人工智能在制药行业：好处、风险和未来道路

AI in Pharma: Benefits, Risks, and the Road AheadSeptember 2024White PaperCITELINE SMARTSOLUTIONSCITELINE CLINICAL2September 2024 Copyright ©️ 2024 Pharma Intelligence UK Limited, a Citeline company (Unauthorized photocopying prohibited)AI in Pharma: Benefits, Risks, and the Road AheadUse of artificial intelligence (AI) now permeates every industry, and pharma is no exception. Whether machine learning (ML) models that make predictions based on existing data or generative AI (GenAI) models that create new data based on the data they were trained on, AI is being used to streamline and accelerate each step of the drug development process from research through approval and marketing.According to McKinsey & Co., generative AI alone could produce $60 billion to $110 billion a year in economic value across the pharma industry value chain. And $13 billion to $25 billion of that annual value alone would be for clinical development.1 AI is able to handle both structured and unstructured data, including multimodal data such as tabular, text, images, and videos. At its most basic level, AI can automate mundane tasks such as structured document and image analyses, enabling experts to spend more time on tasks that require their attention and proficiency.On a deeper level, AI can unveil insights from historical data to inform operations and provide a lens into the future through predictive analytics, supplementing traditional descriptive and diagnostic analytics that solely provide analytical information anchored on historical patterns. It can also enable and accelerate expertise through prescriptive analytics, advising experts on the next best action to take to maximize added value.2IntroductionFigure 1. Value-difficulty trade-off from traditional descriptive analytics to prescriptive analytics via human-AI collaboration for sustainable competitive edge Source: Jaspersoft3September 2024 Copyright ©️ 2024 Pharma Intelligence UK Limited, a Citeline company (Unauthorized photocopying prohibited)AI in Pharma: Benefits, Risks, and the Road AheadHow AI specifically benefits pharmaAI can accelerate drug discovery and development by supporting the analysis of vast and differing datasets, including comprehensive drug databases, biochemical data, clinical trial data, and electronic health records (EHR). AI analysis is much faster and cheaper than traditional methods at identifying potential drug candidates, reducing the time required for drug discovery and maximizing the quality of the novel compound.For example, AI-driven drug discovery platforms have significantly reduced time to identify drug candidates. What used to take four to five years can now take as little as eight months.3 AI can also empower drug repurposing. It can identify drug compounds already approved for other indications and help to predict their probability of success when repurposed to treat different diseases. There are AI-enabled systems that help prioritize the most promising candidates and