Author: Gary Hutson

Feed: R-bloggers. Author: Gary Hutson. My current company Draper and Dash have been working on the Healthcare DSP for a number of months and we are now ready to launch. Find out what the HTN had to say: https://www.thehtn.co.uk/2020/09/15/new-health-data-science-platform-launches/A word from D&D’s Chief Technology OfficerData Science Resilience & Collaboration in times of unprecedented disruption https://t.co/pPYTw55w4g – all powered by R and Python under the hood. It has been great to work on this project.— Gary Hutson (@StatsGary) September 17, 2020What it does?The DSP uses web technologies alongside Healthcare models built in R and Python to combine analytics with predictive machine ... Read More

Feed: R-bloggers. Author: Gary Hutson. Yesterday (17th June) I did a session with the NHS-R Community relating to how to use the brilliant CARET package to build, evaluate, train and improve machine learning models. This was an entry level webinar to highlight the possibilities of how supervised machine learning could be used in the NHS to inform and augment decisions. For access to the webinar, check out the video: Advanced Modelling in R with CARET – focus on supervised machine learningWhere to find the content The materials for the session can be downloaded from the NHS-R git repository, as ... Read More

Feed: R-bloggers. Author: Gary Hutson. When I am doing a Machine Learning project with R it is crucial to save those precious seconds, minutes, hours in model training. To make sure you optimise your CPU and crank up the performance you will need to load in the parallel and doParallel libraries, alongside library(caret). A wrapper function to help with this I have created a wrapper function to help with this. I will stored this in a separate file, located on a shared directory, that I can call and use with my projects in R. The bones of the function The ... Read More

Feed: R-bloggers. Author: Gary Hutson. Motivation for this The background to this package linked to a project I undertook about a year ago. The video relates to the project and the how R really sped up the process. The exam question was to use a regression model to predict admissions and we had to evaluate, as a consequence, 60 different variations. In Excel, this would have been a nightmare. Again, R to the rescue. You can see the presentation below, if interested: Getting off my arse and creating the documentation / package Reflecting and cogitating on the NHS-R conference this ... Read More

Feed: R-bloggers. Author: Gary Hutson. Recently, our team at Draper and Dash have been busy creating an NHS operational command centre. This command centre is different, as it uses a collection and ensemble of cutting edge predictive and machine learning techniques. To read the blog you can access this below: We have really enjoyed the process and we are in the process of creating the technical documentation for the R scripts and releasing the code. Please watch this space for further updates around the models we have used. All our solutions are created in R and are validated with key ... Read More

Feed: R-bloggers. Author: Gary Hutson. My company Draper and Dash have tasked me with organising a wider meet-up event for anyone who is interested in AI / ML in healthcare. This wider working group consists of people from different sectors, however they are interested in how we can apply AI / ML methods in their organisations. Why did we choose meet-up Meet-up seems like a great way to engage like minded people from across different communities. What is our first event Our first event is detailed below: Using Supervised ML Methods to augment intelligent dashboards in Healthcare Wednesday, Nov 6, ... Read More

Feed: R-bloggers. Author: Gary Hutson. Lots of exciting things are happening with Draper and Dash at the moment. We have been working with key healthcare partners to design some core predictive machine learning algorithms to enable trusts to more effectively manage their performance, demand and capacity pressures. This series focuses on Stranded Patients and Super Stranded patients – these are patients who have been in hospital for 7 or more days, with super stranded being longer than 21 days. What the aim of our algorithm is the detection of these stranded patients, by risk stratification and classification methods. What this ... Read More

Feed: R-bloggers. Author: Gary Hutson. Our company have been at it again. This time from my colleagues and fellow Data Scientist Alfonso Portabales. For this post we look at Draper and Dash’s custom method of highlighting dominant predictors in your machine learning models: If you are interested in our solutions in healthcare then please contact [email protected]. Additionally, we are also available for speaking gigs at conferences to show how we have become a market leader in terms of augmented BI solutions. Consulting is something we also do on how to integrate ML with various BI solutions e.g. Tableau, Power BI ... Read More

Feed: R-bloggers. Author: Gary Hutson. As a product of a series of training sessions Draper & Dash have been undertaking on Machine Learning using R – a candidate from the course asked “how do you split a model to later be used in a live / production environment?”. This post aims to answer that question: I hope you find this useful and keep posted for more updated indirectly by me. Related If you got this far, why not subscribe for updates from the site? Choose your flavor: e-mail, twitter, RSS, or facebook ... Read More

Feed: R-bloggers. Author: Gary Hutson. As part of my companies commitment to allow our users access to some of our code – we have created a visual way you can assess your accuracy in a confusion matrix. The below was posted on our blog site and shows how to interpret a confusion matrix. I hope the attached article is useful. Please check out Draper and Dash’s main website for more information about the exciting and innovative way we are using data science with healthcare data. Signing off! And remember… Related If you got this far, why not subscribe for updates ... Read More