Using AI to Prepare for a Clinical Trial Conversation After a Medulloblastoma Diagnosis

In my role as a Research Support Coordinator, with a background in nursing and clinical trials, much of my work has focused on helping make complex clinical information more accessible.

One of the most consistent challenges I see is how much information families are given early in the process, and how complex that information can be. In diseases like medulloblastoma, conversations about treatment and clinical trials often happen quickly, and they involve terminology and details that are difficult to process in real time.

These conversations often require families to take in and process a significant amount of information in a short period of time, which can make it difficult to fully process information in the moment. For that reason, reviewing and organizing information before discussing clinical trial options can make these discussions more manageable.

While AI is not a clinical tool and should never guide medical decision making, it can serve as a useful way to prepare for these discussions, particularly when clinical trials are part of the conversation.

Making Clinical Trial Information More Accessible

Clinical trial protocols are written for scientific accuracy, not necessarily for clarity. Even for those with a medical background, they can take time to interpret. This is often the case when reviewing trial listings on sites such as ClinicalTrials.gov, where the level of detail can feel overwhelming.

AI can help translate that information into more accessible language. Reviewing a trial description in advance and asking for a plain language summary can provide a clearer understanding of the study’s purpose, eligibility criteria, and what participation may involve.

This does not replace the conversation with the care team, but it can make that conversation easier to follow and more productive. It can also help clarify common terms that come up quickly, such as what distinguishes a Phase 1 trial from later phase studies, or how eligibility criteria are applied in practice.

A Personal Example

I saw the value of this kind of preparation more clearly during a recent experience with my own family.

My father had been living with myelodysplastic syndrome (MDS) for several years when his care team reached a point where they wanted to discuss clinical trial options. We received a call asking us to come into clinic, and based on that conversation, I suspected they already had a specific trial in mind.

The night before the appointment, I used AI to review clinical trial options for myelodysplastic syndrome. I identified one trial that seemed likely to be the one they would present, and I spent time reviewing its design and eligibility criteria. I also looked more broadly at emerging treatment approaches to better understand the landscape.

One detail that stood out was that significant cardiovascular history was listed as a potential exclusion criterion, which was particularly relevant given my father’s medical history. 

When we arrived at the clinic the next day, the physician, fellow, and research nurse came in with consent materials for that exact trial. Because I had already reviewed the information, I was able to ask more focused questions in the moment. We discussed whether my father’s cardiovascular history might affect eligibility, and how participating in this trial could influence access to future options that were still in development.

That preparation did not change the role of the clinical team, and it did not determine the outcome of the conversation. It did, however, allow me to engage more directly, ask more specific questions, and better understand the discussion as it was happening.

Applying This to Medulloblastoma Clinical Trial Conversations

A similar approach can be helpful when preparing for clinical trial discussions in medulloblastoma. Reviewing trial information in advance, whether from a physician, ClinicalTrials.gov, or a trusted organization, provides a starting point. Using AI to translate that information, summarize key elements, or generate potential questions can reduce the amount of information that needs to be processed during the appointment. 

Instead of trying to absorb everything in real time, you are entering the conversation with a framework already in place. This often leads to more focused discussions around topics that matter most, including eligibility, logistics, potential risks, and how a trial may fit within the broader treatment plan.

Using AI as New Information Becomes Available

Another important aspect of clinical trial discussions is that they can change over time. Early conversations are often based on the information available at diagnosis. As additional diagnostic data is gathered, such as biopsy results or molecular and genomic analysis, the set of potential clinical trial options may shift.

This is an area where AI can be particularly useful, not for interpreting results, but for helping families recognize what questions to ask as new information becomes available.

For example, a family reviewing a clinical trial may notice that eligibility depends on a specific molecular feature. Using AI to better understand that requirement can help clarify what that marker means and how it is typically identified.

That understanding can then lead to more informed questions for the care team. Families may ask whether that type of testing has already been performed, whether it is recommended, or whether additional procedures such as biopsy or lumbar puncture could provide information that might influence trial eligibility.

In this way, AI can help surface questions that might not otherwise come up, especially in situations where the relevance of certain tests is not immediately clear.

AI can also help families revisit and organize information as new results become available, and prepare for follow up discussions with the clinical team. This highlights an important point. Clinical trial decisions are not always made at once, but often evolve as more information becomes available.

Using AI Within Its Limits

As useful as this approach can be, it is important to be clear about its limitations.

AI does not have access to an individual patient’s full clinical picture. It cannot interpret imaging, evaluate risk in a personalized way, or determine the most appropriate treatment option. It may also present information that is incomplete or lacks important context. In some cases, AI may also provide information that is incorrect or not fully aligned with clinical practice. 

For these reasons, it is best used as a preparation tool, not as a source of medical guidance. Any questions, concerns, or conclusions that come from using AI should be brought back to the clinical team. Those conversations remain central to decision making.

Supporting More Focused, Informed Conversations

The goal of using AI in this setting is not to replace expertise, but to make it easier to engage with it.

Clinical trial discussions are complex and often take place under difficult circumstances. Having the opportunity to review information ahead of time, organize questions, and clarify terminology can make those conversations more manageable.

In my experience, preparation improves the quality of the discussion. It allows for clearer questions, stronger understanding, and a more collaborative exchange between families and their care teams. While no tool can simplify these decisions, having a way to prepare can help families approach these conversations with greater clarity and confidence.

Rachel Chon is the Research Support Coordinator with The Cure Starts Now, with a background in nursing and clinical trials. Her work focuses on helping families navigate clinical trial information and understand research options as they make care decisions.