Jailbreaking spine fracture braces. The image is CC by Parée.
Continuing on the theme of #2MuchMed (see BMJ’s campaign) I figured it may be worth highlighting two recent studies on stable compression fractures of the spine. Both failed to show any benefit with standard bracing treatment. As some patients experience the brace as claustrophobic and uncomfortable (from my own patients’ experience), I’m thrilled to have this option available. Continue reading
Will Carson et al.’s study be the garlic that deters the most blood thirsty colleagues? The image is CC by Gaviota Paseandera.
As I have a weakness for studies that challenge the dogma, I was ecstatic when I stumbled upon Carson et al.’s bold study on blood transfusions. In their study they selected 2000 patients with cardiovascular disease that were undergoing surgery due to hip fracture. Interestingly, there was no difference in 3-year mortality when randomizing between transfusion Hemoglobin thresholds of 100 g/L or 80 g/L! Continue reading
The abilities of deep learning are fascinating, just as this Paschke arch CC by David DeHetre
One of the successful insights to training neural networks has been the rectified linear unit, or short the ReLU, as a fast alternative to the traditional activation functions such as the sigmoid or the tanh. One of the major advantages of the simle ReLu is that it does not saturate at the upper end, thus the network is able to distinguish a poor answer from a really poor answer and correct accordingly.
A schematic of the PReLU. The LReLU has the same schematic with the only difference being the α being a constant. Curtesy PReLU article.
A modification to the ReLU, the Leaky ReLU, that would not saturate in the opposite direction has been tested but did not help. Interestingly in a recent paper by the Microsoft© deep learning team, He et al. revisited the subject and introduced a Parametric ReLU, the PReLU, achieving superhuman performance on the imagenet. The PReLU learns the parameter α (alpha) and adjusts it through basic gradient descent.
In this tutorial I will benchmark a few different implementations of the ReLU and PReLU together with Theano. The benchmark test will be on the MNIST database, mostly for convenience. Continue reading
Age is perhaps one of the most important confounder that none of us can escape. The image is CC by Sara.
Age is an important confounder in studying most health related outcomes [1, s 5], and perhaps the most commonly adjusted variable. In this and next post I will go into (1) what we know about the age effect in relation to total hip replacements (THR) re-operations and mortality, (2) what I found in my study on age and health-related quality of life (HRQoL) using splines, and (3) how I implemented and evaluated different splines using R for this study. Continue reading
Even the operation of the century has a dark side. The image is CC by Holley And Chris Melton.
While total hip replacements (THR), also known as total hip arthroplasties, are hugely successful there still are, and will always be, poor outcomes. This post is an excerpt from my thesis where I tried to summarize the dark side of THR. Continue reading
Title: Evaluation of patient related factors influencing outcomes after total hip replacement
On May 29:th I successfully defended my thesis at the Karolinska Institute and I’m now a “Doctor of Philosophy“, i.e. PhD. It has been a fun and rewarding project that spurred me into starting this blog and diving into R. Below you can find the thesis abstract and my reflections on the subject. Continue reading
A DAG can help you take the right path. The image is CC by Ian Sane
I recently wrote about blood transfusions and their inherent risk of postoperative infections. This post is a tutorial on some of the basics of drawing a directed acyclic graph (DAG). Blood transfusions and infections is a great topic as most are familiar with risk factors for infections. Continue reading
A beautiful old document. Probably state of the art in those days. The image is CC by storebukkebruse.
Fast-track publishing using knitr is a short series on how I use knitr to get my articles faster published. By fast-track publishing I mean eliminating as many of the obstacles as possible during the manuscript phase, and not the fast-track some journals offer. In this first introductory article I will try to (1) define the main groups of obstacles I have experienced motivating knitr, (2) options I’ve used for extracting knitted results into MS Word. The emphasis will be on general principles and what have worked for me. Continue reading
![Pubmed trends showing how the popularity of analyzing comorbidities have increased over time. The search query is "Arthroplasty[MeSH Major Topic] AND (comorbidity OR co-morbidity)", for the blue bar I also added "AND (Charlson OR Elixhauser)" to indicate that the popularity of using scores that summarize the comorbidities also are increasing.](http://gforge.se/wp-content/uploads/2013/09/fig_1_pubmed_trends.png)
Pubmed trends showing how the popularity of analyzing comorbidities have increased over time. The search query is “Arthroplasty[MeSH Major Topic] AND (comorbidity OR co-morbidity)”, for the blue bar I also added “AND (Charlson OR Elixhauser)” to indicate that the popularity of using scores that summarize the comorbidities also are increasing.
Using large databases for extracting data can be cumbersome, fortunately it’s more reliable than sifting for gold. The image is CC by Won-Tolla.
I put a lot of effort in to my first article to calculate the comorbidities of a patient according to the Charlson & Elixhauser scores. The available scripts were in SAS and Stata, as I started out using SPSS I decided to implement the code in the neat Python plugin that SPSS provides. In this post I’ll provide you with a detailed walk through of my code, and hopefully it will save you some time. Continue reading