Salvato in:
Dettagli Bibliografici
Autori principali: Eser, Umut, Gozin, Yael, Stallons, L. Jay, Caroline, Ari, Preusse, Martin, Rice, Brandon, Wright, Scott, Robertson, Andrew
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2509.09738
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909783245717504
author Eser, Umut
Gozin, Yael
Stallons, L. Jay
Caroline, Ari
Preusse, Martin
Rice, Brandon
Wright, Scott
Robertson, Andrew
author_facet Eser, Umut
Gozin, Yael
Stallons, L. Jay
Caroline, Ari
Preusse, Martin
Rice, Brandon
Wright, Scott
Robertson, Andrew
contents 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$100 h to 3.7 h for 18,870 pages/61 reports in IND-1; and to 2.6 h for 11,425 pages/58 reports in IND-2). Quality scores were 69.6\% and 77.9\% for IND-1 and IND-2. No critical regulatory errors were detected, but deficiencies in emphasis, conciseness, and clarity were noted. Conclusions: AutoIND can dramatically accelerate IND drafting, but expert regulatory writers remain essential to mature outputs to submission-ready quality. Systematic deficiencies identified provide a roadmap for targeted model improvements.
format Preprint
id arxiv_https___arxiv_org_abs_2509_09738
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Human-AI Collaboration Increases Efficiency in Regulatory Writing
Eser, Umut
Gozin, Yael
Stallons, L. Jay
Caroline, Ari
Preusse, Martin
Rice, Brandon
Wright, Scott
Robertson, Andrew
Artificial Intelligence
Quantitative Methods
I.2.7
Background: Investigational New Drug (IND) application preparation is time-intensive and expertise-dependent, slowing early clinical development. Objective: To evaluate whether a large language model (LLM) platform (AutoIND) can reduce first-draft composition time while maintaining document quality in regulatory submissions. Methods: Drafting times for IND nonclinical written summaries (eCTD modules 2.6.2, 2.6.4, 2.6.6) generated by AutoIND were directly recorded. For comparison, manual drafting times for IND summaries previously cleared by the U.S. FDA were estimated from the experience of regulatory writers ($\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.
title Human-AI Collaboration Increases Efficiency in Regulatory Writing
topic Artificial Intelligence
Quantitative Methods
I.2.7
url https://arxiv.org/abs/2509.09738