Trip Database Blog

This is the fourth in the series exploring how Trip compares with the most popular medical database – PubMed. In relation to a previous comparison we received the following comment recently:

I like this comparison, but I wonder if it would be more meaningful to compare TRIP with a PubMed Clinical Queries search (Clinical Queries – PubMed). I still think TRIP would “win” because of your emphasis on the evidence hierarchy, inclusion of SRs and EB guidelines, but I think it would be a more refined comparison.

ChatGPT describes PubMed Clinical Queries as “…a feature of PubMed designed to help users quickly find evidence-based information relevant to clinical practice. It focuses on filtering search results into predefined categories tailored to specific clinical needs. This tool is especially useful for healthcare professionals seeking high-quality and focused information to aid in patient care.“

So, sounds like more of a fair challenge, so, lets try it on the search migraine prevention. Clinical Queries (CQ) allows you to select different query types so for this test I selected ‘Therapy’ and after that you have two choices – broad or narrow. Broad maximises sensitivity (trying to identify all possible results) while narrow maximises specificity (trying to identify the most relevant articles). Here are the top five for each database:

To try the search for yourself, here are the links:

• Trip search for migraine prevention
• Clinical Queries Broad search for migraine prevention
• Clinical Queries Narrow search for migraine prevention

For the test I will actually use the top ten results for each database and ask ChatGPT to rate them based on clinical relevance, quality of the evidence and recency. The actual prompt used was:

Below are 3 set of results for a search for ‘migraine prevention’. Comment on quality of evidence, recency of articles and applicability to answering questions on the topic. And give an overall view on which database is likely most useful to a busy health professional.

ChatGPT’s comparison:

Another win for Trip….

This is the third in our series comparing Trip to PubMed. The first two prostate cancer screening and asthma diagnosis are still available!

We took a representative clinical question and ran it through Trip Pro, PubMed Best Match (the default algorithm) and PubMed Most Recent. We then exported the top ten results from each – our assumption was that it’s a busy health professional who doesn’t have lots of times to look through pages of results!

The clinical question this time related to the use of use and safety of SSRIs during pregnancy. For each database we used the search terms SSRIs AND pregnancy – you can try the search yourself using these links:

• Trip Pro (NOTE: this assumes you have access to Pro)
• PubMed Best Match
• PubMed Most Recent

We then asked ChatGPT to compare the results using this prompt:

Below are three set of results for a search for ‘SSRIs AND pregnancy’ with a view to answering the question about the use and safety of SSRIs during pregnancy. Comment on quality of evidence, recency of articles and applicability to answering the question. And give an overall view on which database is likely most useful to a busy health professional.

It made the following assessment for each database:

Trip Pro: This database provides up-to-date and practical information with fewer older references, making it suitable for answering clinical questions efficiently.

PubMed Best Match: This database offers a mix of high-quality and relevant evidence but includes some outdated material. Its focus on SSRIs in pregnancy makes it useful, but its age range might require careful selection of the most recent and relevant articles.

PubMed Most Recent: This database excels in recency and breadth but may be less practical for quickly answering focused clinical questions due to its diversity and inclusion of less clinically relevant research.

And it gave this final comment:

Recommendation for Busy Health Professionals
Trip Pro is likely the most useful due to its balance of recency, applicability, and practicality. It provides high-quality, up-to-date evidence without being overly broad or outdated, making it ideal for answering focused clinical questions about the safety of SSRIs during pregnancy.

If you’d like a trial of Trip Pro please get in touch: jon.brassey@tripdatabase.com

2024 was a great year for Trip.

We continue to have a impressive impact on care around the globe, helping support millions of decisions with evidence-based content. This is Trip’s core function, as such, it’s ‘business as usual’. However, we have continued to improve the site as much as we can and 2024 was full of significant improvements (BTW this opening section is identical to last year’s review – apart from the update to the year)!

Across the year our Rapid Review (RR) service has brought us great joy and an equal amount of challenge. Doing RRs for sectors we’ve not usually worked with has been particularly interesting. Given our experience and skills we can produce great rapid reviews at a much lower price than most, so if your organisation needs a RR undertaking in 2025, then send us an email: rapidreviews@tripdatabase.com.

January 2024
We spent a lot of time working with LLMs to get to grips with Q&A. Our initial attempts were really encouraging and we know – nearly 12 months later – a lot more of the potential for LLMs.

February 2024
More work on LLMs, this time with a latest evidence feature. This was great fun and is now a live project on Trip (see here), and this is likely to expand in 2025.
We also added a large number of new guideline scores to Trip. The title of the announcement Disappointing guideline scores, sums up our thoughts!

March 2024
Many of our searches are really simple so it was great to better understand the motivations of our users with by launching a survey. We also had a blast from the past, courtesy of the Internet Archive, with the original 25 publishers included in Trip:

April 2024
More fun with LLMs including extracting recommendations from guidelines and systematic reviews and using them to analyse clickstream data.

May 2024
This was a really significant month. We moved our infrastructure onto the cloud and made a really big change to our search results.

June 2024
Another user survey, this time asking our users about their thoughts on our use of AI.

July 2024
As well as releasing the results on the AI survey we improved our inclusion of full-text documents (for Pro users) with over 85% of our journal articles linking to full-text.

August 2024
A quiet month with a simple announcement regarding miss-spelling!

September 2024
We released the mis-spelling feature mentioned above but more importantly we broke a record for the number of systematic reviews we link to, with over 550,000!

October 2024
Latest evidence was launched! This is going down really well and so we’re looking to expand to areas outside of primary care.

November 2024
Trip is often asked how to we compare with PubMed. To help we created a comparison based on an example search. We have now done two comparisons (one and two). We used ChatGPT to undertake the analysis – felt it was less biased than asking ourselves. If you’re interested in answering clinical questions using high-quality evidence then the results are clear….

December 2024
We released some important design changes (see here and here). Many were small but boosted transparency and usability of the site.

We also started working with Mind Maps, really amazing feature that we hope to roll out in early 2025. This combines LLMs and a lovely graphical interface.

If we had to summarise 2024 it would be the year we got comfortable with LLMs (as you’ll see in 2025) and the year we continued to push out new features to make Trip a better service for our users. And, in the spirit of this year and next, we asked ChatGPT to summarise our year:

In 2024, Trip Database focused on leveraging LLMs for innovation, enhancing infrastructure and usability, and expanding evidence-based features like “latest evidence.” User feedback and AI played central roles in refining offerings, while milestone achievements and transparency-driven updates set the foundation for future advancements.

This is the second in our series comparing Trip to PubMed, the first can be seen here. Last time we explored prostate cancer screening, while this time it is for the search asthma diagnosis.

For Trip we used the default Pro search and for PubMed we will show the top 5 results for both their ‘Best match’ algorithm and ‘Most recent’.

Trip	PubMed Best Match	PubMed Most Recent
Fractional Exhaled Nitric Oxide Testing for the Diagnosis and Management of Asthma: a Health Technology Assessment, Health Quality Ontario 2024	Asthma: definitions and pathophysiology, Int Forum Allergy Rhinol 2015	The Association Between Obesity and the Unified Airway in Children, Ear Nose Throat J 2024
Asthma Diagnosis, Education and Management, Clinical Practice Guidelines and Protocols in British Columbia 2023	Advances in asthma: New understandings of asthma’s natural history, risk factors, underlying mechanisms, and clinical management, J Allergy Clin Immunol. 2021	Treatment of metastatic ALK-positive non-small cell lung cancer: real-world outcomes in a single center study, Transl Lung Cancer Res 2024
The Saudi initiative for asthma – 2024 update: Guidelines for the diagnosis and management of asthma in adults and children, Saudi Clinical Guidelines 2024	Severe asthma: definition, diagnosis and treatment, Dtsch Arztebl Int. 2014	Obesity at the age of 4-5 related to asthma diagnosis in later childhood: A longitudinal study using linked routinely collected data from Wales, Int J Popul Data Sci 2024
Enhancing GP direct access to diagnostic tests for patients with suspected chronic obstructive pulmonary disease, asthma, or heart failure, NHS England 2024	Understanding the immunology of asthma: Pathophysiology, biomarkers, and treatments for asthma endotypes, Paediatr Respir Rev. 2020	Today’s Problem Tomorrow’s Crisis: A Retrospective, Single-Centre Observational Study of Nonagenarians in the Emergency Department, Cureus 2024
Guideline update: Diagnosis and management of asthma in preschoolers, children and adults, Canadian Thoracic Society 2021	Asthma diagnosis in infants and preschool children: a systematic review of clinical guidelines, Allergol Immunopathol (Madr). 2019	Association of psychological problems for which help was sought with physical illness, Am J Prev Med 2024

We then took the top ten results for each of the three different searches and asked ChatGPT to compare the results exploring issues like clinical relevance, quality of the evidence and recency. ChatGPT’s response was:

Again, like last time, it’s pretty clear…

The roll out of the synonym system, yesterday, is already proving beneficial.

Before we didn’t have a synonym for surgery, so we will now add surgical!

• surgery – 578,100 results
• surgical – 407,425 results
• surgical OR surgery – 779,828 results

It does raise interesting questions about how strict we make the synonyms. One could argue that surgery and surgical are not strict synonyms as they can be used slightly differently. But the overlap seems large enough to warrant it!

UPDATE: And another:

• UTI – 7,314 results
• urinary tract infection – 22,470 results
• urinary tract infection OR uti – 22,608 results

UPDATE 2:

• osteopathy – 628 results
• osteopathic – 2,639 results
• osteopathic OR osteopathy – 3,010 results

Two weeks ago we announced a raft of design changes, today is a more modest update. It relates to being transparent about the synonyms we use in Trip. Until now it has never been possible to see what synonyms we used. Well, from now you can see and also comment.

When you do a search there is a subtle Synonyms box:

If you click on the box it shows the synonyms used in the search:

In this case we can see that we used the synonym acetaminophen for paracetamol.

You’ll also notice a Comments section. If you use Trip and you feel the current synonyms are poor then let us know. Similarly, if there is no synonym and you think there should be, then also let us know. Your input can help make Trip better for you and for other users.

We’re interested in allowing users to create topic maps for a search. We have tried this ‘mind map’ approach for a search for prostate cancer. There are two examples below, the first based on the top 100 search results and the second on the top 300 results.

I think these are really interesting, giving users an instant overview of the topic. I dare say it could be used for search refinement. By that, start with a broad search and then decide to focus on diagnosis or focal therapy…

Mind Map using top 100 results

Mind Map using top 300 results

We’ve just rolled out some big and some little design changes.

Above the search results:

‘Order By’ has been changed to TripRank, previously it was quality. ‘Quality’ was mis-leading as the default algorithm takes into account quality, date and relevancy. TripRank better reflects this.

‘Show Results’ now allows users to select 20, 50 or 100 results on the page. Previously users were only able to see 20 results on a single page.

‘Results page key’ now opens up within the same window – as a modal – previously it opened up in a new window.

Date Range:

Clearly labelled and when a user clicks in the ‘From’ or ‘To’ box there is a drop-down selection (although users can still simply type the year)

Broken link:

Currently, when a user clicks the ‘Broken link?’ button they get a simple ‘thank you’. However, from now users will be able to leave their email so that we can update them when we resolve the issue – likely an updated URL or notification that it has been deleted. This feels really important to me as Trip benefits enormously from these reports, it feels like we’re giving something back directly to the person reporting the issue!

Export articles:

We have slimmed down the export options area and now reads ‘top to bottom’, making the options more logical (a few people have reached out expressing confusion while using this feature):

Accessibility Statement:

This has now been added to the footer

One final, subtle change, and this is in colours for primary research and controlled trials:

At the top was the previous red and beneath is the new orangey/red. Red is associated with danger so seeing lots of reds seemed quite negative (and I felt it looked a bit angry). The orange seems more peaceful.

PubMed is probably the most used search tool in the medical world. As such we are often asked how does Trip differ from PubMed? Or, put it another way, why should we bother with Trip? If you ask ChatGPT it states:

“The Trip Database is a clinical search engine focused on delivering evidence-based summaries, guidelines, and tools for healthcare professionals, making it user-friendly for clinical decision-making. PubMed, by contrast, is a comprehensive repository of biomedical research articles, aimed at researchers and clinicians needing in-depth primary studies. Trip emphasizes practical application, while PubMed is broader and research-oriented.“

But, practically how does this manifest itself? Below is an example that can illustrate the differences. The search stems from a likely clinician question. Trip is focussed on clinical decision making so we focus on the clinical question scenario. As ChatGPT states, PubMed’s aim is broader – so has to accommodate more diverse needs.

Prostate Cancer Screening

• Trip search
• PubMed search

Here are the top 3 side-by-side (Trip on the left-hand side):

The top three from Trip are all secondary evidence ie higher quality compared to PubMed’s. One of PubMed’s article is a case report and two are about imaging. Below is the top ten:

Trip	PubMed
Stockholm3 for prostate cancer screening (NICE)	A case of primary duodenal Brunner’s gland hamartoma that gradually underwent morphological changes over a period of 10 years (DEN Open)
MRI screening for prostate cancer shows promise (NIHR Evidence)	Posttreatment Lower Urinary Tract and Prostate Imaging (Urol Clin North Am)
Rising metastatic prostate cancer rates and better noninvasive testing: might PSA screening make a comeback? (Clinical Correlations)	The Role of Nuclear Medicine in Imaging and Therapy of Prostate Cancer: The State of the Art (Urol Clin North Am)
Canadian Urological Association recommendations on prostate cancer screening and early diagnosis (Canadian Urological Association)	Urologic Imaging of the Prostate: Cancer and Mimics (Urol Clin North Am)
Prostate Cancer Screening (PDQ Cancer Information)	2D Fe/Co-MOF/SOX cascade reactors for fast noninvasive detection of sarcosine level in prostate cancer urine (J Colloid Interface Sci)
Prostate cancer screening with the PSA test (Institute for Quality and Efficiency in Healthcare)	Benign prostatic hyperplasia genetic variants in Asians (Clin Chim Acta)
A Detailed Evaluation of the Effect of Prostate-specific Antigen-based Screening on Morbidity and Mortality of Prostate Cancer: 21-year Follow-up Results of the Rotterdam Section of the European Randomised Study of Screening for Prostate Cancer (European Urology and EvidenceUpdates)	Comparison of Morphological and Functional MRI Assessments of Periprostatic Fat for Predicting Prostate Cancer Aggressiveness (Int Braz J Urol)
Prostate-Specific Antigen Screening and 15-Year Prostate Cancer Mortality: A Secondary Analysis of the CAP Randomized Clinical Trial (JAMA)	Single‑center, retrospective, evaluator‑blinded, pilot and pivotal clinical trials: Assessing the mirCaP Kit (hsv2‑miR‑H9/hsa‑miR‑3659) as a diagnostic marker for prostate cancer in patients with PSA levels in the gray zone (Oncol Lett)
Which men benefit from prostate cancer screening? Prostate cancer mortality by subgroup in the European Randomised Study of Screening for Prostate Cancer (BJU international)	The State-of-the-Art PET Tracers in Glioblastoma and High-grade Gliomas and Implications for Theranostics (PET Clin)
Prostate cancer screening with prostate-specific antigen (PSA) test (BMJ Rapid Recommendations)	Photoelectrochemical biosensors: Prospects of graphite carbon nitride-based sensors in prostate-specific antigen diagnosis (Anal Biochem)

We asked ChatGPT to compare the results and from the perspective of a busy health professional with a clinical question relating to prostate cancer screening that affects patient care. We also asked it to consider the quality of the evidence.

It concluded: “For a busy health professional addressing a clinical question about prostate cancer screening, Trip Database provides a more focused, clinically actionable, and evidence-based set of results. Its emphasis on guidelines and systematic reviews ensures better support for patient care. In contrast, PubMed excels in breadth and niche research but lacks the specificity and usability required for immediate clinical decision-making.“

Pretty clear….

We will continue to generate these comparisons, it’s useful to help explain the strengths of Trip