制药行业中的人工智能与机器学习：重新定义预测格局

AI and ML in Pharma: Redefining theForecasting Landscape Today’s Presenters DANIEL CHANCELLOR DAVID JAMES STEFANO DRIUSSI VP Thought Leadership,Evaluate Founder,J+D Forecasting Head of Software Engineering,J+D Forecasting J+D Forecasting Evaluate,aNorstellaCompany 20+ years of experiencesupporting Pharmaceutical andBiotech companieswith theirforecasting needs. By combiningEvaluate'sworld-classconsensus forecasting and consultingexpertise with J+D Forecasting'sspecialisedmodels, delivered through cloud-basedmanagement and analytical solutions,clientscan achieve a comprehensiveunderstanding of the competitive landscape,seize important opportunities, and enhancethe decision-making process. ▪Expertsin all pharmaceutical forecastingmethodologies. Usinginnovativeapproachesto resolve forecastingchallenges. ▪Led by asenior levelteam of forecasting,market research, technical and data analysisprofessionals, withextensive experience. ▪Advanced technical capabilities, havingdeveloped over1,000 forecast modelsanddeployed our FC+ software and FC365forecasting platformin 70+ countries. General Overview Application of AI in Pharma Practical uses of AI in Forecasting AI Revolution–What to Expect Q&A AI in Pharma Forecasting–Challenges and Opportunities General Overview “A.I. could be ‘more profound’than both fire and electricity” Sundar Pichai,CEO Alphabet Different areas ofArtificial Intelligence. Tomorrow Today Artificial GeneralIntelligence(capable as humans in everytask) Artificial SuperIntelligence(better than humans inevery task) Artificial NarrowIntelligence(better than humans in ONEspecific task) AI in Pharma Forecasting–Challenges and Opportunities Application of AI in Pharma Application ofAI in Pharma •Globally valued at ~$905 million in 2021–($9,241 million by 2030) •50% of global healthcare companies plan to implement AI strategies (by 2025) •AI-driven new drug development expected to grow 40% annually–($4bn in 2024)AI-driven AI Applications in Pharma AI and ML in Pharma:Redefining the ForecastingLandscape AI withinDrug Discovery Artificial intelligence has many implications for research, drugdiscovery and development and trials: •Identifynew drug moleculesthat have so far eluded scientists •Synthetic data can bridge population data gaps•Increase the probability ofsuccess of NCE’s•Lower R&D costs& reduced time to market Already making drug discovery fasterand cheaper, with a number ofmultiple AI-designed drugs now beingtested in humans: (Estimatedpredictions)) Cost of drugdiscovery Time fordrugdiscovery https://itrexgroup.com/blog/why-use-ai-in-pharma-and-how-to-get-it-right/#:~:text=Artificial%20intelligence%20can%20reduce%20drug,billion%20annually%20on%20R%26D%20costshttps://asia.nikkei.com/Business/Pharmaceuticals/AI-slashes-time-and-cost-of-drug-discovery-and-development AI within Drug Discovery:Forecasting Implications Impact: Est. around 270 companies currentlyworking on AI-driven drug discovery. ▪The future competitive environment will change asmore drugs are discovered.▪An increase in partnership deals between industryand vendors.▪Reduction in time to market and associated costswill change financial thresholds for new drugs. Lack of in-house AI expertise drivingvendor partnerships: ▪GSK has partnered with CloudPharmaceuticals and InsilicoMedicine to utilize their AI platformsfor target identification, drugdesign, and lead generation. ▪Sanofi partnered withAtomwisetodiscover and synthesise drugcompounds for five different targets,paying $20 million upfront for theirinnovation and AI capabilities. AI and ML in Pharma: Redefining the ForecastingLandscape AI within Clinical Trials. Benefits of AI application: AI can help to make clinical trials moreefficient,more accurate, and more effective. Patient recruitment and screeningAI can help to reduce the time and cost of clinical trials, and it can also help to ensure that the right patients areenrolled in the right trials. Data collection and analysisAI can help to identify patterns and trends in the data, ▪Around 90% of clinical trials run significantlyover time or over budget.▪86% of clinical trials fail to recruit enoughpatients within their target time frame.▪Between 25% to 40% of trials will fail becausethey cannot meet their goals. plus identify patients who are most likely to benefit from aparticular treatment. Risk assessment AI can help to ensure the safety of patients, and it canalso help to identify patients who are at risk ofexperiencing adverse events. Predictive modellingAI can help develop predictive models to identify trials that are most likely to be successful, and those that aremost likely to fail. Decision supportAI can help investigators to make informed decisions Successprobability Key financemetrics Time tolaunch about the design, conduct, and interpretation of clinicaltrials. AI within Clinical Trials:Forecasting Implications. Impact: Potential to revolutionise the