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.
Continue reading “Digital Privacy”
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.
my first startup. It’s done, we’ve shut it down.
I joined Entrepreneur First‘s initial Berlin cohort in April (2018). Through the process, I very quickly met my cofounder and founded Simmunology Limited. We followed the checkpoints laid down by Entrepreneur First (EF), through founding the company, right up to receiving an initial investment of UK£80,000 in return for 10% of the company. Then, at the end of the kick-off meeting, I told them I wanted to shut it down… Continue reading “Simmunology was…”
The hosts of PyData Berlin 2018 have published the video of my talk on YouTube. I previously described the talk in detail in my post on AI in Healthcare.
This is an article which I don’t want to write, but I also do. I live my life as if nothing happened. I pretend nothing happened. But the effects on my life both then and since have been enormous.
Where were you when 9/11 happened? I was at my parents’ house in Ireland, preparing for my first day at university. I know this because I’ve told myself the story many times by now. I’ve seen the TV reports so often that I can remember the planes crashing into the towers. Only I can’t. I don’t remember any of it.
I was 19 and at least 6 months of my life are completely missing. I got up most days. I talked with people. I successfully registered for university. I moved into on-campus accommodation. I did sport on rare occasions. I even had a girlfriend for 3 months. But the memories were never formed, or if they were I have never had subsequent access (for the neuroscientists out there: they faded out about 12 months later). Continue reading “Chronic Fatigue Syndrome”
Continued from Part I
Part I of this article appeared last week. In it I introduced the topic of statistical vs biophysical approaches to biological applications. I discussed the huge power of statistical approaches in image analysis and providing decision support services to doctors. I then discussed the 5 major limitations of data-driven approaches when they are applied to biological problems.
I will now continue by looking at biophysical approaches, their pros and cons, and finishing up with a brief introduction to hybrids which attempt to combine these two methods. Continue reading “AI in Healthcare II”
I live in Berlin, which is fast becoming the tech hub of Europe. Over the past two years we have seen a massive up-tick in the number of healthcare oriented startups, which are receiving funding on the basis of their use of Artificial Intelligence (AI). As somebody who knows a bit about the underlying technical and application problems of AI, what I see has made me very uneasy.
As a result of some personal conversations I was invited to give a Keynote address to the Digital Health Forum of the Berlin Institute of Health in March. This is a big deal because the BIH is a joint venture between Europe’s biggest teaching hospital, Charité Berlin, and one of Germany’s foremost centres for biological research, the Max-Delbrueck-Center, Berlin. The talk was extremely well received, so I have now given a public version at PyData Berlin 2018 which will be published on their YouTube channel in the coming weeks. (Update: the video is available here). In the meantime, I have written the discussion up as an article in two parts: part I is below and part II is available here. Continue reading “AI in Healthcare I”