Public Health


From social media to public health surveillance: Word embedding based clustering method for twitter classification

@machinelearnbot

Social media provide a low-cost alternative source for public health surveillance and health-related classification plays an important role to identify useful information. We summarized the recent classification methods using social media in public health. These methods rely on bag-of-words (BOW) model and have difficulty grasping the semantic meaning of texts. Unlike these methods, we present a word embedding based clustering method. Word embedding is one of the strongest trends in Natural Language Processing (NLP) at this moment.


Using the IoT and machine learning to track progression of lung disease

#artificialintelligence

IBM scientists Thomas Brunschwiler and Rahel Straessle are developing machine learning algorithms to interpret the IoT data. COPD, is a progressive lung disease which causes breathlessness and is often caused by cigarette smoke and air pollution. By 2030, it is expected to be the third leading cause of death worldwide, with 90% occurring in low and middle-income countries, according to the World Health Organization. The Centers for Disease Control and Prevention reports that by 2020 the expected cost of medical care for adults in the US with COPD will be more than $90 billion, mainly due to complications and multiple hospitalizations, many of which are preventable with better healthcare management and more personalized and frequent patient support. Management and prevention of COPD is the focus of a new research project presented today at the 19th annual IEEE Healthcom Conference, in Dalian, China.


Science Says _13 Reasons Why_ May Be the Public Health Scare People Thought

WIRED

They've done things like use Twitter data to call attention to a spike in distracted driving incidents thanks to Pokemon Go players behind the wheel. And previous studies have found correlations between suicide search trends and actual suicide rates. So Ayers and his colleagues grabbed search queries from the US between March 31, 2017, the series' release date and April 18, a date the team selected as a cutoff because news of former NFL player Aaron Hernandez's prison suicide might have contaminated the results otherwise. They looked at all searches containing the word "suicide," except for those accompanied by the word "squad," for obvious reasons.


Why Is U.S. Maternal Mortality So High?

Slate

Maternal-fetal medicine specialists like us are tasked with caring for women with "high-risk" pregnancies, usually defined as pregnancies complicated by chronic or acute maternal illness, fetal concerns, or problems related to pregnancy itself (e.g. Our nuclear event--one of the worst things that can happen when we practice--is a mother dying. Maternal mortality in the United States is rare but, sadly, nowhere near rare enough: Data collected from 1990–2015 show that the number of maternal deaths per 100,000 births has increased from 16.9 1990 to 26.4 in 2015. Not only are more American mothers dying than in our peer countries, but we're one of the only developed countries where the death rate is increasing, not decreasing.


AI can play key role in good governance: Microsoft official

#artificialintelligence

Artificial intelligence or AI as it is called in cyber parlance, and believed to be the next big thing in information and technology, can play a key role in good governance, a senior Microsoft official has said. "We are seeing that governments are benefitting through Artificial Intelligence and are able to bring (governance) closer to people in their countries," Dave Forstrom, director of communications for the Artificial Intelligence (AI) group at Microsoft, told PTI. "In terms of helping create good governance we're seeing an approach industry--wide right now where it's focused on ethical design and those principles that will help to really govern that," he said on the sidelines of the Microsoft's annual developers conference Build 2017. The senior Microsoft official said AI could be of great usage in various fields, including public health, law and order, education and even city sanitation and cleanliness.


First FDA Approval For Clinical Cloud-Based Deep Learning In Healthcare

#artificialintelligence

The first FDA approval for a machine learning application to be used in a clinical setting is a big step forward for AI and machine learning in healthcare and industry as a whole. Arterys's medical imaging platform has been approved to be put into use to help doctors diagnose heart problems. It uses a self-teaching artificial neural network which has learned from 1,000 cases so far, and will continue to improve its knowledge and understanding of how the heart works with each new case it examines. In order to be approved by the US Food and Drug Administration (FDA), it had to pass tests to show it can produce results at least as accurately as humans are currently able to. The key difference though is that Arterys takes an average of 15 seconds to produce a result for one case, which a professional human analyst would expect to spend between 30 minutes to an hour working on.


First FDA Approval For Clinical Cloud-Based Deep Learning In Healthcare

Forbes

The first FDA approval for a machine learning application to be used in a clinical setting is a big step forward for AI and machine learning in healthcare and industry as a whole. Arterys's medical imaging platform has been approved to be put into use to help doctors diagnose heart problems. It uses a self-teaching artificial neural network which has learned from 1,000 cases so far, and will continue to improve its knowledge and understanding of how the heart works with each new case it examines. In order to be approved by the US Food and Drug Administration (FDA), it had to pass tests to show it can produce results at least as accurately as humans are currently able to. The key difference though is that Arterys takes an average of 15 seconds to produce a result for one case, which a professional human analyst would expect to spend between 30 minutes to an hour working on.


Artificial intelligence used to predict death rates of heart patients - SiliconANGLE

#artificialintelligence

Companies are already using artificial intelligence to play board games and recommend content, and now researchers want to use AI for something a bit more personal: predicting how long heart patients have to live. In a paper recently published in the journal Radiology, researchers at the MRC London Institute of Medical Sciences used machine learning to predict the mortality rates of patients suffering from pulmonary hypertension, a rare and serious lung disorder that restricts the amount of oxygen going to the heart. If left untreated, roughly one-third of patients suffering from PH die within five years. Because the disorder is worsens over time, it is important for doctors to accurately estimate a patient's life expectancy to determine how aggressively they should treat the condition. Using machine learning, the researchers trained an AI using over eight years of patient health data.


The Road Ahead for Deep Learning in Healthcare

#artificialintelligence

While there are some sectors of the tech-driven economy that thrive on rapid adoption on new innovations, other areas become rooted in traditional approaches due to regulatory and other constraints. Despite great advances toward precision medicine goals, the healthcare industry, like other important segments of the economy, is tied by several specific bounds that make it slower to adapt to potentially higher performing tools and techniques. Although deep learning is nothing new, its application set is expanding. There is promise for the more mature variants of traditional deep learning (convolutional and recurrent neural networks are the prime example) to morph into domain-specific tools to bolster healthcare capabilities in new ways. Of course, this is not without a set of challenges, which we will get to in a moment.


A universal basic income: the answer to poverty, insecurity, and health inequality?

#artificialintelligence

For four years in the mid-1970s an unusual experiment took place in the small Canadian town of Dauphin. Statistically significant benefits for those who took part included fewer physician contacts related to mental health and fewer hospital admissions for "accident and injury." Mental health diagnoses in Dauphin also fell. Once the experiment ended, these public health benefits evaporated.1 What was the treatment being tested? It was what has become known as a basic income--a regular, unconditional payment made to each and every citizen.