Bioinformatics and machine learning driven key genes screening for hepatocellular carcinoma

Shen, Ye; Huang, Juanjie; Jia, Lei; Zhang, Chi; Xu, Jianxing

doi:10.1016/j.bbrep.2023.101587

Cited by 2 publications

(1 citation statement)

References 81 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Advanced machine learning algorithms applied to diverse omics data show promise for elucidating mechanisms of metabolic dysfunction-associated fatty liver disease pathogenesis, enabling noninvasive disease prediction through the integration of clinical information and imaging features. 53 Sophisticated deep learning models may also aid in optimizing and personalizing treatment strategies and facilitating translational efforts to improve clinical outcomes of metabolic dysfunction-associated fatty liver disease. 54 However, model interpretability, prospective validation in diverse patient populations, and assessment of clinical utility remain critical priorities before the widespread adoption of artificial intelligence tools for guiding the management of this condition in clinical practice.…”

Section: Practice and Future Directionsmentioning

confidence: 99%

Transforming Screening, Risk Stratification, and Treatment Optimization in Chronic Liver Disease Through Data Science and translational Innovation

Addissouky

2024

InaJGHE

View full text Add to dashboard Cite

Background: Chronic liver diseases continue to face challenges in prognosis, treatment selection, disease mechanisms, screening, and therapeutic optimization. Promising innovations could address these gaps through data integration and novel analytic approaches.Main Body: MAPS-CRAFITY integrating clinical variables, AFP, and CT/MRI findings, and transformer modeling of RFA data improve HCC outcome prediction to guide management. Analyses revealing IL21R as a PBC susceptibility gene and implicating dysfunctional VWF processing in portal hypertension deliver mechanistic insights. Quantifying childhood MAFLD informs screening needs, while supporting use of G6PD deficient liver donors enables transplantation access expansion through risk stratification. Updating Baveno criteria enhances PBC prognosis, and an HCC prognostic score identifies optimal RFA candidates to maximize treatment efficacy.Conclusion: Recent research leverages diverse data types, genetics, imaging, and machine learning to develop integrated predictive systems that allow more personalized therapy selection. Elucidating molecular pathways provides therapeutic targets and prognostic biomarkers. Evidence-based screening and risk models facilitate delivering tailored interventions. Optimization of current modalities through prognostic validation and patient selection improves real-world effectiveness. Multifaceted modern research approaches promise to address unmet needs and transform hepatology care.

show abstract

Section: Practice and Future Directionsmentioning

confidence: 99%

Transforming Screening, Risk Stratification, and Treatment Optimization in Chronic Liver Disease Through Data Science and translational Innovation

Addissouky

2024

InaJGHE

View full text Add to dashboard Cite

show abstract

Harnessing exosomes as cancer biomarkers in clinical oncology

Ghosh,

Rajendran,

Mahajan

et al. 2024

Cancer Cell Int

View full text Add to dashboard Cite

Exosomes are extracellular vesicles well known for facilitating cell-to-cell communication by distributing essential macromolecules like proteins, DNA, mRNA, lipids, and miRNA. These vesicles are abundant in fluids distributed throughout the body, including urine, blood, saliva, and even bile. They are important diagnostic tools for breast, lung, gastrointestinal cancers, etc. However, their application as cancer biomarkers has not yet been implemented in most parts of the world. In this review, we discuss how OMICs profiling of exosomes can be practiced by substituting traditional imaging or biopsy methods for cancer detection. Previous methods like extensive imaging and biopsy used for screening were expensive, mostly invasive, and could not easily provide early detection for various types of cancer. Exosomal biomarkers can be utilized for routine screening by simply collecting body fluids from the individual. We anticipate that the use of exosomes will be brought to light by the success of clinical trials investigating their potential to enhance cancer detection and treatment in the upcoming years. Graphical Abstract

show abstract

Bioinformatics and machine learning driven key genes screening for hepatocellular carcinoma

Cited by 2 publications

References 81 publications

Transforming Screening, Risk Stratification, and Treatment Optimization in Chronic Liver Disease Through Data Science and translational Innovation

Transforming Screening, Risk Stratification, and Treatment Optimization in Chronic Liver Disease Through Data Science and translational Innovation

Harnessing exosomes as cancer biomarkers in clinical oncology

Contact Info

Product

Resources

About