A recent partnership expected to be announced today between mobile ad firm 4Info and pharma data company Crossix could help drug advertisers find out if their mobile ads actually influenced someone to get a prescription or visit a medical specialist. The relationship represents the potential reward -- and risk -- of targeted advertising on personal devices in the highly regulated healthcare industry.

4Info, which aims mobile ads based on actual household data associated with consumers' home addresses, has been on the lookout for a data partner that could assist it in tapping more pharma ad dollars.

"Pharma is a huge opportunity," said 4Info CEO Tim Jenkins. Before partnering with Crossix, the company has worked with pharma advertisers targeting ads for over-the-counter drugs based on shopper loyalty card data.

Crossix does not use any actual medical data that would identify an individual as having a specific disease or condition; rather, it gathers information from healthcare data distributors and individual companies to gauge a consumer's propensity towards having an affliction based on over-the-counter drug purchases using loyalty cards, medical claims data indicating a doctor visit, and information from retail pharmacies showing prescription refills.

The end result is modeled data that uses correlations to make educated guesses as to whether someone is likely to have Type II diabetes or eczema, for example.

To determine a mobile users' home address, 4Info tracks locations of mobile devices when people open certain apps. After a device has been spotted several times during certain hours in a particular residential location, it is determined to be a home address that can then be matched to household data showing purchases and other demographic information. The company also verifies home location data through mapping apps that give directions to or from a home address provided directly by the user.

Strict regulations based on the 1996 federal Health Insurance Portability and Accountability Act are a significant hurdle to targeted digital advertising for pharmaceutical drugs.

"It's a lot more complex just because of the HIPAA regulations," said Mr. Jenkins, describing a six-month set-up process ensuring that personally-identifiable data never touched the partners' systems. Data broker and services firm Acxiom sits in between Crossix and 4Info. Acxiom matches its household-level data with 4Info's household-level data associated with mobile device IDs, and in turn connects it with a unique Crossix ID. The process produces de-identified groups of consumers showing a propensity to have certain health conditions for ad targeting. Only anonymized segments of consumers indicating a likelihood to have a disease are targeted, not specific individuals.

"We couldn't find a partner out there on the data and measurement side that had constructed a platform that allowed them to, in a very de-identified way, create target groups that we knew complied with all the HIPAA requirements until Crossix came along," said Mr. Jenkins.

"These propensity scores are very, very strong in terms of identifying who could be Type II Diabetes sufferers," he added as an example.

HIPAA rules prevent marketers from targeting individuals directly based on prescription-drug-transaction data. HIPAA requires data be de-identified before it's shared with partners, and once it's stripped of names and other identifiable data, companies could have free rein to share and sell it the way they would other purchase data or online behavioral information, depending on what uses the consumer OK'd when it was collected.

Along with stricter data-use rules, pharma advertisers must include the same litany of drug side-effect information in tiny mobile ads that is featured in TV and web display ads. In the mobile environment, those disclosures usually appear via a drop down menu or if a user clicks to view more information.

In addition to demographic correlations such as age and gender, Crossix uncovers less likely correlations with medical conditions, such as the types of books consumers purchase.

While the system will not show whether particular individuals filled a drug prescription or made a doctor visit as a result of being served an ad, it can determine whether ads aimed at a targeted group led to more prescription purchases or visits to specialists associated with a particular ailment. As a result, an advertiser might decide to deliver more ads to that consumer segment.

"By measuring meaningful leading indicators of [prescription] sales like doctor visitation, for example, pharma advertisers are able to better understand the impact and value of their mobile ad campaigns, while optimizing performance and efficiency along the way," said Daniel Stein, senior VP of product strategy at Crossix.