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.Continue reading “RCTs vs Real-World Evidence for medical AI”
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.Continue reading “Invited Speaker: Dynamics of Immune Responses”
First a mea culpa, I have a huge backlog of relatively heavy articles that I really want to add to the blog. But I’ve been busy getting married – congratulations to me – and I didn’t have enough time. I strongly believe in following relatively strict guidelines on writing and editing articles, where I set myself deadlines and avoid over-writing on topics – it is just a blog after all – but for deep insights I do also have a minimum standard that I want to be able to produce before I’m willing to hit the Publish button.Continue reading “Build – Test – Move”
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.Continue reading “New Project: Causal Inference”
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.Continue reading “Closing a Chapter @ Fosanis”
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.Continue reading “Why do Trees work better than DNNs on genome data?”
How do I really feel about this topic? I think that I can only work out the answer to this question by writing about it.
My suspicion is that those who shout loudest about personalised medicine know least about it. I fear that the promises being made publicly are categorically not possible. My hope is that I am wrong on this.Continue reading “Personalised Medicine – A statistical theory approach”
Apparently, it’s that time again. I just gave my second invited keynote at a conference at Charité Berlin. It was really fun.
The audience were dentists – academic dentists. I confess that I struggled to understand why they thought I would be a good fit for their conference. My previous keynote was at the BIH Digital Health Forum – a much more obviously appropriate audience. But, perhaps strangely, the fit was very good.Continue reading “Keynote @ Charité Berlin”
Last week I was invited to chair the panel discussion at the Digital Health Forum of the Berlin Institute of Health. The keynote was a joint presentation by Michelle Livne, the CTO of recently founded ai4health, and Kerstin Ritter, a junior professor at Charité Berlin.
I started working at a new job last week. I am now the Head of Data Science at Fosanis GmbH. We’re a startup in Berlin, two years old, and we provide support services for cancer patients. My task is to personalise the approach.
Think personalised medicine, without the medicine. The content we provide has been professionally curated and has been shown to be beneficial to cancer patients. If you speak German, you can try out the content online right now. We will be launching an App-based implementation in the new year.
I want to then take this to the next level. Patients will be treated as a combination of their statistical attributes and their individual trajectories through the interface. From a technological point-of-view, we will be aping many of the approaches pioneered by Facebook. However, we will try to maximise a much trickier to define Quality of Life metric, rather than page refreshes or time spent on the Wall.
This is a really exciting project. I have been looking for a while to find a project where I can apply behavioural modelling approaches to healthcare goals. In a world of rapidly expanding autoimmune diseases I see this ultimately as the new treatment paradigm. What is especially nice is that, in the space in which we are operating there are no real conflicts of interest. I hope that I don’t look back on that statement as hopelessly naive. My impression is that most people in oncology are really trying to make patients’ lives better.
We will be hiring in the first couple of months of 2019, so if you know any talented biological modellers who might be interested, please tell them to email me their CV.