I am asked quite often how I see Data Science in the biomedical industry. I have, of course, many answers each of which is context dependent. However one theme which I find frequently recurring is a sort of straw-man debate which seems to inherently attract technical practitioners.
The debate is usually structured as follows: How do you see the validation of medical AI products working in practice? Answer: clinical trials, test-validation sets, blah, blah But doesn’t this lead to enormous overheads? Answer: yes, but there are shortcuts But if you take these shortcuts then don’t you run the risk of running into costly failures when you finally run the clinical trials? It goes on….
Working in industrial research is usually very motivating but occasionally it is also frustrating. You’ve just done something really cool but you’re not allowed to tell anybody outside the company about it. Indeed, in a small company there might not be anybody inside of the company who can even appreciate it!
I have worked on roughly 4 really cool projects since leaving academia at the end of 2017. And apart from some basic mentions in my blog (e.g. here and here) most of what I have done has been known only to a few key stakeholders.
Randomised controlled trials (RCTs) have been the gold standard for statistical evidence, of treatment effect, for over 100 years. Their strength is in their attempt to avoid major sources of bias in a comparison of the evidence. However, they are costly to run, particularly in the domain of personalised medicine, to which medical AI products typically belong.
There is a growing awareness in the field of immunology of the potential for using mathematical techniques. The wedge-issue here is the cascade of data appearing via new cytometry techniques; large-data looks like a math issue to most people. I of course come from the other side of a spectrum – everything looks like a math issue to me – I wanted to stimulate drug development which engages with immune system dynamics by founding my company.
I have a short thought, stemming from a combination of projects that I’m working on at the moment, and I want to share it.
The current trend towards Causality in AI is very attractive to people like me. It matches our personal biases and views of the world. However, it is lacking a natural heuristic. How do we decide how much resources to devote to alternative models of the world, as we gather evidence as to their accuracy?
Like I say, I have a number of parallel projects, many of which address exactly this question on technical and biological levels.
There is something from the world of business, studying entrepreneurship, which might be a better heuristic than any normative model I can come up with. Effectual entrepreneurship is a perspective on entrepreneurship, studying highly successful repeat entrepreneurs (eg. Elon Musk), which establishes control, rather than planning, at the core of entrepreneurial activities.
I am beginning a new project this week, the topic is Causal Inference. This is something I have been reading about, and wrestling with, for quite some time. Now seems a good point to take some time out, form a project, and see what I can get done on the topic.
Today is my last official day under contract to Fosanis GmbH. I had my first encounter with the founders following my talk at the Digital Health Forum in March 2018. Following that initial meeting I became an advisor, writing a major funding proposal, bringing scientific techniques to the core of the product. In November 2018, following the closure of my own company, I became a full-time member of staff – as Head of Data Science – and led the project on the basis of the ideas contained in my funding proposal.
I sometimes see myself as a slow learner. I am extremely fast at deep-thinking, which somewhat disguises this fact, but I learn things from the ground up. Until I can think a topic through I sometimes feel unsure about operating from an incomplete understanding.
When I worked in academia I prefered to learn rather than to force my opinions on others. Everybody seemed reasonably smart, and they were absolutely convinced of their own correctness, and so I listened and learned. Continue reading “Why I write”
This topic occurred to me following my recent talk at a dental conference at Charité Berlin. Upon hearing that I have a strong interest in inference, my fellow keynote mentioned that it drives him crazy that random forests, and similar algorithms, work so much better than DNNs on genomic data. He challenged me to come up with a reason for why this is the case.
I think that I know why. The problem I have is that I suspect that I can never prove it. That issue of not being able to prove things in machine learning is probably an equally interesting topic, for a future article, but here I want to address my theory of why random forests work better than DNNs for analysing genome data.