Human-AI Collaboration Increases Efficiency in Regulatory Writing

2025-09-10

AI Summary

Drafting nonclinical summaries for Investigational New Drug (IND) applications is time-intensive and heavily reliant on expert knowledge, impeding early-stage drug development efficiency. Method: We propose AutoIND—a human-in-the-loop platform leveraging large language models (LLMs) to automatically generate draft summaries, coupled with a blinded, multidimensional quality assessment framework evaluating seven criteria: correctness, completeness, consistency, clarity, regulatory compliance, traceability, and coherence. Contribution/Results: AutoIND reduces drafting time by 97% (from 100 hours to 2.6–3.7 hours) while processing reports spanning tens of thousands of pages. Generated drafts achieve quality scores of 69.6%–77.9% and contain no critical regulatory deficiencies. This work represents the first systematic application of LLMs to core IND document generation, empirically validating a high-quality, high-efficiency, and regulatory-compliant AI-augmented authoring paradigm. It delivers a reproducible methodology and practical implementation pathway for intelligent drug development.

Technology Category

• Natural Language Processing: Generation
• Machine Learning: Large Multimodal Models (LMMs)
• Humans and AI: AI for Accessibility

Application Category

• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

Background: Investigational New Drug (IND) application preparation is time-intensive and expertise-dependent, slowing early clinical development. Objective: To evaluate whether a large language model (LLM) platform (AutoIND) can reduce first-draft composition time while maintaining document quality in regulatory submissions. Methods: Drafting times for IND nonclinical written summaries (eCTD modules 2.6.2, 2.6.4, 2.6.6) generated by AutoIND were directly recorded. For comparison, manual drafting times for IND summaries previously cleared by the U.S. FDA were estimated from the experience of regulatory writers ($geq$6 years) and used as industry-standard benchmarks. Quality was assessed by a blinded regulatory writing assessor using seven pre-specified categories: correctness, completeness, conciseness, consistency, clarity, redundancy, and emphasis. Each sub-criterion was scored 0-3 and normalized to a percentage. A critical regulatory error was defined as any misrepresentation or omission likely to alter regulatory interpretation (e.g., incorrect NOAEL, omission of mandatory GLP dose-formulation analysis). Results: AutoIND reduced initial drafting time by $sim$97% (from $sim$100 h to 3.7 h for 18,870 pages/61 reports in IND-1; and to 2.6 h for 11,425 pages/58 reports in IND-2). Quality scores were 69.6% and 77.9% for IND-1 and IND-2. No critical regulatory errors were detected, but deficiencies in emphasis, conciseness, and clarity were noted. Conclusions: AutoIND can dramatically accelerate IND drafting, but expert regulatory writers remain essential to mature outputs to submission-ready quality. Systematic deficiencies identified provide a roadmap for targeted model improvements.

Problem

• Reducing time for IND application drafting
• Maintaining quality in regulatory document writing
• Evaluating AI-human collaboration efficiency in pharma

Innovation

• LLM platform automates regulatory document drafting
• Reduces drafting time by 97% through AI
• Maintains quality while requiring expert refinement