Characterizing phenotypic abnormalities associated with high-risk individuals developing lung cancer using electronic health records from the All of Us researcher workbench

Adoption of the OMOP CDM for Cancer Research using Real-world Data: Current Status and Opportunities

Background

The Observational Medical Outcomes Partnership (OMOP) common data model (CDM) that is developed and maintained by the Observational Health Data Sciences and Informatics (OHDSI) community supports large scale cancer research by enabling distributed network analysis. As the number of studies using the OMOP CDM for cancer research increases, there is a growing need for an overview of the scope of cancer research that relies on the OMOP CDM ecosystem.

Objectives

In this study, we present a comprehensive review of the adoption of the OMOP CDM for cancer research and offer some insights on opportunities in leveraging the OMOP CDM ecosystem for advancing cancer research.

Materials and Methods

Published literature databases were searched to retrieve OMOP CDM and cancer-related English language articles published between January 2010 and December 2023. A charting form was developed for two main themes, i.e., clinically focused data analysis studies and infrastructure development studies in the cancer domain.

Results

In total, 50 unique articles were included, with 30 for the data analysis theme and 23 for the infrastructure theme, with 3 articles belonging to both themes. The topics covered by the existing body of research was depicted.

Conclusion

Through depicting the status quo of research efforts to improve or leverage the potential of the OMOP CDM ecosystem for advancing cancer research, we identify challenges and opportunities surrounding data analysis and infrastructure including data quality, advanced analytics methodology adoption, in-depth phenotypic data inclusion through NLP, and multisite evaluation.

Optimizing lung cancer prediction: leveraging Kernel PCA with dendritic neural models

Lung cancer is considered a cause of increased mortality rate due to delays in diagnostics. There is an urgent need to develop an effective lung cancer prediction model that will help in the early diagnosis of cancer and save patients from unnecessary treatments. The objective of the current paper is to meet the extensiveness measure by using collaborative feature selection and feature extraction methods to enhance the dendritic neural model (DNM) in comparison to traditional machine learning (ML) models with minimum features and boost the accuracy, precision, and sensitivity of lung cancer prediction. Comprehensive experiments on a dataset comprising 1000 lung cancer patients and 23 features obtained from Kaggle. Crucial features are identified, and the proposed method's effectiveness is evaluated using metrics such as accuracy, precision, F1 score, sensitivity, specificity, and confusion matrix against other ML models. Feature extraction techniques including Principal Component Analysis (PCA), Kernel PCA (K-PCA), and Uniform Manifold Approximation and Projection (UMAP) are employed to optimize model performance. PCA evaluated the DNM accuracy at 96.50%, precision at 96.64% and 97.45% sensitivity. K-PCA explained the DNM accuracy of 98.50%, precision rate of 99.42%, and 98.84% sensitivity and UMAP elaborated the DNM accuracy of 98%, precision of 98.82%, and 98.82% sensitivity. The K-PCA approach showed outstanding performance in enhancing the DNM model. Highlighting the DNM's accurate prediction of lung cancer. These results emphasize the potential of the DNM model to contribute positively to healthcare research by providing better predictive outcomes.

Comprehensive analysis of genetic associations and single-cell expression profiles reveals potential links between migraine and multiple diseases: a phenome-wide association study

Migraine is a common neurological disorder that affects more than one billion people worldwide. Recent genome-wide association studies have identified 123 genetic loci associated with migraine risk. However, the biological mechanisms underlying migraine and its relationships with other complex diseases remain unclear. We performed a phenome-wide association study (PheWAS) using UK Biobank data to investigate associations between migraine and 416 phenotypes. Mendelian randomization was employed using the IVW method. For loci associated with multiple diseases, pleiotropy was tested using MR-Egger. Single-cell RNA sequencing data was analyzed to profile the expression of 73 migraine susceptibility genes across brain cell types. qPCR was used to validate the expression of selected genes in microglia. PheWAS identified 15 disorders significantly associated with migraine, with one association detecting potential pleiotropy. Single-cell analysis revealed elevated expression of seven susceptibility genes (including ZEB2, RUNX1, SLC24A3, ANKDD1B, etc.) in brain glial cells. And qPCR confirmed the upregulation of these genes in LPS-treated microglia. This multimodal analysis provides novel insights into the link between migraine and other diseases. The single-cell profiling suggests the involvement of specific brain cells and molecular pathways. Validation of gene expression in microglia supports their potential role in migraine pathology. Overall, this study uncovers pleiotropic relationships and the biological underpinnings of migraine susceptibility.

Machine Learning for Lung Cancer Diagnosis, Treatment, and Prognosis

The recent development of imaging and sequencing technologies enables systematic advances in the clinical study of lung cancer. Meanwhile, the human mind is limited in effectively handling and fully utilizing the accumulation of such enormous amounts of data. Machine learning-based approaches play a critical role in integrating and analyzing these large and complex datasets, which have extensively characterized lung cancer through the use of different perspectives from these accrued data. In this review, we provide an overview of machine learning-based approaches that strengthen the varying aspects of lung cancer diagnosis and therapy, including early detection, auxiliary diagnosis, prognosis prediction, and immunotherapy practice. Moreover, we highlight the challenges and opportunities for future applications of machine learning in lung cancer.