Search

Machine learning has been pervasively touching many fields of science. Chemistry and materials science are no exception. While machine learning has been making a great impact, it is still not reaching its full potential or maturity. In this perspective, we first outline current applications across a diversity of problems in chemistry. Then, we discuss how machine learning researchers view and approach problems in the field. Finally, we provide our considerations for maximizing impact when researching machine learning for chemistry.

Methods for clustering people into construals--social affinity groups of individuals who share similarities in how they organize their outlooks on a collection of issues--have recently gained traction. Relational Class Analysis (RCA) is currently the most commonly used method for construal clustering. RCA has been applied to identify affinity groups in social spheres as varied as politics, musical preferences, and attitudes towards science. In this study, we highlight limitations in RCA's ability to accurately identify the number and underlying structure of construals. These limitations stem from RCA's mathematical underpinnings and its insensitivity to the bipolar structure of the survey items, which require respondents to place themselves in a support or rejection space and then express the intensity of their support or rejection. We develop an alternative method, which we call Bipolar Class Analysis (BCA), that aims to address this foundational limitation. BCA conceptualizes people's attitudinal positions as moving along support/rejection semispaces and assesses similarity in opinion organization by taking into account position switches across these semispaces. We conduct extensive simulation analyses, with data organized around different construals, to demonstrate that BCA clusters individuals more accurately than RCA and other available alternatives. We also replicate previous analyses to show that BCA leads to substantively different empirical results than those produced by RCA in its original and later versions, and by Correlational Clustering Analysis (CCA), a method that has been proposed as an alternative to RCA.

We present emission maps (1.5'$\times$1.5' scale, corresponding to 0.18 pc) of the DCN ($J=2-1$) and DCO$^+$ ($J=2-1$) lines in the 2 mm band toward the Orion KL region obtained with the 2 mm receiver system named B4R installed on the Large Millimeter Telescope (LMT). The DCN emission shows a peak at the Orion KL hot core position, whereas no DCO$^+$ emission has been detected there. The DCO$^+$ emission shows enhancement at the west side of the hot core, which is well shielded from the UV radiation from OB massive stars in the Trapezium cluster. We have derived the abundance ratio of DCN/DCO$^+$ at three representative positions where both species have been detected. The gas components with $V_{\rm {LSR}} \approx 7.5-8.7$ km/s are associated with low abundance ratios of $\sim4-6$, whereas much higher abundance ratios ($\sim22-30$) are derived for the gas components with $V_{\rm {LSR}} \approx 9.2-11.6$ km/s. We have compared the observed abundance ratio to our chemical models and found that the observed differences in the DCN/DCO$^+$ abundance ratios are explained by different densities., Comment: Accepted by The Astrophysical Journal, 13 pages, 5 figures, 5 tables

Background: Accurate volumetric assessment of spontaneous subarachnoid hemorrhage (SAH) is a labor-intensive task performed with current manual and semiautomatic methods that might be relevant for its clinical and prognostic implications. In the present research, we sought to develop and validate an artificial intelligence-driven, fully automated blood segmentation tool for SAH patients via noncontrast computed tomography (NCCT) scans employing a transformer-based Swin UNETR architecture. Methods: We retrospectively analyzed NCCT scans from patients with confirmed aneurysmal subarachnoid hemorrhage (aSAH) utilizing the Swin UNETR for segmentation. The performance of the proposed method was evaluated against manually segmented ground truth data using metrics such as Dice score, intersection over union (IoU), the volumetric similarity index (VSI), the symmetric average surface distance (SASD), and sensitivity and specificity. A validation cohort from an external institution was included to test the generalizability of the model. Results: The model demonstrated high accuracy with robust performance metrics across the internal and external validation cohorts. Notably, it achieved high Dice coefficient (0.873), IoU (0.810), VSI (0.840), sensitivity (0.821) and specificity (0.996) values and a low SASD (1.866), suggesting proficiency in segmenting blood in SAH patients. The model's efficiency was reflected in its processing speed, indicating potential for real-time applications. Conclusions: Our Swin UNETR-based model offers significant advances in the automated segmentation of blood after aSAH on NCCT images. Despite the computational intensity, the model operates effectively on standard hardware with a user-friendly interface, facilitating broader clinical adoption. Further validation across diverse datasets is warranted to confirm its clinical reliability.

The International Workshop on Locational Analysis and Related Problems will take place during September 7-8, 2023 in Edinburgh (United Kingdom). It is organized by the Spanish Location Network and the Location Group GELOCA from the Spanish Society of Statistics and Operations Research (SEIO). The Spanish Location Network is a group of more than 140 researchers from several Spanish universities organized into 7 thematic groups. The Network has been funded by the Spanish Government since 2003. The current project is RED2022-134149-T. One of the main activities of the Network is a yearly meeting aimed at promoting the communication among its members and between them and other researchers, and to contribute to the development of the location field and related problems. As a proof of the internationalization of this research group, this will be the first time that the meeting is held out of Spain. The topics of interest are location analysis and related problems. This includes location models, networks, transportation, logistics, exact and heuristic solution methods, and computational geometry, among others., Comment: The proceedings book of the previous editions can be found at arXiv:2002.08287 arXiv:2002.08293 arXiv:2002.08300 arXiv:2002.01702 arXiv:2202.13878

PURPOSE: Subarachnoid hemorrhage (SAH) entails high morbidity and mortality rates. Convolutional neural networks (CNN), a form of deep learning, are capable of generating highly accurate predictions from imaging data. Our objective was to predict mortality in SAH patients by processing the initial CT scan on a CNN based algorithm. METHODS: Retrospective multicentric study of a consecutive cohort of patients with SAH between 2011-2022. Demographic, clinical and radiological variables were analyzed. Pre-processed baseline CT scan images were used as the input for training a CNN using AUCMEDI Framework. Our model's architecture leverages the DenseNet-121 structure, employing transfer learning principles. The output variable was mortality in the first three months. Performance of the model was evaluated by statistical parameters conventionally used in studies involving artificial intelligence methods. RESULTS: Images from 219 patients were processed, 175 for training and validation of the CNN and 44 for its evaluation. 52%(115/219) of patients were female, and the median age was 58(SD=13.06) years. 18.5%(39/219) were idiopathic SAH. Mortality rate was 28.5%(63/219). The model showed good accuracy at predicting mortality in SAH patients exclusively using the images of the initial CT scan (Accuracy=74%, F1=75% and AUC=82%). CONCLUSION: Modern image processing techniques based on AI and CNN make possible to predict mortality in SAH patients with high accuracy using CT scan images as the only input. These models might be optimized by including more data and patients resulting in better training, development and performance on tasks which are beyond the skills of conventional clinical knowledge.

Glioblastoma, a highly aggressive primary brain tumor, is associated with poor patient outcomes. Although magnetic resonance imaging (MRI) plays a critical role in diagnosing, characterizing, and forecasting glioblastoma progression, public MRI repositories present significant drawbacks, including insufficient postoperative and follow-up studies as well as expert tumor segmentations. To address these issues, we present the "R\'io Hortega University Hospital Glioblastoma Dataset (RHUH-GBM)," a collection of multiparametric MRI images, volumetric assessments, molecular data, and survival details for glioblastoma patients who underwent total or near-total enhancing tumor resection. The dataset features expert-corrected segmentations of tumor subregions, offering valuable ground truth data for developing algorithms for postoperative and follow-up MRI scans. The public release of the RHUH-GBM dataset significantly contributes to glioblastoma research, enabling the scientific community to study recurrence patterns and develop new diagnostic and prognostic models. This may result in more personalized, effective treatments and ultimately improved patient outcomes.

Scenario-based testing for automated driving systems (ADS) must be able to simulate traffic scenarios that rely on interactions with other vehicles. Although many languages for high-level scenario modelling have been proposed, they lack the features to precisely and reliably control the required micro-simulation, while also supporting behavior reuse and test reproducibility for a wide range of interactive scenarios. To fill this gap between scenario design and execution, we propose the Simulated Driver-Vehicle (SDV) model to represent and simulate vehicles as dynamic entities with their behavior being constrained by scenario design and goals set by testers. The model combines driver and vehicle as a single entity. It is based on human-like driving and the mechanical limitations of real vehicles for realistic simulation. The model leverages behavior trees to express high-level behaviors in terms of lower-level maneuvers, affording multiple driving styles and reuse. Furthermore, optimization-based maneuver planners guide the simulated vehicles towards the desired behavior. Our extensive evaluation shows the model's design effectiveness using NHTSA pre-crash scenarios, its motion realism in comparison to naturalistic urban traffic, and its scalability with traffic density. Finally, we show the applicability of our SDV model to test a real ADS and to identify crash scenarios, which are impractical to represent using predefined vehicle trajectories. The SDV model instances can be injected into existing simulation environments via co-simulation., Comment: 15 pages, 15 figures