Software engineers are improving healthcare behind the curtains
Introduction
The purpose of this post is to give a glimpse of how young people with diabetes type 1 are implementing new technologies in an unusual way to improve their lives.
What is Diabetes type 1?
Type 1 diabetes is an autoimmune disease in which the insulin producing cells of the pancreas are destroyed by the immune system. Insulin is a hormone required for all cells in the body to use glucose as energy after it has been absorbed from food into the bloodstream. Insulin thereby helps to regulate glucose levels in the bloodstream. Without insulin, patients with type 1 diabetes will suffer from the consequences…
A tutorial about automation with Python and ReportLab
The first humans set foot on the moon in 1969. It’s now 2021 and the routine completion of medical forms is still done in some cases with pen and paper…
Let’s take the case of a death declaration. With pen and paper, you have to find the information in different tables scattered throughout a patient file and write them down. This takes about 5–10 minutes of your time if you’re lucky. But if you’re doing it in the middle of the night and you make a mistake because your head is still dreaming about that nice vacation on the beautiful…
Thoughts of a German genius in a digital world
Marx his analysis
In my path of becoming code literate, I was reluctant to get into algorithmic trading. I had been mostly confronted with the dark sides of capitalism, so I wasn’t interested. That was until I began to see the results of what I could do with Python in some small projects. After these successes, I needed more challenging projects, but also a more serious project, a project I could use to get more experience in coding solutions for real-life problems. …
An argument for the second “hello word”
Python can extend the power of your brain exponentially through mass data analysis, but getting started with coding can be just as chaotic as entering any community within normal life. There are different versions of the language, different modules to achieve the same thing, different habits for testing and debugging code, different software programs you can use as a coding interface, etc. In everyday culture, there are rituals that give structure to the chaotic environment that we live in. We say “Hi” to our neighbours, we go to school to get a diploma, we comb our hair in the morning…
Machine learning is a double-edged sword
Introduction
There has been a lot of controversy about how bias in machine learning portrays social inequalities and how this might affect the outcomes of minority groups (also see this article named “AI is sending people to jail”). To be blunt, I don’t agree. Looking past the headlines that try to stimulate the emotional part of our brain will show you that machine learning is a two-edged sword. This post was written to demonstrate the other side of this sword. …
I couldn’t find a Medium post on this one. There is one by Angelica Dietzel but it’s unfortunately only readable if you have a paid account on Medium. If you have any suggestions for improvement on the method I will demonstrate here please leave a comment.
A typical website hierarchy
We start with a visual hierarchical representation of a website.
In red are pages that contain links where you don’t want to go (Facebook, Linkedin, other social media pages). In green are the places where you want to extract valuable information from. …
A short article review
Introduction
As you might know from your own experience, or from the experiences of the people around you, medical assessments in the emergency department can take a painfully long time. This post is a short review of the paper Machine learning for developing a prediction model of hospital admission of emergency department patients: Hype or hope? scheduled for publication in August 2021 in the International Journal of Medical Informatics. The authors used logistic regression, random forest trees, XGBoost gradient boosted decision trees and deep neural networks to predict whether patients will be hospitalized after they visited the…
Options for passing around stock information within Python code:
- Raw dictionary
Creating a dictionary with stocks as keys and stock characteristic as values, passing the dictionary around as a function input parameter or in a pickle file. - List of lists
Doing the same as above with stock saved as a list of characteristics and assigned to a variable of which the name is a reference to a stock. Then create a list of lists as the collection of stocks and pass it around as above. - Dictionary of class objects
Creating a class for stocks, creating a class instance for every stock…
An excerpt from small talk at work
Colleague: Are you new over here?
Me: No I’m the medical backup for the vaccinations that are taking place. I’m here to help in the case something bad happens.
Colleague: Yes, you need a doctor for that of course. I’ve applied for the Janssen vaccination but I didn’t hear anything yet from my family doctor. I’m above 60.
Me: Oh wow. That’s strange…
Colleague: Yes but a time ago I refused AstraZeneca. I don’t want that.
Me: Mhm…
Colleague: I’m seeing young people around me that get vaccinated and I’m 63 years old…
At the start of a shift for a nursery home organisation, you are the first contact for nurses. It’s often not clear what has happened in the different departments within the last few days. How many calls were related to COVID? How many patients are in isolation? How many patients are in palliative care? How have these numbers changed in recent days?
Beneath is a Python script for analysing the covid workload during the last week in a nursery home. There are notes within the script to clarify the different steps. Some steps are cumbersome and can be condensed but it was a good exercise to go through it step by step without dense code. When you plot the data in a Dash graph you get the following graph:
This is the code:
Kelvin Kramp
MD and PhD. Let’s bring health and tech together.
