Artificial Intelligence in Pharmacovigilance

The integration of Artificial Intelligence (AI) into pharmacovigilance has emerged as a transformative force, revolutionizing the monitoring and assessment of drug safety. This article provides a comprehensive overview of the application of AI in pharmacovigilance, elucidating its impact on the identification, evaluation, and management of adverse drug reactions (ADRs). AI-driven algorithms, machine learning, and natural language processing empower automated signal detection, enabling more efficient and proactive risk assessment. The review explores the utilization of AI in mining diverse data sources, including electronic health records, social media, and scientific literature, to enhance the sensitivity and specificity of ADR detection. Additionally, the article delves into the role of AI in streamlining case processing, automating data validation, and facilitating trend analysis, thereby optimizing the pharmacovigilance workflow. Challenges, such as data quality and interpretability of AI-generated insights, are critically examined, alongside ongoing efforts to address these concerns. The regulatory landscape and the incorporation of AI technologies into pharmacovigilance guidelines are discussed, highlighting the evolving framework for ensuring patient safety. As AI continues to evolve, its synergy with traditional pharmacovigilance practices opens new avenues for enhanced surveillance and proactive risk management in the dynamic field of drug safety.

1. Welcome ARTIFICIAL INTELLIGENCE IN PHARMACOVIGILANCE. Emani.Sai Sri Jayanthi Pharm.D 203/102023 10/18/2022 www.clinosol.com | follow us on social media @clinosolresearch 1

2. Index Introduction to artificial intelligence and pharmacovigilance . Artificial intelligence application in pharmacovigilance . How AI enhances PV? Pharmacovigilance Automation tools. Benefits of automation in pv . Integration of AI and PV. Challenges. Future of AI in PV. Conclusion. References. 10/18/2022 www.clinosol.com | follow us on social media @clinosolresearch 2

3. ARTIFICIAL INTELLIGENCE: Artificial intelligence (AI) is a field of study in computer science that develops and studies intelligent machines. AI is the intelligence of machines or software, as opposed to the intelligence of humans or animals. PHARMACOVIGILANCE: The word “ Pharmacovigilance ” was derived from the Greek literature “ pharmakon ” (means drug) and the word “ vigilare ” (means keep watch) in Latin. According to WHO it is defined as the science and activities relating to the detection,assessment,understanding , and prevention of adverse events or any other medicine-related problems. 10/18/2022 www.clinosol.com | follow us on social media @clinosolresearch 3

4. Artificial intelligence's application in pharmacovigilance : AI has the potential to revolutionize pharmacovigilance , making drug safety processes more efficient and accurate. The effectiveness of artificial intelligence (AI) can enable to reduce case processing costs to improve PV activities. AI has specific features, such as machine learning (ML) and natural learning processing (NLP). ML techniques analyze the structured data such as imaging and genetic data. Unstructured and free-text form is detected by NLP which is being able to understand and interpret human language. AI can employ sophisticated algorithm to extract valuable information from the massive volume of healthcare data, improving the accuracy of the data. 10/18/2022 www.clinosol.com | follow us on social media @clinosolresearch 4

5. HOW AI ENHANCES PV? There are several factors other than just an advere event which define the extent of harm caused by a pharmaceutical drug in the market-wide circulation like adr , risk factor, serious reaction and signal. These factors are etremely important and are the sensitive sources of data and require intense scrutinity as human lives are at stake.Here is exactly where the AI can help. AI models can assist in identifying new potential signals (indications of possible causal relationships between a drug and an adverse event) from large databases. These models can identify patterns that might be missed by traditional statistical methods. AI can also play a major role in data mining, ae reporting, predictive analysis, automated case processing, clinical trial monitoring and risk management. 10/18/2022 www.clinosol.com | follow us on social media @clinosolresearch 5

6. Data Mining : With the ever-growing volume of biomedical literature and clinical trial data, AI can assist in mining these data sources for new information related to drug safety. Adverse Event Reporting : Traditional methods of adverse event (AE) reporting are manual and can be time-consuming. Natural Language Processing (NLP), a subset of AI, can be utilized to automate the extraction of relevant AE information from textual data such as patient records, literature, or social media. Predictive Analysis : Machine learning models can be d to predict potential AEs for new drugs based on their structures and known information about similar compounds. Automated Case Processing : Once an AE is reported, it needs to be processed. AI can help in automating many of these steps, such as duplicate detection, data entry, and initial severity classification. Clinical Trial Monitoring : AI tools can be applied to monitor clinical trial data in real-time, enabling quicker detection of potential safety issues. Risk Management : AI can assist in developing better risk management plans by analyzing data from various sources and predicting potential risk factors and mitigation strategies. 10/18/2022 www.clinosol.com | follow us on social media @clinosolresearch 6

7. Individual case safety Reports: ICSR is a document that contains information about a single AE or a SAR to medicinal product.ICSR’S are used by the FDA to capture information needed to support reporting of: >ADVERSE EVENTS >PRODUCT PROLEMS >CONSUMER COMPLAINTS associated with the use of FDA regulated products. There are two categories in AI in ICSR processing: 1.Insertion of structured and unstructured content. 2.AI for decision-making. 10/18/2022 www.clinosol.com | follow us on social media @clinosolresearch 7

8. Sentiment analysis and social media monitoring: Social media platforms and online forums have become places where individuals often share their healthcare experiences, including adverse drug reactions (ADRs). AI-powered sentiment analysis can sift through these vast amounts of unstructured text data to identify and categorize mentions of drug-related experiences. It can determine whether the sentiment expressed is positive, negative, or neutral and understand the context in which the drug is discussed. 10/18/2022 www.clinosol.com | follow us on social media @clinosolresearch 8

9. GENOMIC DATA INTEGRATION: Integrating genomic data with pharmacovigilance efforts allows for a more personalized approach to drug safety. AI can analyze a patient's genetic profile to identify genetic markers associated with drug metabolism and adverse reactions. By considering genetic variations, healthcare providers can make more informed decisions about which medications are most suitable for individual patients, reducing the risk of adverse events. 10/18/2022 www.clinosol.com | follow us on social media @clinosolresearch 9

10. PHARMACOVIGILANCE AUTOMATION TOOLS The pharmacovigilance automation tools are powered by AI which have the potential to revolutionarize the way adr’s are identified, reported and managed. Examples of such tools are FDA’s Sentinel system and VigiLanz,IBM Watson,Trifacta . A recent survey conducted by TransCelerate Biopharma revealed the improvement in efficiency and beneficial developments from integration of AI automation tools and pharmacovigilance as follows AI Technologies in PV which are very helpful in extraction of accurate information.Examples of such technologies are VigiBase,VigiAccess,VigiLyze,VigiGrade,VigiMatch,VigiRank . 10/18/2022 www.clinosol.com | follow us on social media @clinosolresearch 10

11. BENEFITS OF AUTOMATION IN PV 10/18/2022 www.clinosol.com | follow us on social media @clinosolresearch 11

12. INTEGRATION OF AI AND PV The integration of AI into pharmacovigilance (PV) offers a wide range of benefits, aiming to improve drug safety, streamline processes, and ensure more comprehensive monitoring. Here are some of the benefits: 1.Increased efficiency 2. Scalability 3.Reduced human error 4.Enhanced signal detection 5.Data integration 6.Real-time analysis 10/18/2022 www.clinosol.com | follow us on social media @clinosolresearch 12

13. 7.Natural language processing (NLP) 8.Cost savings 9. Predictive analytics 10.Global harmonization, 11.Continuous learning, and improved decision-making. Automation can handle repetitive tasks, speed up adverse event reporting and analysis, reduce human error, and improve data accuracy. AI can also predict potential adverse events based on historical data, making global safety surveillance more seamless. 10/18/2022 www.clinosol.com | follow us on social media @clinosolresearch 13

14. CHALLENGES AI's application in pharmacovigilance presents several challenges, including data quality, interpretation, regulatory concerns, over-reliance on automation, bias in AI models, data privacy and security, integration with existing systems, training and expertise, cost implications, model validation and verification, global consistency, continuous monitoring, and ethical considerations. Data quality and integrity are crucial for accurate predictions, while interpretation of AI outputs can be complex. Pharmacovigilance is a heavily regulated field, and obtaining approval for AI-driven approaches can be challenging. Over-reliance on automation, bias in AI models, and data privacy and security are also significant issues. Integrating AI into existing systems and bridging the skills gap are also essential. A collaborative approach between AI experts, pharmacovigilance professionals, regulators, and other stakeholders is crucial for the safe and effective use of AI in pharmacovigilance . 10/18/2022 www.clinosol.com | follow us on social media @clinosolresearch 14

15. FUTURE OF AI IN PV AI can enhance the current adverse event reporting which relies on hcp’s,patients and pharmaceutical company which has certain limitations like underreporting,incomplete information, delayed reporting and duplicate reports. The future of pv is an AI-enabled adverse event reporting system which would have potential to: >IMPROVE PATIENT SAFETY . > REDUCE THE RISK OF ADR’S. >SPEED UP DRUG DEVELOPMENT PROCESS. 10/18/2022 www.clinosol.com | follow us on social media @clinosolresearch 15

16. CONCLUSION Pharmacovigilance plays a vital role in protecting public health by ensuring medicines are safe and effective. AI techniques will be useful in identifying and initiate a hidden relationship for accurate ICSR processing in PV. Nowadays, awareness about AI in PV is infancy. This awareness can be influenced by the collaboration of IT firms and pharmaceutical companies, through which latter and medical device companies could improve regulatory compliance, achieve cost reduction, etc. The overall process from case receipt to reporting can be automated with the help of AI process. These processes will not only reduce the cost, but also it will improve the quality and accuracy. Increasing awareness about websites accessible to public like “ VigiAccess ” for data of ADRs. For PvPI , the burden of the overall process from case receipt to reporting can be reduced by automated input with the help of AI techniques. These processes will not only reduce the cost, also it will improve the quality and accuracy. The automated data are harmonized world widely and UMC Sweden is capable to monitor the collected data by different PV centers. The future strategies of drug safety could become more advanced, driven by AI techniques. More researches are needed in the field of AI with respect to PV. AI, databases, and tools are in primary stage of development, and it could poof its advancement in future in the field of PV. 10/18/2022 www.clinosol.com | follow us on social media @clinosolresearch 16

17. https://www.who.int   Celgene . Chrysalis Fact Sheet.  https://www.celgene.com/newsroom/media-library/chrysalis-fact-sheet/ .   Meyboom RH, Egberts AC, Gribnau FW, Hekster YA. Pharmacovigilance in perspective.  Drug Saf .  1999;21:429–47. [ PubMed ] [ Google Scholar ] Pranali Wani , Arti Shelke , ROLE OF AI IN PHARMACOVIGILACEhttps://doi.org/10.47750/pnr.2022.13.S07.747 . 10/18/2022 www.clinosol.com | follow us on social media @clinosolresearch 17 REFERENCES

18. Thank You! www.clinosol.com (India | Canada) 9121151622/623/624 [email protected] 10/18/2022 www.clinosol.com | follow us on social media @clinosolresearch 18