Trip’s image search is unique and based on a database of millions of images. As with all things at Trip it’s designed to be easy to use and still deliver great results. Access to our images is a ‘Pro’ feature and to see other benefits of ‘Pro’ visit our upgrade page.
Below are four examples of screengrabs for a given search. For each example you can see the search term used and a sample of the images returned:
Trip’s primary aim is to answer the clinical questions of health professionals. We’re pretty good, answering over 70% of them. But what about the remaining 30%?
If you don’t know the answer to a question it’s hard, but if you know the answer it’s easy – it stands to reason. So, what if Trip allowed users to ask questions they have not been able to answer and forward them to people we think may be able to answer it?
So, a general/family practitioner may have a question on heart failure. We could allow the user to record their question and we would forward it to people on Trip with an interest in cardiology/heart failure. One imagines, if the user knows the answer, it’ll only take a short amount of time to post a reply.
The above all makes sense but relies on Trip users sharing their knowledge. So, an open question – would you? Please let us know via the ‘Sharing Knowledge’ poll below!
The main purpose of Trip is to improve patient care. Our approach to achieve this is to support health professionals to answer their clinical questions using the best available evidence. While we’re not perfect we’re pretty good (there’s always room for improvement). Previous studies have shown that if we look at 1,000 searches of Trip this is how they may break down:
So, around 40.8% of searches of Trip result in improved patient care (a whopping 70.7% of the times clinicians come to Trip to get answers to support their care, they get an answer). While the figures should be taken highly sceptically (we’re written why they may overestimate and underestimate impact) they offer us a reasonable figure to base our impact measurement. Therefore, to approximate the impact of Trip we multiple the number of searches of Trip by 40.77%.
For January-March 2016 we were searched approximately 713,000 times. Therefore, Trip positively impacted on care around 290,700 times. The equates to around:
Those figures have got to be seen positively, but why be content with 3,194 per day, why not 50,000 per day? With the forthcoming changes to Trip (improved search results, answer engine, better content management) this should surely be our goal.
I’m just back from a meeting of KConnect, an EU funded consortium bringing together academia, SMEs and care providers with a view to improving health care. This is the 3rd meeting in two months and thankfully this one was in London (the others being in Luxembourg and Vienna).
There was lots of exciting developments and the following apply to Trip:
Answer engine. The answer engine is a system designed to infer questions from a users search terms and pull through the best answer (as well as the usual search results). We have a proof of concept model, which is great. However, there are a few issues with it. A few conversations with consortia members and it looks like that will be fixed fairly easily. With the prototype I estimate we got between 50-60% right and with the new tweaks, when they’re rolled should see that rise to over 80%.
The answer engine relies on being able to match search queries to articles. That needs us to accurately reduce document titles down to medical concepts. We should now be able to do this more accurately, more quickly and it’ll give us lots more flexibility with how we display the results.
Search log analysis. I typically refer to this as clickstream data, but search log analysis appears the favoured term. A new feature that we’ll be rolling out relates to search refinement and this will manifest itself in two ways:
Below is a list of query suggestions based on a search for hypertension:
So, if you’ve search for hypertension we might show the above and say, something like ‘are you interested in hypertension pulmonary, hypertension arterial etc. A user clicking on a search phrase will see the search automatically undertaken.
This should be rolled out shortly and we’ll test it to ensure it actually improves things!
Algorithm changes. Already planned from my visit to Vienna but further refinement of the specification which will see us trying multiple tweaks – in isolation and in combination – to try to ensure an optimal new search algorithm.
There are a few other bits and bobs that significantly affect Trip’s future development – but these are outside of KConnect and therefore can wait for another post. But, rest assured, these changes are all ambitious and doable!
Large sites, such as Trip, are complex and when you create a new design things can be missed and the following is a case in point.
At the top of the image (above) is the advanced search from the old site and below that is the new site. Apart from the design there is a bit of functionality missing – the ability to combine search (called ‘recent searches’ at the top). This allowed users to build up fairly complex searches.
We’re now aware of this and hope to get a fix out early next week!
Picture the scene – you’ve gone to Trip and searched for an article to answer your question. You find a paper that looks interesting and click on the link – and it leads to a dead link. I appreciate the frustration – I really do.
Websites change URLs for many reasons such as a new design for the site, withdrawing out of date content. It’s a constant battle for Trip to keep up to date. Thankfully we have a new and powerful tool to help with the release of a broken link system. Here’s what it does:
While it is not perfect it’s a significant enhancement to the site.
Linked to the notion of quality we have just introduced a new system to grab guidelines from the American guideline.gov. This is a great site and our system broke when they changed their URL from guidelines.gov to guideline.gov! But – from now – the links should work fine. So, as well as grabbing new guidelines we should automatically remove ‘withdrawn’ guidelines.
Great news if you work for NHS England, you can access Trip Pro for ‘free’. Health Education England has entered into a trial, till the end of 2016. This makes Trip Pro free to all NHS staff in England.
If you work for the NHS in England and are not automatically upgraded to Trip Pro (we use your computers IP address) either contact your library or me: jon.brassey@tripdatabase.com
I’m not sure how many of these ‘the future of Trip’ articles I’ve written over the years, but there have been a few. I like to set out my current thinking of the direction of Trip with some reflections on the past.
Business model – our move to a freemium business model last year (most of the site free but a ‘pro’ section for those willing to pay for extra content and functionality) has been a great success. For years we have been concerned about the financial security of Trip and this new approach has allowed us to diversify our income streams and bring the security we craved!
New Design – It’s been out for a few weeks now and I’m loving it and the reaction. We rolled out a few new features but it was more cleaning up the interface. It was a major piece of work and it’s great that this particular project has finished.
Answer engine – This has been talked about for years and it’ll finally be here shortly. It’ll be a learning system to give answers as well as search results.
As all this has been going on as I’ve been reading the very interesting ‘Business for Punks‘ which is an overview of the rise of the Scottish brewery Brewdog. It’s refreshing and has given me the inspiration to write this post. One big factor in their success has been the relationship with their customers, in effect, being their brand ambassadors – helping promote the business and the brand. To a large extent this happens with Trip. We have lots of fans and a great connection and I can always rely on our registered users to help out when I need advice. But one thing that Brewdog have shown is that you cannot do enough customer/user engagement. So, I’m hoping to reflect on better ways of making the Trip users feel part of Trip.
But another really powerful message is to properly define what you’re trying to do and really focus on making that magical. This is something I’ve been pondering for a while and this book helped crystallize my thinking:
Trip started as a service to my work answering clinical questions for general practitioners in Gwent, South Wales in 1997. Q&A is my passion. When we ask users about Trip we get three main reasons for using the site:
The focus of Trip developments has always been the top reason (Q&A) but I’ve been keen to support the other two. I think this will always be the case. But I do think I may have lost sight of what the Q&A component means. What do I want the site to do, in relation to Q&A? A few alternatives:
or
or
They all amount, roughly, to the same thing. The top one answers it best albeit being a bit wordy (but we can work on that). So, the plans for the next major developments involve supporting clinical question answering! This requires a number of components:
Answer engine – as mentioned above it’ll be rolled out soon. It won’t be perfect but it’s a great start and it’s a learning system so it’ll get better with time.
Search algorithm – we’ve followed the same basic algorithm for years, arranging results based on a mixture of word matching (between search term(s) and documents in the Trip index), year of publication and quality of the publisher. This is fine, to a point, but search has moved on massively and we’ve not moved with the times. So, we will be looking to overhaul this. As part of my work in the KConnect I will be working with information retrieval experts to exploit current ‘best practice’.
Belief – Underlying the changing has to be a belief that we can be the best.
Community – Trip needs to state our aim to be the best and to actually be the best. This will rely on our community of users letting us know when we’re great and when we’re less than great. So, our engagement with users needs to be enhanced – from good to great.
So, Trip’s future:
Trip is involved in the extremely interesting KConnect project, via the EU’s Horizon 2020 funding stream. One output of this has been a nice interface to explore our clickstream data. Clickstream data being a record of how people interact with the site eg search terms used, articles viewed etc.
This gives us a glimpse of clinical uncertainties, ‘hot topics’, useful sites etc. Below are three images to highlight potential uses, but we know there are more. Imagination is the limitation with this data!
Image One – this is a record of searches for breast cancer and a drug. So, which drugs are most popular when used in conjunction with the term breast cancer? In this case, it’s trastuzumab!
Image Two – As we record the date and time of the search we can plot search term popularity. So, you can clearly see a peak of searching for ebola around October last year.
Image Three – for searches which publications have been most visited? Top is PubMed, followed by NHS CRD, then NICE. http://dx.doi…. refers to Cochrane and the final entry to the top five is CADTH.
Trip Database Blog 
Recent Comments