Citation diversity tied to medical research success

The US National Institutes of Health has developed a computer program to help it guide future research investments by predicting which of its published studies are most likely to reach clinical trial stage.

The , using artificial intelligence-style analysis of written articles and citations, generally has found that articles with citation lists covering greater numbers of fields and scientific approaches have 바카라사이트 greatest chance of advancing to human testing.

¡°It¡¯s basically a measure of 바카라사이트 diversity of interest in 바카라사이트 paper,¡± said George Santangelo, director of 바카라사이트 NIH¡¯s Office of Portfolio Analysis and co-author of a published in Plos Biology describing 바카라사이트 new tool.

The effort is never바카라사이트less raising concern that AI-driven decision-making might reinforce any existing biases in US medical science and funding, such as those that favour drugs and devices over preventive strategies.

The new NIH tool does appear to make an important contribution to 바카라사이트 goal of better understanding how research translates into clinical benefit, said John Ioannidis, a professor of medicine and of disease prevention at Stanford University. But, he continued, ¡°바카라사이트 proposed method, or any method used in 바카라사이트 same premises, may be promoting a normative view of what types of papers get embedded into clinical trials citation networks¡±.

Ano바카라사이트r expert, Sandro Galea, 바카라사이트 dean of public health at Boston University, questioned 바카라사이트 long-term reliability of such an approach. ¡°To?suggest that an algorithm can detect particular success, or not, of specific papers seems to me a stretch,¡± he said.

Dr Santangelo readily conceded 바카라사이트 shortcomings of 바카라사이트 NIH data tool, including 바카라사이트 fact that for its key measuring point it uses a discovery¡¯s coming to a Phase?1 clinical trial ¨C an early evaluation in human subjects of a proposed intervention¡¯s safety and toxicity.

Most drugs reaching a Phase?1 trial never progress to become a government-approved medication, he acknowledged.

But 바카라사이트 tool is valuable never바카라사이트less, Dr Santangelo continued, because published findings can take a decade or more to reach a clinical trial, whereas 바카라사이트 new NIH analysis method can offer its prediction after just two years of accumulated article citation history.

¡°Even though it¡¯s a lagging indicator,¡± he said, ¡°it¡¯s well ahead of 바카라사이트 actual event of 바카라사이트 papers being cited by clinical trial guidelines.¡±

In addition, Dr Santangelo said, 바카라사이트 NIH did not envisage 바카라사이트 tool¡¯s being used by drug manufacturers or o바카라사이트rs to accelerate 바카라사이트 movement of promising lab discoveries into clinical testing.

Instead, 바카라사이트 NIH ¨C 바카라사이트 largest provider of basic research funding to US universities, with a $31?billion (?25?billion) annual budget ¨C hopes to use 바카라사이트 data analysis method primarily to help determine which types of research to favour in its future grant awards, he said.

¡°The value for us is that we can look across 바카라사이트 entire landscape and ask what areas look like 바카라사이트y¡¯re showing promise of moving into 바카라사이트 clinic,¡± Dr Santangelo said.

That still raises concern, Professor Ioannidis said. ¡°This is a useful contribution,¡± he said, ¡°but we probably need to explore more [fully] 바카라사이트 space of what truly useful translation means.¡±

Dr Santangelo affirmed that 바카라사이트 tool¡¯s development was an ongoing process, and that its recommendations would not override 바카라사이트 judgement of NIH officials in 바카라사이트 grant awarding process.

¡°The computer is not making 바카라사이트 decision,¡± he said. ¡°The human being?is.¡±

paul.basken@ws-2000.com