Intel has announced recently that it's Collaborative Cancer Cloud (CCC) is a step further towards a worldwide roll-out with two more universities joining in on its project. The CCC is a project to put data on cancer diagnosis's of millions of patients into a database that doctors can use to identify patterns for different kinds of cancers and to be able to pinpoint appropriate treatments.
One of the things mentioned in the article is why it is so important to do this and why it could save a cancer patient's life. In the article, Joe Gray, who is from Oregon Health and Science University (OHSU) said that, "the difficulty researchers face when trying to achieve this is the fact cancers are “remarkably heterogeneous”, said Gray, which is why they are using cloud to effectively create a global database of information that can be drawn on for diagnostic purposes" (Donnelly). In other words, each cancer diagnosis has its own unique problems and complications associated with the individual that it was diagnosed in. Therefore, this makes it important to have a database where doctors and researchers can identify patterns in a sample of millions of cancer diagnoses in order to come up with a treatment for the patient quickly. Mr. Gray went on to further say that, "we need to have a database we can use to compare our individual cancer. To have enough statistical power to identify relevant patterns, we’re going to have to compare our cancers to samples from millions of patient to really make this precise" (Donnelly).
An issue that was brought up in the article was the issue of the use of big data and how there are many logistical problems to overcome with using the amount of big data that these databases are planning on using. What they want to be able to do is have machines that screen for the cancer and then automatically upload the data to a database in which they can analyze the data there. As the article explains it, "[the] patient would undergo a biopsy, have the information gleaned from that immediately analysed and swiftly compared with other samples to establish how best to treat it" (Donnelly). This all has to be done very quickly. Joe Gray stated that, "we can't take months and months to do this. We have to be able to render a decision in a few days, and our goal by working with Intel is to do all that in a day [by] 2020" (Donnelly).
In order to get the computing power they need to do this, "CCC is taking a cloud-based approach to managing this data[...]" (Donnelly). The storage needed to do this will be gigantic and so to combat this, CCC is using the computing power, storage, and capabilities of the cloud to store, analyze, and retrieve data for doctors and researchers. "Rather than trying to centralise the data[...]" (Donnelly), they will use the cloud to, "seamlessly send our compute to the data" (Donnelly).
Article: http://www.computerweekly.com/news/450280580/Intel-backed-Collaborative-Cancer-Cloud-gets-one-step-closer-to-worldwide-rollout
I agree with the major issue that was brought up in the article with the use of big data and how there are many logistical problems to overcome with using the amount of big data that these databases are planning on using. However, Intel had backed the project to put data on cancer diagnosis's of millions of patients into a database that doctors can use to identify patterns for different kinds of cancers and to be able to pinpoint appropriate treatments.
ReplyDeleteThe potential that this project has is immense, and all for a good cause. Usually when databases are recording personal medical information it can become a serious problem. However, I believe in this instance that the information on the database could be anonymous since really the only information that doctors will need is what type of cancer and the appropriate treatments. Having millions of records to analyze to make informed decisions could completely revolutionize the way we treat cancer.
ReplyDeleteA major upgrade to the infrastructure of hospitals and medical services would be needed to support this push for big data analysis in hospitals. Like any new system implementation, this new system would also need to take multiple stages in order for the CCC to reach its completion. Perhaps, university hospitals can slowly opt-in into the program, and from there, the amount of data being increased can be controlled. It would be very interesting to see this medical database, as logistically, it would save the time of putting in the same information at each hospital one would visit throughout someone's life. In addition, if the database could also be used by private practices (or if a separate one could be made), people would be able to switch the doctors they see more often. Overall, I feel that the implementation of big data use in hospitals would be similar to how big data is used in business intelligence; clustering would involve more records of data and better correlations can be made towards causes or effects of cancer and treatments.
ReplyDelete