Innovation Roundup (( by Hamid Ghanbari, MD ))
A newsletter about innovation, technology and empathy in medicine (10-2-21)
Hi Everyone,
Here is the best of what I have been reading and writing this week. I hope that you enjoy them as much as I did.
Hamid
I had a great conversation with my friend and colleague Elaine Wan from Columbia about her recent white paper. We discussed the future of digital health, opportunities and challenges in the coming decades.
Department of Reading
“A very popular error: having the courage of one’s convictions; rather it is a matter of having the courage for an attack on one’s convictions.”
—Nietzsche
How trust in science undermines science - I recently discovered the works in progress website and it is treasure trove of fascinating pieces. It has become one of the website I visit regularly. This piece was a great exploration between trust and the scientific process.
Our success is based on scientific discovery, so it’s not surprising how much faith we put into it. But we now trust science so implicitly that our trust undermines the institution itself.
We can take the unquestioning attitude towards a wide variety of objects and artifacts. To trust, in this sense, is to have stepped away from the deliberative process. It is a way of settling one’s mind about something. To trust is to lower the barrier of monitoring, challenging, checking, and questioning—to let something inside, and permit it to play an immediate role in one’s cognition and activity. It is, in a sense, to give an external resource a direct line into one’s reasoning and agency.
Life is disaster, life is beautiful- A great meditation on life using one of my favorite movies (Life is Beautiful) and books (The Road) of all time.
The world is terrifying in its vastness and apparent unconcern for the things that are most important to us. Far from being simple ignorance or some kind of sad joke played on the weak and pathetic, our games are among the most noble and beautiful of human inventions. They are a flowering of life and an insistent refusal to give in to nihilism and hopelessness.
… Perhaps my essay here only describes the response of the Fool, but I’m not convinced that the Fool is not possessed of a deeper wisdom which eludes my rationalist friends.
Dealing with uncertainty A tour de force on uncertainty, what it is and how to make predictions under uncertain conditions and why we must accept more failure in the pursuit of long-term success
The Desk- Beautifully written memoir on poverty, family, immigration and how we use objects to shield us from reality
I spent more and more time at the desk, doing homework, drawing, putting things in the drawers, taking them out again, fantasizing about the pictures inside... The pictures were portals to other worlds. My room, I told my parents. This is my room
Department of Digital Health
A deep transfer learning approach for wearable sleep stage classification with photoplethysmography
The authors trained a deep recurrent neural network using a large sleep data set with ECG data to perform 4-class sleep stage classification (wake, rapid-eye-movement, N1/N2, and N3). A small part of its weights was adapted to a smaller, newer PPG data set through three variations of transfer learning. Best results (Cohen’s kappa of 0.65 ± 0.11, accuracy of 76.36 ± 7.57%) were achieved with the domain and decision combined transfer learning strategy, significantly outperforming the PPG-trained and ECG-trained baselines. This is promising work especially if it can perform this well in sleep apnea or other sleep related disorders
A survey in transfer learning -
The paper above led me down the transfer learning rabbit hole. This is great paper outlining this technique.
The technique intuitively involves transferring knowledge from a model trained on a large “source” data set to solve a new but related problem where less data samples are available in a “target” data set.
Department of Innovation
Clusters rule everything around me- Interesting essay on how tech cluster develop and how we can use them replicate success. There is fascinating angle here as move to more and more remote innovation. I am a bit more optimistic than the author but he makes a very persuasive argument here.
a world with widespread remote work will still benefit from tech clusters so long as physical human interaction provides benefits to innovation above and beyond the best interactions offered digitally
Department of Productivity
A fun video with ranking of the best productivity hacks of all time.
Podcast
I am a big fan of Lex Fridman and I think this conversation will show you why. This is personal and interesting conversation about AI, robots, loneliness, violence and love. Recommended
Department of Aesthetics
Album of the week
The Doors - Maybe one of the greatest Classic Rock albums of all time
Painting of the week
Girl Reading, Pierre-Auguste Renoir, c. 1890
Thank you again for reading my newsletter.
If you enjoy reading this newsletter, please share it with someone else who might enjoy reading it.
Talk Soon,
Hamid