Trip Database Blog

Three recent questions submitted to AskTrip made me think about the relationship between the evidence we make available and the knowledge people actually need. They all came in this morning – one at 6.46am, the next at 6.52am and the final one at 7.01am – my assumption is these were all from the same person!

All three concerned sexual and reproductive rights: how they differ across countries, the distinction between sexual rights and reproductive rights, and how sexual rights are defined in the literature.

AskTrip produced answers, but the material it found was limited or only partly relevant. Reading them, I wondered whether a general-purpose AI model, drawing on broader sources, might have been better suited to these questions.

Trip is primarily focused on evidence to inform healthcare. These questions sit at the intersection of health, law, ethics and public policy. That makes them useful examples of what happens when a knowledge need extends beyond the strongest coverage of an evidence resource.

But looking more closely, there was something else going on.

The answers sometimes assessed the available material using criteria that did not fit the question.

The first question asked how sexual and reproductive rights compare across countries. The answer opened:

“Evidence on sexual and reproductive rights shows significant disparities in service quality and access across countries…”

It went on to discuss sexual health services, STI screening and sexual harassment. These are relevant to the realisation of rights, but they provide only part of the comparison requested. A reader could finish the answer knowing that access to services varies, while still knowing little about how countries’ legal protections differ.

The answer acknowledged this:

“many studies discuss service provision or healthcare outcomes rather than explicitly comparing legal frameworks”

That is an important qualification. It also identifies the central problem: the retrieved material largely answers a neighbouring question.

A more useful approach would first establish which countries and which rights the user wanted to compare, then examine legal protections alongside practical access. A country comparison needs both, with dates and sources attached.

The second question asked about the difference between sexual rights and reproductive rights. Its opening distinction was helpful:

“Sexual rights focus on the right to safe, consensual, and pleasurable experiences related to sexuality, while reproductive rights emphasize the ability to make informed decisions about reproduction…”

However, the limitations section criticised the available material for lacking:

“exhaustive empirical validation of the distinctions”

This seems to apply the wrong test. The user is asking for a conceptual explanation. Definitions need attribution, clarity and attention to areas of disagreement. Their usefulness does not depend on being validated in the same way as a treatment effect.

An illustrative alternative would be:

Sexual rights concern autonomy, equality and freedom from coercion in relation to sexuality and sexual relationships. Reproductive rights concern decisions about reproduction, including whether and when to have children. They overlap, but sexuality extends beyond reproduction. A fuller answer should explain how particular organisations define the terms and where those formulations differ.

That is a starting explanation, rather than a complete review. It addresses the distinction directly and makes clear what further sourcing would add.

Significantly, AskTrip had already searched beyond Trip for this answer and found a WHO source. Broader retrieval helped, but the answer still judged the source through an inappropriate empirical lens.

The third question asked how sexual rights are defined in the relevant literature. The answer assembled themes from literature concerning different populations, then observed:

“The literature heavily leans on international conventions and human rights frameworks”

For this question, those frameworks could be central to a good answer. WHO’s sexual health page, for example, explicitly presents a working definition of sexual rights grounded in existing human rights.

A more direct answer could begin with that definition, explain its scope, and compare it with other relevant formulations. It would distinguish an organisation’s definition from rights enforceable in a particular jurisdiction. Population-specific research could then show how those rights are understood or experienced in practice.

Across these examples, I see three questions for an evidence service:

• Do we hold the sources needed to answer the question?
• Have we retrieved material that directly addresses it?
• Are we judging that material using criteria appropriate to the knowledge being sought?

These are separate problems. Adding sources will not necessarily fix an answer that treats a definition as an inadequately validated empirical claim.

Would a general-purpose model do better? Probably. Its broader knowledge could help it explain concepts and recognise relevant legal or ethical frameworks. But fluent writing is not proof of accuracy. Current country comparisons still require checked sources, and a fair comparison would assess accuracy, relevance and attribution rather than how convincing the answers sound. The alternatives above illustrate a different approach; they are not a formal test of competing systems.

For me, the most useful lesson concerns the phrase “limited evidence”. It can describe a genuine lack of research, a gap in a database, or a search that has failed to find suitable material. Those meanings should not be interchangeable.

“The sources we found do not adequately answer this question” is sometimes the more accurate statement.

A question can concern health while requiring knowledge that biomedical research alone cannot supply. The challenge for AskTrip – and for evidence services more broadly – is to recognise the knowledge need, find appropriate sources, and be clear when the fit is poor.

AskTrip has now answered 25,000 questions. That’s a milestone we’re delighted to reach, and the question that took us there deserves a closer look. It asked whether bed-based exercises could improve pressure areas, wellbeing or discharge outcomes and whether there was research supporting video-guided exercises.

A practical question about everyday care. Could something relatively simple make a meaningful difference to someone in hospital?

For me, that makes it a fitting milestone question.

It brings together several things that matter: preventing harm, helping someone feel better and supporting their recovery towards leaving hospital. It also reflects the curiosity behind evidence-based practice: here is something we could do, but what research supports it?

The answer also illustrates why uncertainty matters. AskTrip reported that it had not identified direct evidence answering the precise question, although it found related evidence concerning broader mobility interventions.

That distinction deserves attention. Evidence about mobility in general does not automatically establish the benefits of a particular bed-based exercise programme. And whether exercises help is a separate question from whether video is an effective way to deliver them. Equally, not finding direct evidence does not mean an intervention has been shown not to work. It means the specific question remains open.

That can still be a useful starting point. It helps us think about what we would need to know next. Does video guidance make exercises easier to follow? Do patients participate more? Which outcomes should a service measure to understand whether its approach is helping?

Reaching 25,000 Q&As is a reason to celebrate the people asking the questions, too. This particular question reminds us that improving care depends on people noticing opportunities, questioning assumptions and looking for evidence.

Thank you to everyone who has used AskTrip, challenged an answer or offered feedback. Your questions and observations help us improve it.

Read our 25,000th Q&A: Are there studies on the impact of bed-based exercises on pressure areas, wellbeing, or discharge pathways, and is there research supporting video bed-based exercises?

A little over a week ago we published a blog about user feedback on the AskTrip Answer Score. The concern was that the colours and overall rating could give a reassuring impression even when the evidence was limited. I felt this needed addressing quickly, so we have prioritised an update.

We have removed the colour-coded overall score and replaced it with a more neutral display showing two separate ratings:

• Evidence base: how strong and directly relevant the evidence found is.
• Answer quality: how well the answer addresses the question and reflects the evidence found, including its limitations.
  

The distinction matters. An answer can explain weak or inconclusive evidence accurately and usefully, and therefore score highly for answer quality. That does not mean the evidence itself is strong.

The new design is deliberately more understated. We want these ratings to help you understand the basis for an answer, without the colours suggesting more certainty than the evidence supports.

Thank you to everyone who gave feedback. Please keep it coming—it helps us make AskTrip better.

When should you use Trip search, and when should you use AskTrip?

Trip offers two ways to explore clinical evidence: search for relevant documents, or ask a question and receive a referenced answer. Which should you choose?

A practical example helps illustrate what each offers:

Is oral or IV iron the best practice for treating iron deficiency in individuals over 65 years old?

With Trip search, a simple starting point is iron deficiency AND elderly.

This opens up the wider topic. The results include research on iron deficiency in geriatric patients, studies of investigation and outcomes, and the British Society of Gastroenterology guideline on managing iron deficiency anaemia in adults.

That breadth is useful when you want to understand what evidence is available, find a particular guideline, or choose which studies to read. You can filter by evidence type, such as systematic reviews or guidelines, and use the year range to focus your search.

It is also a starting point rather than a finished search strategy. The query does not specify oral or intravenous treatment, so not every result will address that comparison. You can refine the terms as you discover which aspects of the topic matter to your question.

AskTrip starts with the question you want answered. Rather than translating it into search terms, you can ask it in full.

In this AskTrip example, the answer presents oral iron as the usual starting option and identifies circumstances in which IV iron may be preferred, including intolerance, inadequate response or a need for rapid correction.

The answer then expands on the evidence, safety, monitoring and research gaps, with references to explore. It also highlights an important limitation: much of the available research comes from specific settings, such as surgery, and may not directly answer questions about older adults living in the community.

This makes AskTrip useful when you have a focused question and want an initial synthesis to orient your reading. The references allow you to examine the sources behind it; the summary still needs to be assessed in the context of the patient and the applicability of the evidence.

You can then take the question further. The “Explore further” feature lets you ask for more detail or challenge the answer. Suggested follow-ups in this example include when to switch from oral to IV iron and what is known about longer-term health outcomes.

You can also move to Trip search to explore a guideline in full, look for additional studies or widen your reading beyond the treatment comparison.

Equally, you might begin with search, identify an issue that needs clarification, and take that question to AskTrip.

Use Trip search when your priority is finding and selecting the documents you want to examine. Use AskTrip when your priority is a referenced synthesis of a specific question, with the option to explore it further.

Try the two links above with the same clinical problem and see how each supports a different part of finding and understanding the evidence.

We recently received some thoughtful, and slightly concerning, feedback about AskTrip’s answer-confidence display.

A clinician asked about radiation therapy for osteoarthritis. AskTrip’s Clinical Bottom Line was cautious:

Limited and indirect evidence exists regarding the use of radiation therapy for osteoarthritis, particularly in the shoulder, suggesting it remains investigational rather than mainstream treatment.

Alongside this, however, the answer-confidence graphic displayed a green box labelled “Good.”

The clinician and a medical student initially interpreted the green as indicating that AskTrip was more supportive of radiation therapy than another evidence tool they were comparing it with. It took them a little while to realise that the green referred to confidence in AskTrip’s cautious answer, not support for the intervention itself.

This raises an interesting design problem. Most of us have learned to interpret green as “go,” “positive” or “recommended.” Even when the accompanying labels say something different, that immediate visual impression may dominate, particularly when someone is scanning an answer quickly.

We are therefore wondering whether our confidence graphic is communicating what we intended. Would a neutral colour work better? Should “Answer Confidence” become “Confidence in this evidence summary”? Or should the evidence base and answer quality be presented separately without an overall green rating?

We would be interested to hear from other AskTrip users: does the current display make sense to you, or could you also interpret green as endorsing the treatment?