MSc. Design for Interaction, TU Delft
Bremo
A Personalised AI Chatbot Companion for Individuals with Breast Cancer Post-Diagnosis
Master Thesis, Technical University of Delft, Netherlands
My Role
Project Lead
Tools
Figma, Figjam, Atlas.ti, Miro, Adobe Photoshop, Adobe Illustrator
Year
2024
Collaboration
Background Study
1 in 8
individuals will develop breast cancer at some point in their lives.
- National Institute of Public Health and the Environment of the Netherlands
The Challenge
When faced with a breast cancer diagnosis, individuals must manage many responsibilities: consulting healthcare providers, undergoing tests, learning about the illness, managing medications, making critical decisions, and staying connected with their support network. This creates a complex web of interactions.
At the same time, they are presented with medical jargon that is often overwhelming and difficult to interpret. To make informed decisions, they need clear and accessible information. However, the complexity of medical materials frequently creates barriers, leaving patients uncertain and less confident in their choices.
"How might we make medical information more accessible and understandable for individuals diagnosed with breast cancer?"
80%
Information shared during consultations is often lost due to emotional stress and overwhelming circumstances
Shortage of healthcare providers and the growing number of cases
Medical Jargon
Complex web of interactions
Diverse Cases and Stages of Cancer
Use of unverified information sources cause more anxiety and stress
The Impact
The design solution is proposed to make the lives of 15000+ breast cancer patients better by providing personalised information in an empathetic way. It connects the various existing credible sources of information and reduces the strain on healthcare providers.
The flexibility of this solution extends its utility beyond breast cancer, offering scalability to other types of cancer and stages of illness.
Design Outcome
An AI cancer companion named Bremo was proposed to address individuals' diverse informational and emotional needs. Its integration into the existing healthcare system enhances patient engagement by providing personalised information through the conversational chatbot.
Bremo breaks the traditional, one-dimensional approach of static documents by offering interactive, conversations from multiple reliable sources. This streamlines healthcare providers' workloads by reducing the need to repeat similar information, saving time, and promoting connections between healthcare organizations.
15000+
breast cancer individuals and their companions will be supported through the proposed concept
Reduces the load on healthcare providers
Connects hospitals with cancer organsiations
Design Process
DEFINE
USER RESEARCH
IDEATE
DESIGN
EVALUATE
1
2
3
4
5
30+
Research Papers
3+
Exploratory Talks
25+
Qualitative Interviews
01
Journey Mapping
02
Design Workshops
6+
Ideation sessions
3+
Iterations
6+
User Tests
10+
Prototypes
01. Define
An individual with breast cancer navigates numerous responsibilities, including consulting healthcare providers, undergoing examinations, understanding the illness, managing medications, making decisions, and engaging with a network of people, often creating a complex web of interactions.
How do they navigate this complexity, managing multiple interactions and decisions post-diagnosis?
How do they make decisions in moments of vulnerability, when emotions run high?
As a designer, how can I simplify the process of accessing complex medical information for them?
02. User Research
Research Methodology
To understand the unmet needs of individuals with breast cancer, I conducted 25+ qualitative interviews and mapped the breast cancer care journey and experiences with the help of the Metro Mapping Tool (Metro Mapping, n.d.) and other mapping activities. The insights generated from this phase helped define the design principles for the ideation session.
Metro Mapping
The metro map was co-created with an oncologist, a surgical oncologist and a healthcare designer from Panton to gain insights into the information flow within the breast cancer care pathway. The map has four layers: 1) Layer Metro which maps the cancer care trajectory. 2) Layer Information which is divided into four components-information provided, channels of information, goals of information, and information collected. 3) Layer Experience and Emotions which maps the emotional experiences of the individuals during the diagnosis process.
Metro Mapping: Information Map in Breast Cancer Care
Qualitative Interviews
04
Healthcare Providers and Nurse Practitioners
07
Representatives of Research Institutes and Cancer Organisations
02
Companions (Family members of individuals)
07
Individuals with Breast Cancer
02
AI Experts
Thematic Analysis of the Interviews
Mapping Activities
During the research, a variety of mapping activities were conducted to explore key aspects such as the sources of information, the level of trust placed in those sources, and their accessibility. These activities provided valuable insights into how individuals interact with and rely on different information channels.
1. Categorisation of Sources of Information, 2. Sources of Information Based on Trustworthiness and Accessibility, 3. Preferred Sources of Information, 4. Level of Trust on the Preferred Source of Information, 5. Preferences on the Type of Information Needs
Quotes from the interviews
"She said, “now I have a new job because the job is now breast cancer."
- Representative from Patient Organisation
"
- Healthcare Provider
"Sometimes the information is too hard to understand. And that’s not easy."
"I think the world, this hole opened up and I just fell like several levels through the floor."
- Individual with Breast Cancer
"I’m not educated as a physician. I think some of the abbreviations were new to me [...] I think it’s a lot of professional language that you are suddenly confronted with."
- Individual with Breast Cancer
"
Key Insights
01.
Overwhelming Nature of Cancer Diagnosis
02.
Nature of Information: Complex and Abundant
05.
Short Duration of the Consultation Sessions
06.
Avoid Joining the Patient Organisation
The Unmet Needs
Despite the support available from various sources, the overwhelming nature of cancer diagnosis makes individuals feel isolated and highlights the need for more support that can address their information and emotional needs. These needs are interconnected and interact continuously with each other. To reduce uncertainty, they go look for information and due to the nature of illness and the information it presents, they need emotional support. The findings also complement the literature study. Although there is an overlap between these needs, they vary from person to person and hence require more personalised support.
03.
Influence of Seeking Information from Various Sources
04.
Variability in Seeking and Understanding Information
07.
Variations in Information-Seeking Behaviours
08.
Varied Emotional Support and Coping Strategies
The Design Principles
To conclude the research phase, I created a set of design principles.The design principles serve as a foundation for ideation
Assist in Making Information Clear and Easy to Comprehend
Understand the Emotional State and Address the Emotional Needs
Foster Approchability and Affective Interaction
Provide Personalised and Relevant Information
Ensure Transparency, Reliability and Trustworthiness
03. Ideate
With the findings of the conducted research, the outcomes of the needs of people and the formulation of the design principles, the next
step was to create a base for the design. A design goal was formulated based on the overarching research question to carry out the design explorations.
“To create an AI-driven intervention that supports people with breast cancer in dealing or preventing information overload post-diagnosis”
Design Facilitation Workshops
Design Workshops
02
10
Participants
I conducted two design facilitation sessions each with a distinct group, to gather diverse insights on the support needs of individuals.
With fellow design students
With healthcare designers at Panton
Ideations and Brainstorming
During ideation, I began by formulating "How To" questions for each design principle to explore potential solutions and guide idea generation. A brainstorming session followed, focusing on concepts addressing users' informational and emotional needs. This process yielded six distinct ideas, two of which shared functionalities but differed in delivery mediums. The ideas were evaluated using the Harris Profile, leading to the selection of a final design direction.
Design Direction
In the current interaction, individuals consult healthcare providers, receive documents, and seek additional information to reduce uncertainty. However, this often leads to fragmented, overwhelming, and one-dimensional information, causing information overload.
The desired interaction with 'My Cancer Companion' minimizes reliance on unreliable sources by retrieving trusted information and presenting it in simple, clear, and interactive conversations. It centralizes accurate information while offering empathetic communication.
Current Interaction
Desired Interaction
Design Outcome: Bremo
Bremo breaks the traditional, one-dimensional approach of static documents by offering interactive, conversational access to information, from multiple reliable sources. It also serves as a sounding board where individuals can share their feelings and concerns. It is envisioned as a secondary source of information to be accessible via smartphones.
04. Design
Introduction of Bremo during Consultation Sessions
Bremo will be introduced to people with breast cancer during consultation sessions through the following steps:
Wireframing
3+
Iterations
Prototyping
Prototypes
10+
1
2
3
4
Ensuring secure access through government-authorized DigiD login
Conversational interactions to ask and clarify medical questions
Compiling a personalized question bank to prepare for the next medical consultation
Recording consultation sessions to revisit and listen later
05. Evaluate
Bremo was evaluated with three distinct user groups to ensure a comprehensive understanding of its usability, feasibility, and potential:
1. Individuals with Breast Cancer: To evaluate the usability and overall user experience, ensuring the design addresses their needs effectively.
2. Healthcare Designers from Panton: To assess its integration within the Dutch healthcare system using a Desirability, Feasibility, and Viability framework, ensuring alignment with system requirements and user expectations.
3. AI Experts: To explore the technical capabilities of AI and identify opportunities for further enhancement in supporting users.
"I think you found something that there's a gap and then it's valuable. I like that it's very integrative with various established data sources."
- Individual with Breast Cancer
"
“I would maybe say this intervention is very useful because you can use it as a recording app for your conversations and have it summarize it, and also have the only information that you need in one app then is each, it could make our complete patient journey a little easier and even and we reduce some of the stress.”
- Healthcare Designer from Panton
"
"It has the potential to be very effective. It could be very good at summarisation."
- AI Expert
Explore Other Case Studies
Digital Interface Redesign: Mobility Scooter
Happiness Card Deck
.png)
The Tube