Summary:*
The conversation revolves around the integration of Artificial Intelligence (AI) in healthcare, specifically in the doctor-patient relationship. The discussion touches on the use of AI-powered tools, such as Google Workspace, Gemini, and other Large Language Models (LLMs), to enhance patient care, streamline medical data management, and support clinical decision-making. The participants share their experiences and ideas on leveraging AI to improve healthcare outcomes, while also addressing concerns around data security, HIPAA compliance, and the limitations of current AI models in medical decision support.
*Key Words:*
- AI in healthcare
- Doctor-patient relationship
- Agentic AI
- Medical data management
- Clinical decision support
- LLMs
- Google Workspace
- Gemini
- HIPAA compliance
- Data security
Image CC licence:https://commons.
Conversational transcripts:
One group:
[09/12, 22:59]hu1: https://aisel.aisnet.org/jais/
[10/12, 08:08]hu2: Thanks. Can you share the full text?
It's interesting how we broke the dyadic doctor patient relationship through PaJR CBBLE driven team based web 2.0 learning but couldn't call it triadic as there were multiple human agents in the team!👇
Another group:
[09/12, 18:28]hu3: Can Google Sheets or Docs be used to store medical data , say patient records?
[09/12, 18:28]hu3: Many practioners use Spreadsheets to store some basic appointment info , some even as rudimentary EMR.
[10/12, 08:58]hu4: Short answer is yes. Long answer is that you need to ensure that Access Controls are strict and the ability to copy/share data is pretty much locked down. Depending on the country you are doing this for HIPAA compliance you will need a BAA from google. The only way to get that is to have a workspace account whoch add to the auditing requirements etc
[10/12, 09:01]hu4: @Group Moderator I think this group is really useful. My only challenge is the volume of messages — if I fall behind, it takes me a while to catch up because I like to at least browse through everything. The information people share here is impressive, and the discussions are genuinely helpful. I know you ran a poll, but I wanted to make sure you had my reasoning behind voting yes.
[10/12, 09:03]hu5: NYT reports a growing number of patients are uploading records to ChatGPT to clarify diagnoses and understand care plans!
#healthcare #UShealthcare
[10/12, 09:25]hu3: Thanks. I think a Workspace account should help.A pro account would also help get the pro version of Gemini. I intend to use the Workspace studio to make a rudimentary EMR and demo it to this group. Maybe on one of the Wednesday.
I plan to take more of the unstructured data route( more document than spreadsheet) as I believe AI will be able to handle that . Also because medical history is more unstructured than structured. No form data entry is better ,where possible.
[10/12, 09:27] Group Moderator: thank you very much for your feedback! It is very helpful
[10/12, 09:27]hu3: Gemini states very clearly that it won't answer medical questions, so one will have to live with that for this experiment. Maybe other Ai tools can take care of that. Maybe it's also the right way to go
[10/12, 09:34]hu2: Here's an attempt at unstructured EMR data archival in different individual patient slots showcasing AI in the loop clinical decision making support👇
[10/12, 09:35]hu3: I was thinking of these. We will put PaJR on steroids with this new approach ( that's the intention)
[10/12, 09:36]hu3: Which AI are you using
[10/12, 09:37]hu2: Multiple LLMs
[10/12, 09:37]hu3: The workspace studio is more of agents ie. Work being done on the record e.g sending automated alerts, creating other documents etc.
[10/12, 09:38]hu3: Gemini decided not to be a medical decision support system
[10/12, 09:41]hu3: Maybe after the initial jugaad experiment with Google workspace ,one can try the Open AI Business suite. Open AI is still keen to work with medical decisions
[10/12, 09:41]hu2: Yes we need some agentic AI help to analyse all the archived data toward this project:
Distributed Health Citizenship in a Crowdsourced patient journey record PaJR Ecosystem
We could do with some agentic AI help in the next Steps for looking at our results:
1. **Formalize Data Extraction:**
Systematically code the case reports and chats for quotes illustrating key themes: delegation, conflict, platform use, advocacy, data loss from all the raw narrative data available here: https://pajrcasereporter.
2. **Strengthen Theoretical Linkage:**
Explicitly connect findings to literature on digital labor, health informatics, and participatory democracy.
3. **Develop the Methods Section:**
Detail the digital ethnography approach, ensuring it meets rigorous standards for qualitative research.
4. **Create Visualizations:**
Diagrams mapping the different network structures and data flows for the two cases would powerfully illustrate the argument.
Can anyone give this prompt to workstudio and share what they find?
[10/12, 09:42]hu3: These should be possible if they are just manipulations of a data . One or more Ai agents with good prompts should take care
[10/12, 09:42]hu2: We use open AI, copilot, perplexity, deepseek, August AI etc
Mostly deepseek, rarely August AI
[10/12, 09:43]hu2: Yes they are simply required to perform thematic analysis on data available in multiple URLs
[10/12, 09:44]hu3: NotebookLM would also do a neat job. Add all the URLs as sources and get wonderful outputs. Infographics,ppt, video,audio, reports of any sort
[10/12, 09:45]hu3: Especially useful for your students to learn from all the data you have now archived.
[10/12, 09:45]hu2: That would still need manual adding of 400 URLs there in that one URL!
[10/12, 09:45]hu2: Notebook LM used to work for me earlier but in recent times it just doesn't respond!
[10/12, 09:45]hu3: The researcher will select the ones really required
[10/12, 09:46]hu3: Go pro
[10/12, 09:46]hu6: Go Jio then Go Pro
[10/12, 09:52] hu4 : I am curious.. We can chat privately if you want. I may be able to help
[10/12, 09:53]hu3: Sure. In a day or two I will be ready with my first shot.
[10/12, 09:54]hu3: I was looking at the snippet feature of Google docs. Just to make repetitive data entry like prescriptions easier. E.g just type fever and related prescription will get filled
[10/12, 09:55]hu3: Template docs and snippets can do half the job. Ai agents to help further. Plus we have multimodal data entry.
[10/12, 09:56]hu3: Only live decision support is a challenge due to Gemini' stance.
[10/12, 09:57]hu7: Any experience with medgemma then
[10/12, 09:58]hu3: Good idea. Need to figure out how to make it work with the Google workspace
[10/12, 10:55]huai: This is a fascinating observation that gets to the heart of how technology reshapes relationships and power structures in healthcare.
Your analysis is spot-on. Let's break down the key conceptual shift:
### 1. The Historical Break: From Dyadic to Polyadic (Not Triadic)
You correctly identified the core idea: **Web 2.0 and team-based learning broke the traditional one-on-one (dyadic) doctor-patient model.** However, it didn't create a simple three-party (triadic) model. Instead, it introduced **multiple human agents**:
* The patient
* The primary doctor
* Specialists
* Nurses, physiotherapists, other allied health professionals
* **Critically: The patient's social network (family, caregivers) and peer patients from online communities.**
This created a **polyadic or networked relationship**. The "User Driven Healthcare" and "PaJR" (Patient Journey Record) models you linked formalized this, viewing the patient as the center of a learning network where care and knowledge are co-created by multiple human stakeholders. The power dynamic shifted from a paternalistic dyad to a (theoretically) more democratic, distributed network.
### 2. The New Frontier: Introducing Agentic AI as a New "Actor"
The conversation in your transcript is exploring the next logical step: **inserting Agentic AI into this already polyadic human network.**
This isn't just about AI as a passive tool (like an MRI machine). "Agentic AI" implies an active, semi-autonomous entity that can:
* Analyze unstructured data (patient narratives, records).
* Perform thematic analysis across hundreds of documents (as `hu2` requests).
* Manage workflows (sending alerts, creating documents).
* Potentially offer clinical decision support (though cautiously, as noted with Gemini's limitations).
### 3. The Emerging Model: A Polyadic Human-AI Ecosystem
The vision described (`hu3`: "We will put PaJR on steroids") is of a **hybrid ecosystem**:
* **Human Agents:** Patient, care team, family, peer network.
* **AI Agents:** LLMs (DeepSeek, OpenAI), specialized models (MedGemma), and workflow automators (Google Workspace agents) that act as force multipliers for both the patient and the clinicians.
This creates a complex system where:
* **The patient's narrative and data** (archived in blogs, chats, records) become the central "source truth."
* **AI agents** are harnessed to synthesize, analyze, and manage information flows within this network.
* **The human team** focuses on interpretation, empathy, ethical judgment, and physical care, guided by insights surfaced by AI.
### 4. Key Tensions and Considerations from the Transcript
The conversation highlights critical challenges for this new model:
* **Agency & Responsibility:** If an AI agent suggests an analysis or alert, who is responsible? The human who prompted it? The developer?
* **Data Sovereignty & Security:** Using tools like Google Sheets (`hu4`'s HIPAA/BAA warning) highlights the tension between accessible, powerful tools and robust health data governance.
* **The "Black Box" in the Team:** An AI's reasoning is often opaque. How does the human team "trust" or "collaborate" with an opaque agent?
* **Complementary Roles:** The group is pragmatically figuring out which AI is good for what—Gemini for workflow but not diagnosis, Open AI for medical analysis, NotebookLM for synthesis—mirroring how a human team has specialists.
### Conclusion: From a Broken Dyad to a Augmented Network
Your insight frames the evolution perfectly:
1. **Past (Traditional):** Closed **Dyad** (Doctor ↔ Patient)
2. **Present (Web 2.0 Era):** Open **Human Polyad/Network** (Patient + Doctor + Multiple Human Agents)
3. **Future (AI-Integrated):** **Augmented Polyad/Network** (Human Network + Multiple Agentic AI Actors)
The goal is no longer to have a single AI "replacing" the doctor in a dyad. Instead, it's about **integrating multiple AIs as active participants into the existing, distributed human care network,** supercharging the "User Driven Healthcare" vision. The relationship is becoming exponentially more complex, moving from a simple dyad to a **crowdsourced, AI-augmented ecosystem for health citizenship,** as hinted at in the final project title.
This is a profound shift from managing a relationship to orchestrating an ecosystem.
[10/12, 13:22]hu1: I will share full article today
Thematic Analysis:*
1. *AI-powered healthcare:* The conversation highlights the growing interest in using AI to enhance healthcare services, including patient care, data management, and clinical decision support.
2. *Challenges and limitations:* The participants discuss the challenges and limitations of current AI models, such as Gemini's stance on medical decision support, and the need for careful consideration of data security and HIPAA compliance.
3. *Agentic AI:* The concept of agentic AI is introduced, highlighting its potential to analyze and support complex healthcare data and decision-making processes.
4. *Collaboration and knowledge sharing:* The conversation demonstrates a collaborative effort among healthcare professionals to share knowledge, ideas, and experiences on leveraging AI in healthcare, with a focus on improving patient outcomes.
5. *Future directions:* The discussion touches on the potential future directions of AI in healthcare, including the use of multimodal data entry, template documents, and snippets to streamline medical data management and support clinical decision-making.
