In this piece I contrast absolute and relative risks, compare risks and odds, and show how to derive each measure in a generalised linear model framework using R.

What is the risk of a new creditor to default on their loan? what is the “risk” of watching a certain movie on Netflix given a certain viewing history? What is my risk of dying given a certain diagnosis and how is this affected by a certain treatment? Risks are…

Make your next R project reproducible with these five easy principles, and generate the same results again, and again, and again.

We’ve all been there. You are asked to quickly rerun one of the complex analysis projects you had completed a few months ago. A new cut of the data has arrived and the new results need to be generated quickly. Confident you open the folder with all the analysis and…

In this article I show how to quickly deploy R/Shiny Apps on Azure and make them available globally within seconds.

R/Shiny apps are a great way of prototyping, and visualising your results in an interactive way while also exploiting the R data science and machine learning capabilities. R/Shiny apps are easy to build in a local development environment but they are somewhat harder to deploy. …

In this piece I investigate to to what extent Covid-19 case rates are driven by social inequality using data from the UK.

While Covid-19 is still raging, and retaining a firm grip on societies around the globe it is worth focusing our attention not only on the purely medical aspects of the pandemic but also its societal consequences.

Society is inherently stratified. Some people earn more than others. Other people achieved high…

In this introduction I show how to build and deploy R/Shiny and MS SQL Server containers.

R/Shiny apps are a great way of visualising your results in an interactive way while also exploiting the R data science and machine learning capabilities. While R/Shiny apps are easy to build in a local development environment they are somewhat harder to deploy. Common options include the free and paid…

In this article I show how machine learning can be used to optimise systems to book medical appointments and reduce waste of physician time

Non-attendance of medical appointments is more common than you might think. In the NHS in England 15 million general practice (GP) appointments are being wasted every year. This adds up to 1.2 million GP hours wasted each year, which is the equivalent of over 600 GPs working full time for…

Dr Andreas Ochs

Andreas is a Biostatistician, passionate about using large-scale healthcare data to inform strategic and operative decision-making in healthcare delivery.

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store