Knowledge Graph-Enabled Cancer Data Analytics

Abstract

Cancer registries collect unstructured and structured cancer data for surveillance purposes which provide important insights regarding cancer characteristics, treatments, and outcomes. Cancer registry data typically (1) categorize each reportable cancer case or tumor at the time of diagnosis, (2) contain demographic information about the patient such as age, gender, and location at time of diagnosis, (3) include planned and completed primary treatment information, and (4) may contain survival outcomes. As structured data is being extracted from various unstructured sources, such as pathology reports, radiology reports, medical records, and stored for reporting and other needs, the associated information representing a reportable cancer is constantly expanding and evolving. While some popular analytic approaches including SEER*Stat and SAS exist, we provide a knowledge graph approach to organizing cancer registry data. Our approach offers unique advantages for timely data analysis and presentation and visualization of valuable information. This knowledge graph approach semantically enriches the data, and easily enables linking with third-party data which can help explain variation in cancer incidence patterns, disparities, and outcomes. We developed a prototype knowledge graph based on the Louisiana Tumor Registry dataset. We present the advantages of the knowledge graph approach by examining: i) scenario-specific queries, ii) links with openly available external datasets, iii) schema evolution for iterative analysis, and iv) data visualization. Our results demonstrate that this graph based solution can perform complex queries, improve query run-time performance by Manuscript

Solicitation of Knowledge Graph Enhanced Neural Network Objects Detection by Sentiment Analysis

“…We classify the algorithm and applied it to determine the sentiment predictions. Also, compare our proposal in dialogues with an n-gram embedding based model (deep learning) and sentiment analysis (LU et al, 2020;Shamimul Hasan et al, 2020). The expected results show that our proposal is able in n-gram models, and getting to 87% and an FI-score of 85%.…”

“…The expected results of this study are based on sentiment in the contexts of market, film, industry, image, and diverse emotions. However, predicting sentiment challenges in Facebook and Twitter, like most dialogues do not have a well-formed formal structure (Shamimul Hasan et al, 2020;Zhang et al, 2021). In this situation, nowadays existing increasing sentiment techniques to determine the accurate, explainable, and tracible results, also as for the better performance of dialogues structure and sound.…”

Catalyzing Knowledge-Driven Discovery in Environmental Health Sciences through a Community-Driven Harmonized Language

“…Efforts to integrate biomedical databases have resulted in the creation of several related, but often unconnected, biomedical knowledge graphs [40]. While these graphs are being used to better understand cancer [41], identify new drug candidates [42], and diagnose rare diseases [43], insights about the effect of environmental exposures are not forthcoming, largely because the environmental aspect of diseases is not included in these knowledge graphs. This is for two reasons: there are few curated data sources that associate environmental exposures to phenotypic outcomes in a structured manner [18,44], and the complexity of exposure science has not yet been modeled sufficiently using modern semantic structures to allow for large-scale data integration [18].…”

Knowledge integration and decision support for accelerated discovery of antibiotic resistance genes

“…This design helps to identify patterns among data, and to utilize the information content they carry to gain insights into the mechanisms of action, associations, and testable hypotheses 2 , 10 . In the biomedical domain, knowledge graphs 11 with thousands to millions of RDF triples are used to organize knowledge in life sciences 12 , 13 , including health conditions such as cancer 14 and cardiovascular disease 15 . In the case of antibiotic resistance genes (ARGs), there exist both graph databases like CARD 16 and ARDB 17 that represent ontologies, as well as traditional databases like MEGARes 18 , ARGO 19 , and ARG-ANNOT 20 that store ARG sequencing data.…”