Introduction to Patchs AI

Gwynneth Derere
Gwynneth Derere
  • Updated

What is Patchs AI?

Patchs AI is an optional feature of Patchs that automates triage, workflow, and signposting.

The aim of Patchs AI is to reduce GP practice workload and improve patient safety.

Patchs AI has been available since January 2021, and all GP practices that use it have found it both useful and safe.

There are different Patchs AI modules, which do different things:

  • Urgency AI flags patient requests as urgent or emergency as soon as they are submitted.
  • Signpost AI signposts patients away to self-care, NHS 111, or emergency services as appropriate.
  • Topic AI works out the clinical topics of a patient request and can be used to send patients messages before they submit their request including questionnaire or advice templates, and Pharmacy First information.
  • Assign AI assigns requests to a ‘Clinical’ inbox if they need input from a clinician.
  • Face-to-Face (F2F) AI highlights requests that may need an in-person consultation so they can be booked in sooner.

🚀 NEW - AI CARE NAVIGATOR! Patchs AI modules can now be combined and their actions tailored to suit the way you work and local pathways using the AI Care Navigator.

How does Patchs AI work?

Patchs AI helps your practice manage patient requests more effectively by analyzing patient information to recommend the right course of action, saving you valuable time. Here’s a simple breakdown of how it works.

1. Analysing Patient Information

Patchs AI uses Natural Language Processing (NLP) and machine learning to understand the free text patients submit.

  • It's not just a keyword search. Instead of simply looking for specific words, the AI analyses the context of the patient's message, much like a human would. It considers the patient's age, sex, and the type of request they've selected (e.g., 'health problem' or 'admin query') to build a complete picture.

  • This allows it to handle real-world complexities, including spelling mistakes and nuanced descriptions of symptoms.

2. Learning from Clinical Decisions

Patchs AI learns directly from the expertise of clinicians. This process is called supervised learning.

  • Every time a GP or other clinical staff member at your practice makes a triage decision on a patient request, they are "teaching" the AI. It learns to connect the information in a patient's request with the triage decision you make, just like a clinical trainee learns from experience.

  • The AI has been trained on millions of real-world patient requests triaged by thousands of clinicians across the UK. This collective experience - often called "the wisdom of the crowd" - makes the system robust and effective.

  • For requests that don't require clinical input, the AI also learns from decisions made by non-clinical staff.

3. Continuous Improvement

Patchs AI is constantly improving. Your clinical decisions directly improve the AI's accuracy over time, tailoring it specifically to your practice's patient population.

Important Considerations

  • It's a clinical tool. Because Patchs AI assists with clinical decisions, it primarily learns from clinicians. To ensure the system learns correctly, it's essential that requests requiring clinical input are assigned to clinical staff members within Patchs.

  • It's not perfect. Like most clinical tools, the AI is designed to support, not replace, your professional judgment. Think of it as a co-pilot that assists with navigation, while you remain the pilot in command of the final decision.

How is Patchs AI regulated? Is it safe?

Patchs AI meets the highest standards for safety, compliance, and performance:

  • Registered with the MHRA (ref 8387) as a Class I Medical Device and UKCA marked
  • NHS Data Security & Protection Toolkit (DPST)
  • NHS Digital Technology Assessment Criteria (DTAC)
  • Clinical Risk Management (DCB0129)
  • Cyber Essentials Plus
  • ISO 27001 Information Security
  • ISO 9001 Quality Management
  • GDPR

Patchs AI is considered a Class I Medical Device because it offers ‘triage and signposting of next steps based on filters by severity and probability of a match’, but without ‘direct diagnosis’.

This means we undertake rigorous clinical evaluations and safety assessments before releasing Patchs AI modules to customers, and conduct ongoing post-market surveillance after they are released.

This process includes multiple stages of testing including on historic patient requests, newly collected patient requests, interviews with staff and patients, and direct comparisons with GPs.

Because Patchs AI is used in the NHS, it is also governed by DCB0129: Clinical Risk Management: its Application in the Manufacture of Health IT Systems. It regularly undergoes clinical risk assessment and has its own Clinical Safety Case Report, which should be read and understood by GP practices before it is used.

How should Patchs AI be used by GP practices?

Patchs AI is meant to assist, not replace, human decision-making.

Because Patchs AI can make mistakes, staff should read, respond, and triage all patient messages as soon possible.

How does Patchs AI work? Is it complicated to activate Patchs AI?

No, it’s straightforward.

You can enable Patchs AI with just a click on your 'Feature settings' page, accessed via 'Edit Practice.' For a detailed guide on how to enable these features, go to this page.

Is additional training required to use Patchs AI?

No. As a UKCA-marked Class I Medical Device, Patchs AI is straightforward and safe to use.

Simply familiarise yourself with the relevant Patchs AI help pages and AI clinical safety documentation.

There are recommended eLearning modules available via elearning@oneadvanced.com should you wish to use them, but these are optional.

Do we have to change how we work to use Patchs AI?

No. Patchs AI automates tasks that you already do - including triage, signposting, assigning requests, booking appointments, asking patients questions and giving them advice.

You can also customise Patchs AI to align with your local pathways using the AI Care Navigator so it works exactly how you want it to.

What success stories using Patchs AI are there?

Yes! Hundreds of general practices the country are already experiencing the benefits of Patchs AI. Here's what some of them have had to say:

🌟 “Whenever there is a red flag highlighted by Patchs AI... I’ll think, hang on, let me just pop in and just make sure… When we didn’t have that AI, we could be scrolling through the list before we found something urgent…” Receptionist, London

🌟 “Artificial intelligence and electronic consultations are the future of communicating with our patients. Patchs is able to integrate all of these into one system.” GP, Leeds

How does Patchs AI work with Patchs Translate and Telephone Assistant?

Patchs is primarily meant to be used in English. However, GP practices can choose to use Patchs Translate. This feature allows patients to submit requests in non-English languages that are then automatically translated into English by Patchs.

Patchs AI has primarily learned from requests written by patients in English, so non-English language requests are first translated to English then analysed by Patchs AI. This may reduce the accuracy of Patchs AI.

To make translated patient requests quicker and easier to identify, there is a language icon next to them in the Patchs inbox.

mceclip7.png

Patchs Telephone Assistant allows patients to use the telephone to submit Patchs requests by speaking to an automated voice assistant.

Their voice message is then automatically transcribed into a written message, which can be analysed by Urgency AI, Signpost AI, Assign AI, and Face-to-Face (F2F) AI.

Patchs AI has primarily learned from requests written by patients, not spoken by them. Therefore, Patchs AI may be less accurate when analysing messages submitted via Telephone Assistant.

How is Patchs AI kept up to date?

We constantly monitor the performance of Patchs AI using triage decisions made by GP practice staff.

If GP practice staff change a decision made by Patchs AI, we consider Patchs AI to have been incorrect. As we collect more data, we use it to re-train Patchs AI to keep it up to date.

Periodically, we release these new versions of Patchs AI - but only once we are satisfied they perform better than older versions.

What work are we doing on the use of AI in general?

The use of AI in clinical care is a developing and fast-moving area. Patchs is at the forefront in terms of AI research, practice, and regulation.

We are working with NHS Digital on how best to assure AI in online consultations, using Patchs as an exemplar. We are also preparing peer-reviewed scientific publications about Patchs AI with The University of Manchester.

Regulatory Information

Product: Patchs AI v1.108

Purpose: Patchs AI automates parts of the triage and workflow process for GP practices when a patient or their carer uses the Patchs online consultation system. It is intended to assist, not replace human decision-making. Patchs AI aims to reduce GP practice workload by minimising manual tasks and improve patient safety by helping patients receive appropriate care sooner. Patchs AI uses information about the patient and their online consultation to suggest an urgency, clinical topic, staff role, and mode to conduct the consultation. Based on these suggestions it can provide patients with relevant health information, ask questions to elicit further information, and/or advise them to contact alternative care providers. Suggestions from Patchs AI can be accepted or rejected by GP practice staff and patients, which are used to monitor its safety and re-train the system. Patchs AI is intended to be used by both clinical and non-clinical GP practice staff who have received training in how to use it, and who are knowledgeable of its potential risks.

Classification: Class I Medical Device (UK MDR 2002)

Manufacturer:
Patchs Health Ltd
70 Gracechurch St, London, EC3V 0HR

info@patchshealth.com

Safety Warnings

⚠️ Always apply professional clinical judgment
⚠️ AI-generated content requires clinical review

A paper copy of the instructions for use is available on request

UKCA black fill.png  Complies with UK MDR 2002

 

 

 

 

Was this article helpful?