Melissa Launches Druginator, Clinical Data Quality Powered by Machine Reasoning

Melissa, a leading provider of global contact data quality and identity verification solutions, today announced Druginator, a new, tightly targeted element of its comprehensive data quality toolset to clean, harmonize, and connect disparate content sources for clinical insight and discovery. As part of the Melissa Informatics array of data quality solutions, datasets, and knowledge engineering resources, Druginator checks and validates millions of pharmaceutical drug names, variants, dosages, and spellings in real-time, against a comprehensive drug lexicon aligned with industry standards. The Melissa Informatics team will feature Druginator at the Bio-IT World Conference and Expo, #BioIT18, booth M634, May 15-17, 2018, at the Seaport World Trade Center in Boston.

Druginator provides a web-based UI for checking, verifying, and enriching drug names or lists of drugs, as well as web service APIs for drug data. Diverse, misspelled, and otherwise “dirty” drug information, whether from electronic medical records (EMRs) or from pharmaceutical dictionaries, studies, or public sources, is checked and reported with standardized “preferred terms” to become instantly usable for pharmaceutical and healthcare informatics. This provides an efficient resource to help researchers and clinicians check, verify, and normalize drug terms to reduce costs, increase accuracy, and improve research and patient outcomes.

Aligning with the industry goal to advance medicine through optimized data, Druginator harnesses the power of formal semantic technologies to apply machine reasoning to infer new concepts, linkages, and corrections to data about drugs. Future versions of Druginator will harmonize other types of mission-critical clinical data, such as diseases, genes, and proteins.

“Disconnected data is messy and not contextualized, slowing mission-critical goals such as FDA approval, time to market and understanding real-world use patterns for drugs. For example, a single medical records database was shown to contain nearly 200 different variations, spellings, and compounds of just one drug commonly used in the treatment of Parkinson’s disease. Discrepancies like this can have crucial implications on patient analyses, treatments, and treatment outcomes,” said Daniel Kha Le, vice president, Melissa Informatics.

Melissa Informatics’ drug, patient, disease, gene, protein, metabolic, and consumer-centered ontologies allow clinicians to easily refocus their research, tapping into different contextual insights based on the same data sets. With Druginator, drug names are checked and verified against a database of drug standard names, to meet FDA, UMLS and other terminology standards as required. Druginator’s append feature searches variations, alternate names, combination drugs, and available dosages to deliver comprehensive intelligence about your checked and verified drug. Autocompletion capabilities accelerate data entry, ensure standardization, and reduce clerical errors by offering an auto-populated list of variants matched in real-time.

Druginator is part of Melissa Informatics’ Sentient™ platform – semantic technologies that can be applied horizontally to accommodate the broad spectrum of pharmaceutical and clinical data harmonization and enrichment needs, integrating content across virtually any data format or terminology regardless of its original source.To connect with Melissa Informatics or members of Melissa’s global intelligence team, visit https://www.melissa.com/uk/ or call +44 (0)20 3051 0140.

Melissa’s data quality solution for precise and well-timed information

Companies everywhere recognize that 'knowing your customer' is critical to today's business practices. An ideal single view of the customer will help improve customer service and marketing, enhance business intelligence, and meet regulatory compliance. Knowing who your customers are, which products they own, what their history is, and how profitable they are can provide a truly competitive edge.

While most companies already have the data necessary to gain these insights, it is often fragmented or scattered, held in incompatible formats, in legacy systems, generally not well integrated, and always changing - making data hygiene a difficult, albeit essential, element to the accuracy of the single view. Data quality tools and techniques are vital to the process.

What is full contact data quality?

Determining whether two or more records refer to the same customer can be extremely difficult. For example, in one database a customer's full first name might be referenced as a nickname in another (i.e., Robert versus Bob). This particular customer may also have a valid email address in one data set, but a different email address in another. Customer information fields may also be missing or inconsistently completed. A single view can only be achieved with consistent, current and accurate data.

It is difficult to consolidate duplicate records and match accurate data to the actual customer without a method to determine the data interconnectivity between similar records. Fortunately, "full contact data quality" can help businesses make clear connections throughout and across data sets. The full contact data quality process links historical snapshots of each contact data component to identify the most up-to-date records (i.e., the most current street address on file). The process brings the entire customer record to its most current form, enhancing the single view of the customer.

Beyond validation

Companies often rely on the validation of their contact data and call their DQ efforts complete. As a "rules-based" approach, validation is used to determine whether data fits the required format. If the data is reasonable and possible. For instance, validating a phone number requires that there are 10 digits and no letters in the string. Or, when entering a date, the validation for month is 1-12; entering a '13' is not allowable as it is out of range. Unfortunately, this traditional process falls short of true data quality.

Full contact data quality goes further to verify data by comparing that data to a set of reference data for accuracy. By implementing this process, an organization can match its data to USPS data to identify which customer addresses are deliverable, which can be corrected, and which are completely undeliverable. Verified and corrected addresses can then be recorded in a standardized form. The same process of matching customer data to reference datasets can be used to verify and correct full names, telephone numbers, email addresses, and other contact data.

The benefits of verified contact data are significant and include postage savings, reduced return mail, better response and conversions for marketing campaigns, and enhanced customer satisfaction.

Connecting with customers is crucial

Possessing verified contact data is only part of the puzzle. Knowing that contacts are reachable is essential. For example, customer John Smith is associated with the following address: 100 Main Street, Anytown, California 92688. We can certainly verify that the address exists and is deliverable, but how do we know Mr. Smith still lives there? Or that he ever lived there, for that matter? The same goes for John Smith's telephone numbers, and even his email address.

Full contact data quality compares data across multiple sources, including USPS records, telco data, title information, and other public and proprietary information -current and historical. This process first associates and then connects verified contact data to the specific customer. With full contact data quality, an organization has the assurance that a direct marketing or telemarketing campaign, for example, will reach the targeted customers and prospects because they are reachable.

Quality comes from completeness

Just about every CRM system is missing one or more piece of data on any given customer. Fortunately, a skilled data quality vendor can fill these holes with verified street addresses, email addresses, phone numbers, and even relevant demographics. With a collection of accurate, reachable, and complete contact data, businesses may now perform more holistic, meaningful analysis of their customers to generate further growth opportunities.

Data quality has evolved significantly over the past 20 years. Just as decision support systems, data warehousing, and business intelligence have prompted more in-depth analysis of the data used to measure and monitor corporate performance, a changing attitude has steadily altered our perception of what is meant by "quality information." Today, the concept goes well beyond data cleansing, standardization, and enhancement, to include full contact data quality. With its unique ability to resolve disparate representations of a record and then link together all touch points of customer data, full contact data quality offers the means to attain and enhance a true single view of the customer.