82: The 6 stages of doing data science + crowdsourcing medical datasets for education
Hey there,
Hope you’ve had a great week :)
What I’ve made for you
A crowd-sourced list of medical datasets for education
While making exercises to teach machine learning for healthcare, I’ve spent a lot of time actively looking for appropriate datasets. I came across some existing list of medical datasets, but they had a different focus - so I’ve made a new one. Keen to crowdsource this, so if you’ve worked with a medical dataset that you’ve found helpful, and don’t see it on the list, please consider adding it! (Thank you 🙂)
How to apply data science to solve real-world problems - the data science pipeline (a presentation)
I made a presentation to answer the following questions:
What does it mean to do data science?
Why is data science useful?
What is the “data science pipeline”? (and an in-depth consideration of each of the six steps of this pipeline)
I’m creating this as part of my module (“Python for Data Science and Machine Learning in Healthcare”) at Imperial College London in a few months - some of the other slides are accessible here.
All the slides are still somewhat in-draft, so any initial feedback appreciated. I’m planning to do some more structured/formal feedback-gathering at some point down the road.
What I’m thinking about
I’m spending a bunch of time recently trying to extract things I’ve learnt and thought about over the last few years into writing (across data science, start-ups, freelancing, language learning, information processing and a bunch of other interest areas). I just want to get the ideas onto paper, but I’m actively not focussing on shipping them all right now.
At some point down the line, I want to focus on “packaging” these up to be more consumable: writing nice punchy articles, making YouTube videos of the key ideas, making my website look nicer.
However, right now the ideas themselves feel more important - and I’m just focussing purely on that.
I feel like I’m going against the grain here - the conventional wisdom seems to be that you should always be shipping things as you go along. But I’m hoping this will help me make things that are better quality, or more deeply thought-through. I guess time will tell whether this ends up being the case.
About Me
👋 Hi, I'm Chris Lovejoy.
I'm a medical doctor 🩺 -> machine learning engineer 👨💻 -> start-up founder 💡
I'm on a mission to improve how we manage our health - and share my learnings and experiences here, on my personal website and on YouTube.
I also throw in my favourite things from the internet, and the occasional joke (humour is work-in-progress).