Search

Background and Objective: Glioblastoma (GBM) is one of the most aggressive and lethal human cancers. Intra-tumoral genetic heterogeneity poses a significant challenge for treatment. Biopsy is invasive, which motivates the development of non-invasive, MRI-based machine learning (ML) models to quantify intra-tumoral genetic heterogeneity for each patient. This capability holds great promise for enabling better therapeutic selection to improve patient outcome., Methods: We proposed a novel Weakly Supervised Ordinal Support Vector Machine (WSO-SVM) to predict regional genetic alteration status within each GBM tumor using MRI. WSO-SVM was applied to a unique dataset of 318 image-localized biopsies with spatially matched multiparametric MRI from 74 GBM patients. The model was trained to predict the regional genetic alteration of three GBM driver genes (EGFR, PDGFRA and PTEN) based on features extracted from the corresponding region of five MRI contrast images. For comparison, a variety of existing ML algorithms were also applied. Classification accuracy of each gene were compared between the different algorithms. The SHapley Additive exPlanations (SHAP) method was further applied to compute contribution scores of different contrast images. Finally, the trained WSO-SVM was used to generate prediction maps within the tumoral area of each patient to help visualize the intra-tumoral genetic heterogeneity., Results: WSO-SVM achieved 0.80 accuracy, 0.79 sensitivity, and 0.81 specificity for classifying EGFR; 0.71 accuracy, 0.70 sensitivity, and 0.72 specificity for classifying PDGFRA; 0.80 accuracy, 0.78 sensitivity, and 0.83 specificity for classifying PTEN; these results significantly outperformed the existing ML algorithms. Using SHAP, we found that the relative contributions of the five contrast images differ between genes, which are consistent with findings in the literature. The prediction maps revealed extensive intra-tumoral region-to-region heterogeneity within each individual tumor in terms of the alteration status of the three genes., Conclusions: This study demonstrated the feasibility of using MRI and WSO-SVM to enable non-invasive prediction of intra-tumoral regional genetic alteration for each GBM patient, which can inform future adaptive therapies for individualized oncology., Competing Interests: The authors have declared that no competing interests exist., (Copyright: © 2024 Wang et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.)

While shifts in organismal biology stemming from climate change are receiving increased attention, we know relatively little about how organisms respond to other forms of anthropogenic disturbance. The urban heat island (UHI) effect describes the capture of heat by built structures (e.g. asphalt), resulting in elevated urban temperatures. The UHI is a well-studied phenomenon, but only a handful of studies have investigated trait-based shifts resulting from the UHI, and even fewer have attempted to quantify the magnitude of the UHI experienced at the microclimate scale. Here, using a common urban exploiter, the Western black widow spider (Latrodectus hesperus), we show that the UHI experienced by spiders in July in their urban Phoenix, AZ refuges is 6°C hotter (33°C) than conditions in the refuges of spiders from Sonoran Desert habitat outside of Phoenix's development (27°C). We then use this field microclimate UHI estimate to compare the development speed, mass gain and mortality of replicate siblings from 36 urban lineages reared at 'urban' and 'desert' temperatures. We show that extreme heat is slowing the growth of spiderlings and increasing mortality. In contrast, we show that development of male spiders to their penultimate moult is accelerated by 2 weeks. Lastly, in terms of behavioral shifts, UHI temperatures caused late-stage juvenile male spiders to heighten their foraging voracity and late-stage juvenile female spiders to curtail their web-building behavior. Trait-based approaches like the one presented herein help us better understand the mechanisms that lead to the explosive population growth of urban (sometimes invasive) species, possibly at the expense of urban biodiversity. Studies of organismal responses to the present day UHI can be used as informative surrogates that help us grasp the impact that projected climate change will have on biodiversity., Competing Interests: The authors have declared that no competing interests exist.

Purpose: We investigated whether a tool using patient-entered wellness data to generate tailored electronic recommendations improved preventive care delivery., Methods: We conducted a mixed-methods retrospective study of primary care encounters utilizing an Integrated Wellness Tool with a matched-comparison before-and-after study design. Encounters took place at a single clinic within the Cleveland Clinic Health System. The primary outcome was preventive orders placed. Index patients were matched, based on propensity scores, with comparison patients seen in the same clinic several months earlier., Results: Five providers conducted 863 patient encounters using the tool during the study period. During encounters using the tool, providers placed more orders for smoking cessation programs (2.4 vs 0.5%, P < .01), lifestyle medicine (2.4 vs 0%, P < .01) and psychology (2.3 vs 1.0%, P = .04) consults, online nutrition (2.4 vs 1.4%, P = .04) and stress management (5.5 vs 0.9%, P < .01) programs, spirometry (5.9 vs 1.7%, P < .01) and polysomnography (6.3 vs 1.3%, P < .01) tests, and antidepressant (7.2 vs 3.9%, P = .01) and hypnotic (2.2 vs 0.7%, P = .01) medications when compared with matched encounters., Conclusions: Patients are willing to enter lifestyle data, and these data influence provider orders., Competing Interests: Conflict of interest: none declared., (© Copyright 2017 by the American Board of Family Medicine.)