There is an ever-increasing need to generate biomarkers that predict the development, progression and treatment of human diseases. Such predictive biomarkers can accelerate the diagnosis of diseases to allow for altering lifestyle interventions or earlier treatment through other means. Therapeutic development efforts benefit from biomarkers that can track the efficacy of treatments during clinical trials. Efforts to develop such biomarkers increasingly leverage various multi-omics technologies to gather extensive data on large populations of patients to allow for unbiased discovery of novel candidates. Effective analysis of such large data sets require advanced techniques to determine candidate biomarkers for further validation. Various artificial intelligence analytics approaches, including supervised and non-supervised machine learning, provide powerful discovery tools to reveal novel biomarkers from these large data sets. This provides new ways to address the unmet needs for biomarker discovery in various diseases.
There are recent and ongoing efforts to use artificial intelligence to detect potential biomarkers for a variety of human diseases. While advanced laboratory technologies allow for assembly of large data sets be generated from biofluid or biopsy samples from patients, the ability to mine such data for predictive biomarkers has lagged. Such efforts require new or optimized machine learning approaches, including supervised learning-based support vector machine algorithms, random forest algorithms and unsupervised learning methods like autoencoders, to examine large data sets to reveal potential biomarkers. Efforts to develop new machine learning approaches, integrate these with laboratory efforts and validation of biomarkers identified through these efforts represent a major direction for the field now and in the future.
This Research Topic calls for papers based on the following topics:
• Studies that propose new biomarkers for any human disease through the application of artificial intelligence or machine learning algorithms.
• New approaches for the analysis of large data sets for the discovery of predicted biomarkers.
• Studies that predict drug responses for a specific patient cohort based on machine learning analysis.
• Validation of markers for human diseases discovered using machine learning based discovery.
• This Research Topic is open to primary studies, validation studies and reviews of the current state of the art.
Keywords:
machine learning, algorithms, omics, validation, predictive biomarkers
Important Note:
All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.
There is an ever-increasing need to generate biomarkers that predict the development, progression and treatment of human diseases. Such predictive biomarkers can accelerate the diagnosis of diseases to allow for altering lifestyle interventions or earlier treatment through other means. Therapeutic development efforts benefit from biomarkers that can track the efficacy of treatments during clinical trials. Efforts to develop such biomarkers increasingly leverage various multi-omics technologies to gather extensive data on large populations of patients to allow for unbiased discovery of novel candidates. Effective analysis of such large data sets require advanced techniques to determine candidate biomarkers for further validation. Various artificial intelligence analytics approaches, including supervised and non-supervised machine learning, provide powerful discovery tools to reveal novel biomarkers from these large data sets. This provides new ways to address the unmet needs for biomarker discovery in various diseases.
There are recent and ongoing efforts to use artificial intelligence to detect potential biomarkers for a variety of human diseases. While advanced laboratory technologies allow for assembly of large data sets be generated from biofluid or biopsy samples from patients, the ability to mine such data for predictive biomarkers has lagged. Such efforts require new or optimized machine learning approaches, including supervised learning-based support vector machine algorithms, random forest algorithms and unsupervised learning methods like autoencoders, to examine large data sets to reveal potential biomarkers. Efforts to develop new machine learning approaches, integrate these with laboratory efforts and validation of biomarkers identified through these efforts represent a major direction for the field now and in the future.
This Research Topic calls for papers based on the following topics:
• Studies that propose new biomarkers for any human disease through the application of artificial intelligence or machine learning algorithms.
• New approaches for the analysis of large data sets for the discovery of predicted biomarkers.
• Studies that predict drug responses for a specific patient cohort based on machine learning analysis.
• Validation of markers for human diseases discovered using machine learning based discovery.
• This Research Topic is open to primary studies, validation studies and reviews of the current state of the art.
Keywords:
machine learning, algorithms, omics, validation, predictive biomarkers
Important Note:
All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.