We present a Machine Learning (ML) study case to illustrate the challenges of clinical translation for a real-time AI-empowered echocardiography system with data of ICU patients in LMICs. Such ML case study includes data preparation, curation and labelling from 2D Ultrasound videos of 31 ICU patients in LMICs and model selection, validation and deployment of three thinner neural networks to classify apical four-chamber view. Results of the ML heuristics showed the promising implementation, validation and application of thinner networks to classify 4CV with limited datasets. We conclude this work mentioning the need for (a) datasets to improve diversity of demographics, diseases, and (b) the need of further investigations of thinner models to be run and implemented in low-cost hardware to be clinically translated in the ICU in LMICs. The code and other resources to reproduce this work are available at https://github.com/vital-ultrasound/ai-assisted-echocardiography-for-low-resource-countries.

Scientists studying Antarctica's vast Thwaites Glacier – nicknamed the "Doomsday Glacier" – say warm water is seeping into its weak spots, threatening its demise and a massive sea rise. Thwaites, which is roughly the size of Florida, represents more than half a metre (1.6 feet) of global sea level rise potential, and could destabilise neighbouring glaciers that could cause a further 3-metre (9.8-foot) rise. As part of the International Thwaites Glacier Collaboration – the biggest field campaign ever attempted in Antarctica – a team of 13 scientists from the United States and United Kingdom spent about six weeks on the glacier in late 2019 and early 2020. Using an underwater robot vehicle known as Icefin, mooring data and sensors, they monitored the glacier's grounding line, where ice slides off the glacier and meets the ocean for the first time. In one of two papers published on Wednesday in the journal Nature, led by Cornell University-based scientist Britney Schmidt, researchers found warmer water was making its way into crevasses and other openings known as terraces, causing sideways melt of 30 metres (98 feet) or more per year.

Icefin the robot is designed to go where no human can, swimming off the coast of Antarctica under 2,000 feet of ice. Lowered through a borehole drilled with hot water, the torpedo-shaped machine takes readings and--most strikingly--video of Thwaites Glacier's vulnerable underbelly. This Florida-sized chunk of ice is also known as the Doomsday Glacier, and for good reason: It's rapidly deteriorating, and if it collapses, global sea levels could rise over a foot. It could also tug on surrounding glaciers as it dies, which would add another 10 feet to rising seas. In a pair of papers published today in the journal Nature, scientists describe what Icefin and other instruments have discovered underneath all that ice.

This story was originally published by Wired and is reproduced here as part of the Climate Desk collaboration. Two Decembers ago, Erin Pettit layered up, slapped on goggles, cued up an audio book, and went on a hike--across Thwaites Glacier in Antarctica. Behind her, she dragged a sled loaded with a ground-penetrating radar, which fired pulses through a thousand feet of ice and analyzed the radio waves that bounced off the seawater below, thus building a detailed image of the glacier beneath her feet. Pettit--a glaciologist and climate scientist at Oregon State University--hiked alone through the snow, sometimes eschewing headphones for the absolute auditory stillness of the most remote landscape on Earth. "It was actually kind of an amazing, meditative field season," she says, "I just bundled up, I went out there and pulled my sled, and just walked for miles and miles."

Two Decembers ago, Erin Pettit layered up, slapped on goggles, cued up an audio book, and went on a hike--across Thwaites Glacier in Antarctica. Behind her, she dragged a sled loaded with a ground-penetrating radar, which fired pulses through a thousand feet of ice and analyzed the radio waves that bounced off the seawater below, thus building a detailed image of the glacier beneath her feet. Pettit--a glaciologist and climate scientist at Oregon State University--hiked alone through the snow, sometimes eschewing headphones for the absolute auditory stillness of the most remote landscape on Earth. "It was actually kind of an amazing, meditative field season," she says, "I just bundled up, I went out there and pulled my sled, and just walked for miles and miles." In case you were worried, her colleagues always knew where Pettit was; every so often someone would roll out on a snow machine to bring her supplies or to swap out the radar's battery.

Conditional preference networks (CP-nets) are a graphical representation of a person's (conditional) preferences over a set of discrete features. In this paper, we introduce a novel method of quantifying preference for any given outcome based on a CP-net representation of a user's preferences. We demonstrate that these values are useful for reasoning about user preferences. In particular, they allow us to order (any subset of) the possible outcomes in accordance with the user's preferences. Further, these values can be used to improve the efficiency of outcome dominance testing. That is, given a pair of outcomes, we can determine which the user prefers more efficiently. Through experimental results, we show that this method is more effective than existing techniques for improving dominance testing efficiency. We show that the above results also hold for CP-nets that express indifference between variable values.