Machine learning of serum metabolic patterns encodes early-stage lung adenocarcinoma

2021 ◽  
Author(s):  
Lin Huang ◽  
Kun Qian
Keyword(s):  
Machine Learning ◽  
Lung Adenocarcinoma ◽  
Cancer Detection ◽  
High Performance ◽  
Large Scale ◽  
Early Cancer ◽  
Early Stage ◽  
Early Cancer Detection ◽  
Ionization Mass ◽  
Efficient Test

Abstract Early cancer detection greatly increases the chances for successful treatment, but available diagnostics for some tumours, including lung adenocarcinoma (LA), are limited. An ideal early-stage diagnosis of LA for large-scale clinical use must address quick detection, low invasiveness, and high performance. Here, we conduct machine learning of serum metabolic patterns to detect early-stage LA. We extract direct metabolic patterns by the optimized ferric particle-assisted laser desorption/ionization mass spectrometry within 1 second using only 50 nL of serum. We define a metabolic range of 100-400 Da with 143 m/z features. We diagnose early-stage LA with sensitivity~70-90% and specificity~90-93% through the sparse regression machine learning of patterns. We identify a biomarker panel of seven metabolites and relevant pathways to distinguish early-stage LA from controls (p < 0.05). Our approach advances the design of metabolic analysis for early cancer detection and holds promise as an efficient test for low-cost rollout to clinics.

scholarly journals A mathematical model of ctDNA shedding predicts tumor detection size

2020 ◽  
Author(s):  
Stefano Avanzini ◽  
David M. Kurtz ◽  
Jacob J. Chabon ◽  
Everett J. Moding ◽  
Sharon Seiko Hori ◽  
...  
Keyword(s):  
Mathematical Model ◽  
Cancer Detection ◽  
Lung Tumor ◽  
Early Cancer ◽  
Early Stage ◽  
A Priori ◽  
Circulating Tumor Dna ◽  
Early Cancer Detection ◽  
Tumor Evolution ◽  
Early Stage Lung Cancer

AbstractEarly cancer detection aims to find tumors before they progress to an incurable stage. We developed a stochastic mathematical model of tumor evolution and circulating tumor DNA (ctDNA) shedding to determine the potential and the limitations of cancer early detection tests. We inferred normalized ctDNA shedding rates from 176 early stage lung cancer subjects and calculated that a 15 mL blood sample contains on average 1.7 genome equivalents of ctDNA for lung tumors with a volume of 1 cm3. For annual screening, the model predicts median detection sizes between 3.8 and 6.6 cm3 corresponding to lead times between 310 and 450 days compared to current lung tumor sizes at diagnosis. For monthly cancer relapse testing based on 20 a priori known mutations, the model predicts a median detection size of 0.26 cm3 corresponding to a lead time of 150 days. This mechanistic framework can help to optimize early cancer detection approaches.

scholarly journals Rank-Based miRNA Signatures for Early Cancer Detection

2014 ◽  
Vol 2014 ◽  
pp. 1-7 ◽  
Author(s):  
Mario Lauria
Keyword(s):  
Cancer Detection ◽  
Large Scale ◽  
Early Cancer ◽  
Early Cancer Detection ◽  
Widespread Application ◽  
New Approach ◽  
Circulating Mirna ◽  
Transcriptional Signature ◽  
Current State ◽  
Reference Map

We describe a new signature definition and analysis method to be used as biomarker for early cancer detection. Our new approach is based on the construction of a reference map of transcriptional signatures of both healthy and cancer affected individuals using circulating miRNA from a large number of subjects. Once such a map is available, the diagnosis for a new patient can be performed by observing the relative position on the map of his/her transcriptional signature. To demonstrate its efficacy for this specific application we report the results of the application of our method to published datasets of circulating miRNA, and we quantify its performance compared to current state-of-the-art methods. A number of additional features make this method an ideal candidate for large-scale use, for example, as a mass screening tool for early cancer detection or for at-home diagnostics. Specifically, our method is minimally invasive (because it works well with circulating miRNA), it is robust with respect to lab-to-lab protocol variability and batch effects (it requires that only the relative ranking of expression value of miRNA in a profile be accurate not their absolute values), and it is scalable to a large number of subjects. Finally we discuss the need for HPC capability in a widespread application of our or similar methods.

scholarly journals CRISPR Cas/Exosome Based Diagnostics: Future of Early Cancer Detection

2021 ◽  
Author(s):  
P.P. Mubthasima ◽  
Kaumudi Pande ◽  
Rajalakshmi Prakash ◽  
Anbarasu Kannan
Keyword(s):  
Cancer Cells ◽  
Cancer Detection ◽  
Diagnostic Tool ◽  
Early Cancer ◽  
Early Stage ◽  
Extracellular Vesicle ◽  
Early Cancer Detection ◽  
Diagnostic Tools ◽  
Per Se ◽  
Almost All

Trending and Thriving, CRISPR/Cas has expanded its wings towards diagnostics in recent years. The potential of evading off targeting has not only made CRISPR/Cas an effective therapeutic aid but also an impressive diagnostic tool for various pathological conditions. Exosomes, 30 - 150nm sized extracellular vesicle present and secreted by almost all type of cells in body per se used as an effective diagnostic tool in early cancer detection. Cancer being the leading cause of global morbidity and mortality can be effectively targeted if detected in the early stage, but most of the currently used diagnostic tool fails to do so as they can only detect the cancer in the later stage. This can be overcome by the use of combo of the two fore mentioned diagnostic aids, CRISPR/Cas alongside exosomes, which can bridge the gap compensating the cons. This chapter focus on two plausible use of CRISPR/Cas, one being the combinatorial aid of CRISPR/Cas and Exosome, the two substantial diagnostic tools for successfully combating cancer and other, the use of CRISPR in detecting and targeting cancer exosomes, since they are released in a significant quantity in early stage by the cancer cells.

Early Cancer Detection from Genome-wide Cell-free DNA Fragmentation via Shuffled Frog Leaping Algorithm and Support Vector Machine

2021 ◽  
Author(s):  
Linjing Liu ◽  
Xingjian Chen ◽  
Ka-Chun Wong
Keyword(s):  
Machine Learning ◽  
Support Vector Machine ◽  
Cancer Detection ◽  
Early Cancer ◽  
Machine Learning Algorithms ◽  
Early Cancer Detection ◽  
Supplementary Information ◽  
Support Vector ◽  
Shuffled Frog Leaping Algorithm ◽  
Shuffled Frog Leaping

Abstract Motivation Early cancer detection is significant for the patient mortality rate reduction. Although machine learning has been widely employed in that context, there are still deficiencies. In this work, we studied different machine learning algorithms for early cancer detection and proposed an Adaptive Support Vector Machine (ASVM) method by synergizing Shuffled Frog Leaping Algorithm (SFLA) and Support Vector Machine (SVM) in this paper. Results As ASVM regulates SVM for parameter adaption based on data characteristics, the experimental results demonstrated the robust generalization capability of ASVM on different datasets under different settings; for instance, ASVM can enhance the sensitivity by over 10% for early cancer detection compared with SVM. Besides, our proposed ASVM outperformed Grid Search + SVM and Random Search + SVM by significant margins in terms of the area under the ROC curve (AUC) (0.938 vs. 0.922 vs. 0.921). Availability The proposed algorithm and dataset are available at https://github.com/ElaineLIU-920/ASVM-for-Early-Cancer-Detection. Supplementary information Supplementary data are available at Bioinformatics online.

scholarly journals Statistical and machine learning models for optimizing energy in parallel applications

2019 ◽  
Vol 33 (6) ◽  
pp. 1079-1097 ◽  
Author(s):  
Mark Endrei ◽  
Chao Jin ◽  
Minh Ngoc Dinh ◽  
David Abramson ◽  
Heidi Poxon ◽  
...  
Keyword(s):  
Machine Learning ◽  
Energy Efficiency ◽  
High Performance ◽  
Large Scale ◽  
Energy Use ◽  
Parallel Applications ◽  
Learning Models ◽  
Trade Off ◽  
Time Required ◽  
Machine Learning Models

Rising power costs and constraints are driving a growing focus on the energy efficiency of high performance computing systems. The unique characteristics of a particular system and workload and their effect on performance and energy efficiency are typically difficult for application users to assess and to control. Settings for optimum performance and energy efficiency can also diverge, so we need to identify trade-off options that guide a suitable balance between energy use and performance. We present statistical and machine learning models that only require a small number of runs to make accurate Pareto-optimal trade-off predictions using parameters that users can control. We study model training and validation using several parallel kernels and more complex workloads, including Algebraic Multigrid (AMG), Large-scale Atomic Molecular Massively Parallel Simulator, and Livermore Unstructured Lagrangian Explicit Shock Hydrodynamics. We demonstrate that we can train the models using as few as 12 runs, with prediction error of less than 10%. Our AMG results identify trade-off options that provide up to 45% improvement in energy efficiency for around 10% performance loss. We reduce the sample measurement time required for AMG by 90%, from 13 h to 74 min.

scholarly journals Small-area data on socioeconomic status and immigrant groups for evaluating equity of early cancer detection and care

2021 ◽  
pp. 1-6
Author(s):  
Ulf Strömberg ◽  
Brandon L. Parkes ◽  
Amir Baigi ◽  
Carl Bonander ◽  
Anders Holmén ◽  
...  
Keyword(s):  
Socioeconomic Status ◽  
Cancer Detection ◽  
Small Area ◽  
Early Cancer ◽  
Early Cancer Detection ◽  
Area Data

Dying To Be Men: Masculinity and Early Cancer Detection Among Nigerian Men

2021 ◽  
pp. 0272684X2110049
Author(s):  
Darlingtina Esiaka ◽  
Candidus Nwakasi ◽  
Kelsey Brodie ◽  
Aaron Philip ◽  
Kalu Ogba
Keyword(s):  
Public Health ◽  
Cancer Detection ◽  
Attachment Styles ◽  
Early Cancer ◽  
Sub Saharan Africa ◽  
Early Cancer Detection ◽  
Anxious Attachment ◽  
Incidence And Mortality ◽  
Nigerian Men ◽  
Sub Saharan

Cancer incidence and mortality in Nigeria are increasing at an alarming rate, especially among Nigerian men. Despite the numerous public health campaigns and education on the importance of early cancer detection in Nigeria, there exist high rate of fatal/advanced stage cancer diagnoses among Nigerian men, even among affluent Nigerian men. However, there is limited information on patterns of cancer screening and psychosocial predictors of early cancer detection behaviors among Nigerian men. In this cross-sectional study, we examined demographic and psychosocial factors influencing early cancer detection behaviors among Nigerian men. Participants (N = 143; Mage = 44.73) responded to survey assessing: masculinity, attachment styles, current and future cancer detection behaviors, and sociodemographic characteristics. We found that among the participants studied, education, masculinity and anxious attachment were significantly associated with current cancer detection behaviors. Additionally, education and anxious attachment were significantly associated with future cancer detection behaviors. Our finding is best served for clinicians and public health professionals, especially those in the field of oncology in Sub-Saharan Africa. Also, the study may be used as a groundwork for future research and health intervention programs targeting men in Sub-Saharan Africa.

Sign in / Sign up

Export Citation Format

Share Document