When 1 in 3 humans are affected by a disease, it needs attention and help from all corners. There are many types of cancers, so it’s hard to say if we’ll ever be able to completely cure cancer. But prevention, early detection and proper care are crucial in cancer diagnosis and its treatment.
As David Agus, a cancer doctor, would like to say:
In health care today, we spend most of the dollars — in terms of treating disease — in the last two years of a person’s life.
I pondered on it one evening and thought I’d find out about some “programmable” possibilities related to cancer research for hackers from the non-scientific community, besides the obvious means of help like donations (both charity and research), awareness drives and volunteering.
I got in touch with Jon Kiddy, a software engineer who works at Roswell Park Cancer Institute. Jon kindly shared his views and pointed out that the current state of cancer research can be summed up in one of Daniel Markham’s excellent posts. After having read the book on the subject called “The Emperor of All Maladies”, Daniel went on to state the general problem with cancer research is that the US healthcare isn’t setup to support individualized care and treatment, which is currently undergoing the most intensive scrutiny. A commentor on Hacker News responded to Daniel’s post with this inspiring message:
You want to fix cancer, don’t wait for the scientists. They are hobbled by regulation. Be an engineer: get out there and make one of the viable solutions work, and make it work outside the US.
What started as modest self-education, has led me to several impactful ways in helping with cancer research:
1. Distributed Computing Projects – In 2003, with grid computing, in less than three months scientists identified 44 potential treatments to fight the deadly smallpox disease. Without the grid, the work would have taken more than one year to complete. Participating in a distributed computing project is the easiest way to get involved with cancer research.
Grid computing works by splitting complex computations into small pieces that can be processed simultaneously on individual public nodes, there-by reducing research time and making the technology infrastructure cost-effective.
2. Build on “Big Data” – Massive amounts of raw data is available for analysis in cancer research. As Jon wrote back to me:
The problem comes when there is such a large amount of data to process in a field where each individual’s treatment is usually uniquely suited only to them. Hadoop/Hbase is in use by The Cancer Genome Atlas to make some of this process more bearable. Their datasets are invaluable.
The combination of Apache Hadoop (for distributed computing), HBase (distributed database), MapReduce (for distributed computing on large datasets on clusters of computers), R Project (for statistical computing), and Gephi (for visualization and exploration) changes the way we think about analysis of Big Data.
Data analysis, data visualization and even Web crawler technology are all important in cancer research, for processing highly distributable problems across huge datasets using a large number of computers.
Last year, the Cloudera Data Science Team wrote about some of their work with Hadoop:
Instead of focusing on a handful of outcomes, we can process all of the events in the data set at the same time. We can try out hundreds of different strategies for cleaning records, stratifying observations into clusters, and scoring drug-reaction tuples, run everything in parallel, and analyze the data at a fraction of the cost of a traditional supercomputer. We can render the results of our analyses using visualization tools that can be used by domain experts to explore relationships within our data that they might never have thought to look for. By dramatically reducing the costs of exploration and experimentation, we foster an environment that enables innovation and discovery.
3. Apps and Tools – Personal profiling and monitoring could be another area of focus for developers interested in cancer research or general health-related diagnosis.
- Whether it’s an app to protect against or detect (early) skin cancer,
- a wearable computing device to track Adverse Drug Events (ADE),
- a crowdsourced game to solve scientific puzzles,
- a prediction model based on social trends,
- or a Web-based tool (similar to mappiness or TrackYourHappiness) to monitor a persons diet (it’s been widely discussed that smoking, ingestion of sugar and excessive red meat may set the stage for rise in cancer occurrences).
There are lots of possibilities for personal solutions that aid in collective science.
“In lieu of spending a decade in training to become an oncologist, I have been able to put my skills to practical use.”, Jon says about the impact he’s making.
I really wish for many more technology enthusiasts to devote their time, skills and efforts in the fight against cancer.