Predicting the Best Lung Cancer Treatment Through Experimental Big Data Tool

Big Data

A man using big data to know the health complaints of his patient. / Photo by: Getty Images


A personalized risk assessment tool that can be used in predicting the survival rate and how early-stage lung cancer patients respond to treatment was developed by researchers from the National University of Singapore. The new predictive tool was able to identify as many as 2,000 early-stage patients whose lives were prolonged by adjuvant chemotherapy. It can be described as a major development in the field of cancer therapeutics because treatments can be customized to improve the survival rates of cancer patients, as reported by the NUS News. 

As more knowledge is gained about tumor variability or heterogeneity, the idea of personalized medicine is starting to materialize. Precision medicine aims to provide the best treatment to the right person at the proper dosage in a timely manner, according to Lim Chwee Teck, a professor from the department of biomedical engineering at NUS and the study’s lead researcher. Prof. Lim added that the potential for personalized medicine is even greater when it leverages the power of big data. He pointed out that they were able to make use of genomic data across multiple cancer types through various databases as a result of global joint efforts in large-scale data sharing. 

Since they had access to open databases, they were able to detect 29 unique extracellular matrix genes that can be used as biomarkers in predicting the progression and treatment of lung cancer. Prof. Lim said their research proves that big amounts of genomic data can be used in creating a decision-making tool that can be used in routine clinical practice. He is thrilled that their research can be applied in the nascent field of liquid biopsy, which is touted to be less painful and less invasive than tissue biopsy. They are also developing a platform that will integrate bioinformatics, microfluidics, and cancer genomics in the testing of tissue samples from patients.