Questions

Below are questions that the organizers found interesting. Please use these samples as inspiration for the question(s) you want to explore! We've separated the questions by track, but don't let that cramp your creativity!

In parenthesis, we've provided a link to a suggested dataset that you can use to answer the question. You may also wish to consider other datasets for another perspective or complementary information. For example, you may be able to join two datasets about doctors on their National Provider Identifier (NPI).

Describe the Disorder

1. Which companies made the most payments? (CMS Open Payments)
2. Which physicians received the most payments and why? Are there payment outliers? What drives the payments? Note: one physician can bill under another and outliers may be misleading; take a look at middle of distribution in addition to outliers. (CMS Open Payments)
3. Which states received the most payments? (CMS Open Payments)
4. What is the total amount of payments by type of physician. (CMS Open Payments)
5. How much ownership do physicians have in Manu/GPOs? (CMS Open Payments)
6. What dollar amount was disputed? Are any physicians/hospitals more likely to dispute than others? (CMS Open Payments)
7. What is the dollar amount of payments made through third parties? Are any physicians/hospitals more likely to pay through 3rd parties than others? (CMS Open Payments)
8. Which are the most costly chronic conditions, in terms of total dollar amount (avg payment x bene count) and aggregated by chronic condition? (Chronic Conditions)
9. Are there any conditions and age group combinations that are expensive to treat? (Chronic Conditions)
10. How do Medicare Part A and B differ? (Chronic Conditions)
11. How do Medicare Part A and B interact? (Chronic Conditions)
12. How much did Medicare payments increase from 2008 to 2010? (Chronic Conditions)
13. Which county has the highest total cost for hospital inpatient stays? (SPARCS)
14. Which illness is the most expensive? What about chronic conditions? (SPARCS)
15. Which procedure is the most expensive? (SPARCS)
16. What conditions and age group combinations are most expensive to treat? (SPARCS)
17. Did the total hospital inpatient charges change from 2012 to 2013? Do the results depend on the type of illness? (SPARCS)
18. Is the risk of mortality linked to the total cost? (SPARCS)
19. Is the source of payment linked to the length of stay? (SPARCS)
20. Is there a correlation between malpractice claims and cost? (Malpractice Data)
21. Do malpractice claims cause an increase in cost? Try analyzing the cost of healthcare at a geographic or at a practitioner level. (Malpractice Data)
22. Does Medicare always pay a standard amount? Compare AVERAGE_MEDICARE_ALLOWED_AMT, AVERAGE_MEDICARE_PAYMENT_AMT and AVERAGE_SUBMITTED_CHRG_AMT and figure out if submitted amount is relevant. (Medicare Provider Utilization and Payment Data)
23. What are the most expensive procedures, both per procedure and also total cost to Medicare? (Medicare Provider Utilization and Payment Data)
24. How much does charged amount vary by state? (Medicare Provider Utilization and Payment Data)
25. Which states have the biggest Medicare expenses relative to population? (Hint: Florida and Arizona) (Medicare Provider Utilization and Payment Data)
26. Can we link Medicare data to other demographic information, like number of people 65+ in each state? (Medicare Provider Utilization and Payment Data)

Model the Mess

1. What diseases have good media coverage and why? Find important words from the abstract and use the MeSH terms as features to build a prediction model of newsworthiness. Try to link diseases that have a good coverage in the media (e.g., in the top 50-100 most predictive features) to the healthcare cost. The article considers articles from September 2012 to present, so you could look at the results from a different time period(s) and compare. Are there trends with time? (Elhadad)
2. What features are predictive of the average medicare payment? (Chronic Conditions)
3. Can you identify outliers in Medicare data? (Medicare Provider Utilization and Payment Data)

Clean the Clutter

1. Separate the CMS Open Payments data into two tables: one for recipients that are physicians and one for recipients that are teaching hospitals. (CMS Open Payments)
2. Properly normalize the data, create separate tables for physician info, Manu/GPO info, hospital info and pure transaction information. (CMS Open Payments)