Make the reasoning easier to inspect
An evidence review has a job to do: help a responsible person decide what deserves action, which alternatives matter and what needs further investigation. Its value lies in how well another person can examine the reasoning.
NEUVIOR’s evidence-review direction within PHARMORIS focuses on that work. We are developing an approach that connects the question, relevant sources, professional challenge and the decision that follows. The aim is to make an important review more useful across medicines organisations.
In the conversation.
NEUVIOR and our founder’s perspectives have appeared across science, business and technology publications.
Reporting, commentary, letters and podcast appearances | Read each feature for its format and source.
A clear question gives the review a purpose
A hospital medicines team may be considering a generic opportunity. A pharmacy group may be examining the case for a service. An industry team may need to understand the evidence behind an implementation barrier. Each has a different decision to support.
Define the setting, the intended user and the consequence of getting the answer wrong. Agree which alternatives deserve comparison and what would count as relevant information. This helps a reviewer focus effort on the evidence that could change the decision, rather than accumulate material because it is available.
Return to the source when meaning matters
A statement can change as it moves through summaries. A study finding, a policy recommendation and an economic assumption may end up sounding equally certain when their original context has disappeared.
Our design aim is to keep important statements connected to the material behind them. A reviewer should be able to inspect the date, setting and limits, then decide how much weight the statement deserves. That connection also makes correction practical: the team can address the reasoning that needs to change, rather than rewrite an entire review without understanding why.
Resolve the uncertainty that changes the decision
A missing input, conflicting source and finding from a different setting are distinct problems. They call for different responses. A single confidence label may tell the reviewer very little about what to do next.
Make the uncertainty specific. Is another source needed? Would a local operational fact change the answer? Is an assumption too influential to leave untested? A useful review helps the team choose its next investigation, narrow the claim or leave a decision open with a clear reason. This can be valuable before any new intervention is introduced.
Connect the evidence to the working setting
A convincing recommendation still has to meet local conditions. Staff capacity, supply arrangements, existing policy and professional responsibilities may affect whether a proposed change is appropriate or practical.
For a community pharmacy, the review should recognise the people and time needed to deliver a service. For a provider medicines team, it should make the implementation requirements visible alongside the evidence. This allows clinical, operational and financial colleagues to examine the same case from their responsibilities, while keeping disagreements and unanswered questions clear.
A good source still needs the right question.
A study, specification and operational dataset can each contribute something different. Their value depends on whether the source addresses the decision in front of the reviewer.
Make that connection inspectable: what was studied, in which setting, with which comparison and limits? A finding can be useful without supporting every conclusion someone might want to draw from it.
Film source and contextStock sample-placement footage. Cell identity is unspecified; not a NEUVIOR experiment, tumour image or research result.
A public decision brief | An illustrative example
Open the question.
Inspect the reasoning.
Choose a business question, then look beneath its claim. See what a public source supports, what depends on the local setting and what a useful next step could be.
A medicines or implementation team considering an AI-supported evidence review.
Would a quicker review make the decision better?
The interesting question is the complete piece of work: finding relevant material, checking it, correcting the draft and reaching an accountable decision.
A proposition to investigate
Less preparation. The same ability to challenge.
An evidence-review approach could be useful if it reduces avoidable preparation while preserving source access, relevant qualifications and professional checking. That is the proposed value to test. No time reduction, accuracy improvement or customer result is asserted in this example.
The proposition is constructed for this public brief. It is not a published finding about PHARMORIS.
What the next brief would contain
A decision someone
can commission.
- The decision
- Whether one defined review task merits an agreed evaluation.
- The comparator
- The team's existing complete review process, including checking and corrections.
- The evidence
- Representative cases, source records, reviewer decisions, complete-task effort and exceptions.
- Stop or redesign
- Stop or redesign if source checking weakens, errors are unacceptable or the complete task offers insufficient value.
Constructed public example | Not PHARMORIS-generated software output or a measured customer result.
Keep this example briefMeasure the full professional effort
A faster first draft can create more checking later. An informative evaluation needs to consider preparation, source inspection, corrections and the work of resolving disagreements. The complete task is the meaningful comparison.
Our planned evidence-review evaluation would examine accuracy, relevance, completeness, material omissions and total reviewer effort against competent existing practice. Qualified judgement is central to that comparison. The result should identify where assistance earns its place, where it adds burden and which tasks need a different approach. It should also examine whether the output is understandable to the people asked to rely on it.
Make the result useful to the next person
The next reviewer needs to understand what was examined and why a conclusion was reached. Clear source context, a stated comparison and visible assumptions make a case easier to revisit as evidence or local circumstances change.
That is particularly valuable when work crosses organisations or moves from one team to another. The aim is continuity in the reasoning, with professional responsibility retained by the relevant people. An evaluation should test whether the record remains useful beyond its author and whether maintaining it is proportionate to the value it provides.
Bring a review worth improving
Tell us the medicines decision, the people who currently prepare and check the case, and where effort repeatedly accumulates. A useful starting task has a clear owner and a comparison the team considers meaningful.
We welcome organisations and reviewers who can help establish what a better evidence review would allow them to do. That gives a possible PHARMORIS evaluation a practical purpose.