Analytics in Precision Medicine

It is apparent by now that analytics is not a mechanism limited only to the tech industry. One sector that could greatly benefit from analytics is that of cancer research, specifically in precision medicine.

Genomic data is rich with valuable information

Precision medicine is a field of cancer research that focuses on tailoring treatments to patients based on their cancer type and genomic data. The research focuses on performing high throughput drug screening (HTDS), which is the process of applying many different drugs to tumor tissue and seeing which drug was the most effective.

Each well contains a portion of tumor tissue and various drugs are applied to each well

The issues with this current process of HTDS are that the lab needs to obtain enough tumor tissue to run the entire process and the time between tissue collection and treatment recommendation is crucial time for the patient.

There is huge potential in utilizing machine learning to predict a cancer patient’s response to a drug based on their genomic data. Rather than performing HTDS and seeing which drug is the most effective for a given patient, we can use historical data and machine learning to predict which drug will be the most effective. This new process would require less tumor tissue since the lab would only need enough for DNA and RNA sequencing and would help the recommendations reach the patient more quickly.

Machine learning is beginning to be used more in the field of precision medicine

Although machine learning seems like a promising addition to the field of precision medicine, there are various challenges that make it difficult to implement. One challenge is the sheer amount of genomic data available for even a single patient. DNA and RNA sequencing for a single patient can be costly, and it produces a large amount of data. Researchers state that, “combining data profiles at various levels would result in high dimensionality with large number of covariates” which can make it difficult to store and create models with (Xu et al.).

Despite these challenges, utilizing machine learning in precision medicine can be extremely beneficial not only for cancer research, but for patients everywhere.

References:

• Low, Siew-Kee, et al. “Breast Cancer: The Translation of Big Genomic Data to Cancer Precision Medicine.” Cancer Science, vol. 109, no. 3, 2017, pp. 497–506., doi:10.1111/cas.13463.
• Xu, Jia, et al. “Translating Cancer Genomics into Precision Medicine with Artificial Intelligence: Applications, Challenges and Future Perspectives.” Human Genetics, vol. 138, no. 2, 2019, pp. 109–124., doi:10.1007/s00439–019–01970–5.