MEDICDOJO
I wanted to arm myself with basic knowledge so I can protect myself and patients.
ITU Registrar · Guy's and St Thomas'

<machine_learning for |>

Build an ML portfolio project in a weekend. Understand the models behind the AI you're using.

Dates
26–27 September 2026
Sat & Sun · 8am–6pm
Location
South Kensington, London
Exact venue confirmed closer to the date
Deposit
£150 to reserve
Fully refundable. See policy below.

Course organisers

Samar Ali Hussain

Dr Samar Ali Hussain

MBBS, MRCS

Completed core surgical training with a focus on plastic surgery, and now completing an MSc in Computing at Imperial College London. Teaches from the perspective of a clinician who's had to learn ML from scratch, so nothing gets skipped or assumed.

Aamal Abbas Hussain

Dr Aamal Abbas Hussain

BSc, MSc, PhD

BSc in Physics, MSc in Robotics and Computation, PhD in multi-agent systems and reinforcement learning. Currently building AI systems at a robotics startup. Brings deep technical grounding without the academic distance.

Teaching is delivered by current Imperial College London PhD and MSc students in computing and machine learning. You'll be learning from people who are actively researching and building in the field.

TLDR

  • → Applied machine learning for healthcare professionals
  • → Build a working clinical predictor you can put on GitHub or reference at interview
  • → One in-person weekend in South Kensington, London (26–27 September 2026, 8am–6pm each day)
  • → Pre-course e-learning materials so you arrive ready to build
  • → Taught by Imperial-trained computer scientists
  • → £150 fully refundable deposit reserves your place
  • → Limited places
£999

Total course price

£150 refundable deposit reserves your place today

Fully refundable if the course doesn't run or you cancel more than 14 days before the start date

Understand the models. Appraise the papers. Cut through the hype. No technical background required.

A hands-on machine learning course designed specifically for healthcare professionals. Over one weekend you'll build a working clinical predictor from scratch. The kind of project you can put on GitHub, reference at interview, or use as a springboard into your own audit or research work.

You'll leave able to:

  • Understand the models behind modern clinical AI
  • Critically appraise ML papers and commercial tools
  • Build and evaluate models on clinical data yourself

Delivered as one intensive in-person weekend in South Kensington, London, by Imperial-trained computer scientists.

Includes pre-course e-learning materials so day one starts with building, not setup.

What we'll cover

Pre-course · E-learning materials

Self-paced primer on Python essentials, key ML terminology, and the datasets we'll use. Complete it before the weekend so we hit the ground running.

Weekend · In-person intensive (8am–6pm)

Day 1: Foundations of Machine Learning

Supervised vs unsupervised learning, model evaluation, and hands-on training of your first clinical predictor.

Day 2: Applied Clinical ML

Working with clinical datasets and imaging, interpreting model outputs, understanding bias, and critical appraisal of AI papers and commercial tools.

This course

  • Taught by Imperial-trained computer scientists, in person
  • Small cohort, personal attention
  • Built around clinical use cases from day one
  • Better value per hour of teaching than a typical bootcamp

Typical online alternatives

  • Large cohorts, no personal attention
  • Self-paced, so it's easy to fall behind and get lost
  • Generic examples, not clinical
  • Limited access to instructors

Course Price

£999

£150 refundable deposit reserves your place today

⚠️ Please enter an actively-used email address at checkout so we can send joining instructions.

Full balance collected 4 weeks before the course

What you get

  • A working clinical predictor. A portfolio-ready notebook you can share on GitHub or reference at interview.
  • One intensive in-person weekend. Saturday and Sunday, 8am to 6pm, in South Kensington.
  • Pre-course e-learning materials. A self-paced primer so day one starts with building, not setup.
  • Personal attention. Small cohort, direct access to instructors throughout.
  • All course materials. Notebooks, code, datasets, and exercises to keep.
  • A network of peers. Fellow clinicians thinking seriously about ML in their own practice.

Refund policy

14-day cooling-off: You can cancel within 14 days of paying your deposit for a full refund, no questions asked.

More than 14 days before the course: Full refund of any amount paid.

If the course doesn't run: Full refund of any amount paid.

Within 14 days of the course: Deposit non-refundable but transferable to a future cohort on request.