UX Research Case study

Originmedical.ai : Problem Space Exploration

Discovery Phase:

Understanding Sonography Workflow Challenges

To design an AI-powered solution that seamlessly integrates into the sonography workflow, I first needed to understand the existing challenges sonographers face in their day-to-day tasks. 
My goal was to uncover inefficiencies, usability gaps, and pain points that impact workflow efficiency, ergonomics, and overall user experience.

My process…

I followed the Double Diamond framework—focusing entirely on exploring and defining the problem space. 

This research-first approach allowed me to deeply understand user behaviors, pain points, and systemic gaps before moving into ideation. 
I used a mix of secondary research, whitepaper reviews, competitive analysis, and primary user interviews to uncover key insights. These findings were synthesized through user segmentation, stakeholder analysis, journey mapping, and mind mapping to frame user challenges and opportunities. 
The insights from this research laid the strategic foundation for the multiple subsequent UX design Projects, where I translated these findings into actionable design solutions.

Secondary research

To build a strong foundation, I began with secondary research, exploring key areas that influence the sonography process:

  • Ergonomic Design – Understanding how sonographers interact with ultrasound machines and the physical strain involved.

  • Clinical Workflow – Mapping how sonographers move through their tasks, from patient prep to image acquisition and reporting.

  • Work-Related Musculoskeletal Disorders – Examining common injuries and discomforts experienced by sonographers due to repetitive movements.

  • Ultrasound Machines & Brands – Exploring different hardware interfaces, controls, and usability standards across various ultrasound systems.

  • Basics of Ultrasounds – Gaining insights into how ultrasound imaging works and the factors affecting scan quality.

  • Pregnancy Scans – Understanding the unique requirements and challenges of obstetric ultrasound procedures.

This research helped me establish a baseline understanding of sonography workflows, identify recurring pain points, and frame key areas for further user research.

The generative research surfaced five key areas that shape the day-to-day experience of sonographers and influence clinical outcomes

Together, these factors not only affect sonographer performance and wellbeing, but also impact patient satisfaction, scan quality, and clinical decision-making.

These insights pointed to a significant opportunity:

To design truly impactful AI-assisted tools, we need to dive deeper into understanding the user's environment and challenges.

A dedicated phase of primary user research—centered around ergonomics, workflow design, and interface usability—would be essential to uncover nuanced needs and guide product decisions grounded in real-world use.

Whitepaper research…

To effectively prepare for primary user research, I supplemented these insights with a targeted review of white papers and clinical guidelines.

This included deep dives into pregnancy life cycle, fetal imaging protocols, international clinical guidelines, and hospital workflow documentation.

I also explored medical device manufacturing guidelines and scan room design standards to better understand the technical, spatial, and regulatory constraints sonographers and MFM specialists work within.

With this research i found out :

Many international bodies, provide comprehensive guidelines to standardize ultrasound practices, ensuring high-quality patient care. These include:

  • The World Health Organization (WHO),

  • American Institute of Ultrasound in Medicine (AIUM),

  • American College of Obstetricians and Gynecologists (ACOG) and

  • the International Society of Ultrasound in Obstetrics and Gynecology (ISUOG)

These guidelines lay out detailed protocols for various ultrasound examinations during different phases of the pregnancy lifecycle, ensuring consistency & standardization, thoroughness & quality and emphasis on comprehensive documentation of ultrasound findings.

These protocols not only requires accuracy of the fetal assessments and standardization across different patient cases but also demands vigilance, high cognitive load tolerance and mental stamina.

This underscores the critical importance of sonographers being not only highly trained but also deeply aligned & updated with standardized imaging protocols and workflow requirements to ensure diagnostic accuracy, patient safety, and operational efficiency.

To enable this high-performance environment, medical device standards and scan room design must prioritize ergonomics, ISO-compliant manufacturing, and seamless clinical integration—reducing cognitive and physical strain while enhancing workflow efficiency and diagnostic precision.

Competitive analysis…

To contextualize the problem space
and identify opportunities for differentiation,
I conducted a competitive analysis of both direct and indirect competitors in the AI-driven medical imaging space.

Direct competitors included products focused on ultrasound diagnostics, particularly in prenatal care…

While indirect competitors ranged from tools addressing Vascular & cardiac imaging to diabetic retinopathy and chest X-rays.

To uncover underlying opportunities for innovation and design impact, I conducted a SWOT analysis—examining the strengths, weaknesses, opportunities, and threats across their key features.

This helped reveal not only what these solutions do well but also where usability gaps, adoption barriers, and growth potential exist, guiding more informed UX decisions for future product strategy.

These references helped frame informed research questions and ensure that the upcoming user interviews were grounded in clinical and operational realities.

Primary research…

With foundational insights from secondary and white paper research, I structured my primary research to dive deeper into the lived experiences and preferences of radiologists and sonographers.

The key objective was to understand how AI integration can align with real-world workflows, clinical expectations, and user control. My interview guide was designed to explore themes across five critical areas: workflow initiation, image capture, AI assistance, interaction preferences, and quality evaluation.

After conducting interviews with 8 clinicians, a mix of Sonographers, OB/GYNs, MFMs and Radiologists, I recorded and analyses their inputs into the following themes and Insights:

From our primary research, we derived a detailed multi stakeholder journey map that charts the entire ecosystem in which the end-to-end experience of sonographers exists across different clinical settings.

These maps highlighted key actions, touchpoints, pain points, and emotional states throughout the scanning workflow.

Define Phase…

Meet the Expectant Parent: A 30-year-old individual in their second trimester has been experiencing mild discomfort and wants reassurance about their baby's health. Their healthcare provider recommends a detailed fetal ultrasound. This journey follows their experience while highlighting the roles of various stakeholders.

A Multi-Stakeholder Journey Mapping

After mapping the stakeholder journey, it became essential to analyze their specific needs, influences, and challenges in greater detail.

This deeper understanding helped identify pain points and opportunities for designing an AI-powered solution that seamlessly integrates into their workflow.

After charting the multistakeholder journey and mapping the influences of clinicians, patients, administrators, and vendors, I shifted focus from “who interacts with the product?” to “how each primary user thinks, feels, and struggles in context.?”

To do this, I created detailed user mind maps for sonographers.

Building on those mind maps, I distilled the most pressing challenges sonographers face day‑to‑day:

The mind‑maps gave me a 360‑degree view of a sonographer’s world, while the challenge matrix highlighted where the role becomes painful, risky, or inefficient. To translate those rich but complex findings into actionable design decisions, I organized them through user segmentation.

Mapping Research Streams to User Segments

Through in-depth primary research involving radiologists and sonographers across diverse clinical settings— I identified distinct behavioral patterns, pain points, and preferences.

These qualitative insights directly informed my user segmentation, allowing me to categorize users not just by demographics or institutional type, but also by their workflow challenges, socioeconomic groups, adoption readiness, ergonomic needs, and cultural attitudes toward technology.

By combining insights, I developed clear profiles for each user type. Our user base can be segmented into three primary groups.

Urban Innovators

The early adopters—typically younger, tech-savvy professionals working in private clinics or advanced fetal medicine centers.

They are open to AI tools that enhance precision and efficiency.

Suburban Realists

The mid-career sonographers working in suburban hospitals or specialty practices.

They are pragmatic, moderately tech-literate, and adopt new tools if they clearly improve workflow without adding complexity.

Rural Skeptics

The late adopters, often older professionals in public or rural healthcare settings.

With limited access to advanced equipment and lower tech literacy, they are cautious about adopting AI and value reliability and simplicity over innovation.

These were not yet full personas but serve as detailed sketches of user types within each segment.

To bring clarity and pattern recognition, it's helpful to visualize these segments using tools like segmentation matrices and radar charts.

User personas per segment were then built to showcase when pain points, motivations, and workarounds that occur across a clinical task flow.

These visuals not only facilitated stakeholder alignment but also enabled product team to spot overlaps, outliers, and opportunities that might otherwise be missed in purely textual documentation.

Previous

Originmedical.ai
Next

From Science to Design: My Transition