Pharma Focus Asia

Automation in Pharmaceutical Sector by Implementation of Artificial Intelligence

Amol Shinde, Assistant Manager - Medical Affairs and Pharmacovigilance, Unichem Laboratories Ltd.

Globally, there are automation in several fields of the pharmaceuticals such as pharmacovigilance, clinical research, medical affairs, and marketing. Advanced technology like artificial intelligence (AI) emphasizes the massive use of the internet for drug development, drug safety, marketing, and customer engagement to achieve the goal of pharmaceuticals and healthcare.


Since 1950s, AI has been utilised in sectors like banking and financial industries. Over the past decade, it has significant innovations within many domains like pharmaceuticals, healthcare, insurance industries. In pharmaceuticals, current challenges like majority of drug requires more than 10-year time to come into market and even clinical trial cost is in billions, at the same time there are often chances it may not succeed in late-stage trials. In pharmacovigilance (PV) most of costrequired for case processing, therefore overall adverse events reporting may disturb. In healthcare of developing countries going which has high disease burden, poor infrastructure and insufficient in skilled HCPs, there are several challenges in PV. Hence, it is in such setting that AI has extensive role to enhance efficiency and the speed of drug development even produce advanced technology for developing and prolonging patient lives with safety.

Automation of jobs and AI have generated discussion across all industries that are either affected by or considering developing this technology to aid in their extensive functions. One of the mostly discussed questions is whether AI will replace humans in their roles. One school of thought believes the use of AI will not result in widespread unemployment and humans losing their jobs but will instead create jobs.

Use AI in pharmacovigilance:

The most crucial task in PV is detection and reporting of ADRs, coding of AE in technical terms, preparing individual case safety report (ICSR), assessment of seriousness, and relationship with suspected drug. It is all depend on the human interference, which is time consuming. Hence, the detection and analysis of ADRs requires a new technology. The pharmaceutical industry has overall PV budget consumes extra cost to contract out, case processing spending. There is opportunity to affect strongest PV cost driver by automation of AE case processing through AI. So, assistive technology such as AI to support the drug safety (DS) professional with the increasing volume and complexity of work. AI technology help to mitigate complex decision making for DS professionals. Implementation of AI, the DS professional’s work life may potentially change as their decision making is augmented and efficiency enhanced. Furthermore, DS professionals may need to learn new skills and competencies to understand and work with AI.

Electronic health records (EHRs), a more promising external data source which generally provide morecomplete and thorough representations of patient health that can include clinical narratives such as symptoms, disease status, severity, confounding factors.The databases, and tools are in primary stage of development, and it could proof its advancement in future in the field of PV.

Use AI in drug design and clinical research:

Implementation of AI technology is increasing role in drug development, drug designing, improving efficiency, and boosting the decision‑making process to make enrollment of patientsin clinical trials. Consequently, reducing the human workload as well as achieving targets in a short time. Implementation of AI in the drug development process can be predicted given that it can aid rational drug design, decision making assistance, establish the appropriate treatment for a patient, including personalized medicines, manage the clinical data and make use of it for future drug development. Hence, AI support to pharmaceutical industries helps to improve overall life cycle of product.

Clinical trials are emphasized to find the safety and efficacy of a drug in humans for a particulardisease and expect 6 to 7 years along with a massivecost involvement. Although only one out of ten drugs come into these trials, gain successful clearance, which is a massive loss in terms of time and money for the pharmaceuticals industry. These failures can result from inappropriate patient selection, scarcity of technical requirements, and poor infrastructure. However, with the massive digital medical data available, these disappointments can be decreased with the application of AI technology. The patient enrolment requires one-third of the clinical trial timeline. The accomplishment of a clinical trial can be ensured by the enrolment of appropriate patients, which otherwise leads to approx. 86 percent of failure cases.

AI use in medical affairs and marketing of pharmaceutical Industry

In medical affairs, scientific information exchange is the key and hence, medical affairs have always been at the frontline, leading external medical interactions with healthcare professionals (HCPs) as well as other key customers. With science becoming more and more complicated, HCPs are looking to pharmaceutical industry for high-level nonpromotional scientific information and engagement. HCPs need to have quick access to scientific information and the ability to easily recall it for the future. So, the medical affairs come up with the introduction of digital solutions to meet these needs and improve customer experience. The COVID-19 pandemic has put a focus on the vital role of scientific information play within a pharmaceutical industry at a time of crisis.

The success of a pharmaceutical industry is in the constant development and business growth. Even with access to huge funds, R&D output in the pharmaceutical industry is collapsing because of the failure of companies to implement new marketing technologies. The developments in digital technologies, it is referred to as ‘fourth industrial revolution’, is helping innovation in digital marketing via a multicriteria decision-making approach, which collects and analyses statistical and mathematical data and implements human inferences to make AI-based decision-making models discover new marketing methodology. Prediction of the market is important for various pharmaceutical distribution industries, which can implement AI application in the field, such as ‘business intelligent smart sales prediction analysis’, which uses a combination of time series forecasting and real-time application. It helps pharmaceutical organisation to forecast the sale of products in advance to prevent costs of excess stock or prevent customer loss because of shortages.

The advancement of AI technology, along with its remarkable tools, continuously decrease challenges faced by pharmaceutical industry, impacting the drug development process along with the overall product lifecycle. With the help of AI-based technologies will not only speed up the time needed for the products to come into the market but will also improve the product quality and safety of the production process, provide every aspect of pharmacovigilance in case processing, risk tracking, which reduces the total processing time and cost, and help to mitigate complex decision making for pharmacovigilance, thereby, increasing the importance of automation.

The most important fear regarding the incorporation of these technologies is the job losses that would follow, and the stringent regulations needed for the implementation of AI platform. AI technology will become a valuable tool in the pharmaceutical industry.


1.    Schmider J, Kumar K, LaForest C, Swankoski B, Naim K, Caubel P. Innovation in Pharmacovigilance: Use of Artificial Intelligence in Adverse Event Case Processing. Clin Pharmacol Therap. 2018;105(4):954- 61.
2.    Cabitza F, Rasoini R, Gensini G. Unintended Consequences of Machine Learning in Medicine. JAMA. 2017;318(6):517.
3.    Nayak V, Khan M, Shukla B, Chaturvedi P. Artificial intelligence in clinical research. Int J Clin Trials. 2016;3(4):187-93.
4.    Hoodbhoy Z, Hasan B, Siddiqui K. Does artificial intelligence have any role in healthcare in low resource settings? J Med Art Intel. 2019;2:13-13.
5.    Danysz K, Cicirello S, Mingle E, Assuncao B, Tetarenko N, Mockute R, et al. Artificial Intelligence and the Future of the Drug Safety Professional. Drug Safety. 2018;42(4):491-7.
6.    Mockute R, Desai S, Perera S, Assuncao B, Danysz K, Tetarenko N, et al. Artificial Intelligence Within Pharmacovigilance: A Means to Identify Cognitive Services and the Framework for Their Validation. Pharm Med. 2019;33(2):109-20.
7.    Frey C, Osborne M. The future of employment: How susceptible are jobs to computerization? 2021. Available at: Accessed on 24 January 2021.
8.    Marr B. Instead of Destroying Jobs Artificial Intelligence (AI) Is Creating New Jobs In 4 Out Of Companies. Forbes. 2021. Available at: 2/instead-of-destroying-jobs-artificial-intelligence-aiis-creating-new-jobs-in-4-out-of-5-companies/Accessed on 24 January 2021.
9.    Basile A, Yahi A, Tatonetti N. Artificial Intelligence for Drug Toxicity and Safety. Trends Pharmacol Sci. 2019;40(9):624-35.
10.    Yang C, Yang H, Jiang L. Post marketing Drug Safety Surveillance Using Publicly Available Health- Consumer-Contributed Content in Social Media.2014;5(1):1-21.
11.    Wang X, Hripcsak G, Markatou M, Friedman C. Active Computerized Pharmacovigilance Using Natural Language Processing, Statistics, and Electronic Health Records: A Feasibility Study. J Am Med Informat Assoc. 2009;16(3):328-37.
12.    Mak KK, Pichika MR. Artificial intelligence in drug development: Present status and future prospects. Drug Discov Today. 2019;24:773-80.
13.    Duch W, Swaminathan K, Meller J. Artificial intelligence approaches for rational drug design and discovery. Curr Pharm Des. 2007;13(14):1497-508.
14.    Blasiak A, Khong J, Kee T. CURATE.AI: Optimizing Personalized Medicine with Artificial Intelligence. SLAS Technol. 2020;25(2):95-105.
15.    Harrer S. Artificial intelligence for clinical trial design. Trends Pharmacol Sci. 2019;40:577-91.
16.    Hay M. Clinical development success rates for investigational drugs. Nature Biotechnol. 2014;32:40-51.
17.    Fogel DB. Factors associated with clinical trials that fail and opportunities for improving the likelihood of success: a review. Contemp Clin Trials Communic.2018;11:156-64.
18.    [Internet]. 2021 [cited 25 January 2021]. Available from:
19. 2020. Accessed May 20, 2020.
20.    Duncan E, Fanderl H, Maechler N, Neher K. Creating value through transforming customer journeys. Winter 2016. July 1, 2016. Accessed May 20, 2020.
21.    Toker, D. et al. (2013) A decision model for pharmaceutical marketing and a case study in Turkey. EkonomskaIstraĹľivanja 26, 101–114
22.    Singh, J. et al. (2019) Sales profession and professionals in the age of digitization and artificial intelligence technologies: concepts, priorities, and questions. Journal Personal Selling Sales Management 39, 2–22
23.    Mahajan, K.N. and Kumar, A. (2017) Business intelligent smart sales prediction analysis for pharmaceutical distribution and proposed generic model. International Journal of Computer Science and Information Technologies 8, 407–412

Amol Shinde

Amol Shinde is Assistant Manager in Department of Medical Affairs and Pharmacovigilance at Unichem Laboratories Ltd., India with approx. 7 years of working experience in various corporate of pharma industries. He has published 4 papers in international and national journals.

magazine-slider-imageHexagon - Expert Insights WebinarMFA + MMA 20244th Annual Cleaning Validation 20242nd Annual Pharma Impurity Conclave 2024CPHI Korea 2024CHEMICAL INDONESIA 2024World Orphan Drug Congress Europe 2024INALAB 2024Thermo Fisher - Drug Discovery and the impact of mAbsAdvanced Therapies USA 2024ISPE Singapore Affiliate Conference & Exhibition 20242024 PDA Aseptic Manufacturing Excellence Conference2024 PDA Aseptic Processing of Biopharmaceuticals Conference