Trip Database Blog

Vector search is becoming increasingly prominent. At Trip we’re exploring its use and – in the spirit of transparency – we wish to share insights into what it is and how it differs from keyword/lexical search! And, to be clear, we’re at the start of the journey…!

From Keywords to Concepts: How Vector Search Is Changing Information Retrieval

For decades, information retrieval has been built on keyword search — matching the words in a user’s query to the same words in documents. It’s the logic behind databases, search engines, and Boolean queries, and it has served information specialists well, particularly when controlled vocabularies like MeSH are used.

But language is slippery. Two people can describe the same idea in very different ways — “heart attack” vs. “myocardial infarction,” “blood sugar” vs. “glucose.” Keyword search struggles when users and authors use different terms for the same concept.

That’s where vector search comes in — a new approach that focuses on meaning rather than exact wording.

What Is Vector Search? (An Intuitive Explanation)

At its core, vector search represents meaning mathematically.
Instead of treating text as a bag of words, it converts language into numbers that capture relationships between concepts.

This transformation happens in three main steps.

---

1. Text to Vectors — Turning Language into Numbers

The starting point is a language model — a type of AI system trained on vast amounts of text (for example, research papers, books, and web content). During training, the model learns how words appear together and in what contexts. Over time, it builds a kind of map of language, where meanings cluster naturally.

Here’s how this works in practice:

• Words that often appear in similar contexts, such as doctor and physician, end up close together in this semantic map.
• Words that rarely co-occur or belong to very different contexts, like insulin and wheelchair, are far apart.

When text is processed by the model, each sentence or paragraph is represented as a vector — a list of numbers indicating its position in this high-dimensional space.
For instance:

• “High blood pressure” → [0.13, -0.45, 0.77, …]
• “Hypertension” → [0.12, -0.47, 0.75, …]

These numbers are coordinates on hundreds of “meaning axes” that the model has learned automatically. While humans can’t easily interpret each axis, together they capture how phrases relate semantically to everything else in the model’s training data.

You can think of these dimensions as encoding things like:

• Whether the phrase is medical or general
• Whether it describes a disease, treatment, or symptom
• Its relationships to concepts such as “cardiovascular” or “chronic condition”

If two texts have vectors that are close together, it means the model recognises that they have similar meanings.

So:

• “High blood pressure” and “hypertension” → almost identical
• “High blood pressure” and “low blood pressure” → related but opposites
• “High blood pressure” and “migraine” → far apart

This process — called embedding — is how modern AI systems move from words to concepts.

---

2. Measuring Similarity

When a user searches, their query is also converted into a vector. The system then compares that query vector to every document (or passage) vector in its database using a measure of semantic closeness, often called cosine similarity.

The closer two vectors are, the more related their meanings. This allows vector search to identify results that discuss the same idea even when the words are completely different.

For example, a query about “lowering blood pressure without medication” might retrieve:

• Trials on “lifestyle modification for hypertension”
• Reviews of “dietary sodium reduction”
• Cohort studies on “exercise and cardiovascular risk”

— even if the exact phrase “lowering blood pressure without medication” doesn’t appear in any of those documents.

---

3. Returning Results

Instead of relying on literal matches, vector search retrieves the documents (or parts of documents) closest in meaning to the user’s query.

In contrast:

• Keyword search finds what you said.
• Vector search finds what you meant.

How It Differs from Keyword Search

Feature	Keyword Search	Vector Search
Basis	Exact word matching	Conceptual similarity
Strengths	Transparent, precise, good for controlled vocabularies	Finds semantically related content, handles synonyms and context
Weaknesses	Misses relevant material with different wording	May surface loosely related material if not tuned carefully
Good for	Narrow, well-defined, reproducible queries	Exploratory or question-based searching

Many systems now use hybrid search, combining keyword and vector methods. Keywords help with precision and reproducibility; vectors help with recall and conceptual understanding.

---

Why It Matters for Information Specialists

For information professionals, vector search introduces both power and complexity.
It enables:

• Retrieval of semantically related evidence, even when vocabulary differs.
• More natural-language searching — closer to how users think and ask questions.
• The foundation for AI-driven Q&A tools, where the system retrieves and synthesises the most relevant evidence rather than just listing papers.

But it also brings new challenges:

• Relevance can be fuzzier and harder to explain.
• Transparency and reproducibility — essential in evidence-based work — need careful handling.
• Understanding how a system defines “similarity” becomes as crucial as knowing how it handles Boolean logic or MeSH terms.

---

The Bottom Line

Vector search doesn’t replace traditional methods — it expands them.
It’s a bridge between human language and machine understanding.

In short:

Keyword search finds the words. Vector search finds the meaning.

Together, they represent the next chapter in evidence discovery and retrieval — one that blends linguistic nuance, AI, and the information specialist’s craft.

We have just rolled out a batch of improvements to AskTrip, with three main changes:

• Medicines information
• Answer consistency
• Improving the efficiency of Beyond Trip

Medicines Information

Previously answers about medicines (e.g. side effects, dose etc) relied on the reports in the research literature. This was fine, to a point, but we realised dedicated information was required. So, now, if we receive a question about medicines we include the relevant content from the DailyMed and openFDA. Both are great medicine resources.

Answer consistency

AI can be a bit inconsistent at times (it’s described as being non-deterministic) and this can manifest itself by giving slightly different answers and using different references for the same or very similar questions. Typically, these differences are small – often just nuances – but they can still feel a bit unsettling! So, we’ve introduced something we call reference stripping. In essence, when we receive a question that’s very similar to a previous Q&A, we ensure the new answer takes the earlier references into account, boosting consistency across responses.

Improving the efficiency of Beyond Trip

Beyond Trip was proving quite expensive to run, so we needed to find ways to reduce costs. Previously, the system reviewed all of the top search results we found. But we soon realised that “top” didn’t always mean relevant. Many results near the top of the list weren’t particularly useful for the actual query.

To fix this, we introduced an extra step to exclude results that are likely to be irrelevant. The remaining results are then reviewed sequentially until we’ve gathered enough evidence for a solid answer. This approach reduces costs and brings a small but welcome speed boost.

Clinical questions frequently form natural clusters – variations on a theme that together reveal a richer, more connected picture of evidence. For example, questions about TSH and lifestyle might include sleep, exercise, diet, stress, and psychosocial factors – each distinct, yet interrelated.

One approach we’re exploring to capture these connections is cluster reviews – analyses that group related clinical questions to uncover overarching patterns in evidence and practice. These reviews would take a bottom-up approach, grounded in real clinical questions asked by health professionals. Unlike traditional top-down reviews that begin with predefined topics or published frameworks, cluster reviews are shaped by the real-world information needs that emerge in clinical settings, offering a practice-driven view of the evidence landscape.

We’re experimenting with an interactive cluster review that brings these related Q&As together into a single, navigable experience. It allows clinicians, researchers, and learners to see how different lifestyle and psychosocial factors intersect, and to identify where evidence is thin or emerging.

The goal is to make evidence engagement interactive, modular, and cumulative – each review builds on previous answers, creating a living, evolving knowledge map rather than static summaries.

You can explore the first prototype, Lifestyle, Psychosocial, and Behavioral Influences on TSH Levels, through the interactive review – and we welcome your feedback on how this could best support your evidence needs. And, to be clear, this is a simple prototype, if we go ahead with this we would work hard to make the design wonderful 🙂

CLICK HERE TO EXPLORE

If you have any specific comments, such as how to improve this, please leave a comment or email me jon.brassey@tripdatabase.com

AskTrip has just reached a remarkable milestone – 5,000 clinical questions answered in under 20 weeks. On its own, that’s an impressive figure. But the real story lies in the contrast with our early work and what this achievement represents for evidence-based healthcare.

From Manual Q&A to the Digital Frontier

Back in 1997, we launched ATTRACT, one of the world’s first evidence-based Q&A services for clinicians. It was followed by the National Library for Health Q&A service – both pioneering efforts, the latter ran until around 2012.

Across those 15 years, our teams of information specialists and clinicians answered around 10,000 clinical questions. Each one required 4–6 hours of careful searching, appraisal, and synthesis – a manual, time-intensive process, but one that had a huge impact on clinical decision-making.

Those services were driven by a simple belief: that busy clinicians should have quick, trusted access to the best available evidence to inform patient care. That belief remains unchanged today.

Trip’s Core Mission: Connecting Clinicians with Evidence

The Trip Database was originally created to support the work of ATTRACT, providing rapid access to high-quality evidence for the team answering clinical questions. Over time, it became clear that Trip could serve a much wider audience – helping clinicians everywhere find reliable evidence efficiently.

From those early days, Trip has always been about one thing: connecting clinical decision-makers with the best available evidence.

Over the years, it has evolved from a focused evidence search tool into a comprehensive evidence ecosystem, helping millions of users around the world find trustworthy answers faster. AskTrip is the latest, and perhaps most exciting, chapter in that ongoing story.

AskTrip: A Natural Extension of Trip’s Mission

AskTrip builds directly on Trip’s foundations but uses a radically different interface – natural language. Clinicians can now simply type a question such as “What’s the best treatment for resistant hypertension in pregnancy?” and receive a clear, concise, evidence-based summary in seconds.

What previously took hours or days of searching can now be achieved almost instantly. Yet the principles that underpin AskTrip are the same as ever: reliability, transparency, and a commitment to evidence, not opinion.

AskTrip doesn’t replace human judgment or the careful reading of full studies – it amplifies access to trusted information when it’s needed most.

A Shift in Scale

The numbers tell the story:

• 10,000 Q&As in 15 years through manual services like ATTRACT and the NLH Q&A service.
• 5,000 Q&As in less than 20 weeks through AskTrip.

That’s not just efficiency – it’s accessibility at scale. Thousands of clinicians have been able to get quick, high-quality answers to their clinical questions, helping improve decision-making in real-world settings.

Looking Ahead

This milestone is more than a statistic; it’s a reflection of how far evidence-based medicine has come – and how technology can help accelerate it without compromising quality.

AskTrip represents the next step in a journey that began nearly three decades ago. The tools may have changed, but the mission remains constant: to connect clinical decision-makers with the best available evidence, as quickly and clearly as possible.

We’re incredibly proud of how far we’ve come – and even more excited about what lies ahead.

We’re excited to share an important update to AskTrip – not quite a version 2, but definitely a strong v1.5. This upgrade builds on what’s working well, while tackling some of the challenges we’ve seen since launch. The result: better answers, more trustworthy evidence, and less noise.

What’s New?

1. More Evidence, More Coverage

AskTrip now considers a wider pool of articles when building answers. This means you’ll benefit from a broader sweep of relevant studies, ensuring that useful evidence doesn’t get missed.

2. Smarter Evidence Extraction

We’ve upgraded both the prompts and the large language model behind AskTrip. These improvements sharpen how the system extracts evidence from research, cutting through complexity to surface the insights that matter.

The payoff? More accurate answers and fewer hallucinations.

3. Improved Quality Scoring

Our enhanced quality score system better balances study design, recency, and relevance. That means you’ll see more reliable evidence, ranked in a way that helps you judge its strength quickly and confidently.

4. Beyond Trip: Smarter Sourcing

Sometimes the evidence available in Trip isn’t enough. With this update, AskTrip automatically extends the search to Google Scholar and OpenAlex when needed – giving you access to a wider world of research without leaving the platform.

Why This Matters

Every improvement we make to AskTrip is guided by one principle: helping health professionals make faster, better-informed decisions. With v1.5, you’ll get answers that are broader in scope, more accurate, and underpinned by higher-quality evidence.

We’ll continue refining AskTrip in response to your feedback, so please keep letting us know what works and where we can improve.

En AskTrip, nuestro objetivo es hacer que la evidencia de alta calidad sea accesible para los profesionales de la salud en todo el mundo, sin importar el idioma. Para nuestros usuarios hispanohablantes, esto significa que traducimos su pregunta al inglés, la procesamos en el sistema de AskTrip y luego traducimos la respuesta nuevamente al español.

Recientemente descubrimos un problema en la forma en que se gestionaban las preguntas en español dentro de AskTrip. Esto ocasionaba dos situaciones principales:

1. La pregunta aparecía en español, pero la respuesta se mostraba en inglés.
2. Tanto la pregunta como la respuesta aparecían en español, pero los términos de búsqueda también se procesaban en español.

El segundo caso era especialmente problemático. Dado que la base de evidencia de Trip está en inglés, realizar búsquedas en español devolvía pocos resultados o, en muchos casos, resultados de muy baja calidad.

Durante el fin de semana implementamos una solución y, desde entonces, no hemos detectado más casos de este problema. Confiamos en que ha quedado resuelto.

Queremos disculparnos sinceramente con nuestros usuarios de habla hispana por esta incidencia. A partir de ahora, deberían notar una clara mejora en la calidad y coherencia de su experiencia en AskTrip.

English Translation: An Apology to Our Spanish-Language Users of AskTrip

At AskTrip, we aim to make high-quality evidence accessible to health professionals worldwide, regardless of language. For our Spanish-speaking users, this means we translate your question into English, process it through the AskTrip system, and then translate the answer back into Spanish.

Recently, we discovered an issue in how Spanish questions were handled within AskTrip. This led to two main problems:

1. The question appeared in Spanish, but the answer was displayed in English.
2. Both the question and the answer were in Spanish, but the search terms were also processed in Spanish.

The second issue was especially problematic. Since Trip’s evidence base is in English, running searches in Spanish returned little – or in many cases, poor – results.

We implemented a fix over the weekend, and since then we’ve seen no further cases of the problem. We’re confident it’s resolved.

We sincerely apologise to our Spanish-language users for this disruption. From now on, you should notice a clear improvement in the quality and consistency of your AskTrip experience.

Sometimes the best answer isn’t within Trip’s core collection. That’s why we’ve introduced Beyond Trip, a new feature designed to broaden the search and deliver stronger, more reliable answers when evidence is limited.

How It Works

Beyond Trip is automatically triggered when AskTrip produces an answer that’s judged to be poor:

• Limited answers, or
• Moderate answers with three or fewer references.

When this happens, AskTrip seamlessly expands the search to Google Scholar and OpenAlex, scanning the wider research landscape for additional evidence.

You don’t need to take any action – the process happens automatically. It adds about 20–30 seconds to generating the answer.

What You’ll See

New answers created through this process are clearly labelled as having used Beyond Trip.

Two outcomes are possible:

1. A stronger answer: If new evidence is found, the revised response will be presented with its expanded reference base. You’ll see a note confirming that the answer has utilised Beyond Trip.
2. A genuine evidence gap: If evidence remains poor, we’ll highlight that even after Beyond Trip, good-quality evidence could not be found. In these cases, we’ll offer five broader or related searches you can try, helping you explore areas where stronger evidence may exist.

Why It Matters

In testing, results have ranged from no change (confirming a genuine lack of evidence) to major improvements – for example, an answer going from zero references in the original output to six references after Beyond Trip.

By intelligently expanding the search only when needed, Beyond Trip ensures you’re not just getting an answer – you’re getting the best possible evidence available.

A nursing friend recently asked me about the types of questions we’re receiving from nurses via AskTrip. Since we don’t record the profession of everyone who submits a question, I can’t say exactly what nurses are asking. What I could do, however, was analyse the 40 questions that directly focused on nursing – a reasonable sample to identify patterns. And 4 themes emerged:

Clinical Practice & Patient Care
This theme captures the heart of nursing – the direct application of skill and evidence to improve patient outcomes. The questions reveal a profession dedicated to continuous quality improvement and safety, seeking out evidence-based practices (EBP) in everything from preventing infections like CLABSIs to the simple act of bathing in a nursing home. There is a strong focus on highly specialised areas (e.g., managing chest drains in neonates after cardiac surgery, providing palliative care education), and a push to empower patients, such as assessing the competence of diabetic patients to self-manage. Ultimately, this theme is about defining and standardising the best possible care across all clinical settings, from the Emergency Department (ED) to the community.

Example questions:

• What are some nurse-driven evidence-based projects by nurses?
• How can nurses care for and manage chest drains in babies following cardiac surgery?

Nursing Roles & Specialisation
Nursing is no longer a one-size-fits-all profession! These questions underscore the dramatic specialisation and diversification occurring within the field. From comparing the functions of a State Diploma Coordinator Nurse versus an Advanced Practice Nurse (APN) in oncology, to understanding the implementation experiences of APNs, nurses are constantly negotiating their scope of practice. The demand for specialist roles – like the Frailty Nurse Specialist who optimises patient flow, or the Head and Neck Cancer Nurse Specialist – shows that hospitals rely on nurses to manage complex patient pathways and drive efficient, coordinated care. This theme explores how nurses are elevating their professional role to meet sophisticated healthcare demands.

Example questions:

• What are the roles or functions of a State Diploma Coordinator Nurse versus an Advanced Practice Nurse in oncology?
• What is the role of a frailty nurse specialist in front-door assessment, admission avoidance, safe discharge planning, and the implementation of least restrictive options in acute care settings?

Education & Professional Development
This grouping dives into how the next generation of nurses is trained, supported, and nurtured. It’s not just about skills; there is a deep academic interest in how nurses acquire professional virtues – the ethical and moral compass – which is fundamental to the profession. Practically, the questions stress the importance of effective teaching and mentorship, focusing on tools like preceptor feedback instruments to improve communication on placement and the use of ePortfolios to support student learning. Whether it’s through innovative continuous professional development (CPD) methods like “Tea-Trolley Teaching” or formalised annual competencies, this theme highlights the commitment to ensuring all nurses remain highly skilled and ethically grounded throughout their careers.

Example questions:

• How do nurses acquire, develop, or learn virtues for practice?
• Are there preceptor feedback tools that facilitate communication between preceptors and preceptees to improve nursing academic outcomes?

Workforce, Organisation & Policy
The final theme addresses the crucial, high-level issues impacting the sustainability and health of the nursing workforce. Questions here center on policy and operational efficiency, including the search for safe staffing ratios and frameworks, particularly in high-demand areas like the ED. The profession is actively tackling burnout and retention by seeking organisational interventions to support new nurses. Furthermore, the interest in creating nursing float pools speaks to the need for flexible, effective staffing solutions. This theme encompasses the external factors that influence the profession, including the impact of social media portrayal on public perception and recruitment, making it a critical area for leadership and policy reform.

Example questions:

• What is the evidence base for safe nursing staffing in emergency departments internationally?
• What organisational interventions have been used to reduce burnout and increase retention in new nurses?

Taken together, these 40 questions paint a picture of a profession that is dynamic, diverse, and deeply committed to improvement. Nurses are seeking evidence not only to refine clinical practice at the bedside, but also to expand their roles, strengthen education and professional development, and influence the policies that shape their working lives. The themes suggest a workforce that is both responsive to today’s challenges and actively shaping the future of healthcare.

With nearly 3,700 questions answered, we’ve gained a wealth of learning. From the very beginning, we’ve closely tracked both the questions and the answers, giving us valuable insights into the system’s strengths and areas for improvement.

Behind the scenes, we’ve been working on a major upgrade (our “v2”), which is now in testing. The key enhancements include:

• Improved search: A new approach that strengthens the link between a user’s question and the articles we identify, ensuring more relevant candidates are surfaced.
• Greater coverage: A more sensitive system that draws on a wider range of articles identified through the improved search.
• Reduced hallucinations: Specific safeguards to minimise inaccurate or invented content.
• Beyond Trip: If evidence is scarce in Trip, the search will automatically expand into the broader academic literature [learn more here].
• Answer scoring: A more refined and nuanced way of rating responses.

Each of these features has been tested individually, and we’ll soon begin testing them together as an integrated system. We’re optimistic these changes will deliver a step change in performance.

And, a final comment, we’re already working on v2.1…