Sign up for our newsletter and get the latest big data news and analysis.

Four Ways AI Can Positively Impact Pharmaceutical Development

In this special guest feature, Updesh Dosanjh, Practice Leader, Technology Solutions for IQVIA, discusses how AI is making its way into pharmacovigilance (the detection, collection, assessment, monitoring, and prevention of adverse effects with pharmaceutical products) platforms and improving efficiencies for pharma companies, in light of the continued growth and proliferation of available data. As Practice Leader for the Technology Solutions business unit of IQVIA, Updesh is responsible developing the overarching strategy regarding AI and Machine Learning as it relates to safety and pharmacovigilance. He has over 25 years of knowledge and experience in the management, development, implementation, and operation of processes and systems within the life sciences and other industries. Most recently, Dosanjh was with Foresight and joined IQVIA as a result of an acquisition. Dosanjh holds a Bachelor’s degree in Materials Science from Manchester University and a Master’s degree in Advanced Manufacturing Systems and Technology from Liverpool University.

Artificial intelligence (AI) has been a buzzword for several years now, but AI has arrived, and it is transformative. Almost every industry is challenged to find real-world use cases that effectively deploy AI’s enormous potential – including the pharmaceutical industry.

IDC estimates global spending on AI systems will reach nearly $100 billion worldwide by 2023. The healthcare industry, in particular, is expected to spend big on AI. According to ReportLinker, healthcare AI spending will jump from $2.1 billion to $36.1 billion by 2025.

Currently, a mere 15% of drugs successfully make it from clinical trials to FDA approval and most failures (73%) are due to safety and efficacy concerns. With the vast amount of healthcare data generated, curated and leveraged, there are many ways AI can be deployed to improve adverse effect detection in large data sets, thereby enabling more comprehensive patient safety efforts – both during the development process and post-approval.

Within pharmacovigilance – the detection, collection, assessment, monitoring, and prevention of adverse effects with pharmaceutical products – there are four key areas where AI can make a significant and immediate impact:

Getting Smart on Literature

A plethora of literature is available on medications and treatments, which can be overwhelming. A pharmacovigilance professional could dedicate hundreds of hours a month to reading articles and abstracts in search of adverse event signals and still not see them all. AI makes the search process much more manageable. It improves the speed of scanning content and provides better accuracy than humans in identifying key areas where a specific event, product, or condition is mentioned. Algorithms are far more likely to locate obscure references than humans, and they free up PV professionals to spend their time on more value-driven tasks.

Monitoring Social Media and Online Channels

People are sharing more and more on social media and online channels – this includes critical details on their health that can be incredibly helpful for drug safety. Employing people to monitor global social media platforms for mentions of adverse events, brand names, and relevant conditions is an almost impossible task. However, AI can easily monitor multiple social media platforms and online forums in any language 24 hours a day. These algorithms can be trained to identify any combination of terms or conditions and even search for obscure references in conversations. AI also provides value in its ability to link symptoms or events, the drugs being used, and a patient’s emotional state, something that is impossible with current tools. This capability can be helpful for more common treatments like medication for depression or new drugs with little or no formal history.

Audio Listening and Language Translation

AI can help screen the myriad of audio files from call centers, which can help identify adverse events that may be mentioned in unrelated contexts. For example, if a customer wants their money back because a product made them nauseous, a service representative may not know to report that as an adverse event, but an algorithm can flag it for a pharmacovigilence (PV) expert to review.

Similarly, AI can easily tackle language transcription from both audio and text files. One of the biggest challenges in PV is finding people with both the language skills and the clinical expertise to accurately translate complex source documents bi-directionally and cull relevant information to send a response.Today’s AI tools can automatically translate files and extract relevant safety details for case processing at high-speed and with a high degree of accuracy.

Medical Assessment and Case Follow-Up

AI can provide real-time feedback on whether a signal is relevant based on the context, causality, and frequency of similar reports. For example, if an algorithm finds that a user of a specific drug had a cardiac episode, it can scan all other cases in available datasets to look for similar events, and predict likely outcomes based on prior circumstances (e.g., hospitalization), even if the issue isn’t mentioned.

A majority of adverse event case files require some level of follow-up to capture missing data or to verify the information. This involves a series of mandated emails or phone calls, which are time-consuming and often get ignored. AI tools automate the follow-up process and can be trained to proactively request missing information at the time the report is made, based on the information provided, thereby reducing the need for follow-ups altogether.

Conclusion

Clinical trials are one of the most urgent and compelling use cases for data analysis fueled by AI. The use of advanced technologies to better manage and analyze growing data sets enables the pharmaceutical industry to set the standard for ethical AI deployment and, most importantly, the ability to improve patient safety and pharmacovigilance.

Sign up for the free insideBIGDATA newsletter.

Leave a Comment

*

Resource Links: