The most well-established risk factor for lung cancer (LC) is smoking, responsible for approximately 85% of cases. The Lung Cancer Risk Assessment Tool (LCRAT) is a key advancement in this field, which predicts individual risk based on factors like smoking habits, demographic details, personal and family medical history, and environmental exposures. This paper proposes a model with fewer features that improves state of the art performance, using a simplified stacking ensemble, making it more accessible and easier to implement in routine healthcare practice. The data used in this work were derived from two cohorts in the United States: The National Lung Screening Trial (NLST) and the Prostate, Lung, Colorectal, and Ovarian (PLCO) Cancer Screening Trial. Both our model and LCRAT achieve an AUC of 0.799 and 0.782 on test respectively. In terms of percentage of positives, in the 50% of the population, both detect 0.766 and 0.754 of the cases. The ensemble of different survival models enhances robustness by mitigating the weakness of individual models and directly impacts the efficiency of the model, increasing the efficiency and generalizability.
Publications
Website LinkVolatile organic compounds (VOCs) play a crucial role in affecting health, environmental integrity, and industrial operations, from air quality to medical diagnostics. The need for highly sensitive and selective detection of these compounds has spurred innovation in sensor technologies. This editorial introduces a special collection of articles in Applied Physics Reviews, exploring the latest advancements in VOC detection technologies. The featured works cover a range of innovations, including electrostatically formed nanowires, chiral liquid crystals, and graphene-based sensors enhanced by machine learning. Together, these articles highlight the dynamic progress in VOC detection, striving for improved sensitivity, selectivity, and real-world applicability. This special collection not only showcases pioneering research but also provides valuable insights into future trends and potential applications in the field.
Key Features
- Discusses the current strategies for fabricating nature-derived bio/chemical sensors
- Presents ways to apply nature-derived bio/chemical sensors in real life
- Describes the future of nature-derived bio/chemical sensors
Description
Nature-Inspired Sensors presents and discusses the basic principles and latest developments in nature-inspired sensing and biosensing materials as well as the design and mechanisms for analyzing their potential in multifunctional sensing applications.
The book starts with a comprehensive review of certain fundamental mechanisms in different living creatures, including humans, animals, and plants. It presents and discusses ways for imitating various nature-inspired structural features and their functional properties, such as hierarchical, interlocked, porous, and bristle-like structures and hetero-layered brick-and-mortar structures.
It also highlights the utility of these structures and their properties for sensing functions, which include static coloration, self-cleaning, adhesive, underwater navigation and object detection, electric charge generation, and sensitive olfactory functions for detecting various substances. This is followed by an appraisal of accumulating knowledge and its translation from the laboratory to the point-of-care phase, using selective sensors as well as desktop and wearable artificial sensing devices, for example, electronic noses and electronic skins, in conjunction with AI-assisted data processing and decision-making in the targeted field of application.
In addition, the book offers an insight into the challenges of continuing the development of nature-inspired smart sensing and biosensing technology and their wider availability, which can be substantially improved. It is a valuable reference for graduates, undergraduates, researchers, and working professionals in the fields of chemistry, materials science, and biomedical and environmental science.
This document presents (1) a summary of the design and development of the design and development of the LUCIA project website and related technical requirements, and (2) an overview of the website sections. D6.5 will be delivered on time while the website will go live in July 2023 as per European Commission PO approval. While it contains only essential information about the project, the LUCIA objectives and preliminary plans; the content will grow as the 4-year project unfolds.
The deliverable “Communication, Dissemination and Exploitation Plan” (due Month 6 [M6]) will provide the strategic framework for content development.
Background: Interstitial lung diseases (ILDs) are an heterogeneous group of infiltrating lung pathologies, for which prompt diagnosis and continuous assessment are of paramount importance. While chest CT is an established diagnostic tool for ILDs, there are no formal guidelines on the follow-up regimen, leaving the frequency and modality of follow-up largely at the clinician’s discretion.
Methods: The study retrospectively evaluated the indication of chest CT in a cohort of 129 ILD patients selected from the ambulatory care polyclinic at University Hospital of Liège. The aim was to determine whether the imagining acquisition had a true impact on clinical course and follow-up. We accepted three different situations for justifying the indication of the CTs: clinical deterioration, a decrease in pulmonary function tests (at least a 10% drop in a parameter), and monitoring for oncological purposes. The other indications, mainly routine follow-up, were classified as “non-justified”. Radiation dose output was evaluated with Computed Tomography Dose Index (CTDI) and Dose Length Product (DLP).
Results: The mean number of CT scans per patient per year was 1.7 ± 0.4, determining irradiation in CTDI (mGy)/year of 34.9 ± 64.9 and DLP in (mGy*cm)/year of 1095 ± 1971. The percentage of justified CT scans was 57 ± 32%, while the scans justified a posteriori were 60 ± 34%. Around 40% of the prescribed monitoring CT scans had no impact on the management of ILD and direct patient care.
Conclusions: Our study identifies a trend of overuse in chest CT scans at follow-up (up to 40%), outside those performed for clinical exacerbation or oncological investigation. In the particular case of ILD exacerbation, CT scan value remains high, underlying the benefit of this strategy.
Mutational signatures are increasingly used to understand the mechanisms causing cancer, predict prognosis and stratify patients for therapy. However, inference of mutational signatures can be error-prone, particularly in the case of featureless, low-sparsity signatures, which often get confounded. One of them is the homologous recombination deficiency-associated signature SBS3, relevant because of its association with prognosis in ovarian and breast cancer and because of its potential use as a biomarker for synthetic lethality therapies. Here, we present the multimodal method for mutational signature extraction, operating on single-base substitutions (SBS) and indels jointly, and highlight its accuracy signature identification and patient survival prediction. Across four different cohorts of whole-genome sequenced ovarian cancers, the multimodal SBS/indel approach correctly distinguished the commonly confused signatures SBS3, SBS8, SBS39, SBS40 and SBS5. Moreover, we identified two different multimodal m-SBS3 signatures, m-SBS3a and m-SBS3b, with distinct patterns in the indel spectrum. Specifically, the m-SBS3b signature was strongly predictive of better survival in high-grade serous ovarian cancer patients, replicating across the four cohorts, with effect sizes greatly exceeding other genetic markers of survival. m-SBS3 further predicted survival in platinum-treated patients with various cancer types, supporting a general utility of the multimodal mutational signatures for generating biologically and clinically meaningful readouts.
Premature termination codons (PTCs) cause ~10–20% of inherited diseases and are a major mechanism of tumor suppressor gene inactivation in cancer. A general strategy to alleviate the effects of PTCs would be to promote translational readthrough. Nonsense suppression by small molecules has proven effective in diverse disease models, but translation into the clinic is hampered by ineffective readthrough of many PTCs. Here we directly tackle the challenge of defining drug efficacy by quantifying the readthrough of ~5,800 human pathogenic stop codons by eight drugs. We find that different drugs promote the readthrough of complementary subsets of PTCs defined by local sequence context. This allows us to build interpretable models that accurately predict drug-induced readthrough genome-wide, and we validate these models by quantifying endogenous stop codon readthrough. Accurate readthrough quantification and prediction will empower clinical trial design and the development of personalized nonsense suppression therapies.
Cancer driver genes can undergo positive selection for various types of genetic alterations, including gain-of-function or loss-of-function mutations and copy number alterations (CNA). We investigated the landscape of different types of alterations affecting driver genes in 17,644 cancer exomes and genomes. We find that oncogenes may simultaneously exhibit signatures of positive selection and also negative selection in different gene segments, suggesting a method to identify additional tumor types where an oncogene is a driver or a vulnerability. Next, we characterize the landscape of CNA-dependent selection effects, revealing a general trend of increased positive selection on oncogene mutations not only upon CNA gains but also upon CNA deletions. Similarly, we observe a positive interaction between mutations and CNA gains in tumor suppressor genes. Thus, two-hit events involving point mutations and CNA are universally observed regardless of the type of CNA and may signal new therapeutic opportunities. An analysis with focus on the somatic CNA two-hit events can help identify additional driver genes relevant to a tumor type. By a global inference of point mutation and CNA selection signatures and interactions thereof across genes and tissues, we identify 9 evolutionary archetypes of driver genes, representing different mechanisms of (in)activation by genetic alterations.
