Detection of cancer signal for over 50 AJCC cancer types with a multi-cancer early-detection test.

2021 ◽  
Vol 39 (15_suppl) ◽  
pp. 3072-3072
Author(s):  
Habte Aragaw Yimer ◽  
Wai Hong Wilson Tang ◽  
Mohan K. Tummala ◽  
Spencer Shao ◽  
Gina G. Chung ◽  
...  
Keyword(s):  
Machine Learning ◽  
Early Detection ◽  
Cancer Type ◽  
Anatomic Site ◽  
The Third ◽  
Cancer Early Detection ◽  
Wide Range ◽  
Source Data ◽  
Cancer Types

3072 Background: The Circulating Cell-free Genome Atlas study (CCGA; NCT02889978) previously demonstrated that a blood-based multi-cancer early detection (MCED) test utilizing cell-free DNA (cfDNA) sequencing in combination with machine learning could detect cancer signals across multiple cancer types and predict cancer signal origin. Cancer classes were defined within the CCGA study for sensitivity reporting. Separately, cancer types defined by the American Joint Committee on Cancer (AJCC) criteria, which outline unique staging requirements and reflect a distinct combination of anatomic site, histology and other biologic features, were assigned to each cancer participant using the same source data for primary site of origin and histologic type. Here, we report CCGA ‘cancer class’ designation and AJCC ‘cancer type’ assignment within the third and final CCGA3 validation substudy to better characterize the diversity of tumors across which a cancer signal could be detected with the MCED test that is nearing clinical availability. Methods: CCGA is a prospective, multicenter, case-control, observational study with longitudinal follow-up (overall population N = 15,254). Plasma cfDNA from evaluable samples was analyzed using a targeted methylation bisulfite sequencing assay and a machine learning approach, and test performance, including sensitivity, was assessed. For sensitivity reporting, CCGA cancer classes were assigned to cancer participants using a combination of the type of primary cancer reported by the site and tumor characteristics abstracted from the site pathology reports by GRAIL pathologists. Each cancer participant also was separately assigned an AJCC cancer type based on the same source data using AJCC staging manual (8th edition) classifications. Results: A total of 4077 participants comprised the independent validation set with confirmed status (cancer: n = 2823; non-cancer: n = 1254 with non-cancer status confirmed at year-one follow-up). Sensitivity was reported for 24 cancer classes (sample sizes ranged from 10 to 524 participants), as well as an “other” cancer class (59 participants). According to AJCC classification, the MCED test was found to detect cancer signals across 50+ AJCC cancer types, including some types not present in the training set; some cancer types had limited representation. Conclusions: This MCED test that is nearing clinical availability and was evaluated in the third CCGA substudy detected cancer signals across 50+ AJCC cancer types. Reporting CCGA cancer classes and AJCC cancer types demonstrates the ability of the MCED test to detect cancer signals across a set of diverse cancer types representing a wide range of biologic characteristics, including cancer types that the classifier has not been trained on, and supports its use on a population-wide scale. Clinical trial information: NCT02889978.

Performance of a targeted methylation-based multi-cancer early detection test by race/ethnicity.

2021 ◽  
Vol 39 (15_suppl) ◽  
pp. 3071-3071
Author(s):  
Wai Hong Wilson Tang ◽  
Habte Aragaw Yimer ◽  
Mohan K. Tummala ◽  
Spencer Shao ◽  
Gina G. Chung ◽  
...  
Keyword(s):  
Early Detection ◽  
Signal Detection ◽  
Ethnic Groups ◽  
Clinical Stage ◽  
Small Sample ◽  
Cancer Type ◽  
The Third ◽  
Cancer Early Detection ◽  
Race Ethnicity ◽  
Racial Ethnic

3071 Background: Disparities in cancer screening and outcomes based on factors such as gender, socioeconomic status, and race/ethnicity are well documented.1 The Circulating Cell-free Genome Atlas study (CCGA; NCT02889978) was designed to develop and validate a blood-based multi-cancer early detection (MCED) test analyzing plasma cell-free DNA (cfDNA) to detect cancer signals across multiple cancer types and simultaneously predict cancer signal origin. Findings stratified by race/ethnicity from the third and final CCGA validation sub-study are reported. Methods: CCGA is a prospective, multicenter, case-control, observational study with longitudinal follow-up (overall N = 15,254). In this pre-specified exploratory analysis from the third substudy, key objectives were to evaluate test performance for cancer signal detection (specificity, overall sensitivity, and sensitivity by clinical stage) among racial/ethnic groups. Plasma cfDNA from evaluable samples was analyzed using a targeted methylation bisulfite sequencing assay and a machine learning approach. Overall, 4077 participants comprised the independent validation set with confirmed status (cancer: n = 2823; non-cancer: n = 1254). The groups stratified by race/ethnicity were White Non-Hispanic, Black Non-Hispanic, Other Non-Hispanic (including but not limited to Asian, Native Hawaiian, Pacific Islander, American Indian, Alaska Native), Hispanic (all races), and Other/unknown. The study was not powered to detect statistical differences between groups. Results: Cancer and non-cancer groups were predominantly White (2316/2823, 82.0% and 996/1254, 79.4%, respectively). Across racial/ethnic groups, specificity for cancer signal detection was 99.6% (White Non-Hispanic: 992/996, 95% confidence interval [99.0-99.8%]), 100.0% (Black Non-Hispanic: 85/85 [95.7-100.0%]), 100.0% (Other Non-Hispanic: 33/33 [89.6-100.0%]), 98.1% (Hispanic: 101/103 [93.2-99.5%]), and 100% (Other/unknown: 37/37 [90.6-100.0%]). Despite slight differences in cancer type and staging across racial/ethnic groups, overall sensitivity for cancer signal detection among groups ranged from 43.9% to 63.0% (White Non-Hispanic: 50.5%, 1169/2316 [48.4-52.5%], Black Non-Hispanic: 53.9%, 104/193 [46.8-60.8%], Other Non-Hispanic: 43.9%, 25/57 [31.8-56.7%], Hispanic: 63.0%, 121/192 [56.0-69.5%], and Other/unknown: 52.3%, 34/65 [40.4-64.0%]). For all racial/ethnic groups, sensitivity generally increased with clinical stage (with limited exceptions at Stage IV in some groups with small sample sizes). Conclusions: The MCED test demonstrated consistent specificity and sensitivity across racial/ethnic groups, though results are limited by sample size for some groups. These findings indicate broad applicability and support clinical implementation of this MCED test on a population scale. 1. Zavela et al. Brit J Cancer 2021. Clinical trial information: NCT02889978.

scholarly journals Chemotherapy for Late-Stage Cancer Patients: Meta-Analysis of Complete Response Rates

F1000Research ◽  
2015 ◽  
Vol 4 ◽  
pp. 232 ◽  
Author(s):  
Martin L. Ashdown ◽  
Andrew P. Robinson ◽  
Steven L. Yatomi-Clarke ◽  
M. Luisa Ashdown ◽  
Andrew Allison ◽  
...  
Keyword(s):  
Cancer Patients ◽  
Late Stage ◽  
Meta Analysis ◽  
Complete Response ◽  
Drug Regimen ◽  
Cancer Type ◽  
Late Stage Cancer ◽  
Pubmed Database ◽  
Wide Range ◽  
Cancer Types

Complete response (CR) rates reported for cytotoxic chemotherapy for late-stage cancer patients are generally low, with few exceptions, regardless of the solid cancer type or drug regimen. We investigated CR rates reported in the literature for clinical trials using chemotherapy alone, across a wide range of tumour types and chemotherapeutic regimens, to determine an overall CR rate for late-stage cancers. A total of 141 reports were located using the PubMed database. A meta-analysis was performed of reported CR from 68 chemotherapy trials (total 2732 patients) using standard agents across late-stage solid cancers—a binomial model with random effects was adopted. Mean CR rates were compared for different cancer types, and for chemotherapeutic agents with different mechanisms of action, using a logistic regression. Our results showed that the CR rates for chemotherapy treatment of late-stage cancer were generally low at 7.4%, regardless of the cancer type or drug regimen used. We found no evidence that CR rates differed between different chemotherapy drug types, but amongst different cancer types small CR differences were evident, although none exceeded a mean CR rate of 11%. This remarkable concordance of CR rates regardless of cancer or therapy type remains currently unexplained, and motivates further investigation.

scholarly journals Assessment and Improvement Strategies for a Breast Cancer Early Detection Program in Rural South Africa

2018 ◽  
pp. 1-12 ◽  
Author(s):  
Megan Hadley ◽  
Lisa A. Mullen ◽  
Lindsay Dickerson ◽  
Susan C. Harvey
Keyword(s):  
Breast Cancer ◽  
Early Detection ◽  
Documentation System ◽  
Rural South ◽  
Breast Cancer Early Detection ◽  
Cancer Early Detection ◽  
Detection Program ◽  
Early Detection Program ◽  
Rural South Africa

Purpose To assess and develop solutions for an ultrasound-based breast cancer early detection program in rural South Africa 1 year after implementation. Methods A WHO-endorsed RAD-AID Radiology Readiness Assessment was used to evaluate clinic resources. In addition, 5 weeks of observation identified resource deficiencies and reviewed existing documentation methods. On the basis of stakeholders’ input and the BI-RADS, we developed new documentation systems. Training was followed by a survey that assessed feasibility and provider acceptance. Results Resource limitations included lack of computers, unpredictable electrical supply, and inconsistent Internet. The assessment revealed incomplete documentation of breast clinical examinations and history, breast lesions, and follow-up. Furthermore, limitations negatively affected communication among providers. Three solutions were developed: a paper patient history form, a paper clinical findings form, and a computerized patient-tracking data base compliant with BI-RADS. Three nurses, three nursing assistants, and one counselor completed the survey. Seventy-one percent indicated positive general attitudes, and 100% agreed that the documentation system is easy and useful and improves overall quality of care, follow-up, decision making; access to clinical information; and communication between clinicians and patients. Five of the seven providers reported that the system increased visit time, but three of those five believed that the process was valuable. Conclusion Implementation of a breast cancer early detection program in resource-limited regions is challenging, and continual assessment is essential. As a result of identified needs, we developed a documentation system that was broadly accepted. Future steps should focus on increasing efficiency, evaluation of provider attitudes long term, and clinical effect.

scholarly journals Compendiums of cancer transcriptomes for machine learning applications

2019 ◽  
Vol 6 (1) ◽  
Author(s):  
Su Bin Lim ◽  
Swee Jin Tan ◽  
Wan-Teck Lim ◽  
Chwee Teck Lim
Keyword(s):  
Machine Learning ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
Data Reuse ◽  
Rna Seq ◽  
Genomic Landscape ◽  
Source Data ◽  
Machine Learning Applications ◽  
Cancer Types ◽  
Data Source

Abstract There are massive transcriptome profiles in the form of microarray. The challenge is that they are processed using diverse platforms and preprocessing tools, requiring considerable time and informatics expertise for cross-dataset analyses. If there exists a single, integrated data source, data-reuse can be facilitated for discovery, analysis, and validation of biomarker-based clinical strategy. Here, we present merged microarray-acquired datasets (MMDs) across 11 major cancer types, curating 8,386 patient-derived tumor and tumor-free samples from 95 GEO datasets. Using machine learning algorithms, we show that diagnostic models trained from MMDs can be directly applied to RNA-seq-acquired TCGA data with high classification accuracy. Machine learning optimized MMD further aids to reveal immune landscape across various carcinomas critically needed in disease management and clinical interventions. This unified data source may serve as an excellent training or test set to apply, develop, and refine machine learning algorithms that can be tapped to better define genomic landscape of human cancers.

scholarly journals Genomic Copy Number Signatures Based Classifiers for Subtype Identification in Cancer

2020 ◽  
Author(s):  
Bo Gao ◽  
Michael Baudis
Keyword(s):  
Copy Number ◽  
Cancer Type ◽  
Driver Genes ◽  
Bioinformatic Pipeline ◽  
Cancer Subtypes ◽  
The Past ◽  
Source Data ◽  
Subtype Identification ◽  
Limited Application ◽  
Cancer Types

AbstractCopy number aberrations (CNA) are one of the most important classes of genomic mutations related to oncogenetic effects. In the past three decades, a vast amount of CNA data has been generated by molecular-cytogenetic and genome sequencing based methods. While this data has been instrumental in the identification of cancer-related genes and promoted research into the relation between CNA and histo-pathologically defined cancer types, the heterogeneity of source data and derived CNV profiles pose great challenges for data integration and comparative analysis. Furthermore, a majority of existing studies has been focused on the association of CNA to pre-selected “driver” genes with limited application to rare drivers and other genomic elements.In this study, we developed a bioinformatic pipeline to integrate a collection of 44,988 high-quality CNA profiles of high diversity. Using a hybrid model of neural networks and attention algorithm, we generated the CNA signatures of 31 cancer subtypes, depicting the uniqueness of their respective CNA landscapes. Finally, we constructed a multi-label classifier to identify the cancer type and the organ of origin from copy number profiling data. The investigation of the signatures suggested common patterns, not only of physiologically related cancer types but also of clinico-pathologically distant cancer types such as different cancers originating from the neural crest. Further experiments of classification models confirmed the effectiveness of the signatures in distinguishing different cancer types and demonstrated their potential in tumor classification.

scholarly journals Towards Personalized Diagnosis of Glioblastoma in Fluid-Attenuated Inversion Recovery (FLAIR) by Topological Interpretable Machine Learning

Mathematics ◽  
2020 ◽  
Vol 8 (5) ◽  
pp. 770
Author(s):  
Matteo Rucco ◽  
Giovanna Viticchi ◽  
Lorenzo Falsetti
Keyword(s):  
Machine Learning ◽  
Data Analysis ◽  
Tumor Growth ◽  
Topological Data Analysis ◽  
Textural Features ◽  
The Third ◽  
Interpretable Machine Learning ◽  
Fluid Attenuated Inversion Recovery ◽  
Topological Data

Glioblastoma multiforme (GBM) is a fast-growing and highly invasive brain tumor, which tends to occur in adults between the ages of 45 and 70 and it accounts for 52 percent of all primary brain tumors. Usually, GBMs are detected by magnetic resonance images (MRI). Among MRI, a fluid-attenuated inversion recovery (FLAIR) sequence produces high quality digital tumor representation. Fast computer-aided detection and segmentation techniques are needed for overcoming subjective medical doctors (MDs) judgment. This study has three main novelties for demonstrating the role of topological features as new set of radiomics features which can be used as pillars of a personalized diagnostic systems of GBM analysis from FLAIR. For the first time topological data analysis is used for analyzing GBM from three complementary perspectives—tumor growth at cell level, temporal evolution of GBM in follow-up period and eventually GBM detection. The second novelty is represented by the definition of a new Shannon-like topological entropy, the so-called Generator Entropy. The third novelty is the combination of topological and textural features for training automatic interpretable machine learning. These novelties are demonstrated by three numerical experiments. Topological Data Analysis of a simplified 2D tumor growth mathematical model had allowed to understand the bio-chemical conditions that facilitate tumor growth—the higher the concentration of chemical nutrients the more virulent the process. Topological data analysis was used for evaluating GBM temporal progression on FLAIR recorded within 90 days following treatment completion and at progression. The experiment had confirmed that persistent entropy is a viable statistics for monitoring GBM evolution during the follow-up period. In the third experiment we developed a novel methodology based on topological and textural features and automatic interpretable machine learning for automatic GBM classification on FLAIR. The algorithm reached a classification accuracy up to 97%.

scholarly journals Machine Learning Approaches to Classify Primary and Metastatic Cancers Using Tissue of Origin-Based DNA Methylation Profiles

Cancers ◽  
2021 ◽  
Vol 13 (15) ◽  
pp. 3768
Author(s):  
Vijayachitra Modhukur ◽  
Shakshi Sharma ◽  
Mainak Mondal ◽  
Ankita Lawarde ◽  
Keiu Kask ◽  
...  
Keyword(s):  
Machine Learning ◽  
Dna Methylation ◽  
Metastatic Cancer ◽  
Gradient Boosting ◽  
Support Vector ◽  
Cancer Type ◽  
Data Repositories ◽  
Extreme Gradient Boosting ◽  
Cancer Types ◽  
Tissue Of Origin

Metastatic cancers account for up to 90% of cancer-related deaths. The clear differentiation of metastatic cancers from primary cancers is crucial for cancer type identification and developing targeted treatment for each cancer type. DNA methylation patterns are suggested to be an intriguing target for cancer prediction and are also considered to be an important mediator for the transition to metastatic cancer. In the present study, we used 24 cancer types and 9303 methylome samples downloaded from publicly available data repositories, including The Cancer Genome Atlas (TCGA) and the Gene Expression Omnibus (GEO). We constructed machine learning classifiers to discriminate metastatic, primary, and non-cancerous methylome samples. We applied support vector machines (SVM), Naive Bayes (NB), extreme gradient boosting (XGBoost), and random forest (RF) machine learning models to classify the cancer types based on their tissue of origin. RF outperformed the other classifiers, with an average accuracy of 99%. Moreover, we applied local interpretable model-agnostic explanations (LIME) to explain important methylation biomarkers to classify cancer types.

scholarly journals Feature Selection for Breast Cancer Detection using Machine Learning Algorithms

2019 ◽  
Vol 8 (9) ◽  
pp. 2080-2083
Keyword(s):  
Breast Cancer ◽  
Machine Learning ◽  
Neural Networks ◽  
Cancer Detection ◽  
Predictive Models ◽  
Machine Learning Algorithms ◽  
Machine Learning Techniques ◽  
Cancer Type ◽  
Wide Range ◽  
Logistic Regression Algorithm

Cancer has been portrayed as a heterogeneous disease comprising of a wide range of subtypes. The early diagnosis of a cancer type is very important to determine the course of medical treatment required by the patient. The significance of classifying cancerous cells into benign or malignant has driven many research studies, in the biomedical and the bioinformatics field. In the past years researchers have been encouraged to use different machine learning (ML) techniques for cancer detection, as well as prediction of survivability and recurrence. What's more, ML instruments can be used to distinguish key highlights from complex datasets and uncover their significance. An assortment of these procedures, including Artificial Neural Networks (ANNs), Bayesian Networks (BNs), Random Forest Methods (RVMs) and Decision Trees (DTs) has been usually used in cancer research for the development of predictive models, resulting in successful and exact decision making. Although it is obvious that the usage of machine learning techniques can enhance our comprehension of cancer detection, progression, recurrence and survivability, a proper level of accuracy is required for these strategies to be considered in the ordinary clinical practice. The predictive models talked about here depend on different administered ML strategies and on various input features and data samples. We have used Naïve-Bayes classifier, Neural Networks method, Decision Tree and Logistic Regression algorithm to detect the type of breast cancer (Benign or Malignant) and selection of features which are more relevant for prediction. We have made a comparative study to find out the best algorithm of the above four, for prediction of cancer type. With a high level of accuracy, any of these methods can be used to predict the type of breast cancer of any particular patient

Sign in / Sign up

Export Citation Format

Share Document