New Ways to Search PubMed Central (PMC) 

To make the most of the full text that’s available in PubMed Central (PMC), its search was recently updated!

For those new to this resource, PMC is a free full-text archive of biomedical and life sciences journal literature hosted by the National Library of Medicine (NLM). While PMC is a part of PubMed, and your searches in PubMed will undoubtedly show you some PMC results, not everything in PubMed will have full text immediately available to you. Starting your search directly in the PMC search interface means you’ll only get full-text PMC results.

PMC’s new search lets you harness that full text in new ways. To learn about everything new or updated, or how to use PMC, explore the PMC User Guide.

The new features I’m most excited about are:

  1. The ability to use proximity searching (also known as adjacency searching) within 14 different fields of a record. An example of this is “cancer pain”[ti:~1]. The double quotation marks and the information within the square brackets will pull in any record where cancer and pain are adjacent to each other by one or less terms in its title. It will bring in the phrases “cancer pain” as well as “pain of cancer.”
  2. Updated truncation searching that allows for unlimited variations of a term, instead of only the first 600 variations. An example of this is intervention*[tiab]. The asterisk and the information within the square brackets will pull in any record where a term that starts with intervention appears in its title or abstract. It will bring in the terms intervention, interventions, and interventional.
  3. The search field tag of [body] to search the full text of a record, meaning it searches all words and numbers in the body of an article, but not the abstract or references. An example of this is coping skill*[body]. The asterisk and the information within the square brackets will pull in any record where a phrase that starts with “coping skill” appears in its body. It will bring in the phrases “coping skill” as well as “coping skills.”

Below is an example of a search that showcases the new features I listed above, each connected with the Boolean AND. You can copy and paste this into the PMC search bar or just click on the hyperlink to be taken to a list of results.

“cancer pain”[ti:~1] AND intervention*[tiab] AND coping skill*[body]

While I’ve been enjoying the new PMC search, two things to note:

  1. A missing search feature requires your feedback.
  2. The federal government shutdown means you can’t give feedback.

There’s been some library listserv discussion about what was lost when PMC made the search switch, such as not being able to combine search strings or select a filter for language.

PMC Beta Search was introduced in April 2025 to give users a preview of the new search that went live in September 2025. Digging into recent PMC search announcements, there was subtle mention that some features would no longer be available once PMC Beta Search became the default. An August 2025 announcement built on an earlier April 2025 announcement and included the line “Some features of the current PMC search will not be included in this initial release.”

A notice on the PMC User Guide, included as a screenshot below, includes the line “the new PMC search represents a minimum-viable-product (MVP) approach.” The surrounding text implies a decision was made to deliver this new search experience with a focus on speed and not perfection, and that more search features could be coming based on user feedback.

Screenshot of the notice from the PMC User Guide. Its title is "September 2025 - PMC Search Functionality and User Experience Updated." The body of the notice is "In order to provide users with the benefits of a new search on a reasonable timeline, the new PMC search represents a minimum-viable-product (MVP) approach. NLM is committed to continued PubMed Central development, including iteratively adding functions and improving the system based on user needs and feedback to ensure that PMC remains a trusted and accessible source of biomedical literature today and in the future. For more information about this update, please see NCBI Insights: New PMC Search."

Taken as a whole, you can see that anything you think is missing from PMC search needs your input in order to be known and prioritized. The two announcements and notice all recommend reaching out to the NLM Help Desk with feedback.

However, October 1 was the first day of the ongoing federal government shutdown. The NLM Help Desk and PMC are government-run, and consequently, no suggestions to improve PMC search can be received or implemented at this time.

But we MSK librarians are here! If at any time you have questions about PMC or searching in general, please reach out.

MSK Chatbots Can’t Perform a Literature Search

MSK now offers employees access to Open WebUI, a source for several chatbots available for workplace use. But if you think this tool can be used for searching the literature, think again.

What is Open WebUI and How Do I Access It?

This portal is “a proprietary, user-friendly, and PHI-secure portal where staff can access a wide array of popular large language models (LLMs) as well as tools for experienced developers behind the MSK firewall.”

To access:

  1. Log on to the VPN or be onsite
  2. Visit https://chat.aicopilot.aws.mskcc.org/
  3. Select “Continue with MSK PingID” if prompted
  4. You’ll then get the message “Account Activation Pending” followed by “Contact Admin for WebUI Access.”

No further action is needed and contacting admin isn’t necessary. You will not get confirmation once your account has been activated. But once it has, visiting the URL while onsite or on the VPN will take you to the tools.

Open WebUI includes the following chatbots:

Chatbot Description
Amazon Nova Pro A reasoning model for general analysis and summarization. Knowledge cutoff date: Unknown
Claude Sonnet 3.5 A general-use model by Anthropic. Effective with code generation. Knowledge cutoff date: April 15th, 2024
Claude Sonnet 3.7 Improved version of Sonnet 3.5, and also targets code generation as a differentiator. Knowledge cutoff date: October 2024
Claude Sonnet 4 High intelligence and balanced performance. Good for complex coding/debugging, detailed explanations, and documentation review. Detailed prompts recommended. Knowledge cutoff date: January 2024
DeepSeek R1 A reasoning model for logical inference, math problem-solving, code generation, or text-based clinical reasoning. Cannot process images. Knowledge cutoff date: October 2023
OpenAI o1 A reasoning model that thinks before it answers, making it suitable for deep analysis, task breakdown, or image-based clinical analysis. Knowledge cutoff date: October 2023
OpenAI GPT-4o A general-purpose model that balances quality, speed, and cost-effectiveness. Knowledge cutoff date: October 2023

You can toggle between tools on the top left of the page and click the “set as default” option under a tool name after you’ve selected it.

Why Can’t I Use These Tools to Perform a Literature Search?

When you ask Amazon Nova Pro to perform a literature search, it appears to do so:

A screenshot of Amazon Nova Pro appearing to summarize the literature in response to a prompt.

However, a follow-up question reveals that all is not as it seems, and that any citations provided are likely not real:

Amazon Nova Pro answering a prompt asking if it searched databases to come up with its answer. It says it did not.

Other tools are clearer about their limitations from the start:

OpenAI o1 saying it does not have database access and giving advice on how to search.
Claude Sonnet 3.7 saying it does not have database access and recommending speaking to a librarian.

What Should I Do Instead?

There are AI tools that specialize in searching the literature, but even these are typically limited to open-source texts. Use these tools cautiously, perhaps in the brainstorming and planning stages of a project.

As an alternative, we welcome you to contact us to request a literature search.

Want to learn more about the use of AI for literature searching? Sign up for our next class on August 19 from 12-1 pm.

How To Search for a Phrase in PubMed

Searching for phrases in PubMed can be an exercise in frustration. To understand why, we need to look at how PubMed interprets your search, a process that is now described in detail in a new training module from the National Library of Medicine.

When you enter a phrase into PubMed without using quotation marks, the database does several things:

  1. Looks for the phrase as a subject heading, or MeSH, term. Subject headings have been preselected by the database and are assigned to each citation on a topic.
  2. Breaks apart the phrase and looks for each word separately.
  3. Looks for the phrase, if recognized.
A graphic describing how PubMed Searches for a phrase.

How PubMed searches for a phrase. From the National Library of Medicine.

Sometimes, this process brings back the results you need. But it can also lead to search results that do not match your topic.

What happens when you search using quotation marks?

  • Instead of looking for matching subject headings, PubMed checks for the phrase in its phrase index, a list drawn from the literature included in the database.
  • Not every phrase is included in the phrase index. If your phrase is not found, PubMed may ignore your quotation marks and follow the search steps above, bringing in irrelevant results.
  • You can see how many results include your phrase from the advanced search page. Start typing your term, then click “Show index” to the right of the search box.
A screenshot showing how to check if a phrase is included in PubMed's phrase index.

Use the “Check index” button on the advanced search page to see if your phrase is included in PubMed’s Phrase index. From the National Library of Medicine.

Fortunately, there is a workaround if your phrase is not found. You can recommend the addition of phrases to PubMed. You can try searching for the phrase in different databases,  most of which are much more user-friendly when phrase searching. You can also try searching for the phrase in PubMed using adjacency.

For example, “Adult Non-Verbal Pain Scale” is not a phrase PubMed recognizes. Have PubMed look for the phrase with all words next to each other, in any order, by telling it to look in the title and abstract fields (tiab) with the words adjacent to each other (:~0):

The PubMed advanced search page showing the difference in results using quotation marks and proximity searching for a phrase.

Using proximity searching ([tiab:~0]) when a phrase is not included in PubMed’s phrase index can lead to more focused results compared to using quotation marks alone.

For more search help, or to request a literature search, contact the Library.