If you would like to join my mailing list and receive updates with links to newly published content, let me know by emailing me at email@example.com
It a recent study, machine learning algorithms were able to predict age, gender, smoking status, systolic blood pressure, and major adverse cardiac events, using nothing but pictures of patients’ retinas. The accuracy of these predictions is quite high, as you can see by reading the excerpt below. The fact that this degree of accuracy can be achieved by using nothing but pictures of retinas is pretty astounding.
“Using deep-learning models trained on data from 284,335 patients and validated on two independent datasets of 12,026 and 999 patients, we predicted cardiovascular risk factors not previously thought to be present or quantifiable in retinal images, such as age (mean absolute error within 3.26 years), gender (area under the receiver operating characteristic curve (AUC) = 0.97), smoking status (AUC = 0.71), systolic blood pressure (mean absolute error within 11.23 mmHg) and major adverse cardiac events (AUC = 0.70). We also show that the trained deep-learning models used anatomical features, such as the optic disc or blood vessels, to generate each prediction.”
AUC: A measurement of the accuracy used in machine learning. Higher values equal better accuracy.
“The move on Tuesday is the latest sign that market forces are throttling the Trump administration’s bid to save the industry.”
“Once the source of over 40 percent of the country’s power, coal produced 28 percent in 2018. That share has declined to just 25 percent this year, and the Energy Department projects that it will drop to 22 percent next year.”
If you’d like to learn about some of the dangers the burning of coal poses to public health, check out this article I wrote for The Environmental Magazine: Just How Bad Is Air Pollution in China and How Can We Fix It?
“Our freedoms are disappearing, and I don’t want to live in a place where I can’t speak freely about my opinion.”
“I’m still too young to stand on the front line, but one day I will stand up and tell the whole world that we in Hong Kong are not afraid, and that we will not hide or escape, and that we’ll always fight for freedom.”
“The emissions generated by watching a half hour of Netflix is the same as from driving almost 4 miles.” (Depending on what type of car you are driving)
“Taken in total over last year, online video streaming services generated as much in emissions as the country of Spain.”
Streaming data requires energy. Video files are very large, and require quite a lot of energy to send across the internet. The additional load this energy puts on the grid is the reason for streaming’s relatively high carbon footprint.
Although there are many, more climatologically impactful activities than streaming videos over the internet, the study cited in this article clearly demonstrates the fact that many of our day to day activities have subtle effects on the environment that often fly under the radar.
Powerful Interview with Jose Mujica, the former President of Uruguay
“…now, I’m the president. And tomorrow, like everyone, I’ll just be a pile of worms, and disappear.”
- Mujica was president of Uruguay from 2010 to 2015. During this time, he donated approximately 90% of his $12,000 per month salary to charity.
Excerpt from the book Tribe, by Sebastian Junger
In late 2015, a bus entering eastern Kenya was stopped by gunmen from an extremist group named Al-Shabaab that made a practice of massacring Christians as part of a terrorism campaign against the Western-aligned Kenyan government. The gunmen demanded that Muslim and Christian passengers separate themselves into two groups so that the Christians could be killed, but the Muslims – most of whom were women – refused to do it. They told the gunmen that they would all die together if necessary, but that the Christians would not be singled out for execution. The Shabaab eventually let everyone go.