AI-DRIVEN INNOVATIONS IN PHARMACOVIGILANCE: TRANSFORMING DRUG SAFETY SURVEILLANCE FOR THE FUTURE

AI-DRIVEN INNOVATIONS IN PHARMACOVIGILANCE: TRANSFORMING DRUG SAFETY SURVEILLANCE FOR THE FUTURE

S. P. Bhakat, A. Modak, K. Dakua, S. Debnath and S. Das *

Department of Pharmaceutical Technology, JIS University, Kolkata, West Bengal, India.

ABSTRACT: The practice of Pharmacovigilance focuses on identifying, evaluating and preventing drug-related adverse events, also referred to as ADRs, which ensure the safety of pharmaceuticals. Regarding these changes in healthcare systems, it is becoming very important to implement new technologies, such as artificial intelligence, in pharmacovigilance operations that promise to enhance drug safety monitoring. Such AI devices as Natural Language Processing (NLP), Machine Learning (ML), Deep Learning and Big Data Analysis are changing the landscape of Primary Adverse Drug Reactions (ADRs): detection, analysis, and reporting. These technologies allow for faster processing, attention and early response to signals, and other problems that have always been creating barriers such as late signal detection, and low levels of reporting. This paper highlights the impact of AI in the process of modernizing the steps of pharmacovigilance, including data analysis and making predictions about involved cases. Also, we elaborate on the ways AI strengthens regulatory reporting, stakeholder engagement, and risk minimization through superior signal detection. However, employing AI for pharmacovigilance also creates some ethical and legal issues such as the privacy of data, biases of the algorithms, and compliance with regulations. Addressing these aspects is essential to ensure AI-driven pharmacovigilance systems are reliable, fair, and aligned with ethical standards. This articlefocuses on how AI could make pharmacovigilance more proactive, Accurate, data-driven, and effective in safeguarding public health.

Keywords: Artificial Intelligence (AI), Pharmacovigilance, Healthcare Transformation, Adverse Drug Reactions

INTRODUCTION:

Overview of Pharmacovigilance: “The World Health Organization (WHO) defines pharmaco-vigilance as the science and activities related to

detecting, assessing, understanding, and preventing adverse effects or other problems related to medicines and vaccines” ¹.  It is essential to ensure the effectiveness and safety of Medications when they are approved, especially when it comes to identifying adverse drug reactions (ADRs) ².

The importance of pharmacovigilance lies in its can monitor drugs in every days of our life, where a wide range in populations of patients and longer period to use may cause safety issues not apparent when clinical trials are run.

Effective pharmacovigilance helps to protect patients also maintains public trusts and tell us about the safe use of medicines. Despite of its significance, pharmacovigilance has several challenges, as example under-reporting of ADRs, the increasing information volume, and taking time to detect safety signals, which can affect the timeliness and effectiveness of drug safety interventions ³.

Introduction to AI: Artificial intelligence is the simulation of human knowledge in machines, which enables to performs activities like learning thinking and problem-solving. In healthcare, AI has already demonstrated promise in the field of diagnosis, treatment planning, and personalized medicine, it has been offering a completely transform patient care ⁴.

AI can significantly increase pharmacovigilance by automating data processing, enhancing the accuracy of ADR detection, and speeding up the identification the signal safety ⁵. AI has the potential to assist overcome many of the limitations with traditional pharmacovigilance systems because of its real-time capacity to analyse large data sets from a range of sources ⁶.

The benefits of AI in pharmacovigilance are- including enhanced the efficiency of case processing, more correct causality assessments, better signal detection, and improved compliance with regulatory requirements. Pharmacovigilance may become more data-driven, proactive, and responsive to the rising difficulty of drug safety surveillance by using AI ⁷.

AI Technologies in Pharmacovigilance:

Natural Language Processing (NLP): NLP is known as a branch of AI that makes it possible for computers to produce, comprehend, as well as interpret human language. It is mainly useful for processing of unstructured text data, such as clinical notes, patient reports, and social media posts ⁸.

In pharmacovigilance, from unprocessed data sources such as spontaneous ADR reports, electronic health records (EHRs), and academic work, NLP can be employed to extract relevant data. By filtering immense quantities of text and detecting relevant keywords, phrases, and patterns, natural language processing (NLP) systems can identify and classify adverse medication reaction ⁹.

NLP helps with the efficient processing of huge amounts of data, significantly decreasing the time and making it easier to identify safety signals which is potential. It also assists in finding ADRs that might not be reported through conventional paths, enhancing the comprehensiveness of pharmacovigilance efforts ¹⁰.

Machine Learning (ML): "Machine learning" is a part of artificial intelligence that contains training algorithms on massive data sets, used to identify patterns, make predictions, and enhance performance as they keep learning over time. Machine learning algorithms are very adaptable because they can use what they learn from historical data and apply that knowledge to work with newly collected data ¹¹.

Applications in Pharmacovigilance:

Pattern Recognition: Algorithms using machine learning (ML) can identify patterns of adverse drug reaction (ADR) data that might highlight new safety concerns. These computer programs may spot minute connections in historical data that human analysts might overlook ¹².

Predictive Modeling: ADR likelihood can be estimated through machine learning (ML) by looking at things like patient demographics, medication features, and other factors. This helps in more proactive safety measures and preventing problems are made possible ¹³.

Signal Detection: ML models can be analysed the large datasets to identify patterns, or ADR signals or clusters that might point to a possible security issue. Based on their statistical significance and potential influence, these models can list signals in order of priority for further investigation ¹⁴.

Deep Learning: Deep Learning is an improved and advanced type of ML that uses neural networks with multiple layers (ex. "deep") to understand complex patterns in data.

It is particularly effective for tasks involving image recognition and natural language processing and others from large amounts of unstructured data ¹⁵.

Applications in ADR Prediction:

Advanced ADR Prediction: Deep learning models can be trained and learn from large, varied datasets to improve the accuracy of predictions about ADRs. To figure out the risk of adverse drug reactions, these models may analyze the connections between medications, patient characteristics, and environmental variables ¹⁶.

Improving Signal Detection: By spotting complex trends in the data that simpler algorithms might overlook, deep learning helps in enhance the recognition of signals. This capacity is particularly useful in finding rare or unexpected ADRs ¹⁷.

Handling Unstructured Data: Algorithms for deep learning can manage and examine unstructured data sources, like social media or free-text reports, to help us understand deeper knowledge of drug safety ¹⁸.

Big Data Analytics:

Understanding Big Data in Pharmacovigilance: Big Data is the term refers to extremely enormous databases that are difficult to manage with traditional data-processing methods because of their complexity. In pharmacovigilance, Big data is collected from a variety of sources, including social media, clinical trials, electronic health records, and spontaneous reporting systems ¹⁹.

Applications in Managing and Analyzing Data:

Data Integration: Big Data analytics makes the ability to bring together information from different sources, giving a comprehensive clear picture of medication safety. The identification of ADRs, which might only become apparent after joining data from various places, depends on this integration ²⁰.

Real-Time Analysis: Big Data technologies make it possible to evaluate incoming data in real-time, which speeds up the detection of potential safety concerns and allows for more prompt interventions ²¹.

Population-Level Insights: Big Data Analytics, through the examination of huge datasets, can offer insights into trends in ADRs across various populations, enabling the recognition of demographic or geographic factors that might affect the safety of medications ²².

Process of Case Procedures in Pharmacovigilance:

Case Intake and Initial Reporting: This step focuses on gathering, checking, and processing adverse drug reaction (ADR) data. For effective monitoring and analysis to be effective, it’s crucial that accurate data entry ²³.

Case Processing: Once the data is collected, it is categorized based on its type and severity. Causality assessments are conducted to evaluate the likelihood that the drug caused the adverse reaction. Methods like signal detection are used to identify patterns or clusters of ADRs ²⁴.

Case Evaluation: Medical professionals review the cases to assess the significance of the ADRs. Signal analysis helps determine whether the data points to a new safety concern or trend ²⁵.

Regulatory Reporting: This phase involves preparing and submitting required reports to regulatory bodies. This includes creating reports for serious adverse drug reactions (ADRs) and compiling Periodic Safety Update Reports (PSURs) to ensure compliance with relevant regulations ²⁶.

Follow-up and Data Enrichment: Follow-up actions are taken to gather additional details and further data on reported ADRs. Predictive models can help identify cases that may require further investigation, and automated systems can request more data from reporters ²⁷.

Closure: After following a thorough evaluation, cases are either closed or marked for continued observation. Final assessments are documented, and cases are archived for future reference and potential regulatory review ²⁸.

Management and Risk Minimization: Any signals detected during the evaluation process are assessed to determine their significance. Risk assessments are conducted to identify potential safety concerns, and necessary interventions are put in place ²⁹.

Case Reporting to Stakeholders: Key findings and updates are communicated to stakeholders, ensuring they are informed of any safety risks and mitigation measures. Feedback is integrated to maintain transparency and safety standards ³⁰.

FIG. 1: CASE PROCEDURES IN PHARMACOVIGILANCE

AI Technologies in Use: Various advanced tools are now being used in pharmacovigilance to improve safety monitoring and streamline data management. These include technologies that support better tracking, analysis, and reporting of drug-related information:

IBM Watson for Drug Discovery: Using AI to examine biomedical data and find out potential safety signals and drug interactions ³¹.

Aris Global's Life Sphere: An AI-powered system for automated case processing, signal identification, and regulatory reporting ³².

Oracle Argus Safety: Leverages AI for streamlining case management and enhanced signal detection ³³.

Med DRA's Vigi Lyze: Uses AI to discover data from WHO Global Individual Case Safety Reports (ICSRs) to detect the signal ³⁴.

Pharmalex's Vigi Flow: An AI-enabled platform for organizing and evaluating adverse event data ³⁵.

AstraZeneca’s R&D AI Tools: Used for data analysis and safety monitoring in drug development and post-market surveillance ³⁶.

These technologies demonstrate the advanced capabilities of AI in modern pharmacovigilance, highlighting how technology can enhance drug safety management and regulatory compliance.

AI in Enhancing Case Procedures: The integration of Artificial Intelligence (AI) in pharmacovigilance has greatly enhanced the efficiency and effectiveness of various case, making case management processes more streamlined. Here’s how AI plays a role in different stages of the workflow:

Automated Data Processing: AI-driven operation has revolutionized the way adverse drug reaction (ADR) data by automating data extraction, entry, and validation. By using natural language processing (NLP) algorithms, these systems can effectively scan, interpret and able to extract relevant information with accuracy from unstructured text from sources such as clinical notes, electronic health records, and spontaneous reports. Automated systems help minimize manual information entry errors and speedup the processing time, enabling quicker identification of potential safety concerns ³⁷.

Smart Classification and Causality Assessment: Machine Learning (ML) models have significantly enhanced the ability to classify of ADR situations and the assessment of causality. By analyze past data, these AI systems can categorize ADRs depending on the severity and type and while also estimating the likelihood that a drug was responsible for the reaction. This lead to enhance the accuracy and speed of causality assessments, which are critical for effective signal detection and risk evaluation ³⁸.

Advanced Signal Detection and Evaluation: Advance AI technologies, particularly ML and Deep Learning algorithms, are increasingly being applied to signal identity and evaluation. These models are capable of detecting complex patterns and trends in bigger datasets, facilitating quick detection of safety signals that might otherwise go unnoticed by traditional methods. By analyzing of vast amounts of data from various sources, AI enhances the ability to spot subtle or emerging safety concerns with greater precision ³⁹.

Automated Regulatory Reporting: AI technologies play a key role in simplifying regulatory reporting by making the process of creating and submitting reports to regulatory authorities. Automation reports like Periodic Safety Update Reports (PSURs), expedited reports, and other regulatory documentation are prepared accurately and submitted on schedule because of these technologies. This not only reduces the administrative workload but also helps to maintain compliance with regulatory standards ⁴⁰.

Predictive Analytics for Follow-ups: AI-driven predictive analytics can help identify which ADR cases are likely to need follow-up, offering valuable insights for proactive case management. Artificial intelligence (AI) models are capable of predicting when more data or work will be required by examining trends in data. This proactive approach improves the management of cases, ensuring that critical data is collected to fully address safety concerns. It ultimately leads to better decision-making in handling dynamic safety issues ³⁹.

Efficient Case Closure and Archiving: In the end, AI technologies make it easy to evaluate and put together ADR cases. Automated systems can help enable processes for case closure, and ensure appropriate reviews take place before cases are archived. This makes sure data management that is needed for regulatory audits and accessible in future ⁴¹.

AI in Signal Management: As for signal management, AI assists in validating and evaluating safety signals when data quality is very high to identify if there are any prevalent or relevant signs detected from sizable sets of data. Thus, there are benefits of AI models to differentiate real safety signals from noise which helps in the risk assessment and better planned the risk mitigation activities ⁴².

Stakeholder Communication: AI-driven systems make stakeholder communication more efficient by automating notifications and reporting. These systems guarantee near-instant dissemination of effective risks and updates to related parties, i.e. healthcare professionals or regulatory bodies etc. Accordingly, automated communication technologies have been found to enable rapid response and informed decision-making by efficiently exchanging data ⁴³.

FIG. 2: AI IN ENHANCING CASE PROCEDURES

Challenges and Ethical Considerations: Application of Artificial Intelligence (AI) to support pharmacovigilance introduces different issues, including its ethical aspects which must be addressed in order for AI use case scenarios to succeed and remain accountable. Concerns have included about data privacy and security, algorithmic bias but also regulatory and legal reasons.

Data Privacy and Security: Amongst the most important aspects to address in deploying AI towards pharmacovigilance lies data privacy. The data managed by pharmacovigilance systems are vast volumes of private health information for which data privacy and security must be rigorously maintained. All AI applications should comply with prevailing data protection law (e.g., such as the General Data Protection Regulation in Europe and Health Insurance Portability & Accountability Act in USA) ⁴⁴. AI systems must be well-encrypted, limited to a certain level of access and placed in an under-cover anonymity cloak covering all attachments saying otherwise. Moreover, data security practices need to be revised regularly because new challenges as well as threats and vulnerabilities emerge ⁴⁵.

Bias and Fairness in AI: The same issue with algorithmic bias also carries over when using AI in pharmacovigilance. These models are running on based historical information which may exhibit biases that would reflect the current state of inequalities in healthcare. If not handled properly, these biases can result in weighted data and give rise to biased outcomes two characteristics with the potential to obstruct conduit for drug safety sequences as well as ADR detection ⁴⁶. Safeguarding the principles of bias combat include equitable and inclusive data, fairness-aware algorithm encapsulation into behavior, as well as adversarial testing to AI outcomes. Researchers and practitioners must be vigilant in identifying and correcting bias to preserve the validity of pharmacovigilance processes ⁴⁷.

Regulatory and Legal Issues: Success in using AI for pharmacovigilance necessitates navigating complex legal and regulatory environments. Regulatory bodies like the U.S. Food and Drug Administration (FDA) in America or the European Medicines Agency have steering mechanisms established for drug safety but their transparency is put into question when AI gets mixed with them as well, bringing along additional oversight and regulatory challenges to combat trust issues ⁴⁸. Also the transparency about what are (other) AI-generated insights in the decision-making process. In addition, legal works must be adapted to the specific features of AI such as intellectual property rights or fault liability and responsibility with respect to developers and users. New guidance is required to guide the ethical use of AI in pharmacovigilance, and must complement existing regulation ⁴⁸.

Future Directions: Pharmacovigilance in the future of AI is moving to new advancements and opportunities. Moving forward, several key areas are anticipated to advance the next generation of drug safety surveillance as AI technology continues to develop.

Advancements in AI: Pharmacovigilance faces significant upgrades with future growth of AI technology. Therefore, new innovations such as more advanced deep learning approaches, machine learning algorithms and natural language processing techniques will lead to higher efficacy ADR detection with greater accuracy. AI systems are anticipated to integrate seamlessly with some medical technologies, like wearables electronic health records (EHRs) and wearable devices, providing a more complete view of patient safety. Improvements in AI, which includes explainable AI (XAI), will also make AI models easier to interpret, promoting awareness and confidence in insights produced by AI. Furthermore, faster reactions to newly developing safety signals will be possible with the development of real-time data processing capabilities ⁴³.

Collaborative Efforts: The confirmed integration of AI in pharmacovigilance will necessary robust cooperation between pharmaceutical companies, regulatory agencies, and AI developers while regulatory bodies provide advice on compliance and standards, pharmaceutical businesses can offer useful data and area experience. AI developers share technical skills and innovations. Working together is important for developing standardized protocols, assuring data sharing while maintaining privacy, and aligning AI solutions with regulatory requirements. Partnerships and collaborative projects will create the development of AI tools that are both effective and confirmed with industry standards, fostering creativity and improving drug safety ⁴⁹.

Personalized Medicine: As well, AI has possible large contributions to make in the development of personalized medicine itself, particularly by improving more individualized drug safety monitoring. When you gain access to this genetic, environmental and lifestyle information about someone an AI can evaluate it for saying the scientist how a patient should uniquely respond to a drug or catch potential adverse drug reactions (ADR). While individualized supervision offers extensive and accurate contact, leading to decreased adverse events with greater outcomes for overall patients. This selective risk evaluation of AI will provide future developments to make real-time monitoring systems and individualised drug safety profiles, leading output for health care provider self-reflecting adequately based on specific software estimation. AI in customised medicine will not only enhance the quality of care but also pharmacovigilance; ultimately it would lead to better and pre-emptive drug safety outcomes ⁵⁰.

CONCLUSION: The integration of AI into medical vigilance has dramatically changed the management of medical safety. AI technologies such as natural language processing, machine learning, deep learning, and big data analytics have improved and accurate detection of adverse drug reactions (ADRs) and safety signals These advances do not make it seem like cases that implementation has not only been simplified but also improved signal detection, risk assessment and regulatory reporting. Despite its potential, however, the application of AI to the drug scandal presents challenges related to data privacy, algorithmic bias, and compliance.

ACKNOWLEDGEMENT: The authors express their gratitude to Guru Nanak Institute of Pharmaceutical Science & Technology and JIS University, Nilgunj Road, Agarpara, Kolkata, for providing a workshop on pharmacovigilance.

CONFLICTS OF INTEREST: The authors declare that they have no conflict of interest.

REFERENCES:

1. Kazi SM, Bais SK and Kore M: Review On: Pharmacovigilance. Int J Pharm & Herb Technol 2023; 3: 81–88.
2. Al-Worafi YM: Technology for drug safety: Current status and future developments. (Springer 2023).
3. Hamid AAA, Rahim R & Teo SP: Pharmacovigilance and its importance for primary health care professionals. Korean J Fam Med 2022; 43: 290.
4. Harry A: The future of medicine: harnessing the power of AI for revolutionizing healthcare. Int J Multidiscip Sci Arts 2023; 2: 36–47.
5. Salas M: The use of artificial intelligence in pharmacovigilance: a systematic review of the literature. Pharmaceut Med 2022; 36: 295–306.
6. Lewis DJ & McCallum JF: Utilizing advanced technologies to augment pharmacovigilance systems: challenges and opportunities. Ther Innov & Regul Sci 2020; 54: 888–899.
7. Thakkar S: Artificial intelligence and real-world data for drug and food safety--A regulatory science perspective. Regul. Toxicol. Pharmacol 2023; 140: 105388.
8. Fanni SC, Febi M, Aghakhanyan G & Neri E: Natural language processing. In Introduction to Artificial Intelligence 2023; 87–99.
9. Joshi C, Attar VZ & Kalamkar SP: An unsupervised topic modeling approach for adverse drug reaction extraction and identification from natural language text. in Advances in Data and Information Sciences: Proceedings of ICDIS 2021; 505–514.
10. Choudhary H, Sharma A & Ahuja DD: Applications of Artificial Intelligence in Pharmaceutical Industries. Int J Pharm Sci Rev Res 2023; 81: 159–164.
11. Tyagi AK & Chahal P: Artificial intelligence and machine learning algorithms. in Challenges and applications for implementing machine learning in computer vision. IGI Global 2020; 188–219.
12. Yang S & Kar S: Application of artificial intelligence and machine learning in early detection of adverse drug reactions (ADRs) and drug-induced toxicity. Artif Intell Chem 2023; 100011.
13. Ayhan M, Dikmen I & Talat Birgonul M: Predicting the occurrence of construction disputes using machine learning techniques. J. Constr. Eng. Manag 2021; 147: 4021022.
14. Kim HR: Analyzing adverse drug reaction using statistical and machine learning methods: A systematic review. Medicine (Baltimore) 2022; 101: e29387.
15. Munsaka M, Liu M, Xing Y & Yang H: Leveraging machine learning, natural language processing, and deep learning in drug safety and pharmacovigilance. in Data Science, AI, and Machine Learning in Drug Development 193–229 (Chapman and Hall/CRC, 2022).
16. Lee CY & Chen YP: P. Prediction of drug adverse events using deep learning in pharmaceutical discovery. Brief Bioinform 2021; 22: 1884–1901.
17. Ibrahim H, Abdo A, El Kerdawy AM & Eldin AS: Signal detection in pharmacovigilance: a review of informatics-driven approaches for the discovery of drug-drug interaction signals in different data sources. Artif Intell life Sci 2021; 1:100005.
18. Wong J: Applying machine learning in distributed data networks for pharmacoepidemiologic and pharmacovigilance studies: opportunities, challenges, and considerations. Drug Saf 2022; 45: 493–510.
19. Kasukurthi SR: Big data analytics in pharmacovigilance-A global trend. Asian J Pharm Clin Res 2021; 14: 19–24.
20. Oyewusi WF: Artificial intelligence for pharmacovigilance in Nigerian social media text. in AI for Public Health Workshop at ICLR 2021; 21: 2021.
21. Lee CY & Chen YP: P. Machine learning on adverse drug reactions for pharmacovigilance. Drug Discov Today 2019; 24: 1332–1343.
22. Islam MS, Hasan MM, Wang X, Germack HD & Noor-E-Alam M: A systematic review on healthcare analytics: application and theoretical perspective of data mining. in Healthcare 2018; 6: 54.
23. Ghosh R: Automation opportunities in pharmacovigilance: an industry survey. Pharmaceut Med 2020; 34: 7–18.
24. Schmider J: Innovation in pharmacovigilance: use of artificial intelligence in adverse event case processing. Clin. Pharmacol. & Ther 2019; 105: 954–961.
25. Sartori D, Aronson JK, Norén GN & Onakpoya IJ: Signals of adverse drug reactions communicated by pharmacovigilance stakeholders: a scoping review of the global literature. Drug Saf 2023; 46: 109–120.
26. Prakash J, Sachdeva R, Shrivastava TP, Jayachandran CV & Sahu A: Adverse event reporting tools and regulatory measures in India through outcome of pharmacovigilance programme of India. Indian J Pharma 2021; 53: 143–52.
27. Moore N, Berda"i, D, Blin P & Droz C: Pharmacovigilance--The next chapter. Therapies 2019; 74: 557–567.
28. van Rijt-Weetink YRJ: Validation of a novel method to assess the clinical quality of information in pregnancy-related pharmacovigilance case reports: A ConcePTION Project. Drug Saf 2024; 47: 261–270.
29. Malikova MA: Practical applications of regulatory requirements for signal detection and communications in pharmacovigilance. Ther Adv Drug Saf 2020; 11: 2042098620909614.
30. Singh P, Vaishnav Y & Verma S: Development of pharmacovigilance system in India and paradigm of pharmacovigilance research: an overview. Curr Drug Saf 2023; 18: 448–464.
31. Chen Y, Argentinis JDE & Weber G: IBM Watson: how cognitive computing can be applied to big data challenges in life sciences research. Clin Ther 2016; 38: 688–701.
32. Bhati V, Nandave M, Kumar A & Pandita D: Databases Used in Pharmacovigilance across the Globe. in Pharmacovigilance Essentials: Advances, Challenges and Global Perspectives 2024; 55–77.
33. Divya P: Automation in pharmacovigilance: artificial intelligence and machine learning for patient safety. J Innov Appl Pharm Sci 2022; 118–122.
34. Murali K, Kaur S, Prakash A & Medhi B: Artificial intelligence in pharmacovigilance: Practical utility. Indian Journal of Pharmacology 2019; 51: 373–376.
35. Vogler M: Electronic reporting systems in pharmacovigilance: the implementation of VigiFlow in Brazil. Pharmaceut Med 2020; 34: 327–334.
36. Kassekert R: Industry Perspective on Artificial Intelligence / Machine Learning in Pharmacovigilance. Drug Saf 2022; 45: 439–448.
37. Voola PK, Mangal A, Singiri S, Chhapola A & Jain S: Enhancing test engineering through AI and automation: Case studies in the life sciences industry. Int J Res Mod Eng Emerg Technol 2024; 12.
38. Ball R & Dal Pan G: “Artificial intelligence” for pharmacovigilance: ready for prime time? Drug Saf 2022; 45: 429–438.
39. Wadhwa D, Kumar K, Batra S & Sharma S: Automation in signal management in pharmacovigilance an insight. Brief Bioinform 2021; 22: 363.
40. Salvo F: Will the future of pharmacovigilance be more automated? Expert Opin. Drug Saf 2023; 22: 541–548.
41. Aronson JK: Artificial intelligence in pharmacovigilance: an introduction to terms, concepts, applications, and limitations. Drug Saf 2022; 45: 407–418.
42. Kompa B: Artificial intelligence based on machine learning in pharmacovigilance: a scoping review. Drug Saf 2022; 45: 477–491.
43. Ahire YS, Patil JH, Chordiya HN, Deore RA & Bairagi VA: Advanced Applications of Artificial Intelligence in Pharmacovigilance: Current Trends and Future Perspectives. J Pharm Res 2024; 23: 24.
44. Oakley A: HIPAA, HIPPA, or HIPPO: What Really Is the Heath Insurance Portability and Accountability Act? Biotechnol. Law Rep 2023; 42: 306–318.
45. Bate A & Stegmann JU: Artificial intelligence and pharmacovigilance: What is happening, what could happen and what should happen? Heal. Policy Technol 2023; 12: 100743.
46. Wójcik MA: Foundation models in healthcare: Opportunities, biases and regulatory prospects in europe. in International Conference on Electronic Government and the Information Systems Perspective 2022; 32–46.
47. Kalita MJK, Bora MG, Mohan MHR & Das PJ: Innovations in Pharmacovigilance: Harnessing AI for Enhancing Drug Safety and Efficacy. Mod. Trends Multi-Disciplinary Res 2024.
48. Kalaiselvan V, Sharma A & Gupta SK: “Feasibility test and application of AI in healthcare” with special emphasis in clinical, pharmacovigilance, and regulatory practices. Health Technol Berl 2021; 11: 1–15.
49. Liang L: Artificial Intelligence ‑ Based Pharmacovigilance in the Setting of Limited Resources 2022; 511–519. doi: 10.1007/s40264-022-01170-7.
50. Silva L: Unveiling the future: precision pharmacovigilance in the era of personalized medicine. Int J Clin Pharm 2024; 1–6.
    

    ---

    How to cite this article:

    Bhakat SP, Modak A, Dakua K, Debnath S and Das S: AI-driven innovations in pharmacovigilance: transforming drug safety surveillance for the future. Int J Pharm Sci & Res 2025; 16(4): 912-19. doi: 10.13040/IJPSR.0975-8232.16(4).912-19.

    ---

    All © 2025 are reserved by International Journal of Pharmaceutical Sciences and Research. This Journal licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.