Artificial Intelligence in Allied Health Newsletter - February 2025

Read Time: 6 minutes

Hello there!

Gosh it feels like the year is already flying by! The last month has been interesting in the AI space, with new models coming out, agents emerging onto the scene and all of this meaning more downstream benefits for allied health. On my end, I’m putting the finishing touches on my workshop to present at AOTA Inspire 2025 in Philadelphia in April. If you’re attending, please let me know as I’d love to catch you there in person! I’m also about half way through writing my Foundational Course, which will be coming out over the coming months and will take you from zero to confident with getting started in your AI in allied health journey.

Industry News

Open AI’s Operator Released

OpenAI (the creators of ChatGPT) released their first AI Agent this month, named Operator. Operator is an agent that can use its own browser to perform tasks for you.

What does this mean? An AI agent is like a person who can go and do a job. It can fulfill a task without you needing to supervise it and can interact with a web browser like we can- clicking, scrolling, typing. An example they’ve given is that it could research and book a holiday for you. Currently access is limited to pro level US users, but I can’t wait to get access and see how we can use operator for allied health.

DeepSeek R1 Disrupted the US Stock Market

A new AI model was released out of China, DeepSeek’s R1. Reportedly cheaper, quicker to build, and with comparable performance to ChatGPT. It’s open source, which means you can see and modify the parameters of the model and it runs with greater efficiency that other models like ChatGPT by only powering up the sections it needs to run your query.

What does this mean? The AI race is continuing to deliver better, faster, more efficient and cheaper models. This will continue to improve accessibility of AI and give us more options in allied health.

Research

A recent study published explores how Artificial Intelligence (AI) can help detect depression by analysing patient health records. It discussed how traditional depression diagnosis relies heavily on clinician interpretation and patient self-reporting, leading to missed or delayed identification of symptoms. This research integrates Natural Language Processing (NLP) and sentiment analysis to identify emotional cues within unstructured medical data, such as doctor’s notes and therapy transcripts. The study assesses AI’s ability to recognize depressive behaviours and discusses the ethical challenges and benefits of using AI in mental health care.

Key findings:

• AI-driven sentiment analysis was able to detect depression patterns in patient records before an official diagnosis.
• The study tested different machine learning models, with Long Short-Term Memory (LSTM) networks achieving the highest accuracy (87%) in identifying depressive symptoms.
• AI models identified emotional trends in patient health records, showing mood deterioration before clinical diagnosis and capturing subtle shifts in emotional language.
• Ethical concerns include data privacy, algorithmic bias, and ensuring AI remains a tool to support, not replace, clinicians in mental health care.

Relevance to Practice

This research highlights the growing role of AI in mental health assessment and its potential to enhance early detection and intervention. While AI can’t replace clinical judgment, it offers a powerful tool to support clinicians in identifying depression earlier and tracking emotional patterns over time. However, considerations around data privacy, compliance, and responsible AI use remain critical for integrating these tools into allied health practice.

 Find the article here.

Prompt of the Month

Each month, I’ll be sharing a useful AI prompt designed to enhance your practice. This month, let’s use the AI to inform how we could use it better (the irony, huh?).

Prompt

"How could AI help streamline one aspect of my work as a (insert health profession here)? Consider all aspects of my role (optional- add extra details about your role, setting, caseload type) – what is one small, AI-driven change that could make a big impact?”

Tried this prompt? Send me an email and let me know how you found it!

AI Tool Spotlight

Otter.ai

Otter.ai is an AI-powered meeting assistant that automates note taking, transcription, and meeting summaries. It creates real time transcripts, identifies speakers, and can automatically generate summaries and action items. It has the ability to assign action items within the platform, streamlining follow-ups. Otter integrates with tools like Slack, CRMs, and video conferencing platforms (e.g., Zoom, Microsoft Teams), to enhance meeting productivity.

While useful for general meeting transcription and workflow automation, it may not be fully compliant with healthcare privacy regulations like HIPAA, so clinicians should assess its suitability for client-related documentation.

Upcoming Events

Free: The Group Chat – group supervision/ community of practice

When: Thursday, 27^th February 2025. 12-1pm AEDT (Australian Eastern Daylight Savings Time- Sydney/ Melbourne time).

Find your timezone here: https://www.timeanddate.com/worldclock/converter.html 

 
Where: Online via Zoom
Cost: Free

Join me for a free, interactive "group chat" to share all things AI in allied health. It's a group supervision, community of practice, or interest group- whatever you want to call it, I'm calling it the 'group chat.' This session will be an open, informal, and mostly unstructured discussion for brainstorming, sharing ideas and challenges and peer learning!

The session will be recorded and available to those unable to attend live.

Sign up here.

Live Webinar: AI Scribes for Allied Health

Struggling with documentation overload? AI scribes can save you time, reduce admin work, and let you focus more on client care- but how do they actually work? Join me for a 1-hour live webinar, where I’ll break down what AI scribes are, how to choose the right one, and the key ethical considerations.

When: Monday 24^th March 2025. 12-1pm AEDT (Australian Eastern Daylight Savings Time- Sydney/ Melbourne time).

Find your timezone here: https://www.timeanddate.com/worldclock/converter.html

Where: Online via Zoom
Cost: $49

The session will be recorded and available to those unable to attend live.

More Information Here.

Thank You for Being Part of Our Community
If you have any questions or feedback, don’t hesitate to reply to this email - I’d love to hear from you!