Scite, Inc. — Department of Health and Human Services SBIR Phase I: NIDA

Description

The opioid epidemic in the United States has been traced to aletter reporting in the prestigious New England Journal of Medicine that synthetic opioids are not addictiveA belated citation analysis led the journal to append this letter with a warning this letter has beenheavily and uncritically citedas evidence that addiction is rare with opioid therapyThis epidemic is but one example of how unreliable and uncritically cited scientific claims can affect public healthas studies from industry report that a substantial part of biomedical reports cannot be independently verifiedYetthere is no publicly available resource or indicator to determine how reliable a scientific claim is without becoming an expert on the subject or retaining oneThe total citation countthe commonly used measureis inherently a poor proxy for research quality because confirming and refuting citations are counted as equalwhile the prestige of the journal is not a guarantee that a claim published there is trueThe lack of indicators for the veracity of reported claims costs the publicbusinessesand governmentsbillions of dollars per yearWe have developed a prototype that automatically classifies statements citing a scientific claim into three classesthose that provide supporting or contradicting evidenceor merely mention the claimThis unique capability enables scite users to analyze the reliability of scientific claims at an unprecedented scale and speedhelping them to make better informed decisionsThe prototype has attracted potential customers among top biotechnology and pharmaceutical companiesresearch institutionsacademiaand academic publishersWe propose to conduct research that will refine scite into an MVP by optimizing prototype efficiency and accuracy until they reach feasible milestonesand will refine the product market fit in our beachhead marketacademic publishingwhose influence on the integrity and reliability of research is difficult to overestimate We propose to develop a platform that can be used to evaluate the reliability of scientific claimsOur deep learning modelcombined with a network of expertsautomatically classifies citations as supportingcontradictingor mentioningallowing users to easily assess the veracity of scientific articles and consequently researchersBy introducing a system that can identify how a research article has been citednot just how many timeswe can assess research better than traditional analytical approachesthus helping to improve public health by identifying and promoting reliable research and by increasing the return on public and private investment in research