Collaborating Authors

Large expert-curated database for benchmarking document similarity detection in biomedical literature search


Document recommendation systems for locating relevant literature have mostly relied on methods developed a decade ago. This is largely due to the lack of a large offline gold-standard benchmark of relevant documents that cover a variety of research fields such that newly developed literature search techniques can be compared, improved and translated into practice. To overcome this bottleneck, we have established the RElevant LIterature SearcH consortium consisting of more than 1500 scientists from 84 countries, who have collectively annotated the relevance of over 180 000 PubMed-listed articles with regard to their respective seed (input) article/s. The majority of annotations were contributed by highly experienced, original authors of the seed articles. The collected data cover 76% of all unique PubMed Medical Subject Headings descriptors. No systematic biases were observed across different experience levels, research fields or time spent on annotations.

What Are The Best Countries For Health Care? U.S. Last Among Wealthy Nations

International Business Times

The United States finished dead last in an analysis of health care quality across several wealthy nations, ranked either the worst or close to worst in categories like affordability, administrative efficiency and the health of the overall population. A report from The Commonwealth Fund, a private, American-based foundation focused on health care issues, compared the country to seven others in Europe -- France, Germany, the Netherlands, Norway, Sweden, Switzerland and the United Kingdom -- as well as to Canada, Australia and New Zealand. Those other 10 were found to spend significantly less on care while enjoying better health, after the foundation inspected 72 "indicators" throughout the health care systems of each nation, which included gathering data from patient and doctor surveys as well as from the World Health Organization and other agencies. "Based on a broad range of indicators, the U.S. health system is an outlier, spending far more but falling short of the performance achieved by other high-income countries," the report said. "The results suggest the U.S. health care system should look at other countries' approaches if it wants to achieve an affordable high-performing health care system that serves all Americans."

Lockdowns prevented over 3 million deaths in 11 countries: Study

Al Jazeera

Strict lockdowns managed to reduce COVID-19 transmission and prevented more than three million deaths in 11 European countries, according to a new study. Research by Imperial College London, whose scientists are advising the British government on the virus, found that restrictions such as stay-at-home orders worked to bring the spread of the coronavirus under control. They estimated that approximately 3.1 million deaths were averted by policies in Germany, France, Italy, the United Kingdom, Spain, Belgium, Austria, Denmark, Norway, Sweden and Switzerland. Using European Centre of Disease Control data on deaths in those 11 nations in the period up to May 4, the scientists compared the number of observed deaths in the countries with those predicted by their model if no restrictions had been imposed. Researchers also calculated that the interventions caused the reproduction number to drop by an average of 82 percent, to below one.

Reinforcement Learning in Healthcare: A Survey Artificial Intelligence

As a subfield of machine learning, \emph{reinforcement learning} (RL) aims at empowering one's capabilities in behavioural decision making by using interaction experience with the world and an evaluative feedback. Unlike traditional supervised learning methods that usually rely on one-shot, exhaustive and supervised reward signals, RL tackles with sequential decision making problems with sampled, evaluative and delayed feedback simultaneously. Such distinctive features make RL technique a suitable candidate for developing powerful solutions in a variety of healthcare domains, where diagnosing decisions or treatment regimes are usually characterized by a prolonged and sequential procedure. This survey will discuss the broad applications of RL techniques in healthcare domains, in order to provide the research community with systematic understanding of theoretical foundations, enabling methods and techniques, existing challenges, and new insights of this emerging paradigm. By first briefly examining theoretical foundations and key techniques in RL research from efficient and representational directions, we then provide an overview of RL applications in a variety of healthcare domains, ranging from dynamic treatment regimes in chronic diseases and critical care, automated medical diagnosis from both unstructured and structured clinical data, as well as many other control or scheduling domains that have infiltrated many aspects of a healthcare system. Finally, we summarize the challenges and open issues in current research, and point out some potential solutions and directions for future research.

Brit Richard Henderson among Nobel Chemistry Prize trio

Daily Mail - Science & tech

The 2017 Nobel Prize for Chemistry has been awarded to Professors Jacques Dubochet, Joachim Frank and British scientist Dr Richard Henderson. The Swedish Royal Academy of Sciences said the trio's method, called cryo-electron microscopy, allows researchers to'freeze biomolecules' mid-movement and visualise previously unseen processes. The technology both simplifies and improves the imaging of biomolecules and has been credited with moving biochemistry into a new era. Scottish chemist Dr Henderson is a researcher at Cambridge University, Professor Dubochet works at the University of Lausanne, Switzerland, while Professor Frank studies at New York's Columbia University. The trio's prize was awarded for developing cryo-electron microscopy.