In everyday drug development processes linked to product safety and regulatory compliance, the vast data banks referred to by Generative AI tools are helping to overcome barriers to machine learning, by reducing the associated ‘training’ and system validation burden, through on-the-fly data discovery, ‘in context’ learning and narrative extrapolation. Ramesh Ramani, VP of Technology at ArisGlobal, and RaviKanth Valigari, VP of Product Development at ArisGlobal distil the potential.
When applying AI to labour-intensive Safety and Regulatory processes in life sciences R&D, the technology up to now has had to be extensively ‘trained’ in what to look for, and extensively validated – one application at a time. AI-based conclusions also need to be ‘explainable’ to regulators, for the sake of compliance, credibility and trust. All of these ‘overheads’ have restricted companies’ ability to fully exploit the technology.
That has changed now, thanks to the latest advances in Artificial Intelligence (AI) and Machine Learning (ML) which offer substantial process transformation potential without the same training, validation and explainability burden.
What’s changed?
Generative AI (GenAI) technology, using large language models (LLMs – the vast data banks referred to by GenAI tools), quickly understands what to look out for and can reliably summarise key findings for the user, without the need for painstaking ‘training’ by overstretched teams or validation of each configuration.
In conjunction with advanced natural language processing (NLP) techniques like retrieval-augmented generation (RAG), LLMs make advanced automation a safe, reliable and efficient reality in key life sciences R&D processes. RAG simplifies the process of fine-tuning AI models by allowing LLMs to integrate proprietary data with publicly-available information, giving them a bigger pool of knowledge – and context – to draw from.
Specialised applications can now be developed that apply GenAI-type techniques, contextually, to data they haven’t seen before – learning from and processing the contents on the fly. For drug developers, this has the potential to transform everything from dynamic data extraction associated with adverse event (AE) intake, to safety case narrative generation, narrative theme analysis in safety signal detection, and the drafting of safety reports.
Carefully combining LLM and RAG capabilities ensures transparency and explainability, meeting regulatory standards for safety and reliability. Responsible AI and compliance are critical in life sciences, so deploying proven, transparent solutions is essential. The LLM/RAG approach addresses potential concerns about data security and privacy, too, as it does not require the use of potentially-sensitive patient data for algorithm training/machine learning. It also stands up to validation, by way of periodic sampling by human team members; sampling which can be calibrated as confidence grows in the technology’s performance – ensuring that efforts to monitor its integrity do not undermine the significant efficiency gains that are possible.
Streamlined technology validation
Because LLMs make it possible to bypass the need to train AI models or algorithms, a single technology solution can handle all variations of incoming data, simplifying the system validation burden. RAG patterns can play an important role here, in explaining a standard operation procedure to an LLM using natural language, so that the system knows what to do with each of many thousands of forms – without the need for special configuration for each relative format.
The potential impact is impressive. Application of LLM-RAG technology to transform AE case intake has been shown to deliver upwards of 65% efficiency gains, with 90%+ data extraction accuracy and quality in early pilots. In safety case narrative generation, the same technology is already demonstrating 80-85% consistency in the summaries it creates. And that’s from a standing start, without prior exposure. Data retrieval – in context
The ability to retrieve data in context, rather than via a ‘Control F’ (find all) command (e.g. everything among a content set that mentions headaches), could transform a range of processes linked to safety/adverse event discovery and reporting.
Going forward, equivalent solutions will help streamline the drafting of hefty regulatory safety reports, with advanced automation generating the preliminary narrative; and perform narrative theme analysis in safety signal detection. The technology could have a significant impact in distilling trends not captured in the structured data (e.g. a history of drug abuse, or of people living with obesity, across 500 patient narratives that are potentially of interest). It is this broader potential that is now being discussed at meetings of life sciences’ new global GenAI Council. Previ objections to smarter automation linked to concerns about reliability or compliance, which are now being addressed directly, are subsiding in the face of a growing urgency to embrace next-generation forms of technology which directly address those concerns and visibly boost process efficiency. As life science technology companies continue to explore and implement these innovations, the industry stands to benefit significantly from these advancements.