MIT computer scientists are hoping to accelerate the use of artificial intelligence to improve medical decision-making, by automating a key step that's usually done by hand--and that's becoming more laborious as certain datasets grow ever-larger. The field of predictive analytics holds increasing promise for helping clinicians diagnose and treat patients. Machine-learning models can be trained to find patterns in patient data to aid in sepsis care, design safer chemotherapy regimens, and predict a patient's risk of having breast cancer or dying in the ICU, to name just a few examples. Typically, training datasets consist of many sick and healthy subjects, but with relatively little data for each subject. Experts must then find just those aspects--or "features"--in the datasets that will be important for making predictions.

The simulated triage workflow let radiologists read scans above the cancer-free threshold, reducing their workload by nearly 20% while also improving their specificity, wrote Adam Yala, with the Massachusetts Institute of Technology in Cambridge, and colleagues.

LONDON--(BUSINESS WIRE)--The global artificial intelligence (AI) market in BFSI sector is expected to post a CAGR of more than 32% during the period 2019-2023, according to the latest market research report by Technavio. A key factor driving the growth of the global artificial intelligence (AI) market size in BFSI sector is the push toward autonomous banking. Automation has become one of the most prioritized digital transformation strategies for banks. Financial institutions are increasingly focusing on developing more self-driving finance solutions owing to increased customer expectations for personalized services and rewards. Therefore, banks and credit unions are integrating AI and big data analytics to understand customer behavior.

JOHANNESBURG – If data is the new oil, artificial intelligence (AI) can arguably be its best drill, able to uncover insights and mine real business value from the huge and complex data sets that typify modern organisations. Enterprises are not blind to the massive opportunities that can be extracted: according to the latest Gartner data, enterprise adoption of AI has grown 270% over the past four years. In the last year alone, AI adoption has essentially tripled within enterprises of all sizes. That's not surprising considering 85% of global CEOs believe AI will fundamentally change the way they conduct business within the next five years. Until recently, the majority of business decision-making was predominantly driven by human centric capabilities.

"It has nothing to do with how smart you are, what school you went to, or how many PhDs you have in your innovation lab. If your team can't emotionally deal with the prospect of failing and having to wear egg on your face for five minutes, it's going to be difficult." Davyde Wachell is the CEO of Responsive, a hybrid wealth-focused startup. Backed by plug and play ventures, Responsive helps wealth managers in upgrading advisor productivity and decisions with next best actions driven by predictive analytics. Davyde studied AI in the Symbolic Systems program at Stanford and has worked in wealthtech for over 15 years, having built everything from quant research platforms to compliance automation tools. His film and opera work have been seen at Tribeca, Sundance and the Hammer Museum in Los Angeles. He lives in Vancouver his partner Holly, who works for Sanctuary AI, a humanoid robotics company. Now hit the Play button! This episode of Wealth Management Today is brought to you by Ezra Group Consulting. If your firm is evaluating new technology or looking to improve your current wealth platform, you need to contact Ezra Group. Don't spend another day using technology that doesn't offer an elegant user experience. Your advisors and clients deserve better and you can deliver it to them with the help of Ezra Group. Craig: Today on the Wealth Management Today podcast I am very happy to have Davyde Wachell, the Founder and CEO of Responsive. He's talking to us today live from the Tuscany region of Italy. Craig: Thanks for taking the time on your vacation overseas to talk on my podcast.

You are free to share this article under the Attribution 4.0 International license. Machine learning algorithms can accurately assess the capabilities of neurosurgeons during virtual surgery before they step into an actual operating room, a new study shows. Researchers recruited fifty participants from four stages of neurosurgical training; neurosurgeons, fellows and senior residents, junior residents, and medical students. The participants performed 250 complex tumor resections using NeuroVR, a virtual reality surgical simulator. The National Research Council of Canada developed the system; CAE recorded all instrument movements in 20 millisecond intervals.

Floods are among the most destructive natural disasters, which are highly complex to model. The research on the advancement of flood prediction models contributed to risk reduction, policy suggestion, minimization of the loss of human life, and reduction the property damage associated with floods. To mimic the complex mathematical expressions of physical processes of floods, during the past two decades, machine learning (ML) methods contributed highly in the advancement of prediction systems providing better performance and cost-effective solutions. Due to the vast benefits and potential of ML, its popularity dramatically increased among hydrologists. Researchers through introducing novel ML methods and hybridizing of the existing ones aim at discovering more accurate and efficient prediction models. The main contribution of this paper is to demonstrate the state of the art of ML models in flood prediction and to give insight into the most suitable models. In this paper, the literature where ML models were benchmarked through a qualitative analysis of robustness, accuracy, effectiveness, and speed are particularly investigated to provide an extensive overview on the various ML algorithms used in the field. The performance comparison of ML models presents an in-depth understanding of the different techniques within the framework of a comprehensive evaluation and discussion. As a result, this paper introduces the most promising prediction methods for both long-term and short-term floods. Furthermore, the major trends in improving the quality of the flood prediction models are investigated. Among them, hybridization, data decomposition, algorithm ensemble, and model optimization are reported as the most effective strategies for the improvement of ML methods.

Determining significant prognostic biomarkers is of increasing importance in many areas of medicine. Scores used in clinical practice often categorize continuous features into binary ones using expert-driven cut-points. Many algorithms have been developed to find one optimal cut-point, but there is often need to determine an optimal number of cut-points and their locations at the same time. However, there exists no standard method to help evaluate how many cut-points are optimal for a given continuous feature in the survival analysis setting. Moreover, most existing methods are univariate, hence not well-suited to high-dimensional frameworks. Here we introduce the binacox, a prognostic method to deal with the problem of detecting multiple cut-points per features in a multivariate setting where a large number of continuous features are available. The method is based on the Cox model and combines one-hot encoding with the binarsity penalty, which uses total-variation regularization together with an extra linear constraint, and enables feature selection. Nonasymptotic oracle inequalities for prediction and estimation with a fast rate of convergence are established. The statistical performance of the method is examined in an extensive Monte Carlo simulation study, and then illustrated on three publicly available genetic cancer datasets. On these high-dimensional datasets, our proposed method significantly outperforms state-of-the-art survival models regarding risk prediction in terms of the C-index, with a computing time orders of magnitude faster. In addition, it provides powerful interpretability from a clinical perspective by automatically pinpointing significant cut-points in relevant variables.

Health management of complex dynamic systems has evolved from simple automated alarms into a subfield of artificial intelligence with techniques for analyzing off-nominal conditions and generating responses. This evolution took place largely apart from the development of automated system control, planning, and scheduling (generally referred to in this work as decision making). While there have been efforts to establish an information exchange between system health management and decision making, successful practical implementations of integrated architectures remain limited. This article proposes that rather than being treated as connected yet distinct entities, system health management and decision making should be unified in their formulations. Enabled by advances in modeling and algorithms, we believe that a unified approach will increase systems' resilience to faults and improve their effectiveness. We overview the prevalent system health management methodology, illustrate its limitations through numerical examples, and describe a proposed unified approach. We then show how typical system health management concepts are accommodated in the proposed approach without loss of functionality or generality. A computational complexity analysis of the unified approach is also provided.

--Channel charting (CC) has been proposed recently to enable logical positioning of user equipments (UEs) in the neighborhood of a multi-antenna base-station solely from channel-state information (CSI). CC relies on dimensionality reduction of high-dimensional CSI features in order to construct a channel chart that captures spatial and radio geometries so that UEs close in space are close in the channel chart. In this paper, we demonstrate that autoencoder (AE)-based CC can be augmented with side information that is obtained during the CSI acquisition process. More specifically, we propose to include pairwise representation constraints into AEs with the goal of improving the quality of the learned channel charts. We show that such representation-constrained AEs recover the global geometry of the learned channel charts, which enables CC to perform approximate positioning without global navigation satellite systems or supervised learning methods that rely on extensive and expensive measurement campaigns.