In an age of uncertainty with the arrival of artificial intelligence (AI) tools and technologies in the healthcare field, many in the industry question how the addition of AI will impact their careers. One particular area is not immune to these changes: radiography. We spoke with Dr. Nick Woznitza, a reporting radiographer at Homerton University Hospital and a clinical academic at Canterbury Christ Church University in the United Kingdom, to gain some insight into what kind of effect AI will have on radiographers' tasks, workflow, and training and what the future holds for the field of radiography. Which routine tasks do radiographers perform that AI cannot assist with? Effective and compassionate communication is a core skill of all radiographers.

AI startup Adarga has closed a £5 million Series A fundraising by Allectus Capital. But this news rather cloaks the fact that it has been building up a head of steam since its founding in 2016, building up what they say is a £30 million-plus sales pipeline through strategic collaborations with a number of global industrial partners and gradually building its management team. The proceeds will be used to continue the expansion of Adarga's data science and software engineering teams and to roll out internationally. Adarga, which comes from the word for an old Moorish shield, is a London and Bristol-based startup. It uses AI to change the way financial institutions, intelligence agencies and defence companies tackle problems, helping crunch vast amounts of data to identify possible threats even before they occur.

Traditionally, off-policy learning algorithms (such as Q-learning) and exploration schemes have been derived separately. Often times, the exploration-exploitation dilemma being addressed through heuristics. In this article we show that both the learning equations and the exploration-exploitation strategy can be derived in tandem as the solution to a unique and well-posed optimization problem whose minimization leads to the optimal value function. We present a new algorithm following this idea. The algorithm is of the gradient type (and therefore has good convergence properties even when used in conjunction with function approximators such as neural networks); it is off-policy; and it specifies both the update equations and the strategy to address the exploration-exploitation dilemma. To the best of our knowledge, this is the first algorithm that has these properties.

Time series classification (TSC) is the area of machine learning interested in learning how to assign labels to time series. The last few decades of work in this area have led to significant progress in the accuracy of classifiers, with the state of the art now represented by the HIVE-COTE algorithm. While extremely accurate, HIVE-COTE is infeasible to use in many applications because of its very high training time complexity in O(N^2*T^4) for a dataset with N time series of length T. For example, it takes HIVE-COTE more than 72,000s to learn from a small dataset with N=700 time series of short length T=46. Deep learning, on the other hand, has now received enormous attention because of its high scalability and state-of-the-art accuracy in computer vision and natural language processing tasks. Deep learning for TSC has only very recently started to be explored, with the first few architectures developed over the last 3 years only. The accuracy of deep learning for TSC has been raised to a competitive level, but has not quite reached the level of HIVE-COTE. This is what this paper achieves: outperforming HIVE-COTE's accuracy together with scalability. We take an important step towards finding the AlexNet network for TSC by presenting InceptionTime---an ensemble of deep Convolutional Neural Network (CNN) models, inspired by the Inception-v4 architecture. Our experiments show that InceptionTime slightly outperforms HIVE-COTE with a win/draw/loss on the UCR archive of 40/6/39. Not only is InceptionTime more accurate, but it is much faster: InceptionTime learns from that same dataset with 700 time series in 2,300s but can also learn from a dataset with 8M time series in 13 hours, a quantity of data that is fully out of reach of HIVE-COTE.

In order to build a national injury surveillance system based on emergency room (ER) visits we are developing a coding system to classify their causes from clinical notes content. Supervised learning techniques have shown good results in this area but require to manually build a large learning annotated dataset. New levels of performance have been recently achieved in neural language models (NLM) with the use of models based on the Transformer architecture with an unsupervised generative pre-training step. Our hypothesis is that methods involving a generative self-supervised pre-training step significantly reduce the number of annotated samples required for supervised fine-tuning. In this case study, we assessed whether we could predict from free text clinical notes whether a visit was the consequence of a traumatic or a non-traumatic event. We compared two strategies: Strategy A consisted in training the GPT-2 NLM on the full 161 930 samples dataset with all labels (trauma/non-trauma). In Strategy B, we split the training dataset in two parts, a large one of 151 930 samples without any label for the self-supervised pre-training phase and a smaller one (up to 10 000 samples) for the supervised fine-tuning with labels. While strategy A needed to process 40 000 samples to achieve good performance (AUC>0.95), strategy B needed only 500 samples, a gain of 80. Moreover, an AUC of 0.93 was measured with only 30 labeled samples processed 3 times (3 epochs). To conclude, it is possible to adapt a multi-purpose NLM model such as the GPT-2 to create a powerful tool for classification of free-text notes with the need of a very small number of labeled samples. Only two modalities (trauma/non-trauma) were predicted for this case study but the same method can be applied for multimodal classification tasks such as diagnosis/disease terminologies.

ABBOTT PARK, Ill., Sept. 12, 2019 -- Abbott announced that new research, published in the journal Circulation, found its algorithm could help doctors in hospital emergency rooms more accurately determine if someone is having a heart attack or not, so that they can receive faster treatments or be safely discharged.1 In this study, researchers from the U.S., Germany, U.K., Switzerland, Australia and New Zealand looked at more than 11,000 patients to determine if Abbott's technology developed using artificial intelligence (AI) could provide a faster, more accurate determination that someone is having a heart attack or not. The study found that the algorithm provided doctors a more comprehensive analysis of the probability that a patient was having a heart attack or not, particularly for those who entered the hospital within the first three hours of when their symptoms started. "With machine learning technology, you can go from a one-size-fits-all approach for diagnosing heart attacks to an individualized and more precise risk assessment that looks at how all the variables interact at that moment in time," said Fred Apple, Ph.D., Hennepin HealthCare/ Hennepin County Medical Center, professor of Laboratory Medicine and Pathology at the University of Minnesota, and one of the study authors. "This could give doctors in the ER more personalized, timely and accurate information to determine if their patient is having a heart attack or not." A team of physicians and statisticians at Abbott developed the algorithm* using AI tools to analyze extensive data sets and identify the variables most predictive for determining a cardiac event, such as age, sex and a person's specific troponin levels (using a high sensitivity troponin-I blood test**) and blood sample timing.

Artificial intelligence is giving medical professionals the ability to create a digital replica of patients, allowing doctors to predict how effective surgery will be. Australia's peak science agency CSIRO is developing AI-powered tools to diagnose mental health disorders more accurately and safeguard patients' genetic data in DNA testing. Northeast Health Wangaratta is already using AI to stop cyber attacks. Using its public hospital in regional Victoria, Northeast Health Wangaratta is investigating the use of AI to create a digital replica of its patients. Doctors then use the replica to trial treatment.

Zygmunt received his PhD degree in Computer Science from the University of Adelaide, Australia in 2013, and his MSc degree in Computer Science from the University of KwaZulu-Natal, South Africa in 2009. He is a senior research fellow at the Australian Institute for Machine Learning. His research lies at the interface of computer vision, machine learning, and challenging industry problems. He develops algorithms that allow computers to perform tasks typically associated with human intelligence. In the last couple of years, his work has focused on the application of machine learning and image processing techniques for the development of smart medical devices.

Over three decades, the Internet has grown from a small network of computers used by research scientists to communicate and exchange data to a technology that has penetrated almost every aspect of our day-to-day lives. Today, it is hard to imagine a life without online access for business, shopping, and socialising. A technology that has connected humanity at a scale never before possible has also amplified some of our worst qualities. Online hate speech spreads virally across the globe with short- and long-term consequences for individuals and societies. These consequences are often difficult to measure and predict. Online social media websites and mobile apps have inadvertently become the platform for the spread and proliferation of hate speech.

Co-organized by Belarus and the United Nations Office of Counter-Terrorism (UNOCT), "Countering terrorism through innovative approaches and the use of new and emerging technologies" concluded on Wednesday in Minsk. The internet "expands technological boundaries literally every day" and AI, 3D printing biotechnology innovations, can help to achieve the Sustainable Development Goals (SDGs), said Vladimir Voronkov, the first-ever Under Secretary-General for the UN Counter-Terrorism Office. The Co-Chair's Summary issued at the end of the @BelarusMFA & @UN_OCT Conference stresses the urgent need to strengthen international cooperation to tackle terrorist abuse of #NewTechnologies & share innovative approaches to counter this threathttps://t.co/55b4vVUq1Y#BY2019UN But it also provides "live video broadcasting of brutal killings", he continued, citing the recent attack in the New Zealand city of Christchurch, where dozens of Muslim worshippers were killed by a self-avowed white supremacist. "This is done in order to spread fear and split society", maintained the UNOCT chief, warning of more serious developments, such as attempts by terrorists to create home-made biological weapons.