OpenClinicalAI: enabling AI to diagnose diseases in real-world clinical settings

This paper quantitatively reveals the state-of-the-art and state-of-the-practice AI systems only achieve acceptable performance on the stringent conditions that all categories of subjects are known, which we call closed clinical settings, but fail to work in real-world clinical settings. Compared to the diagnosis task in the closed setting, real-world clinical settings pose severe challenges, and we must treat them differently. We build a clinical AI benchmark named Clinical AIBench to set up real-world clinical settings to facilitate researches. We propose an open, dynamic machine learning framework and develop an AI system named OpenClinicalAI to diagnose diseases in real-world clinical settings. The first versions of Clinical AIBench and OpenClinicalAI target Alzheimer's disease. In the real-world clinical setting, OpenClinicalAI significantly outperforms the state-of-the-art AI system. In addition, OpenClinicalAI develops personalized diagnosis strategies to avoid unnecessary testing and seamlessly collaborates with clinicians. It is promising to be embedded in the current medical systems to improve medical services.

Towards suitable description of reference architectures

Due to the increasing size and complexity of many current software systems, the architectural design of these systems has become a considerately complicated task. In this scenario, reference architectures have already proven to be very relevant to support the architectural design of systems in diverse critical application domains, such as health, avionics, transportation, and the automotive sector. However, these architectures are described in many different approaches, such as using textual description, informal models, and even modeling languages as UML. Hence, practitioners are faced with a difficult decision of the better approaches to describing reference architectures. The main contribution of this work is to depict a detailed panorama containing the state of the art (from the literature) and state of the practice (based on existing reference architectures) of approaches for describing reference architectures. For this, we firstly examined the existing approaches (e.g., processes, methods, models, and modeling languages) and compared them concerning completeness and applicability. We also examined four well-known, successful reference architectures (AUTOSAR, ARC-IT, IIRA, and AXMEDIS) in view of the approaches used to describe them. As a result, there exists a misalignment between the state of the art and state of the practice, requiring an engagement of the software architecture community, through research collaboration of academia and industry, to propose more suitable means to describe reference architectures and, as a consequence, promoting the sustainability of these architectures.

Monitoring During Lateral Bridge Slide

Slide-in bridge construction (SIBC) is an accelerated bridge construction method. In U.S. state of the art and state of the practice today, the bridge superstructure is moved by sliding laterally into the final alignment following a sequence of construction and demolition events. SIBC implementation components require a temporary support structure, a slide system with railing girders and polytetrafluoroethylene pads or rollers, and an actuating system to initiate and maintain the slide movement. The M-100 bridge over the Canadian National (CN) railway was the third SIBC project implemented by the Michigan Department of Transportation. Each SIBC implementation has been so far unique because the unknowns include slide properties contributing to friction between surfaces, pushing and pulling force levels, and monitoring and controlling the force levels. The purpose of standardization is to develop repeatable procedures for the SIBC method. One aspect of standardization is to develop an understanding of the structural response and the forces developed in the system during slide activities. This understanding requires documentation of various SIBC practices, simulation of slide activities, and monitoring the structural response. The activities of the M-100 road over the CN railway bridge slide, instrumentation and monitoring of the structural response, and the use of acquired acceleration data to calculate the forces that developed during the slide activities are presented.

Equipment Replacement Decision Making:Opportunities and Challenges

The primary function of equipment managers is to replace the right equipment at the right time and at the lowest overall cost. In this paper, the opportunities and challenges associated with equipment replacement optimization (ERO) are discussed in detail. First, a comprehensive review of the state-of-the art and state-of-the practice literature for the ERO problem is conducted. Second, a dynamic programming (DP) based optimization solution methodology is presented to solve the ERO problem. The Bellman’s formulation for the ERO deterministic (DDP) and stochastic dynamic programming (SDP) problems are discussed in detail. Finally, comprehensive ERO numerical results and implications are given.