{"title":"临床研究中的生成式人工智能:监管提交、临床数据管理及其他","authors":"Ihab Mansoor, Javier García Ortiz, Matthew Rector","doi":"10.55752/amwa.2024.304","DOIUrl":null,"url":null,"abstract":"Artificial intelligence and its subsets, such as generative artificial intelligence, have been making headlines due to their potential to accelerate the growth and expansion of various industries, including healthcare. However, the majority of application areas in healthcare revolve around diagnosing diseases, finding lead molecules for potential treatments, optimizing hospital operations, and other related aspects. This means that there are areas where the potential of these technologies is still to be realized. Examples of where such technologies could produce a significant impact across multiple elements are clinical research and its related domains, including regulatory submissions, clinical data management, clinical documentation, and other closely related areas. When artificial intelligence and its related technologies are utilized in these areas, they yield unparalleled outcomes regarding efficiency, consistency, and reproducibility. This, in turn, supports professionals involved in clinical research, like medical writers, statistical programmers, and other stakeholders, to drastically improve the speed by which they produce the initial drafts of various outputs, reduce the risk of errors that could lead to submission rejection, and optimize the overall clinical research workflow. Despite the potential of this area, the number of available solutions that support the aforementioned domains remains low. This is further complicated by the fact that there are even fewer numbers of working solutions.","PeriodicalId":503877,"journal":{"name":"AMWA Journal","volume":"2 2","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Generative AI in Clinical Research: Regulatory Submissions, Clinical Data Management, and Beyond\",\"authors\":\"Ihab Mansoor, Javier García Ortiz, Matthew Rector\",\"doi\":\"10.55752/amwa.2024.304\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Artificial intelligence and its subsets, such as generative artificial intelligence, have been making headlines due to their potential to accelerate the growth and expansion of various industries, including healthcare. However, the majority of application areas in healthcare revolve around diagnosing diseases, finding lead molecules for potential treatments, optimizing hospital operations, and other related aspects. This means that there are areas where the potential of these technologies is still to be realized. Examples of where such technologies could produce a significant impact across multiple elements are clinical research and its related domains, including regulatory submissions, clinical data management, clinical documentation, and other closely related areas. When artificial intelligence and its related technologies are utilized in these areas, they yield unparalleled outcomes regarding efficiency, consistency, and reproducibility. This, in turn, supports professionals involved in clinical research, like medical writers, statistical programmers, and other stakeholders, to drastically improve the speed by which they produce the initial drafts of various outputs, reduce the risk of errors that could lead to submission rejection, and optimize the overall clinical research workflow. Despite the potential of this area, the number of available solutions that support the aforementioned domains remains low. This is further complicated by the fact that there are even fewer numbers of working solutions.\",\"PeriodicalId\":503877,\"journal\":{\"name\":\"AMWA Journal\",\"volume\":\"2 2\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-03-14\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"AMWA Journal\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.55752/amwa.2024.304\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"AMWA Journal","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.55752/amwa.2024.304","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Generative AI in Clinical Research: Regulatory Submissions, Clinical Data Management, and Beyond
Artificial intelligence and its subsets, such as generative artificial intelligence, have been making headlines due to their potential to accelerate the growth and expansion of various industries, including healthcare. However, the majority of application areas in healthcare revolve around diagnosing diseases, finding lead molecules for potential treatments, optimizing hospital operations, and other related aspects. This means that there are areas where the potential of these technologies is still to be realized. Examples of where such technologies could produce a significant impact across multiple elements are clinical research and its related domains, including regulatory submissions, clinical data management, clinical documentation, and other closely related areas. When artificial intelligence and its related technologies are utilized in these areas, they yield unparalleled outcomes regarding efficiency, consistency, and reproducibility. This, in turn, supports professionals involved in clinical research, like medical writers, statistical programmers, and other stakeholders, to drastically improve the speed by which they produce the initial drafts of various outputs, reduce the risk of errors that could lead to submission rejection, and optimize the overall clinical research workflow. Despite the potential of this area, the number of available solutions that support the aforementioned domains remains low. This is further complicated by the fact that there are even fewer numbers of working solutions.