No, PubMed does not search in full-text search. If you want to search full-text you should go to PubMed Central or PapersHive.

In pharmacovigilance and drug related activities, your focus should be on comprehensiveness and inclusion criteria rather than a relevant top ten of results that cannot be explained.

1. Filter by industry and academia 2. Filter by phases. 3. Filter by MeSH.

1. Incorrect use of Boolean operators 2. Lack of parenthesis 3. Lack of morphological variations 4. Missing MeSH terms 5. Non-proper MeSH tags 6. Miss synonyms

When performing a medical literature review you should use PubMed or PapersHive. Use Google Scholar for lookup searches and quick explorations.

A study analyzed PubMed’s log data and identified differences between expert and non expert users. To become better at PubMed you should start using MeSH terms, Advanced Search, use the search functions, field-tags and domain knowledge. These alone would put you to the top 6%.

The first part in building a Reference Manager is the Import. This phase focuses on taking a user input and transforming it into a list of pre-references.

There is no such thing as the best Medical Search Engine. Though we have started noticing patterns when it comes to which area or need each medical professional has. And the best engine associated to it!

PubMed left TF-IDF and started using BestMatch: a two-stages ranking system based on BM25 to gather the first batch of documents, and a Learning-to-Rank model to re-rank the top 500.

When performing a Systematic Literature Review, 56.9% of the initial data could be duplicated. This could cost a bioresearch and pharma company from €224 for an employee to €1,000 per contractor for each screening activity. And well beyond €10k when performing SLR. Unless you have it automated.

You might wonder when is automation useful in your Life Science pipeline for automated screening. In a price-per-seat model, that is €875 divided by the wanted ROI. In an Enterprise model it is up to the number of scientists.

AI on Adverse Effects is usually trained on annotated data. Making it resource and capital intensive. What if we benchmark with models trained on source documents instead?

Your team can shrink a week of manual work in just a few hours. By iterating with 7 of our core customers, we identified 4 steps that could easily automated when performing Pharmacovigilance and Clinical / Monitoring processes thanks to AI and RPA.

We asked 116 medical professionals which search engine they use and for which task. Google was not on the top for medical related activities due to explainability, transparency and privacy.