Sunday, March 23, 2014

MIS Assignment #9 - Decision Support Is Good for Your Health

Q1. The system discussed in this case was decision support system. However, other types of computer-aided support are utilized in medicine. Can you think of ways that the medical profession could use AI system?

AI systems have the potential to revolutionize medicine. While a human physician -- especially a tired one at the end of a long shift -- might overlook or misinterpret the subtle symptoms of a rare disease that he or she hasn't encountered since medical school, computers don't need coffee and sleep and they don't forget information. Better yet, an AI system also may be able to track the latest medical research and even tap continuously into the observations and experiences of other doctors, and then crunch all that data to come up with statistically-validated treatment options.

Source: http://singularityhub.com/2010/05/10/the-ai-doctor-is-ready-to-see-you/

For example how about pattern recognition? Could that help in diagnosing illness?

Genetic screening is an example of pattern recognition where it uses genomics technologies to detect known genetic mutations, also known as genetic markers, in your DNA. These markers are associated with common and rare genetic illnesses or disorders such as cardiovascular diseases (CVD), diabetes and cancers. Genetic markers may also indicate the potential for you to have adverse reactions towards certain types of food or drugs.

Q2. A big worry in collating and aggregation of medical information across departments and even medical institutions is that the more access there is to a person’s medical information, the more exposed that personal information becomes. HIPAA (Health Insurance Portability and Accountability Act), signed into law in 1996, addresses the security and privacy of your health data. The law was enacted to cry to ensure that medical records, electronically stored and transferred, would be protected.

Do you think that making your medical records available to the various branches of the medical industry (doctors, therapists, insurance companies, hospital billing, etc) is, on the whole, good or bad?

On the whole is bad.

Why? Can you think of any instances where disclosure of medical information could cause problems for a patient?

Here are some of the ways that patients' rights to privacy come up short:

Your consent to the use of your medical information is not required if it is used or disclosed for treatment, payment, or health care operations (TPO). In many situations such as emergencies, this makes perfect sense. You don't expect the ambulance driver to get your permission to call the hospital emergency room when you are having a heart attack. On the other hand, since your consent is not required for payment, your health care provider could submit a claim to your insurance company - even for a procedure you wanted to keep private and intended to pay for yourself. In addition, treatment, payment, and health care operations have broad definitions that encompass many activities that most people are not familiar with.

Your past medical information may become available, even if you thought the information was long buried and would remain private. An event, treatment, or procedure from your distant past can be disclosed the same as information about current conditions. Of some comfort, old information is given the same protections under HIPAA as current information. In addition, HIPAA's "minimum necessary" rule applies to old as well as new records. This means that the amount of information disclosed should be limited to what is necessary to accomplish the purpose.

Your private health information can be used for marketing and may be disclosed without your authorization to pharmaceutical companies or businesses looking to recall, repair or replace a product or medication.

You have no right to sue under HIPAA for violations of your privacy. In other words, you do not have a "private right of action." Only the HHS or the U.S. Department of Justice has the authority to file an action for violations of the Privacy Rule. All you can do is complain to the one who violates your privacy or to the HHS. However, you may be able to sue under state law using the HIPAA Privacy Rule to establish the appropriate standard of care.

Business associates of a covered entity can receive protected health information (PHI) without a patient's knowledge or consent. Before entering into an agreement with a business associate, a covered entity must receive assurance that information will be handled appropriately. After that, handling of sensitive data by business associates is left only to an honor system. Even when the limitations of the Privacy Rule are applied, many people can still see your medical records when carrying out the business of the plan or provider.
Business associates may include billing services, lawyers, accountants, data processors, software vendors, and more. Your doctor may, for example, disclose your health information to a business associate that processes medical bills. A written contract for this arrangement is required, but the doctor doesn't have to check to see that your information is being handled correctly. If there is a violation, the business associate is supposed to report it.  

Law enforcement access to protected health information under HIPAA is a significant concern of privacy and civil liberties advocates. Some disclosures may be made to law enforcement without a warrant or court order.

Source: https://www.privacyrights.org/HIPAA-basics-medical-privacy-electronic-age

Q3. Could predictive analytics be a part of the HHC decision support system? If so, what sort of data would it analyze?

Yes. Bioinformatics big data that can map and identify base nucleotide (DNA) changes in the entire human genome.

What might it tell medical staff? Would it be useful only to those who are already ill or could it help healthy people? How?

For example, a normal blood test is less specific and can only detect changes in your body when a disease is already present. Genetic screening is more specific and detects risks for a disease even before the onset of that particular disease.

Q4. A clinical study has shown that telemonitoring, discussed briefly in this case, helps in keeping down medical costs. In facts, monitored patients were hospitalized about half as often as those with the same illness who were not monitored. Emergency room visits were five times more likely among those who were unmonitored.

What types of illnesses could be monitored this way (think chronic diseases like high blood pressure)?

Diabetes is one such illness

Would it make sense to use the system as follow-up care?

Yes. This is because telemonitoring is a cost-effective way to tell the patient when something is wrong before the problem requires an emergency room visit at the convenient from their own home.

How could the data be utilized to help those who might become sick in the future?

When the data are collected and combined with all the other relevant information, health care professionals can build a clear picture of the patient and the outcomes of various treatments. This can reduce of misdiagnosis.

Into what part of Isabel would the data fit?
Database.

Q5. Could an automated medical diagnosis system ever replace live doctors? Why or why not? Would you trust an experienced doctor over a database that you could query yourself? Why or Why not?


No. People don’t usually feel comfortable with machines totally in charge of medical diagnoses and treatments even though statistics indicate that they may be more accurate

Monday, March 3, 2014

MIS Assignment #8 - “Crystal Ball, Clairvoyant, Fortune Telling…Can Predictive Analytics Deliver the Future”

Q1:
Many predictive analytic models are based on neural network technologies. What is the role of neural networks in predictive analytics?

The role of neural networks in predictive analytics is most useful for identification, classification, and prediction and is capable of finding and differentiating patterns. This data can then be used to make predictions about the likelihood of the occurrence of future events.

How can neural networks help predict the likelihood of future events? In answering this questions, specifically reference Blue Cross Blue Shield of Tennessee.

Blue Cross Blue Shield of Tennessee – uses a neural network predictive model to predict which health care resources will be needed by which postoperative patients months and even years into the future. According to Soyal Momin, manager of research and development at Blue Cross Blue Shield, “If we’re seeing a pattern that predicts heart failure, kidney failure, or diabetes, we want to know that as soon as possible.”

Neural networks can help predict the likelihood of future events for Blue Cross Blue Shield of Tennessee because by using artificial intelligence, it can predict any health issue trends. This information can then be used to help treat any medical diseases among patients.

Q2:
What if the Richmond police began to add demographic data its predictive analytics system to further attempt to determine the type of person (by demographic) who would in all likelihood commit a crime. Is predicting the type of person who would commit a crime by demographic data (ethnicity, gender, income level, and so on) good or bad?

Good. Predicting a crime by demographic data may be unethical, but in some cases it could be very helpful to saving people’s lives. Therefore whatever can help with a predictive analytics system is qualified as beneficial.

Q3:
In the movie Gattaca, predictive analytics were used to determine the most successful career for a person. Based on DNA information, the system determined whether or not an individual was able to advance through an educational track to become something like an engineer or if the person should complete only a lower level of education and become a janitor. The government then acted on the system’s recommendations and placed people in various career tracks.

Is this a good or bad use of technology?
This is bad use of predictive analytics because a person may not want to grow up and follow in the same career path as his or her parents. By using the DNA information, the system will come up with careers mainly related to those of the person’s parents. Although there may be patterns in the career fields chosen within a family, there is usually one person in a family that is not exactly like everyone else related to him or her. Therefore, this person would be more likely to pursue a career in a different field than his or her relatives. If a person were to work in the career field chosen through DNA information, he or she may not enjoy it as much as working in a career field of their choice. This is because working in a career field chosen by someone else is not a person’s personal dream in the career industry. This is due to how each people feel, think and behave are different.  

How is this different from the variety of personal tests you can take that inform you of your aptitude for different careers?
Personal tests ask various personal questions, rather than using historical data to predict a person’s future. Personal tests take more into account what the individual taking the test enjoys doing as leisure activities rather than what the previous generations enjoyed to predict a person’s possible career path. Personal tests results can be more individualized because the results depend on the individual’s personal answer, rather than the answer of a relative in the previous generations.

Q4:
What role can geographic information systems (GISs) play in the use of predictive analytics?
GISs can show maps of possible future events.For example GISs could generate a map of the population of certain animals and their location in the coming years or the locations people may start to migrate to.

As you answer this question, specifically reference FedEx’s use of predictive analytics to
(1) determine which customers will respond negatively to a price increase
FedEx can use GISs to map a location where people are poorer.
(2) project additional revenues from proposed drop-box locations
FedEx use GISs to  locate future spots where they can make more revenue.


Q5:
The Department of Defense (DoD) and the Pacific Northwest National Laboratory are combining predictive analytics with visualization technologies to predict the probability that a terrorist attack will occur. For example, suspected terrorists caught on security cameras who loiter too long in a given place might signal their intent to carry out a terrorist attack.

How can this type of predictive analytics be used in an airport?
Put up cameras around the building and if a suspected terrorist seems to be wondering / intending to carry out a terrorist attack, arrest them.
The scanning systems can pick up on traits such as how much luggage they may carry, what they wear, how long they stay in each terminal, etc.

At what other buildings and structure might this be used?
Anywhere where there is already some kind of security, this could be added. For example, tourist attractions, museum, high traffic areas, government buildings, concerts, banks, etc.