Annalise Enterprise: AI Assistant for Medical Imaging

  • 2023

  • Digital

Commissioned By:

Designed In:

Australia, a clinician-led, Australian medical imaging AI developer, helps doctors detect life-threatening conditions, safeguarding patients.

Recognised for an industry-leading comprehensive approach, was approved for a record 124 Chest X-ray findings in 2021 and 130 CT brain findings in 2022, after some of the world’s most extensive clinical AI trials.

view website
view twitter

  • MORE
  • Medical imaging is crucial for early disease detection and treatment, but radiologists face increasing demand and workload. As a “second set of eyes” helps doctors triage and diagnose confidently, reducing the risk of missing life-threatening conditions. Through iterative design research — 100's hours observing, interviewing & testing with 100s of international radiologists — we understood the intense time pressure, unique environment, and fatigue of radiology, so UX design was hyper-focused on ergonomics and cognitive aspects load, usability and speed.

  • Radiologists often interact with highly dense, sometimes user-hostile UIs and use dual-handed input via voice and mouse but minimal keyboard use and are hyper-sensitive to distraction and impediments. The UI design is carefully designed to these sensitivities while the UX eliminates constant manual adjustment while the UI seeks to focus all user attention on detecting critical findings and especially focussed on ergonomics by minimising "eye miles" and clustering supporting information in deliberate spacial relationship to the medical images being interrogated.

  • A tool constantly used under such pressure must be lightweight, low-friction, effective and pleasing to sustain use and positively impact this critical work. Annalise has assisted radiology reporting for over 1 million patients through constant, highly repeated use by radiologists and clinicians, and 93% continue this high-intensity use after 2 months, with 90% indicating it positively impacts their reporting.

  • Ergonomics, usability, efficiency and responsiveness are paramount; a tool used constantly must be lightweight, low-friction, effective and even pleasing to sustain use and positively impact this critical work. We want clinicians only to interact enough to inform diagnosis — the less interaction, the faster to critical information, the sooner to treat the next patient.