Thursday, August 13, 2009

Medical Uses of Wolfram|Alpha

There have been increasing medical uses and capabilities of WolframAlpha, and I am very interested in its potential in medical and health areas. WolframAlpha is like a type of search engine capable of finding and cross referencing relevant data from multiple sources. Unlike other types of search engines, it actually provides real answers to queries rather than only links to possible answers. It returns not only the data, but the relationships between the data. It not only searches data it computes data. Kinda like Google on steroids...

Bertalan Meskó is a medical student at the University of Debrecen, Medical School and Health Science Center. Berci writes a very nice blog at Science Roll. He will graduate from medical school this summer and he has found WolframAlpha very useful. He said "I use WolframAlpha because sometimes (if I know exactly what I want to find) it saves me plenty of time and clicks. If I want to calculate BMI, Google lists me several calculator. WolframAlpha calculates it itself."
He continued, "If I want to find information very fast about a clinical marker, Google gives me resources, WA gives me the best answer in one click. I also use it for ICD classification, as it's more easily accessible than Wikipedia; for epidemiological data and other calculations.
To sum it up, I think WA is for those who perfectly know what they want to find and want to save time and clicks. For other search queries, Google still is the best."

Developers at WolframAlpha have made improvements to the engine's capabilities and scope of knowledge, particularly in medicine and health. They have published an overview and some examples of the types of searches both patients and clinicians will find useful on the Understanding Medical Tests at their blog.
WolframAlpha is a helpful reference for understanding what the tests measure and how to interpret the results. WolframAlpha allows you to query information on a specific medical test or a panel of tests, compare tests and results for patients with specific characteristics, compute your estimated risk for heart disease, and find the diagnosis corresponding to an ICD-9 code. WolframAlpha can take into account specific patient characteristics like gender, age, smoker, non-smoker, pregnant, diabetic, obese, and underweight. WolframAlpha can give you a snapshot of available data that might help you understand how your results compare to others'.
WolframAlpha can provide a number of interesting medical statistics including body measurements, physical exercise, diseases, mortality, medical tests, and medical computations. You can see other examples of Health & Medicine uses here. For example to determine the benefits of running 20 minutes for a 28-year-old 5'11" 185lb male, then type: running 20min, 6min/mi, 28yo male, 5'11", 185lb into the search box. Results would look something like this:

If someone is interested in calculating their daily food intake, WolframAlpha can help. Here is more from Understanding Medical Tests.
We have heard from many people who are interested in learning more about calculating their daily food intake in WolframAlpha. If you have been following our posts on how to use WolframAlpha to help achieve your nutritional and wellness goals, this will be easy as apple pie. Our data curators have been busy working on over 7,000 food entities that are listed in the USDA National Nutrient Database for Standard Reference and other food databases. Currently, they’re adding additional brand-name and specialty food items. Once a food entity is placed into WolframAlpha’s nutrition bank, rules and algorithms are applied to help categorize it by typical attributes (e.g. raw, boiled), units (e.g. cups, tablespoons), and unique serving forms (e.g. slices, pieces). As a result of these categorizations, when you enter a food item such as “strawberries” into the site’s computation bar, WolframAlpha computes a breakdown of total calories, fat, cholesterol, sodium, carbohydrates, protein, and other particular nutrients based on standard serving sizes (units) and attributes.
Or, how about cholesterol information for a 45-year-old male. Type: cholesterol 45yo man into the search box. As you can see there are already many uses for health and wellness that people can use to find and calculate information on nutrition and fitness. But the thing most exciting to me is the possibilities for clinicians that have barely scratched the surface. The widespread adoption of tools like Epocrates and UpToDate show that providers are hungry for mobile, web based services. I believe that as WolframAlpha continues to expand its abilities in medicine and health we will eventually see it used for Clinical Decision Support. When that happens it could cause a pardigm shift in web enabled technologies supporting medical care.