potentially play a vital role in some types of cancer and need more attention in further studies. Conclusion: The results of this study suggest our cuproptosis-related CRLncSig can help to determine the outcome of LUAD and the effectiveness of immunotherapy, as well as help to better select targets and therapeutic agents.