Literature DB >> 35579815

Identifying and Mitigating Potential Biases in Predicting Drug Approvals.

Qingyang Xu1,2, Elaheh Ahmadi3,4, Alexander Amini3,4, Daniela Rus3,4, Andrew W Lo5,6,7,8,9.   

Abstract

INTRODUCTION: Machine learning models are increasingly applied to predict the drug development outcomes based on intermediary clinical trial results. A key challenge to this task is to address various forms of bias in the historical drug approval data.
OBJECTIVE: We aimed to identify and mitigate the bias in drug approval predictions and quantify the impacts of debiasing in terms of financial value and drug safety.
METHODS: We instantiated the Debiasing Variational Autoencoder, the state-of-the-art model for automated debiasing. We trained and evaluated the model on the Citeline dataset provided by Informa Pharma Intelligence to predict the final drug development outcome from phase II trial results.
RESULTS: The debiased Debiasing Variational Autoencoder model achieved better performance (measured by the [Formula: see text] score 0.48) in predicting the drug development outcomes than its un-debiased baseline ([Formula: see text] score 0.25). It had a much higher true-positive rate than baseline (60% vs 15%), while its true-negative rate was slightly lower (88% vs 99%). The Debiasing Variational Autoencoder distinguished between drugs developed by large pharmaceutical firms and those by small biotech companies. The model prediction is strongly influenced by multiple factors such as prior approval of the drug for another indication, whether the trial meets the positive/negative endpoints, and the year when the trial is completed. We estimate that the debiased model generates financial value for the drug developer in six major therapeutic areas, with a range of US$763-1,365 million.
CONCLUSIONS: Our analysis shows that debiasing improves the financial efficiency of late-stage drug development. From the pharmacovigilance perspective, the debiased model is more likely to identify drugs that are both safe and effective. Meanwhile, it may predict a higher probability of success for drugs with potential adverse effects (because of its lower true-negative rate), thus it must be used with caution to predict the development outcomes of drug candidates currently in the pipeline.
© 2022. The Author(s), under exclusive licence to Springer Nature Switzerland AG.

Entities:  

Mesh:

Year:  2022        PMID: 35579815     DOI: 10.1007/s40264-022-01160-9

Source DB:  PubMed          Journal:  Drug Saf        ISSN: 0114-5916            Impact factor:   5.606


  15 in total

Review 1.  Diagnosing the decline in pharmaceutical R&D efficiency.

Authors:  Jack W Scannell; Alex Blanckley; Helen Boldon; Brian Warrington
Journal:  Nat Rev Drug Discov       Date:  2012-03-01       Impact factor: 84.694

2.  A Tool for Predicting Regulatory Approval After Phase II Testing of New Oncology Compounds.

Authors:  J A DiMasi; J C Hermann; K Twyman; R K Kondru; S Stergiopoulos; K A Getz; W Rackoff
Journal:  Clin Pharmacol Ther       Date:  2015-09-24       Impact factor: 6.875

Review 3.  Objective responses in patients with malignant melanoma or renal cell cancer in early clinical studies do not predict regulatory approval.

Authors:  John Goffin; Stefan Baral; Dongsheng Tu; Dora Nomikos; Lesley Seymour
Journal:  Clin Cancer Res       Date:  2005-08-15       Impact factor: 12.531

4.  Translational research: crossing the valley of death.

Authors:  Declan Butler
Journal:  Nature       Date:  2008-06-12       Impact factor: 49.962

5.  Prediction of Drug Approval After Phase I Clinical Trials in Oncology: RESOLVED2.

Authors:  Guillaume Beinse; Virgile Tellier; Valentin Charvet; Eric Deutsch; Isabelle Borget; Christophe Massard; Antoine Hollebecque; Loic Verlingue
Journal:  JCO Clin Cancer Inform       Date:  2019-09

6.  Estimation of clinical trial success rates and related parameters.

Authors:  Chi Heem Wong; Kien Wei Siah; Andrew W Lo
Journal:  Biostatistics       Date:  2019-04-01       Impact factor: 5.899

Review 7.  Review of phase II trial designs used in studies of molecular targeted agents: outcomes and predictors of success in phase III.

Authors:  Robert H El-Maraghi; Elizabeth A Eisenhauer
Journal:  J Clin Oncol       Date:  2008-02-19       Impact factor: 44.544

8.  Predicting success in regulatory approval from Phase I results.

Authors:  Laeeq Malik; Alex Mejia; Helen Parsons; Benjamin Ehler; Devalingam Mahalingam; Andrew Brenner; John Sarantopoulos; Steven Weitman
Journal:  Cancer Chemother Pharmacol       Date:  2014-09-23       Impact factor: 3.333

9.  Estimated Research and Development Investment Needed to Bring a New Medicine to Market, 2009-2018.

Authors:  Olivier J Wouters; Martin McKee; Jeroen Luyten
Journal:  JAMA       Date:  2020-03-03       Impact factor: 157.335

View more
  1 in total

1.  Artificial Intelligence and Machine Learning for Safe Medicines.

Authors:  Andrew Bate; Yuan Luo
Journal:  Drug Saf       Date:  2022-05-17       Impact factor: 5.228

  1 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.