The Government Accountability Office said in a new report that machine learning (ML) could help researchers save time and money in finding insights within biomedical or health-related data sets.

GAO offered that ML could accelerate drug development by screening chemical compounds, and “zero in on promising drug candidates in less time” than it currently takes to do so.

“Machine learning is used throughout the drug development process and could increase its efficiency and effectiveness, decreasing the time and cost required to bring new drugs to market,” GAO said.

GAO laid out three examples of ML use in early steps of drug development including:

  • The Drug Discovery step where “researchers are identifying new drug targets, screening known compounds for new therapeutic applications, and designing new drug candidates”;
  • The Preclinical Research step when researchers run preclinical testing and predict toxicity before human testing; and
  • Clinical Trials when researchers move toward trial design and apply ML to patient selection, recruitment, and stratification.

Additionally, GAO included policy options to address potential challenges of incorporating more ML use into drug development. These policy options include:

  • Promoting basic research for generating improved data and increasing understanding of ML in drug development;
  • Creating mechanisms or incentives to increase high-quality data sharing in the public and private sectors, while protecting patient data;
  • Collaborating with stakeholders to set uniform standards for data and algorithms;
  • Establishing public and private sector opportunities for workers to develop ML skills;
  • Collaborating with stakeholders to create a clear and consistent regulation message for ML in drug development; and
  • Maintaining the status quo by allowing current efforts to proceed uninhibited.

“These improvements could save lives and reduce suffering by getting drugs to patients in need more quickly, and could allow researchers to invest more resources in areas such as rare or orphan diseases,” GAO wrote.

Read More About
More Topics
Jordan Smith
Jordan Smith
Jordan Smith is a MeriTalk Senior Technology Reporter covering the intersection of government and technology.