Short answer

When designing performance analysis tools, don't just present data; explain its significance and the reasoning behind the insights to build user trust and utility.

Field
User-Centred Design
Source
Sensors (2025)
Method
Qualitative research and conceptual framework development
Sample
8 participants
Evidence
Moderate effect

Integrating explainable artificial intelligence (XAI) into multimodal sensing systems for sports analysis can significantly enhance coach understanding and trust by making complex data interpretable and actionable. This user-centred design research insight is drawn from a 2025 study published in Sensors. Using Qualitative research and conceptual framework development with 8 participants, researchers explored how this design variable affects real-world outcomes. The key design takeaway: When designing performance analysis tools, don't just present data; explain its significance and the reasoning behind the insights to build user trust and utility.

Study
User-Centred DesignNew This WeekModerate effect

Explainable AI in Sports Coaching: Bridging the Gap Between Data and Actionable Insights

Integrating explainable artificial intelligence (XAI) into multimodal sensing systems for sports analysis can significantly enhance coach understanding and trust by making complex data interpretable and actionable.

Sensors · 2025

01

Key Findings

  • 01There is a need for interpretable multimodal sensing systems in sports analysis to facilitate adoption in coaching practices.
  • 02Coaches require transparent and actionable insights derived from sensor data to inform their decision-making.
  • 03An explainability-driven design framework can link multimodal sensing with user requirements, leading to more trustworthy decision-support tools.
02

Application

Design takeaway

When designing performance analysis tools, don't just present data; explain its significance and the reasoning behind the insights to build user trust and utility.

How to apply

When developing a new analytics dashboard or performance tracking system, include features that explain *why* a certain metric is important or *how* a conclusion was reached, based on user input.

Project actions

  • 01When designing a product that uses data, think about how you will explain that data to the user.
  • 02Consider involving potential users early to understand what kind of explanations they need.
03

Method & Evidence

AimHow can explainable artificial intelligence (XAI) be integrated into multimodal sensing systems for swimming analysis to provide transparent and actionable insights for coaches?
MethodQualitative research and conceptual framework development
ProcedureThe SWIM-360 project investigated the application of XAI in swimming performance analysis. This involved preliminary results from specific sensors (EO SwimBETTER, TrainRed) and video-based pose estimation. Mock-up visualizations and interaction concepts were developed to gather feedback from coaches. A qualitative questionnaire was administered to eight professional swimming coaches to identify their requirements for explainability, which then informed the design of a multimodal, coach-centered explainability framework.
Sample8 participants
ContextSports performance analysis, specifically swimming coaching

Variables

IV["Integration of Explainable AI (XAI) principles","Multimodal sensing data"]
DV["Coach understanding of performance insights","Coach trust in the system","Actionability of insights"]
CV["Type of sport (swimming)","User role (professional coach)"]
04

Strengths & Limitations

Strengths

  • +Focuses on user requirements for explainability.
  • +Proposes a methodological framework for integrating XAI.
  • +Addresses a practical limitation in current sports analysis technology.

Limitations

The study used mock-ups and a small group of coaches, so the findings might not apply to all sports or all types of users.

Reliability & validity

The qualitative nature of the coach feedback provides rich insights but may be subject to individual interpretation. The use of mock-ups limits the assessment of real-world system reliability. Findings are preliminary and require further validation with larger samples and integrated systems.

Think critically

To what extent can the principles of explainable AI be applied to non-sporting data analysis tools to improve user trust and utility?

05

Design Principles

"Prioritize explainability in data-driven design to enhance user comprehension and trust."

For designers creating performance analysis tools, understanding how users (coaches, athletes) interpret data is crucial. XAI offers a pathway to build more effective and adopted systems by ensuring that the 'why' behind a data-driven insight is as clear as the insight itself, fostering better decision-making.

06

What This Means for Your Design

Imagine a smart watch that tells you your heart rate is high. This research is about making that watch also explain *why* it's high (e.g., 'because you just ran uphill') and what you should do about it, making the information much more useful for athletes and coaches.

How to use in your project

  • 1.Reference this study when discussing the importance of user comprehension and trust in data-driven design, particularly in performance-related applications.
07

Add to My Project

08

Quick Cite

Paragraph starter

The SWIM-360 project highlights the critical need for explainable artificial intelligence (XAI) in performance analysis tools, emphasizing that user comprehension and trust are paramount for effective adoption. By integrating XAI, designers can transform raw sensor data into actionable insights that coaches and athletes can readily understand and act upon, moving beyond mere data presentation to genuine decision support.

09

Source

Sensors

Towards Explainable Multimodal Sensing for Swimming Analysis: Early Findings from the SWIM-360 Project

journal · 2025

View source

Questions About This Research

What does the research say about explainable ai in sports coaching: bridging the gap between data and actionable insights?
When designing performance analysis tools, don't just present data; explain its significance and the reasoning behind the insights to build user trust and utility. Evidence: Sensors (2025).
Why does "Explainable AI in Sports Coaching: Bridging the Gap Between Data and Actionable Insights" matter for design?
For designers creating performance analysis tools, understanding how users (coaches, athletes) interpret data is crucial. XAI offers a pathway to build more effective and adopted systems by ensuring that the 'why' behind a data-driven insight is as clear as the insight itself, fostering better decision-making.
How can designers apply this research?
When designing performance analysis tools, don't just present data; explain its significance and the reasoning behind the insights to build user trust and utility.
What were the main findings?
There is a need for interpretable multimodal sensing systems in sports analysis to facilitate adoption in coaching practices.. Coaches require transparent and actionable insights derived from sensor data to inform their decision-making.. An explainability-driven design framework can link multimodal sensing with user requirements, leading to more trustworthy decision-support tools.
What research method was used?
Qualitative research and conceptual framework development with 8 participants.
How strong is the evidence?
Evidence strength is rated Moderate effect, based on a 2025 journal from Sensors.
What should I do differently in my next project?
When developing a new analytics dashboard or performance tracking system, include features that explain *why* a certain metric is important or *how* a conclusion was reached, based on user input.
What are the limitations?
Early findings, proof-of-concept outputs, and mock-up visualizations were used, rather than a fully integrated system. The study focused on swimming, and generalizability to other sports may vary.