Predicting success in regulatory approval from Phase I results

Malik, Laeeq; Mejia, Alex; Parsons, Helen; Ehler, Benjamin; Mahalingam, Devalingam; Brenner, Andrew; Sarantopoulos, John; Weitman, Steven

doi:10.1007/s00280-014-2596-4

Cited by 10 publications

(3 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition to estimating historical success rates, researchers have applied a variety of statistical and artificial intelligence techniques to predicting clinical trial outcomes. For example, Goffin et al (2005) study the tumor response rates of 58 cytotoxic agents in 100 phase 1 trials and 46 agents in 499 phase 2 trials; El-Maraghi & Eisenhauer (2008) look at the objective responses of 19 phase 2 anticancer drugs in 89 single-agent trials; Malik et al (2014) examine the trial objective responses of 88 anticancer agents in phase 1; DiMasi et al (2015) analyze 62 cancer drugs and propose an approved new drug index algorithm with four factors to predict approval for lead indications within a certain time period after completion (see Hsu et al 2019). This data availability has also enhanced the ability of researchers to view the actual project-level investment decisions of these companies, as we discuss in more detail later.…”

Section: Predicting Clinical Trial Outcomesmentioning

confidence: 99%

Financing Biomedical Innovation

Thakor

2022

Annu. Rev. Financ. Econ.

View full text Add to dashboard Cite

We review the recent literature on financing biomedical innovation, with a specific focus on the drug development process and how it may be enhanced to improve outcomes. We begin by laying out stylized facts about the structure of the drug development process and its associated costs and risks, and we present evidence that the rate of discovery for life-saving treatments has declined over time while costs have increased. We make the argument that these structural features require drug development (i.e., biopharmaceutical) firms to rely on external financing and at the same time amplify market frictions that may hinder the ability of these firms to obtain financing, especially for treatments that may have large societal value relative to the benefits going to the firms and their investors. We then provide an overview of the evidence for various types of market frictions to which these drug development firms are exposed and discuss how these frictions affect their incentive to invest in the development of new drugs, leading to underinvestment in valuable treatments. In light of this evidence, numerous studies have proposed ways to overcome this funding gap, including the use of financial innovation. We discuss the potential of these approaches to improve outcomes.

show abstract

Section: Predicting Clinical Trial Outcomesmentioning

confidence: 99%

Financing Biomedical Innovation

Thakor

2022

Annu. Rev. Financ. Econ.

View full text Add to dashboard Cite

show abstract

“…Statistical (typically both univariate and multivariate) analyses performed by the R&D analytics groups within pharma companies and biotechnology companies. These analyses (e.g., [5]- [7]) typically take into account several parameters (for example data from Phase 1, the mechanism of action of the drug, the availability of patients for the trial, etc. )…”

Section: Expert Input From Experienced Physicians and Drug Developersmentioning

confidence: 99%

A Machine Learning approach for assessing drug development risk

Vergetis

Liaropoulos

Georganaki

et al. 2020

Preprint

View full text Add to dashboard Cite

Identifying new drug targets and developing safe and effective drugs is both challenging and risky. Furthermore, characterizing drug development risk - the probability that a drug will eventually receive regulatory approval - has been notoriously hard given the complexities of drug biology and clinical trials. This inherent risk is often misunderstood and mischaracterized, leading to inefficient allocation of resources, and, as a result, an overall reduction in R&D productivity. We propose a Machine Learning (ML) approach that provides a more accurate and unbiased estimate of drug development risk than traditional models.

show abstract

“…From 2001 to 2009, five articles were published [4][5][6][7][8]. Interest in the topic continued to increase, with six relevant articles being published from 2010 to 2012 [9][10][11][12][13][14] and 12 articles appearing from 2013 to 2015 [15][16][17][18][19][20][21][22][23][24][25][26]. The timeframe for which data were analysed in the studies ranged from 1981 to 2014.…”

Section: Observations Publication Characteristicsmentioning

confidence: 99%