Health & Medicine


Artificial Intelligence (AI) in Healthcare

#artificialintelligence

This application of population health AI data will occur only if the EHR companies can profit from the function by charging the physicians for the tabulated population data analysis. Without concomitant software to overcome prior authorization rationing of prescriptions by insurance companies and Pharmacy Benefit Managers or built-in EHR software to override diagnostic and treatment rationing by insurance bureaucrats, the benefits of AI clinically for the patient or physician will never be applied at the bedside. This function of automated overriding of prior authorization rationing of Artificial Intelligence (or NAI) suggestions could be easily delivered to physicians simply by cross-linking insurance company drug formularies with patients insurance plans using several prescription tracking companies already contracted with EMR companies and used daily in most pharmacies. I'm betting, the low earnings and low profitability potential of prior authorization API overriding software for the EHR industry combined with data (price and formulary) blocking by Pharmaceutical Industry Benefit Managers (PBM's) and the insurance companies will prevent implementation or this most desired clinical function.


Learning Computer Vision with Tensorflow - Udemy

@machinelearnbot

This video aims to help you leverage the power of TensorFlow to perform image processing. Then you will delve into more advanced stuff such as semantic segmentation, Neural Image Caption Generation, and so on, taking advantage of TensorFlow's Deep Neural Networks. Marvin has worked at a deep learning start-up developing neural network architectures. At the forefront of next generation DNA sequencing, he builds intelligent applications with Machine Learning and Deep Learning for precision medicine.


Workflow headaches, patient fears and lack of regulation among barriers to artificial intelligence in healthcare

#artificialintelligence

RELATED: Plenty of buzz for AI in healthcare, but are any systems actually using it? Other concerns include that AI could make already-existing healthcare disparities worse, as the poorest patients would have limited access to the technology. For it to truly succeed, the industry must solve its "data problem," which includes reaching these underserved populations to gather more information on them. Data collection and interoperability are significant shortcomings for one of the most high-profile AI technologies, IBM Watson.


Deep Learning Emerging as an Enterprise AI Essential - Datamation

#artificialintelligence

In fact, 80 percent of data scientists will include deep learning as part of their AI toolkits by 2018, predicted Gartner. And by 2019, deep learning will be delivering demand, fraud and failure predictions with "best-in-class performance," said the analyst firm in a Sept. 20 announcement. Currently, most enterprises fall short on machine learning skills, not to mention deep learning expertise. Tractica recently predicted that the market for AI technologies will reach $43.5 billion by 2024.


Autonomous delivery drone network set to take flight in Switzerland

Engadget

The company has revealed plans to launch the first permanent autonomous drone delivery network in Switzerland, where its flying robot couriers will shuttle blood and pathology samples between hospital facilities. The trick is the Matternet Station you see above: when a drone lands, the Station locks it into place and swaps out both the battery and the cargo (loaded into boxes by humans, who scan QR codes for access). Company chief Andreas Raptopoulos expects the drone network to transfer medical supplies within 30 minutes, and the reliability of a largely automated system means that hospitals don't have to worry about unpredictable delivery times (particularly on the ground). Still, this is an honest-to-goodness example of a practical drone delivery network, and one performing crucial tasks at that -- this isn't just a nice-to-have luxury.


Cognitive health care in 2027

#artificialintelligence

The primary focus of these initiatives is on health care providers, helping them develop treatment approaches that are most effective for individual patients. One consortium of hospitals, researchers, and a startup, for example, is conducting "Project Survival" to identify effective biomarkers for pancreatic cancer.3 In other firms, real-world data sources are being used to identify molecules that might be particularly effective (or ineffective) in clinical trials. Another long-term challenge to be addressed by the life sciences and health care industry is collaboration and integration of data. Project Survival, for example--an effort to find a pancreatic cancer biomarker--involves collaboration among a big data drug development startup (Berg Health), an academic medical center (Beth Israel Deaconess in Boston), a nonprofit (Cancer Research and Biostatistics), and a network of oncology clinicians and researchers (the Pancreatic Research Team).


Medical delivery drones are coming to Switzerland

Mashable

"We hope this will improve quality of care for hospital patients and will bring significant cost savings to hospital systems." So instead of relying on roads for transportation, doctors, nurses, and technicians can send and receive test samples and results via the drone, and the system's accompanying app. Using the Matternet system, a technician would package the blood sample in a standardized box bearing a QR code. In countries where Doctors Without Borders work, medical drone delivery is crucial since roads and safe, timely passage are rarely an option.


AI could spot Alzheimer's in MRI scans up to a decade before symptoms show

#artificialintelligence

The AI was trained to correctly spot the difference between diseased and healthy brains, before being tested on its accuracy abilities on a second set of 148 scans – 52 of which were healthy, 48 had Alzheimer's and the other 48 had a mild cognitive impairment that was known to develop into Alzheimer's within 10 years. The algorithm correctly distinguished between healthy and diseased brains 86% of the time, according to the researchers, who added that it was also able to spot the difference between a healthy brain and a mild impairment with an 84% accuracy rating. Last month mobile game Sea Hero Quest – which uses navigation challenges to gather data about spatial movement as part of research into the disease – was expanded to virtual reality for the first time. The game sets users navigation challenges, and they can opt-in to share their data with the researchers behind the game, who can use player performance data to plot spatial navigation skills of different ages groups and genders.


Handheld scanner divines how nutritious your food really is

New Scientist

FARMERS can now zap their crops with a handheld scanner to instantly determine nutritional content, which could prove crucial in mitigating the effects of climate change on food quality. "Real-time results mean farmers can add fertilisers or tweak moisture levels as crops grow" Farmers can use the app to assess the impact of changing conditions, such as extreme weather and soil quality, on the quality of their crops from year to year. It could allow farmers to mitigate the negative effects of climate change early by adding fertilisers or tweaking moisture levels as crops grow. Other companies are developing similar gadgets for consumers, and sensors that can be fitted onto a smartphone.


Can Your Smartphone Read Your Mind?

Slate

One oft-cited solution to the big data challenge of digital mental health data is to use artificial intelligence approaches like deep learning to help make sense of the raw data. Deep learning is the art and science of building enormous computer models--neural networks--that can be used to predict, classify, edit, describe, and create videos, images, and text. Artificial intelligence programs still struggle with cancer diagnoses, even when complete medical records are available and even with medical knowledge of that cancer well characterized at the genetic level. Creating meaningful categories of mental illnesses is complex, making it difficult to create or train diagnostic algorithms.