Based on the concept of ＂precision medicine＂, this paper is to probe into the thinking innovation thought anddevelopment direction of ＂dialectical theory＂ of TCM, and to compare the development prospects of ＂synd...Based on the concept of ＂precision medicine＂, this paper is to probe into the thinking innovation thought anddevelopment direction of ＂dialectical theory＂ of TCM, and to compare the development prospects of ＂syndromedifferentiation＂ and ＂genetic constitution＂. It points out that the dialectical concept of ＂syndrome differentiation andtreatment＂ is combined with the concept of high and new technology of ＂precision medicine＂ to further clarify thescientific connotation of traditional Chinese medicine.展开更多
Medical genetics is defined as a branch of medicine that involves the diagnosis and management of hereditary disorders by applying genetics to medical care.The Human Genome Project,initiated in1990 and completed in 20...Medical genetics is defined as a branch of medicine that involves the diagnosis and management of hereditary disorders by applying genetics to medical care.The Human Genome Project,initiated in1990 and completed in 2004,has profoundly changed biology and is rapidly catalyzing a transformation of medical genetics and medicine in general（Collins and McKusick,2001;Green and Guyer,2011）.展开更多
Background Overutilization of medical imaging is a significant problem in healthcare,contributing to wasted resources and potentially causing harm to patients.Despite educational efforts and tools,appropriate imaging ...Background Overutilization of medical imaging is a significant problem in healthcare,contributing to wasted resources and potentially causing harm to patients.Despite educational efforts and tools,appropriate imaging adoption remains challenging.To address this,we aimed to train an AI model,termed the Appropriate Medical Imaging Recommendations Generative Pre-trained Transformer(AMIR-GPT),to provide precise recommenda-tions for medical imaging,thereby advancing value-based healthcare.Methods This prospective study used a dataset comprising 1036 paired questions and answers,collected from 26 guidelines in the American College of Radiology Appropriateness Criteria(ACR AC).The dataset,covering common clinical scenarios,was divided into a training set(932 entries)and a test set(104 entries).The OpenAI text-davinci model based on GPT-3 was fine-tuned in four iterations using the training set.The performance of AMIR-GPT was compared to GPT-4 and GPT-3.5 on the test set.Response similarity to standard answers was scored from 1 to 5 using a weighted Cohen’s kappa to measure inter-rater reliability between the model-generated responses and expert reviewers.Statistical significance was assessed using a chi-square test to compare categorical performance metrics across the models.Results AMIR-GPT achieved the highest perfect score rate(33.33%),outperforming GPT-4,Gemini,and GPT-3.5.In the high match category,GPT-3.5 led with 25%,while Gemini excelled in the medium match category at 37.5%.ANOVA confirmed significant differences among models(f=6.49,P=0.0004).Notable pairwise results included significant differences between AMIR-GPT and GPT-3.5(P=0.018)and between GPT-3.5 and Gemini(P=0.000),indicating varied model performance.Conclusion Fine-tuning GPT models for specific medical domains enhances their ability to provide accurate imaging recommendations.However,further validation is needed to confirm the broader applicability of these findings in various clinical settings.展开更多
Drug resistance is one of the key factors affecting the effectiveness of cancer treatment methods,including chemotherapy,radiotherapy,and immunotherapy.Its occurrence is related to factors such as mRNA expression and ...Drug resistance is one of the key factors affecting the effectiveness of cancer treatment methods,including chemotherapy,radiotherapy,and immunotherapy.Its occurrence is related to factors such as mRNA expression and methylation within cancer cells.If drug resistance in patients can be accurately identified early,doctors can devise more effective treatment plans,which is of great significance for improving patients'survival rates and quality of life.Cancer drug resistance prediction based on artificial intelligence(AI)technology has emerged as a current research hotspot,demonstrating promising application prospects in guiding clinical individualized and precise medication for cancer patients.This review aims to comprehensively summarize the research progress in utilizing AI algorithms to analyze multi-omics data including genomics,transcriptomics,epigenomics,proteomics,metabolomics,radiomics,and histopathology,for predicting cancer drug resistance.It provides a detailed exposition of the processes involved in data processing and model construction,examines the current challenges faced in this field and future development directions,with the aim of better advancing the progress of precision medicine.展开更多
文摘Based on the concept of ＂precision medicine＂, this paper is to probe into the thinking innovation thought anddevelopment direction of ＂dialectical theory＂ of TCM, and to compare the development prospects of ＂syndromedifferentiation＂ and ＂genetic constitution＂. It points out that the dialectical concept of ＂syndrome differentiation andtreatment＂ is combined with the concept of high and new technology of ＂precision medicine＂ to further clarify thescientific connotation of traditional Chinese medicine.
文摘Medical genetics is defined as a branch of medicine that involves the diagnosis and management of hereditary disorders by applying genetics to medical care.The Human Genome Project,initiated in1990 and completed in 2004,has profoundly changed biology and is rapidly catalyzing a transformation of medical genetics and medicine in general（Collins and McKusick,2001;Green and Guyer,2011）.
基金supported by the National Natural Science Foundation of China(62171297,61931013).
文摘Background Overutilization of medical imaging is a significant problem in healthcare,contributing to wasted resources and potentially causing harm to patients.Despite educational efforts and tools,appropriate imaging adoption remains challenging.To address this,we aimed to train an AI model,termed the Appropriate Medical Imaging Recommendations Generative Pre-trained Transformer(AMIR-GPT),to provide precise recommenda-tions for medical imaging,thereby advancing value-based healthcare.Methods This prospective study used a dataset comprising 1036 paired questions and answers,collected from 26 guidelines in the American College of Radiology Appropriateness Criteria(ACR AC).The dataset,covering common clinical scenarios,was divided into a training set(932 entries)and a test set(104 entries).The OpenAI text-davinci model based on GPT-3 was fine-tuned in four iterations using the training set.The performance of AMIR-GPT was compared to GPT-4 and GPT-3.5 on the test set.Response similarity to standard answers was scored from 1 to 5 using a weighted Cohen’s kappa to measure inter-rater reliability between the model-generated responses and expert reviewers.Statistical significance was assessed using a chi-square test to compare categorical performance metrics across the models.Results AMIR-GPT achieved the highest perfect score rate(33.33%),outperforming GPT-4,Gemini,and GPT-3.5.In the high match category,GPT-3.5 led with 25%,while Gemini excelled in the medium match category at 37.5%.ANOVA confirmed significant differences among models(f=6.49,P=0.0004).Notable pairwise results included significant differences between AMIR-GPT and GPT-3.5(P=0.018)and between GPT-3.5 and Gemini(P=0.000),indicating varied model performance.Conclusion Fine-tuning GPT models for specific medical domains enhances their ability to provide accurate imaging recommendations.However,further validation is needed to confirm the broader applicability of these findings in various clinical settings.
基金supported by the National Natural Science Foundation of China(No.82404186)the China Postdoctoral Science Foundation(No.2023M743947,China)+2 种基金the Postdoctoral Fellowship Program of CPSF(No.GZB20240869,China)the Hunan Provincial Natural Science Foundation of China(Nos.2024JJ6697 and 2025JJ40074)the Changsha Natural Science Foundation(No.kq2403026,China).
文摘Drug resistance is one of the key factors affecting the effectiveness of cancer treatment methods,including chemotherapy,radiotherapy,and immunotherapy.Its occurrence is related to factors such as mRNA expression and methylation within cancer cells.If drug resistance in patients can be accurately identified early,doctors can devise more effective treatment plans,which is of great significance for improving patients'survival rates and quality of life.Cancer drug resistance prediction based on artificial intelligence(AI)technology has emerged as a current research hotspot,demonstrating promising application prospects in guiding clinical individualized and precise medication for cancer patients.This review aims to comprehensively summarize the research progress in utilizing AI algorithms to analyze multi-omics data including genomics,transcriptomics,epigenomics,proteomics,metabolomics,radiomics,and histopathology,for predicting cancer drug resistance.It provides a detailed exposition of the processes involved in data processing and model construction,examines the current challenges faced in this field and future development directions,with the aim of better advancing the progress of precision medicine.
