Results


This AI Can Diagnose a Rare Eye Condition as Well as a Human Doctor

#artificialintelligence

To this end, a group of Chinese ophthalmologists and computer scientists has demonstrated a machine learning algorithm for identifying congenital cataracts, a rare eye disease that's nonetheless responsible for some 10 percent of all vision loss in children worldwide. The algorithm is based on convolutional neural networks (CNNs), a class of machine learning models that attempts to imitate the neural processing that occurs in the visual cortex of animals. CNNs are widely used for visual recognition tasks but also other domains, like playing Go, natural language processing, and drug discovery. It only started to falter when tasked with making decisions about follow-up care, where the network registered a relatively large number of false positives.


Genetic algorithms for feature selection in Data Analytics

#artificialintelligence

Here the function to optimize is the generalization performance of the predictive model, represented by the error on a selection data set. The fist step is to create and initialize the individuals in the population As the genetic algorithm is an stochastic optimization method, the genes of the individuals are usually initialized at random. To evaluate the fitness, we need to train the predictive model with the training data, and then evaluate its selection error with the selection data. Once the selection operator has chosen half of the population, the crossover operator recombines the selected individuals to generate a new population.


Artificial intelligence used to identify skin cancer Stanford News

#artificialintelligence

Computer scientists at Stanford have created an artificially intelligent diagnosis algorithm for skin cancer that matched the performance of board-certified dermatologists. During testing, the researchers used only high-quality, biopsy-confirmed images provided by the University of Edinburgh and the International Skin Imaging Collaboration Project that represented the most common and deadliest skin cancers – malignant carcinomas and malignant melanomas. The algorithm's performance was measured through the creation of a sensitivity-specificity curve, where sensitivity represented its ability to correctly identify malignant lesions and specificity represented its ability to correctly identify benign lesions. "Advances in computer-aided classification of benign versus malignant skin lesions could greatly assist dermatologists in improved diagnosis for challenging lesions and provide better management options for patients," said Susan Swetter, professor of dermatology and director of the Pigmented Lesion and Melanoma Program at the Stanford Cancer Institute, and co-author of the paper.


Deep learning algorithm does as well as dermatologists in identifying skin cancer

#artificialintelligence

In its diagnoses of skin lesions, which represented the most common and deadliest skin cancers, the algorithm matched the performance of dermatologists. During testing, the researchers used only high-quality, biopsy-confirmed images provided by the University of Edinburgh and the International Skin Imaging Collaboration Project that represented the most common and deadliest skin cancers--malignant carcinomas and malignant melanomas. The algorithm's performance was measured through the creation of a sensitivity-specificity curve, where sensitivity represented its ability to correctly identify malignant lesions and specificity represented its ability to correctly identify benign lesions. "Advances in computer-aided classification of benign versus malignant skin lesions could greatly assist dermatologists in improved diagnosis for challenging lesions and provide better management options for patients," said Susan Swetter, professor of dermatology and director of the Pigmented Lesion and Melanoma Program at the Stanford Cancer Institute, and co-author of the paper.


Machine Learning for Dummies: Part 1

#artificialintelligence

The input layer typically represent sensors, where each input value of the array represents a value from 0.0 to 1.0. The important part is that neural networks can represent complex transformation functions and decisions (up to a limit where bayesian solutions chime in, but that'll come up later). The important part here is that input neurons have no connection to a previous layer, so the compute() method must respect that input neurons just directly get their neuron.value When talking about how neuron's communicate, how the weights change over time and when to activate the next neuron in our network -- that's a so-called activation function. Fast progress at first means a neuron can learn fast, slow ease-out means that the neuron overfits slowly.


The artificially intelligent eye doctor is in

#artificialintelligence

A team at Google DeepMind, a subsidiary of Alphabet focused entirely on AI, is doing similar work, training computers to process optical coherence tomography scans for signs of macular degeneration and other eye disease in collaboration with researchers at Moorfields Eye Hospital in London (see "DeepMind's First Medical Research Gig Will Use AI to Diagnose Eye Disease"). The paper's authors, comprised of computer scientists at Google and medical researchers from the U.S. and India, developed an algorithm to analyze retinal images. The Google researchers collaborated with scientists at the Aravind Medical Research Foundation in India, where a clinical trial involving real patients is ongoing. Lily Peng, a researcher at Google and a medical doctor who was involved with the project, says results from this trial are not yet ready for publication.


5 Machine Learning Research Studies To Understand & Predict Length of Stay in Hospitals

@machinelearnbot

Length of Stay (LOS) is a critical factor in managing hospital quality & economic outcomes in Healthcare. The metric is calculated by summing the total number of days for all discharges & dividing it by the total number of discharges. Insurance programs such as Medicare are moving to a model where they are compensating Hospitals the same amount for a specific surgery (e.g. Joint replacement) regardless of the number of days spent in the hospital. Therefore, hospitals & the overall healthcare ecosystem are motivated to reduce LOS.


The artificially intelligent eye doctor is in

#artificialintelligence

A team at Google DeepMind, a subsidiary of Alphabet focused entirely on AI, is doing similar work, training computers to process optical coherence tomography scans for signs of macular degeneration and other eye disease in collaboration with researchers at Moorfields Eye Hospital in London (see "DeepMind's First Medical Research Gig Will Use AI to Diagnose Eye Disease"). The paper's authors, comprised of computer scientists at Google and medical researchers from the U.S. and India, developed an algorithm to analyze retinal images. The Google researchers collaborated with scientists at the Aravind Medical Research Foundation in India, where a clinical trial involving real patients is ongoing. Lily Peng, a researcher at Google and a medical doctor who was involved with the project, says results from this trial are not yet ready for publication.


Cricket Australia Testing Microsoft's New Intelligent Coaches' Platform

#artificialintelligence

The same Microsoft technology currently used by healthcare organizations and yes, robots, is now being tested throughout the summer months by Cricket Australia, making it the first cricketing nation to integrate the company's team and player performance platform into its decision-making processes across fitness, game strategy, player recovery and team selection. But how could you harness the power of data to even start having a more intelligent informed conversation about performance of teams, performance of players?" Powered by Microsoft's Cloud and Cortana Analytics Suite, the new platform allows organizations like Cricket Australia to leverage predictive analytics and machine-learning to best understand players' performance on the pitch. "The new platform takes this vast amount of data, provides an environment for our sports science folks to explore that data and find insights in it, and then provides a very elegant dashboard that will surface the trends and the information that will be impactful to the coaches," Michael Osborne, Cricket Australia's Head of Technology, told Financial Review.


The Case for a New "Final Frontier" in Data Analytics

@machinelearnbot

As a case in point, see the "Developing Innovation and Growing the Internet of Things Act" or "DIGIT Act", i.e., S. 2607, a bill introduced in the Senate on March 1, 2016 and amended on September 28, 2016, "to ensure appropriate spectrum planning and inter-agency coordination to support the Internet of Things" – A companion bill, H.R. He expresses the concern that "most of the'analytics of things' thus far have been descriptive analytics – bar (and Heaven forbid, pie) charts, means and medians, and alerts for out-of-bounds data," and highlights areas where business analytics can make a difference in IoT beyond descriptive (dashboard-type report on performance) such as diagnostic (alerts that need attention), predictive (e.g., breakdown potential) and prescriptive (recommendations based on predictions, experiments, or optimizations). The same paper proposes an overall definition "in general, prescriptive solutions assist business analysts in decision-making by determining actions and assessing their impact regarding business objectives, requirements, and constraints. The National Institute of Standards and Technology (NIST) defines Cyber-Physical Systems as "smart systems that include engineered interacting networks of physical and computational components," and underscores that "CPS and related systems (including the Internet of Things (IoT) and the Industrial Internet) are widely recognized as having great potential to enable innovative applications and impact multiple economic sectors in the worldwide economy".