Short answer

Shift from designing *for* patients to designing *with* patients when developing AI healthcare solutions.

Field: User-Centred Design
Source: BMC Health Services Research (2023)
Method: Qualitative research, Focus groups
Evidence: Strong effect

Actively involving patients in the design and development of AI healthcare applications leads to more relevant and effective outcomes. This user-centred design research insight is drawn from a 2023 study published in BMC Health Services Research. Using Qualitative research, focus groups, researchers explored how this design variable affects real-world outcomes. The key design takeaway: Shift from designing *for* patients to designing *with* patients when developing AI healthcare solutions.

Study

User-Centred DesignRecentStrong effect

Patient co-creation in AI healthcare development yields more meaningful applications.

Actively involving patients in the design and development of AI healthcare applications leads to more relevant and effective outcomes.

BMC Health Services Research · 2023

Key Findings

01Patients desire active participation in AI healthcare application development.
02Clear frameworks and methods are needed to facilitate meaningful patient engagement.

Application

Design takeaway

Shift from designing *for* patients to designing *with* patients when developing AI healthcare solutions.

How to apply

Incorporate patient advisory boards or user testing panels from the initial concept phase of any AI healthcare project.

Project actions

01Consider how you can get real user feedback early in your design process.
02Think about different ways to involve users, not just surveys.

Method & Evidence

AimHow can patients be effectively engaged in the development of AI applications for healthcare?

MethodQualitative research, Focus groups

ProcedureThe study explored patient perspectives on their involvement in the development of AI healthcare applications through focus group discussions.

ContextHealthcare AI development

Variables

IVPatient engagement in AI healthcare development

DVMeaningfulness and effectiveness of AI applications

Strengths & Limitations

Strengths

+Focuses on a critical and emerging area of healthcare technology.
+Directly addresses the need for patient voice in AI development.

Limitations

It can be challenging to recruit a diverse range of patients, and their input might not always align with technical feasibility or broader healthcare system goals.

Reliability & validity

The validity of the findings relies on the depth of the focus group discussions and the representativeness of the patient participants. Reliability would be enhanced by replicating the study with different patient groups and AI application types.

Think critically

While patient engagement is crucial, how do we balance patient preferences with the expertise of healthcare professionals and the technical constraints of AI development?

Design Principles

"Patient co-creation is essential for the ethical and effective development of AI in healthcare."

As AI rapidly advances in healthcare, neglecting the patient perspective can result in tools that are not aligned with user needs or clinical realities. Prioritizing patient input ensures that AI solutions are not only technologically sound but also ethically considered and practically beneficial for those they are intended to serve.

What This Means for Your Design

When making AI tools for doctors and patients, it's best to ask patients what they think and want, not just guess.

How to use in your project

1.Reference this study when justifying the need for user research and user involvement in your design project, particularly if it involves healthcare or AI.

Add to My Project

Quick Cite

Paragraph starter

This research highlights the critical importance of patient engagement in the development of AI healthcare applications. By actively involving patients throughout the design process, developers can ensure that AI solutions are not only technologically advanced but also user-centered, ethically sound, and clinically relevant, ultimately leading to more effective and accepted healthcare tools.

Source

BMC Health Services Research

Exploring patient perspectives on how they can and should be engaged in the development of artificial intelligence (AI) applications in health care

journal · 2023

View source

Questions About This Research

What does the research say about patient co-creation in ai healthcare development yields more meaningful applications?: Shift from designing *for* patients to designing *with* patients when developing AI healthcare solutions. Evidence: BMC Health Services Research (2023).
Why does "Patient co-creation in AI healthcare development yields more meaningful applications." matter for design?: As AI rapidly advances in healthcare, neglecting the patient perspective can result in tools that are not aligned with user needs or clinical realities. Prioritizing patient input ensures that AI solutions are not only technologically sound but also ethically considered and practically beneficial for those they are intended to serve.
How can designers apply this research?: Shift from designing *for* patients to designing *with* patients when developing AI healthcare solutions.
What were the main findings?: Patients desire active participation in AI healthcare application development.. Clear frameworks and methods are needed to facilitate meaningful patient engagement.
What research method was used?: Qualitative research, Focus groups.
How strong is the evidence?: Evidence strength is rated Strong effect, based on a 2023 journal from BMC Health Services Research.
What should I do differently in my next project?: Incorporate patient advisory boards or user testing panels from the initial concept phase of any AI healthcare project.
What are the limitations?: The study's findings may be specific to the patient groups and AI applications discussed, and further research is needed to generalize the results.