Clinical outcomes in ROS1-fusion positive (ROS1+) non-small cell lung cancer (NSCLC) by fusion partner and resistance mechanisms are limited. This cohort study included 56 ROS1+ patients (FISH or NGS confirmed); fusion partners were identified in 27 cases, including CD74 (n = 10), EZR (n = 7), and SDC4 (n = 7). Clinical data were available for 50 patients (median age 62; 51% female; 32% never-smokers). Forty patients received tyrosine kinase inhibitors (TKIs), mostly crizotinib (n = 38). Crizotinib showed a 55% objective response rate (ORR) and a median progression-free survival (mPFS) of 5.3 months. Brain metastases (HR 2.65, 95% CI 1.06–6.60, P = 0.037) and prior chemotherapy (HR 3.17, 95% CI 1.35–7.45, P = 0.008) had a higher risk of progression. Sixteen patients received subsequent lorlatinib, with an ORR of 28% and mPFS of 3.7 months. G2032R and L2026M resistance mutations were identified in four lorlatinib non-responders, and in vitro studies confirmed resistance to lorlatinib. Fusion partners did not affect crizotinib outcomes. Lorlatinib was ineffective against on-target resistance. Real-world data showed lower TKI efficacy than clinical trials, highlighting the role of clinical and molecular factors in treatment response.
DOCUMENT
Abstract Despite the numerous business benefits of data science, the number of data science models in production is limited. Data science model deployment presents many challenges and many organisations have little model deployment knowledge. This research studied five model deployments in a Dutch government organisation. The study revealed that as a result of model deployment a data science subprocess is added into the target business process, the model itself can be adapted, model maintenance is incorporated in the model development process and a feedback loop is established between the target business process and the model development process. These model deployment effects and the related deployment challenges are different in strategic and operational target business processes. Based on these findings, guidelines are formulated which can form a basis for future principles how to successfully deploy data science models. Organisations can use these guidelines as suggestions to solve their own model deployment challenges.
DOCUMENT
Wat zijn belangrijke succesfactoren om onderzoek, onderwijs en ondernemen bij elkaar te brengen, zó dat 'het klikt'. De uitdaging voor de toekomst van bedrijven in de smart factoryligt bij data science: het omzetten van ruwe (sensor) data naar (zinnige) informatie en kennis, waarmee producten en diensten verbeterd kunnen worden. Tevens programma van het symposium t.g.l. inauguratie 3 december 2015
MULTIFILE
Deploying robots from indoor to outdoor environments (vise versa) with stable and accurate localization is very important for companies to secure the utilization in industrial applications such as delivering harvested fruits from plantations, deploying/docking, navigating under solar panels, passing through tunnels/underpasses and parking in garages. This is because of the sudden changes in operational conditions such as receiving high/low-quality satellite signals, changing field of view, dealing with lighting conditions and addressing different velocities. We observed these limitations especially in indoor-outdoor transitions after conducting different projects with companies and obtaining inaccurate localization using individual Robotics Operating Systems (ROS2) modules. As there are rare commercial solutions for IO-transitions, AlFusIOn is a ROS2-based framework aims to fuse different sensing and data-interpretation techniques (LiDAR, Camera, IMU, GNSS-RTK, Wheel Odometry, Visual Odometry) to guarantee the redundancy and accuracy of the localization system. Moreover, maps will be integrated to robustify the performance and ensure safety by providing geometrical information about the transitioning structures. Furthermore, deep learning will be utilized to understand the operational conditions by labeling indoor and outdoor areas. This information will be encoded in maps to provide robots with expected operational conditions in advance and beyond the current sensing state. Accordingly, this self-awareness capability will be incorporated into the fusion process to control and switch between the localization techniques to achieve accurate and smooth IO-transitions, e.g., GNSS-RTK will be deactivated during the transition. As an urgent and unique demand to have an accurate and continuous IO-transition towards fully autonomous navigation/transportation, Saxion University and the proposal’s partners are determined to design a commercial and modular industrial-based localization system with robust performance, self-awareness about the localization capabilities and less human interference. Furthermore, AlFusIOn will intensively collaborate with MAPS (a RAAKPRO proposed by HAN University) to achieve accurate localization in outdoor environments.
In the last decade, the automotive industry has seen significant advancements in technology (Advanced Driver Assistance Systems (ADAS) and autonomous vehicles) that presents the opportunity to improve traffic safety, efficiency, and comfort. However, the lack of drivers’ knowledge (such as risks, benefits, capabilities, limitations, and components) and confusion (i.e., multiple systems that have similar but not identical functions with different names) concerning the vehicle technology still prevails and thus, limiting the safety potential. The usual sources (such as the owner’s manual, instructions from a sales representative, online forums, and post-purchase training) do not provide adequate and sustainable knowledge to drivers concerning ADAS. Additionally, existing driving training and examinations focus mainly on unassisted driving and are practically unchanged for 30 years. Therefore, where and how drivers should obtain the necessary skills and knowledge for safely and effectively using ADAS? The proposed KIEM project AMIGO aims to create a training framework for learner drivers by combining classroom, online/virtual, and on-the-road training modules for imparting adequate knowledge and skills (such as risk assessment, handling in safety-critical and take-over transitions, and self-evaluation). AMIGO will also develop an assessment procedure to evaluate the impact of ADAS training on drivers’ skills and knowledge by defining key performance indicators (KPIs) using in-vehicle data, eye-tracking data, and subjective measures. For practical reasons, AMIGO will focus on either lane-keeping assistance (LKA) or adaptive cruise control (ACC) for framework development and testing, depending on the system availability. The insights obtained from this project will serve as a foundation for a subsequent research project, which will expand the AMIGO framework to other ADAS systems (e.g., mandatory ADAS systems in new cars from 2020 onwards) and specific driver target groups, such as the elderly and novice.
The traffic safety of cyclists is under pressure. The number of fatalities and injuries is increasing, and the number of single-bicycle accidents is on the rise. However, from a traffic safety perspective, the most concerning trend is the growing number of incidents between motorized vehicles and cyclists. In addition to infrastructural solutions, such as more segregated and wider bike lanes, both industry and government are exploring technological developments to better safeguard cyclist safety. One of the technological solutions being considered is the use of C-V2X communication. C-V2X, Cellular Vehicle-to-X, is a technology that enables short-range signal exchanges between road users, informing them of each other's presence. C-V2X can be used, for example, to alert drivers via dedicated in-car information systems about the presence of cyclists on the road (e.g. at crossings). Although the technology and chipsets have been developed, the application of C-V2X to improve cyclist safety has not yet been thoroughly investigated. Therefore, HAN, Gazelle, and ARK Infomotives are researching the impact of C-V2X (on cyclist safety). Using advanced simulations with a digital twin in an urban environment and rural environment, the study will analyze how drivers respond to cyclist presence signals and determine the maximum penetration rate of ‘connected’ cyclists. Based on this, a pilot study will be conducted in a controlled environment on HAN terrain to validate the direction of the simulation results. The project aligns with the Missiegedreven Innovatiebeleid and the KIA Sleuteltechnologieën, specifically within application of digital and information technologies. This proposal aligns with the innovation domain of Semiconductor Technologies by applying advanced sensor and digital connectivity solutions to enhance cyclist safety. The project fits within the theme of Sleuteltechnologieën en Duurzame Materialen of the strategic research agenda of the VH by utilizing digital connectivity, sensor fusion, and data-driven decision-making for safer mobility solutions.
