Learn more about Mike Dow

Author Bio

Mike Dow

Mike learned of the value of data early in his career. While working at a major EMR vendor in 2001, he led a project to help identify patients who were affected by drug recalls. He continued his work in various roles at Allscripts, including reporting, data exchange and systems architecture. From 2006 to 2015, Mike led the technology group at Galen Healthcare Solutions. While the company and his team grew by 50% annually during this time, they became known for excellence, earning awards like Best in KLAS for Technical Services and a Best Place to Work by Modern Healthcare. Mike joined Health Catalyst in 2015 to help with strategic client implementations. He has since joined the product development team to lead Health Catalyst’s text analytics initiative, making information previously locked in text notes available to Health Catalyst’s apps and data architects.

Read articles by Mike Dow


Mike Dow

Healthcare NLP: Four Essentials to Make the Most of Unstructured Data

Many health systems are eager to embrace the capability of natural language processing (NLP) to access the vast patient insights recorded as unstructured text in clinical notes and records. Many healthcare data and analytics teams, however, aren’t experienced in or prepared for the unique challenges of working with text and, specifically, don’t have the knowledge to transform unstructured text into a usable format for NLP.
Data engineers can follow four need-to-know principles to meet and overcome the challenges of making unstructured text available for advanced NLP analysis:

Text is bigger and more complex.
Text comes from different data sources.
Text is stored in multiple areas.
Text user documentation patterns matter.

Mike Dow
Levi Thatcher

How Healthcare Text Analytics and Machine Learning Work Together to Improve Patient Outcomes

Healthcare organizations that leverage both text analytics and machine learning are better positioned to improve patient outcomes.
Used in tandem, text analytics and machine learning can significantly improve the accuracy of risk scores, used widely in healthcare to help clinicians identify patients at high risk for certain conditions and, therefore, intervene.
Health systems can run machine learning models with input from text analytics to provide tailored risk predictions on both unstructured and structured data. The result? More accurate risk scores and the ability to identify every patient’s level of risk in time to inform decisions about their care.

Mike Dow

Five Lessons for Building Adaptive Healthcare Data Models that Support Innovation

Healthcare data models are the backbone of innovation in healthcare, without which many new technologies may never come to fruition, so it’s important to build models that focus on relevant content and specific use cases.
Health Catalyst has been continuously refining its approach to building concise yet adaptive healthcare data models for years. Because of our experience, we’ve learned five key lessons when it comes to building healthcare data models:

Focus on relevant content.
Externally validate the model.
Commit to providing vital documentation.
Prioritize long-term planning.
Automate data profiling.

These lessons are essential to apply when building adaptive healthcare data models (and their corresponding methodologies, tools, and best practices) given the prominent role they play in fueling the technologies designed to solve healthcare’s toughest problems.

Mike Dow

Text Analytics in Healthcare—Two Promising Frameworks that Meet Its Unique Demands

Text analytics in healthcare is unique because it demands a higher degree of precision than what’s acceptable for a Google search or Yelp recommendation. So, it’s no surprise fewer than five percent of health systems are effectively leveraging clinical information in a truly significant way.
Fortunately, there are two promising frameworks for clinical awareness designed to meet the industry’s unique text analytics demands:

ConText—solves for negation, experiencer, and temporality.
cTAKES—includes the functionality of ConText, and adds the ability to identify the type of clinical term.

By integrating these frameworks into their solutions, health systems can overcome the unique challenges of text analytics in healthcare. They can evolve from simply finding matching text to understanding context and achieving the precision required in patient care.