Perspectives and Reflections Personal Year in Review: 2020 Welcome to my first (formal) year review. I’ve been doing this informally for a while, but this year decided to tidy it up and share in public.I’ll be up-front: This
Coding 6 Reasons You Should Learn to Code Through Projects - Not Courses (Or learn anything, for that matter)"WE ONLY KNOW WHAT WE MAKE." - GIAMBATTISTA VICO (PHILOSOPHER)🖥 Why learn to code?Learning to code is a really valuable skill. You can use it to
Coding Beginner to Data Scientist in 25 months: Every Project and What I Learnt Learning to code as a full-time doctor 🩺At the start of 2018, I had recently graduated from medical school. I knew basic web development and not much more.Since mid-2020, I've been working
Coding I created my own YouTube algorithm (to stop me wasting time) Using the YouTube API and Amazon’s AWS Lambda🚀 Escaping the YouTube algorithmI love watching YouTube videos that improve my life in some tangible way. Unfortunately, the YouTube algorithm doesn’t agree. It
Machine Learning The Best Artificial Intelligence For Healthcare Courses We keep on hearing about how artificial intelligence and machine learning is going to revolutionise Medicine.But what’s hype, and what’s realistic? And how can you get involved?The first step
Machine Learning From Correlation to Causation in Machine Learning: Why and How our AI needs to understand causality What’s wrong with correlation?In May 2016, the COMPAS algorithm was flagged as being racially biased [1]. This algorithm was used by the US to guide criminal sentencing by predicting likelihood of
Machine Learning Test your Medical AI knowledge (the basics) This is intended as a fun exam to test your knowledge on different areas of AI and it's application in healthcare. For those at an early stage in their medical AI journey, it can be helpful to highlight areas you're less familiar with, to prompt further reading.
Careers How I became a Data Scientist during COVID (as a Doctor): 5 takeaways from an unconventional career transition Background3 years ago, I had just finished medical school and started working full-time as a doctor in the UK’s National Health Service (NHS). Now, I work full-time as a data scientist at
Machine Learning Generating Art with Artificial Intelligence After hearing about the AI technique of 'style transfer', I decided to try my hand at creating art work.The basic idea of style transfer is that you take the style of one
Machine Learning Some thoughts on the role of AI in healthcare and whether AI will replace doctors A couple of weeks ago, we published an article in the British Medical Journal reviewing research papers that evaluated AI algorithms and compared their performance with clinicians. Our main findings in the article
Coding Automating my job search with Python (Using BeautifulSoup and Selenium) This article was also featured at Towards Data Science here.MotivationI’m currently looking for a new data science role, but have found it frustrating that there are so many different websites, which
Machine Learning Artificial intelligence in drug discovery This was originally shared as part of my weekly email newsletter.I’ve written in the past more formally about how AI may impact different medical specialties, from psychiatry through to intensive care.
Machine Learning Machine learning in medicine in the 2020s: My thoughts I wanted to articulate some of my current thoughts on the state of AI in medicine, so I wrote this stream-of-consciousness reflection. It's pretty rough, and not comprehensive, so I may tidy it
Machine Learning Predicting Acute Kidney Injury with AI (Research Paper Summary) A clinically applicable approach to continuous prediction of future acute kidney injury - Tomašev et al., Nature, July 2019Original article: https://www.nature.com/articles/s41586-019-1390-1One-sentence summaryIn this paper, a research group from
Research Summaries Predicting Hospital Appointment Attendance using Artificial Intelligence (Research Paper Summary) Predicting scheduled hospital attendance with artificial intelligence - Amy Nelson et al., April 2019Original article: https://www.nature.com/articles/s41746-019-0103-3#MOESM1One-sentence summaryIn this paper, a research group from UCL trained an AdaBoost
I'm starting a weekly email newsletter I've decided to start a weekly email newsletter.Its exact content and theme are not yet tightly defined, but it will broadly be a collection of my experiences as a doctor working in
Machine Learning Predicting Hospital No-Shows using Neural Networks [coding exercise] Approximately 20% of medical appointments that are booked are not attended in the UK. This costs an estimated £1 billion annually. If we were able to predict who might not show up, we
Machine Learning Classifying breast cancer with machine learning [Introductory coding exercise] This exercise takes you through the process of training a neural network to classify pathology slides from lymph node samples as malignant vs benign, based on the features of the images.The exercise
Machine Learning How might you use machine learning in a medical career? If you're a healthcare professional with an interest in machine learning (ML), but unsure how can combine it with your career, then we hope you'll find this post useful.The most common ways
Machine Learning How to find local medical AI projects to get involved with The last several years have seen a huge surge in amount of funding going into, and research papers coming out of, groups working on artificial intelligence in healthcare. Many new research groups are
Machine Learning Understanding Machine Learning in Medicine: An Introductory Webinar We live-streamed a one-hour webinar, covering some of the fundamental principles of machine learning and its application in healthcare. Here's a recording of it.It is aimed at all medical professionals (doctors, medical
Research Summaries Distinguishing cancerous from non-cancerous skin lesions (Research Paper Summary) Dermatologist-level classification of skin cancer with deep neural networks - Esteva et al., Nature, Jan 2017Original article: https://www.nature.com/articles/nature21056NOTE: This is one of the earliest, and most cited, articles
Research Summaries Key research papers in medical AI - read these first We will continue to update this post as new articles are published.Last updated: 14th October 2019This is an extremely active research field, with new papers published regularly. Here we mention some of
Research Summaries Recommending doses of IV fluids and vasopressor in sepsis (Research Paper Summary) The Artificial Intelligence Clinician learns optimal treatment strategies for sepsis in intensive care. - Komorowski et al., Nature Medicine, Nov 2018Original article: https://www.ncbi.nlm.nih.gov/pubmed/30349085 One-sentence summaryIn this
Research Summaries Automatically diagnosing retinal disease from eye scans (Research Paper Summary) Clinically applicable deep learning for diagnosis and referral in retinal disease - De Fauw et al., Nature Medicine, Aug 2018Original article: https://www.nature.com/articles/s41591-018-0107-6One-sentence summaryIn this paper, a research group