Create your survey

Create your survey

Create your survey

How to use AI to analyze responses from patient survey about advance care planning

Adam Sabla - Image Avatar

Adam Sabla

·

Aug 21, 2025

Create your survey

This article will give you tips on how to analyze responses from a patient survey about advance care planning so you can get actionable insights quickly and confidently.

Choosing the right tools for survey response analysis

The approach you take—and the tools you use—depend on the type and structure of your collected data. If you have:

  • Quantitative data: Numbers like “how many patients selected option A” or “percentage aware of ACP” are straightforward to handle using familiar tools, such as Excel or Google Sheets. It’s simple tally work—count, filter, and chart your way to clear results.

  • Qualitative data: Anytime you collect open-ended responses or nuanced feedback, things get trickier. When you’re faced with dozens or hundreds of patient comments, it’s nearly impossible to read and digest everything efficiently. This is where AI tools come in—they can instantly surface patterns, summarize conversations, and help you understand the main themes at a glance.

There are two approaches for tooling when dealing with qualitative responses:

ChatGPT or similar GPT tool for AI analysis

Chat-based AI tools: If you export your survey data, you can copy it into ChatGPT (or a comparable tool) and chat about it directly. This works if the data set is small, but it’s a bit clunky. You’ll spend time cleaning data, pasting blocks of text, and managing context limits. If you want a specific analysis, you’ll have to provide all the context and good prompts manually.

Convenience and limitations: While generic tools like ChatGPT are powerful, they lack domain knowledge about how patient surveys are structured, and there’s no built-in support for filtering, segmenting, or summarizing responses tied to specific question types or follow-ups. Collaboration with your team also means you’re juggling files and copy-pasting outputs.

All-in-one tool like Specific

Purpose-built AI analysis: Platforms like Specific are designed just for surveys. They let you both collect conversational responses (including smart follow-up questions) and run AI-powered analysis as soon as results come in. The AI instantly summarizes responses, identifies key ideas, and turns everything into actionable takeaways—no spreadsheets, no manual grunt work.

Follow-up question advantage: As you build your AI survey, Specific can automatically ask dynamic follow-ups. That means higher-quality answers, richer insights, and less ambiguity—something especially valuable for sensitive topics like advance care planning. Learn more about this approach and its benefits in how automatic AI follow-ups work.

Chat with your data: With Specific, you chat about the results, just like with ChatGPT but with tools designed for survey analysis and healthcare topics. You also get advanced filtering, conversation management, and collaborative features to share insights with your team. Explore these capabilities in more detail with AI-powered survey analysis.

Useful prompts that you can use for analyzing patient survey data about advance care planning

Whether you’re using ChatGPT, Specific, or another AI tool, crafting the right prompts is key to getting smart analysis out of your patient advance care planning survey. Here are some proven prompts (and some tips to customize them) that work every time:

Prompt for core ideas: This prompt is great for surfacing major themes from a large set of patient responses. It’s built into Specific, but you can use it anywhere:

Your task is to extract core ideas in bold (4-5 words per core idea) + up to 2 sentence long explainer.

Output requirements:

- Avoid unnecessary details

- Specify how many people mentioned specific core idea (use numbers, not words), most mentioned on top

- no suggestions

- no indications

Example output:

1. **Core idea text:** explainer text

2. **Core idea text:** explainer text

3. **Core idea text:** explainer text

AI works best when you provide more context—such as your survey’s goal, who your patients are, or any special topics you care about. Here’s a simple addition to add context for your patient survey:

Act as a researcher reviewing a survey of adult patients from a community health clinic about their feelings, awareness, and concerns around advance care planning (ACP). We want to better understand their challenges, emotional barriers, and what support they wish they had. Now, extract core ideas as before.

Prompt for exploring a core theme: Once you’ve surfaced a key idea, follow up: “Tell me more about [core idea].” This helps you dig deeper into what’s behind patient responses, giving you a richer understanding of specific pain points or motivations.

Prompt for specific topics: If you want to check if patients talked about something specific (like “emotional barriers,” “family involvement,” or “legal concerns”), just say:

Did anyone talk about [topic]? Include quotes.

Prompt for pain points and challenges: To get a solid list of issues or frustrations, use:

Analyze the survey responses and list the most common pain points, frustrations, or challenges mentioned. Summarize each, and note any patterns or frequency of occurrence.

Prompt for sentiment analysis: Want a sense of overall mood and attitudes? Try:

Assess the overall sentiment expressed in the survey responses (e.g., positive, negative, neutral). Highlight key phrases or feedback that contribute to each sentiment category.

Prompt for personas: For audience segmentation, use:

Based on the survey responses, identify and describe a list of distinct personas—similar to how “personas” are used in product management. For each persona, summarize their key characteristics, motivations, goals, and any relevant quotes or patterns observed in the conversations.

Want more inspiration or a ready-to-use survey? Check out this advance care planning survey generator and see the best question ideas for patient ACP surveys.

How AI analyzes different types of responses in your survey

AI-powered tools like Specific treat each survey question according to its format. Here’s how they handle analysis for patient advance care planning surveys:

  • Open-ended questions (with or without followups): The AI provides a summary for all patient comments on that question and also digs into responses given to follow-up questions—giving you a fuller picture of concerns and attitudes around ACP.

  • Choices with followups: Each answer option receives its own summary, based on every follow-up response related to that choice. It’s perfect for capturing the “why” behind patient’s choices.

  • NPS questions: For Net Promoter Score data, the AI creates a summary of follow-up answers for each group: detractors, passives, and promoters. You’ll see what’s driving high or low engagement in ACP.

You can get to a similar result using ChatGPT, but it takes more manual setup and effort. With Specific, everything is streamlined and automated—especially when you’re dealing with dozens or hundreds of conversations.

How to overcome AI context size limits in survey analysis

A common challenge when analyzing patient survey data with AI is context size limits. Large sets of responses (for example in ACP surveys with high engagement) may not fit into an AI’s maximum context—meaning you can’t paste or chat about everything at once.

To solve this, you have two approaches, both supported by Specific right out of the box:

  • Filtering: Target analysis on a relevant slice of your data. For example, filter down to only patients who mentioned “family involvement” or who gave a specific answer to a question. The AI now only sees conversations matching your filters, so you stay inside context limits and focus on what matters most.

  • Cropping: Restrict the analysis to selected questions only. If you’re only interested in, say, open-ended feedback about obstacles to ACP, just crop the data sent to AI to that question. This lets you analyze more patient conversations even if you have a large data set.

These smart filtering and cropping techniques help you extract insights without running into AI memory walls—and without the need for time-consuming manual editing.

Collaborative features for analyzing patient survey responses

Collaborating on the analysis of patient advance care planning surveys often means sharing findings, segmenting data, and having real back-and-forth discussions across teams. This process can get messy if you’re using spreadsheets or generic AI tools.

Chat-based collaboration: With Specific, you don’t just analyze your patient survey by yourself—you chat about the results with colleagues, all inside the same interface.

Multiple simultaneous chats: Each chat thread can have unique filters—one might focus on patient concerns about family communication, another on legal barriers to ACP. You instantly see which team member created which chat, so it’s clear who’s exploring what.

Granular visibility: In team chats, every message shows the sender’s avatar, making it easy to track ideas and follow conversations. This gives your team a single source of truth and helps prevent work from being duplicated or lost.

Actionable insights in real-time: As new survey responses come in, you continue exploring and discussing findings with your team—no need to export data or start analysis over. Curious how this works? Explore collaborative survey analysis features or test drive the AI survey editor for building and updating your patient surveys with your team.

Create your patient survey about advance care planning now

Start collecting meaningful, high-quality insights from your patients today by launching an interactive, AI-powered advance care planning survey—and supercharge your analysis with instant AI summaries, deep filtering, and chat-driven collaboration in Specific.

Create your survey

Try it out. It's fun!

Sources

  1. BMC Health Services Research. Attitudes towards and Experiences with Advance Care Planning in Norwegian Patients and Their Next of Kin.

  2. International Journal of Environmental Research and Public Health (MDPI). Factors Affecting Advance Care Planning and Related Barriers in Taiwan.

  3. National Institutes of Health (NIH) PubMed. Awareness and Prevalence of Advance Care Planning Documents in the United Kingdom.

  4. TIME Magazine. How to Get Paid for Planning Your Death.

  5. Journal of Pain and Symptom Management. Awareness of Advance Directives in General Population, Cancer Patients, and Caregivers in Korea.

  6. Journal of the American Geriatrics Society. International Completion Rates of Advance Directives: A Multinational Cross-Sectional Study.

Adam Sabla - Image Avatar

Adam Sabla

Adam Sabla is an entrepreneur with experience building startups that serve over 1M customers, including Disney, Netflix, and BBC, with a strong passion for automation.

Adam Sabla

Adam Sabla is an entrepreneur with experience building startups that serve over 1M customers, including Disney, Netflix, and BBC, with a strong passion for automation.

Adam Sabla

Adam Sabla is an entrepreneur with experience building startups that serve over 1M customers, including Disney, Netflix, and BBC, with a strong passion for automation.