Artificial Intelligence-driven Real World Evidence: the value and practical use for drug safety management

Background: Real world data (RWD) and real-world evidence (RWE) are playing an increasing role in health care decisions. Regulatory bodies, such as the FDA, and Life Sciences companies use RWD and RWE to monitor postmarked safety and adverse events and to make regulatory decisions. The 21st Century Cures Act, passed in 2016, places additional focus on the use of these types of data to support regulatory decision making, including approval of new indications for approved drugs . It defines RWE as data regarding the usage, or the potential benefits or risks, of a drug derived from sources other than traditional clinical trials. By leveraging Artificial Intelligence (AI) and Cloud Computing technological advances for such complex task is the key to accelerate risk identification, safety signals confidence and operational value for all who manages drug safety.

About the presentation: This presentation will describe the post-marketing safety profiles and early detection capabilities of drug's safety concerns by using a holistic Real-World Data perspective, namely Patient's Voice, alongside spontaneous adverse event reporting system and clinical records (EHR) from Israel largest HMO. By utilizing machine learning, namely Natural Language Processing(NLP) for the free text analysis, we are able to tackle the difficult data (unstructured data) exists in many RWD assets. Patient Reported Experiences (PRE) were extracted from Social Platforms, FDA Adverse Event Reporting System (FAERS) data were acquired from publically available FDA site, and EHR data were extracted from Clalit Health Services which has a centralized clinical dataset. More than 250 medical ontologies are used to standardize all these different data formats into a harmonized database ready to be inquired in a Drug: Event relational patterns, over time, using Disproportionality analysis methods to identify potential safety signals in time series. Collectively, the findings presented suggest opportunities to use new RWD, explicitly Patient Online communities for resonating the Patient-Voice, to increase the total understanding of the patient-caregiver-physician perspectives, including increasing confidence in the traditionally collected safety reports and risk management processes. Data2Life has been able to gain new insight into understanding the outlooks of patients beyond the clinic by the adoption of consistent and wide-ranging data sources analysis. Each source and altogether representing the various stakeholders in healthcare. These comprehensive insights will allow us to capture faster, and in detail, the picture of a medical product's functioning beyond controlled randomized clinical trials.

Abstract Reference & Short Personal Biography of Presenting Author

Limor is the founding mother of Data2Life, a Patient-Centric- Digital Health company harnessing the power of artificial intelligence(AI) to tackle the BigData in healthcare and enable Real World Evidence. Evidence that is driven by the health consumers data. Ms. Epstein is a Public Health advocate with Emergency medicine background, who has been analyzing various Health datasets for over a decade; from electronic health records to Patient's generated data and other 'RealWorldData' assets. Ms. Epstein employs her overarching view and know-how to tackle the difficult data in healthcare and distill actionable insights to drive innovation, address unmet needs and make it more personalized then ever!


Organized & Produced by:

POB 4043, Ness Ziona 70400, Israel
Tel.: +972-8-931-3070, Fax: +972-8-931-3071