Criterion B: The IT Background of the Issue
There are various approaches with mining technique when in it comes to mining
healthcare data to help solve problems. Below, [Diagram 1] is a basic mining cycle for
healthcare problems, in which these are the steps where the mining technique would
be used to help solve healthcare issues. In box [Diagram 2 i)], is where the cycle first
start, which is the use of mining technology to extract the knowledge in the data.
Diagram 1 (Journal of computer science, 2006): Data mining cycle
One method to approach healthcare problems with a mining technique would be the Decision tree. A decision tree is a knowledge representation structures each nodes and branches organizes to form a tree like structure. Decision tree models are best suited for data mining. They are inexpensive to be made, easy to understand, easy to join together with database system and they have similar or better accuracy in many applications. The decision tree shown in the diagram below [Diagram 2] is built from the very small graph of 9 patients’ information [Table 1]. In this table each row represents to a patient record and is referring as a data instance. The data set contains three predictor attributes, namely Age, Gender, Intensity of symptoms and one goal attribute, namely disease whose values (to be predicted from symptoms) indicates whether the matching patient have a certain disease or not. (Journal of computer science, 2006)
Diagram 2 (Journal of computer science, 2006): Decision Tree
Table 1 (Journal of computer science, 2006): Table for Decision Tree
Criterion C: The impact of the issue
There is a huge amount of data staked up with Health care including patients’ centric data, resource management data and transformed data. (Journal of computer science, 2006) Using mining technique these massive collection of data could be use in many useful ways. But since all the data would include many personal information about the patients there are a lot privacy concern that would need to be dealt with.
Most concern of privacy issues with data mining would come from Health related data since they are the ones that constrain the most information, from the patient’s name, address to their whole medical history, its almost like a story book into one’s life. Other than the data for traffic congestion, since would contain much less, one would need the auto mobile GPS positioning only, it would have not needed to go into detail into one’s life. Unless you are wanted by someone GPS positioning on a car shouldn’t worry you too much.
Back in 1998, a drug store would send out reminders to their costumers who have not renewed their prescription medication. But soon criticism was received from costumers saying this was a violation in their privacy from their medication records. (Thearling, Kurt 1998) Even if it was just a reminder to their costumers, but in order to do so they would have at take a look into their costumer’s files and medical records which could contain many sensitive and personal information.
In issues of Privacy Times, Hendricks stated out that there are also many laws that could prevent from a successful data mining. These few laws could be found in the US, Canada and the European Union, that could impact the data mining directly or indirectly for the used of data mining technology by databases marketing organization. (Thearling, Kurt 1998) Thanks to these few law we might be safe from intentional or unintentional stealing of our personal data. But this is just a few laws, nowadays many could come up with loop holes that could make sure they would get the data they needed without going against these law.
Criterion D: Solutions to Problems Arising from the Issue
One approach to this problem is for example, hospitals analyzing medical records to see which treatment work best for a particle flue, they could use cryptography to encode the results, which would resolve in protect patient’s privacy. This would also limit the number of people who could have access to the information too. Only the person who will be decrypting the data is able to see the information. Hospitals could choose doctors whom they think is trust worthy enough to give them the decryption key, which will allow them to see the data, which from then they are able to look into their medical research then and are able to compare to find the results in the data.
But problems may be raised also with this solution, since in order to use cryptography they would need to hire someone who has the skills in doing so, and that could be a problem. Since such technology is expensive and not all hospital are willing to spend this much money on the protecting the research.
Works Cited:
Thearling, Kurt. “Data Mining and Privacy: A conflict in the making?” DS (1998. Web. June-July 2010
<>
Kaur, Harleen, and Siri Krishan Wasan. "Empirical Study on Applications of Data Mining Techniques in Healthcare." Journal of Computer Science (2006). Department of Mathematics, Jamia Millia Islamia. Web. June-July 2010. <http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.108.8981&rep=rep1&type=pdf>.
ScienceDaily 18 December 2009. 25 June 2010 <http://www.sciencedaily.com/releases/2009/12/091217141306.htm>.
News Article:
Privacy Concerns Could Limit Benefits from Real-Time Data Analysis
ScienceDaily (Dec. 18, 2009) — Society will be unable to take full advantage of real-time data analysis technologies that might improve health, reduce traffic congestion and give scientists new insights into human behavior until it resolves questions about how much of a person's life can be observed and by whom, a Carnegie Mellon University computer scientist contends in a commentary published December 18 in the journalScience.
In a "Perspectives" column, Tom M. Mitchell, head of the Machine Learning Department in Carnegie Mellon's School of Computer Science, notes that data-mining techniques, once used for scientific analysis or for detecting potential credit card fraud, increasingly are being applied to personal activities, conversations and movements, such as information that can be deduced about an individual by monitoring that person's smart phone.
"The potential benefits of mining such data range from reducing traffic congestion and pollution, to limiting the spread of disease, to better using public resources such as parks, buses, and ambulance services," Mitchell wrote. "But risks to privacy from aggregating these data are on a scale that humans have never before faced."
Technical means can help limit threats to privacy and misuse of data, Mitchell said. One approach is to mine data from many different organizations without ever aggregating the data into a central repository. For instance, individual hospitals might analyze their medical records to see which treatments work best for a particular flu strain, then use cryptography to encode the results and protect patient privacy; only then would the findings be combined with those from thousands of other hospitals.
"Perhaps even more important than technical approaches will be a public discussion about how to rewrite the rules of data collection, ownership, and privacy to deal with this sea change in how much of our lives can be observed, and by whom," Mitchell wrote. "Until these issues are resolved, they are likely to be the limiting factor in realizing the potential of these new data to advance our scientific understanding of society and human behavior, and to improve our daily lives."
Mitchell pointed out that the use of real-time data from individuals already has begun. In many cities, anonymous location data from smart phones is being used to provide up-to-the-minute reports of traffic congestion. Researchers have shown that by analyzing health-related Google queries from particular geographic areas, they can estimate the level of flu-like illnesses in regions of the U.S. before government agencies such as the Centers for Disease Control and Prevention can provide estimates. Scientists are beginning to use real-time sensing of routine behavior to study interpersonal interactions as people go about their daily lives.
Combining data sets could open up many new possibilities, as well as new privacy issues, Mitchell said. "For example, if your phone company and local medical center integrated GPS phone data with up-to-the-minute medical records, they could provide a new kind of medical service using phone GPS data to detect that you have recently been near a person who is just now being diagnosed with a contagious disease -- then automatically phoning to warn you."
