In recent decades, the difficulty of new drug research and development has been partly due to too much emphasis on animal experimental research, and the lack of recording, analysing and critically assessing clinical symptoms and treatment outcomes after taking specific (herbal) medicines. It is the time to considering reverse pharmacology. Research in this area can be based on understanding the effectiveness and efficacy of clinical symptom phenotypes, i.e., on the changing symptom patterns during a treatment regimen. This can also be based on big data and can incorporate artificial intelligence. Ethnopharmacology offers unique opportunities in this context since ‘traditional’ and local treatments are often recorded. Traditional Medicine (TM) has a large amount of clinical data, which is a very important advantage, but it is not well used. Such limited attention to such approaches has also been due to the technical requirements for documenting such changes in symptoms esp. in regions with limited health care. Information acquisition technology, including image acquisition technology, is not convenient and cheap. Second, data mining technology is not perfect and advanced. This research topic aims at overcoming these hurdles and to offer strategies to use traditional clinical data.
This research topic aims to promote the solution to the following problems:
•Artificial intelligence applications with integration of the features of clinical symptom phenotypes in Ethnopharmacology research.
• Real-world clinical research to investigate the value of pharmacology with symptom phenotypes, as well as its action mechanisms and effective components.
• Clinical data mining to explore the value of the changes of TM states (e.g., yin and yang) if these can be linked to pharmacological concepts.
• Novel theories and the use of these theories and related methods to solve the problem of Ethnopharmacology.
• Methods for converting clinical qualitative data into quantitative or semi-quantitative data.
• Investigations of the correlations and relationships of human symptoms, signs, diseases, and physical and chemical indicators, and assessing the pharmacological mechanisms of the phenotype changes and variations using AI techniques.
• Assessments of potential values of imaging features for pharmacological effects and clinical effectiveness using AI-based image recognition or 3D short video understanding.
In this Research Topic, we welcome the following subtopics, but are not limited to the following:
• Artificial intelligence methods to detect symptom phenotypes based on image recognition or 3D short video.
• Frontiers and hotspots for symptomatic phenotype research, include the normal range and clinical significance of symptom phenotypes and the quantitative or semi-quantitative methods of symptom phenotypes.
• Multiple correlations or causal relationships between symptom phenotypes, physical or chemical indexes, and TM particular states (e.g., cold or heat) for the study of ethnopharmacology.
• The differentiation and the value ranges of symptom phenotypes between healthy people and patients, and in the context of different biomedical and environmental factors (e.g., gender, age, and season).
• The regularities of symptom phenotypes after taking drugs, as well as those reflected to the patterns of patient prognosis and outcome.
• Novel methods and applications of clinical effectiveness evaluation utilizing clinical symptom phenotypes.
• Big data & AI techniques for building the symptom phenotype-based diagnostic models of Traditional Medicine.
• Research on establishing evaluation standards of human normal and abnormal function situations based on big data and artificial intelligence in Traditional Medicine.
•Data mining and artificial intelligence analysis on the macro characteristics of Natural Products, including traits, colors, growing seasons, habits, etc., and develop their substitutes and new functions.
Note for the authors:
All manuscripts submitted must comply with our guidelines, Four Pillars of Best Practice in Ethnopharmacology (you can freely download the full version here). We will not accept manuscripts that are using purely in silico data in the context of pharmacological research. Frontiers in Pharmacology focuses on pharmacological research and, as such, experimental, data-driven approaches. More generally, the research must be driven by a clear research question or a testable hypothesis.
In addition, within this research topic in ethnopharmacology also covering artificial intelligence and symptom phenotype we want to encourage submissions on:
• The use of clinical big data in Ethnopharmacology including a focus on symptomatic phenotype changes.
• Novelty approaches and method related to Artificial Intelligence based on image recognition in Ethnopharmacology.
Manuscript types include Original Research and Review articles. Review articles can provide concise and critical updates on Ethnopharmacology research based on artificial intelligence and symptom phenotypes.
In recent decades, the difficulty of new drug research and development has been partly due to too much emphasis on animal experimental research, and the lack of recording, analysing and critically assessing clinical symptoms and treatment outcomes after taking specific (herbal) medicines. It is the time to considering reverse pharmacology. Research in this area can be based on understanding the effectiveness and efficacy of clinical symptom phenotypes, i.e., on the changing symptom patterns during a treatment regimen. This can also be based on big data and can incorporate artificial intelligence. Ethnopharmacology offers unique opportunities in this context since ‘traditional’ and local treatments are often recorded. Traditional Medicine (TM) has a large amount of clinical data, which is a very important advantage, but it is not well used. Such limited attention to such approaches has also been due to the technical requirements for documenting such changes in symptoms esp. in regions with limited health care. Information acquisition technology, including image acquisition technology, is not convenient and cheap. Second, data mining technology is not perfect and advanced. This research topic aims at overcoming these hurdles and to offer strategies to use traditional clinical data.
This research topic aims to promote the solution to the following problems:
•Artificial intelligence applications with integration of the features of clinical symptom phenotypes in Ethnopharmacology research.
• Real-world clinical research to investigate the value of pharmacology with symptom phenotypes, as well as its action mechanisms and effective components.
• Clinical data mining to explore the value of the changes of TM states (e.g., yin and yang) if these can be linked to pharmacological concepts.
• Novel theories and the use of these theories and related methods to solve the problem of Ethnopharmacology.
• Methods for converting clinical qualitative data into quantitative or semi-quantitative data.
• Investigations of the correlations and relationships of human symptoms, signs, diseases, and physical and chemical indicators, and assessing the pharmacological mechanisms of the phenotype changes and variations using AI techniques.
• Assessments of potential values of imaging features for pharmacological effects and clinical effectiveness using AI-based image recognition or 3D short video understanding.
In this Research Topic, we welcome the following subtopics, but are not limited to the following:
• Artificial intelligence methods to detect symptom phenotypes based on image recognition or 3D short video.
• Frontiers and hotspots for symptomatic phenotype research, include the normal range and clinical significance of symptom phenotypes and the quantitative or semi-quantitative methods of symptom phenotypes.
• Multiple correlations or causal relationships between symptom phenotypes, physical or chemical indexes, and TM particular states (e.g., cold or heat) for the study of ethnopharmacology.
• The differentiation and the value ranges of symptom phenotypes between healthy people and patients, and in the context of different biomedical and environmental factors (e.g., gender, age, and season).
• The regularities of symptom phenotypes after taking drugs, as well as those reflected to the patterns of patient prognosis and outcome.
• Novel methods and applications of clinical effectiveness evaluation utilizing clinical symptom phenotypes.
• Big data & AI techniques for building the symptom phenotype-based diagnostic models of Traditional Medicine.
• Research on establishing evaluation standards of human normal and abnormal function situations based on big data and artificial intelligence in Traditional Medicine.
•Data mining and artificial intelligence analysis on the macro characteristics of Natural Products, including traits, colors, growing seasons, habits, etc., and develop their substitutes and new functions.
Note for the authors:
All manuscripts submitted must comply with our guidelines, Four Pillars of Best Practice in Ethnopharmacology (you can freely download the full version here). We will not accept manuscripts that are using purely in silico data in the context of pharmacological research. Frontiers in Pharmacology focuses on pharmacological research and, as such, experimental, data-driven approaches. More generally, the research must be driven by a clear research question or a testable hypothesis.
In addition, within this research topic in ethnopharmacology also covering artificial intelligence and symptom phenotype we want to encourage submissions on:
• The use of clinical big data in Ethnopharmacology including a focus on symptomatic phenotype changes.
• Novelty approaches and method related to Artificial Intelligence based on image recognition in Ethnopharmacology.
Manuscript types include Original Research and Review articles. Review articles can provide concise and critical updates on Ethnopharmacology research based on artificial intelligence and symptom phenotypes.
