Collaborating Authors

Health Care Providers & Services

Facebook and NYU trained an AI to estimate COVID outcomes


COVID-19 has infected more than 23 million Americans and killed 386,000 of them to date, since the global pandemic began last March. Complicating the public health response is the fact that we still know so little about how the virus operates -- such as why some patients remain asymptomatic while it ravages others. Effectively allocating resources like ICU beds and ventilators becomes a Sisyphean task when doctors can only guess as to who might recover and who might be intubated within the next 96 hours. However a trio of new machine learning algorithms developed by Facebook's AI division (FAIR) in cooperation with NYU Langone Health can help predict patient outcomes up to four days in advance using just a patient's chest x-rays. The models can, respectively, predict patient deterioration based on either a single X-ray or a sequence as well as determine how much supplemental oxygen the patient will likely need.

AI-Powered Text From This Program Could Fool the Government


In October 2019, Idaho proposed changing its Medicaid program. The state needed approval from the federal government, which solicited public feedback via But half came not from concerned citizens or even internet trolls. They were generated by artificial intelligence. And a study found that people could not distinguish the real comments from the fake ones.

Healthcare optimized: The role of robots post-COVID


It would be difficult to overestimate the impact COVID-19 appears to be having on the automation sector. No where will the change be more apparent than in healthcare, where a major transition to automation has long been in the offing. What would have been a slower easing in has, in light of overstressed capacity in some areas of healthcare (and an eerie diminishment of demand in others), as well as a complete reorientation of consumer expectations in the pandemic era, set the stage for a jarring transformation. Healthline cuts through the confusion with straightforward, expert-reviewed, person-first experiences -- all designed to help you make the best decisions. Major hospitals have deployed specialized robot nurses with remote patient monitoring tech so that doctors can keep an eye on people from afar.

Sparse encoding for more-interpretable feature-selecting representations in probabilistic matrix factorization Machine Learning

Dimensionality reduction methods for count data are critical to a wide range of applications in medical informatics and other fields where model interpretability is paramount. For such data, hierarchical Poisson matrix factorization (HPF) and other sparse probabilistic non-negative matrix factorization (NMF) methods are considered to be interpretable generative models. They consist of sparse transformations for decoding their learned representations into predictions. However, sparsity in representation decoding does not necessarily imply sparsity in the encoding of representations from the original data features. HPF is often incorrectly interpreted in the literature as if it possesses encoder sparsity. The distinction between decoder sparsity and encoder sparsity is subtle but important. Due to the lack of encoder sparsity, HPF does not possess the column-clustering property of classical NMF -- the factor loading matrix does not sufficiently define how each factor is formed from the original features. We address this deficiency by self-consistently enforcing encoder sparsity, using a generalized additive model (GAM), thereby allowing one to relate each representation coordinate to a subset of the original data features. In doing so, the method also gains the ability to perform feature selection. We demonstrate our method on simulated data and give an example of how encoder sparsity is of practical use in a concrete application of representing inpatient comorbidities in Medicare patients.

How to improve revenue cycle management: 5 tips - MedCity News


As the world continues to battle Covid-19, its effects on population health are just one facet of the crisis. The economic fallout is also seriously impacting both people and businesses, including hospitals and other healthcare facilities. The American Hospital Association (AHA) estimates the country's hospitals and health systems could lose $120.5 billion between July and December 2020. This is in addition to AHA's previous financial impact estimate -- losses of $202.6 billion between March and June 2020 -- bringing total losses for the calendar year to at least $323 billion. Half of all hospitals could be operating in the red during the second half of 2020, according to analysis prepared by Kaufman Hall and released by the AHA.

Could GPT-3 Change The Way Future AI Models Are Developed and Deployed ?


Much has been said about GPT-3 already. Traditionally, we start with data for a problem and develop the model based on the data. The model is specific to the problem. If you want to train a model to predict traffic patterns in New York, you build a model of New York traffic patterns. If you want to model air pollution in New York, that's a different model With GPT-3 you start with the model instead of the data.

How Do You Get Started with AI in Healthcare Organizations? – Eularis


Everyone is aware of AI now, and a lot of people are using it, but many are still sitting on the side lines wondering if it is relevant to them and if so, how to get started and get the value from it that they keep hearing about. The key things foremost in the minds of the non-users appear to be'I understand it can be beneficial for increasing productivity and generating faster revenue – but how?' and'Will it take my job?' I believe that the best way to think of AI is a tool that will save you time and allow you to do your job better to enable you to achieve better results and your company growth gets supercharged. AI is a powerful tool for helping people do a far better job by taking away the guesswork and being able to take in and process more data than a human could ever dream of, and then find the important patterns and connections that humans would miss due to being physically impossible to synthesize that level of data. Take strategic planning for example. I am currently involved with the most amazing piece of AI that actually combines data and does your strategic planning for you – more effectively than humans – and generates stronger results with real time constantly market monitoring.

AI in healthcare: Helping assess risk of patients falling in wards, 3D holograms to assist doctors


SINGAPORE - From a computer model that predicts how likely patients are to fall over to a device that creates 3D holograms to assist doctors, the healthcare of the future is looking towards artificial intelligence (AI). These new developments were showcased last Friday (Dec 11) by the National University Health System (NUHS) at the Singapore Healthcare AI Expo. "There is a digital transformation coming to the whole of society," said Professor Yeoh Khay Guan, chief executive of NUHS. "Healthcare systems are transforming worldwide and we must be ready for that." Increasing efficiency is a goal of Dr Siti Zubaidah Mordiffii and her team.

Artificial intelligence in hospitals - iProcureSecurity


The Fraunhofer Institute has developed six sample scenarios for the use of artificial intelligence (AI) in the treatment of severely injured patients together with partner institutions from the health care system and the legal sciences. Accidents in traffic, at work, in the home or during sports in Germany lead to injuries almost ten million times each year. A small proportion of these accidents lead to serious and multiple injuries. The care of seriously injured patients is one of the most complex situations in accident surgery. Treatment in the early phase is particularly important, i.e. the period until the patient is admitted to an intensive care unit or transferred to a specialised centre.

Knowledge Graph and Machine Learning: 3 Key Business Needs, One Platform Registration


Connect internal and external datasets and pipelines with a distributed Graph Database - UnitedHealth Group is connecting 200 sources to deliver a real-time customer 360 to improve quality of care for 50 million members and deliver call center efficiencies. Xandr (part of AT&T) is connecting multiple data pipelines to build an identity graph for entity resolution to power the next-generation AdTech platform.