What to read next? To address the challenge of helping readers find the most relevant research across an ever-growing number of articles online, we have partnered with TrendMD, the world’s leading scholarly research recommendation engine. Now our readers can quickly discover article recommendations related to what they just finished reading in the moment, without another search.

From an article page on Peritoneal Dialysis International, readers will see “We recommend…. powered by TrendMD.” The recommended articles are selected based on sophisticated algorithms applied across millions of articles served each month and based on actual reader click behavior (“people that read X, also clicked on Y”), similar to what one expects at Amazon, Netflix, and Spotify.

On the left, readers get direct links to recommended articles from the journal they are currently reading. On the right, more article recommendations related to the topic come from across the TrendMD network, which includes over 2,500 publications from world leading publishers of scholarly research and professional publications.

The TrendMD algorithms weight article popularity and the individual reader’s behavior - what the specific visitor has read on past visits to the journal and across all publications on the TrendMD network. Common factors such as semantic classification and key words are built into the algorithms, too. Yet, there may be diminishing returns from discovering more articles on precisely the same subject. By analogy, if I’ve just bought a coffee maker, I probably don’t want to buy another coffee maker, but I may well be interested in buying coffee beans, or descaler.

Collaborative filtering is a powerful way to improve recommendations, identifying this type of correlation through the analysis of anonymized click data. TrendMD makes heavy use of collaborative filtering (sometimes called “The Wisdom of Crowds”) to optimize its recommendations, ensuring that the articles shown by the TrendMD recommendation widget are those predicted to be most useful, based on the pattern of recent click data of millions of other readers who have recently read the article or research on the topic.

So, now it’s easy to decide what to read next. Look for “We recommend…. “ at the end of the next article you read.

And, of course, don’t miss our Most-Frequently Read, and Most-Frequently Cited articles.