“You can match a blood transfusion to a blood type – that was an important discovery. What if matching a cancer cure to our genetic code was just as easy, just as standard? What if figuring out the right dose of medicine was as simple as taking our temperature?” –President Obama, January 30, 2015
There are six key principles of the federal Precision Medicine Initiative (PMI). PMI was a federal initiative announced by President Obama in 2015 and was incorporated into the 2016 budget. The mission statement for PMI is “to enable a new era of medicine through research, technology, and policies that empower patients, researchers, and providers to work together toward development of individualized care.” The White House
- Easier access for patients including ability to share digital health data and donating It for research.
- Engage participants as partners in research, including returning results to them in dynamic, user-centered ways.
- Bring the promise of precision medicine to everyone.
- Open up data and technology tools to invite citizen participation, unleash new discoveries, and bring together diverse collaborators to share their unique skills.
- Adhere to strong privacy and security principles – when you start talking about data exchange and sharing health information, the adherence to the privacy of this health information is very important. Principles include:
- Creating a dynamic and inclusive governance structure
- Building trust and accountability through transparency
- Respecting participant preferences
- Empowering participants through access to information
- Ensuring responsible data sharing, access, and use
- Maintaining data quality and integrity
- Advance and scale precision medicine approaches in clinical practice.
How Precision Medicine Impacts the Collection and Management of Patient Health Information
Pharmacogenetics usually refers to how variation in one single gene influences the response to a single drug whereas pharmacogenomics is a broader term, which studies how all of the genes (the genome) can influence responses to drugs. However, these terms are often used interchangeably.
How close are we really to having pharmacogenomics and pharmacogenetics be part of the clinical practice? Sometimes things are closer than they appear.
When implementing pharmacogenomics in clinical practice there are several things that must be done. First you must have a basic science element to understand how the drug is metabolized by the specific gene or how the gene effects the metabolism. Second, you must analyze the efficacy of how the drug effects actual patients in clinical studies. Cost effectiveness continues to be an issue although it has become less of an issue since the cost of testing has gone down immensely. Consistent clinical agreements are difficult to maintain based off of different societies and groups containing different recommendations. The final item on the checklist of pharmacogenomics clinical practice is the ability to implement consistently across a broad cross-section of specialties and individuals.
4 Data Quality Challenges Healthcare Organizations and Providers Currently Face
There are many quality challenges healthcare organizations and providers face. Here are the top four:
- Clinical studies highlighting efficacy and cost effectiveness.
- Transfer of non-structured data into discrete genetic data. The majority of genetic data--if it exists--is in the form of documents with interpretations. Transforming that unstructured data into discrete data is fundamental to making the data useful to clinical applicaitons.
- Health information exchange and interoperability. This is the ability to rapidly exchange standardized data and incorporate it into a clinical system to dramatically improve the workflow.
- Provider and patient education continues to be important--easier access to information can overcome this challenge.
How Extract Solved the Unstructured Data Problem
About a year ago we were approached by a cancer center to help them solve the problem.
They had a data warehouse set up to hold relevant data with an analytics system procured to help them find what they need from the data; however, pathology and genomic data was stuck in narrative reports in unstructured formats.
How to get discrete pathology data into structured database? Two options, manual abstration or utilizing a technology to automate the process:
Manual Extraction
- Takes lots of time
- High labor cost to abstract
- Higher possibility of errors in data
Document/Language Processing Technologies
- Provides discrete data (not summaries)
- “Translate” and standardize data for consistency in data warehouse
- Higher cost associated with purchase
Extract provided a computer-assisted data capture workflow. These pathology reports were pre-processed with intelligent data extraction software that “reads” reports and automatically identifies desired data elements. This data is then “found” and organized into over 400 discrete fields and standardized. The only hands-on, optional step is to visually inspect using verification screen with pre-validation, approve and output to the data warehouse. This system saved a huge amount of time and effort while assuring quality, accurate data.
For an active walkthrough regarding pharmacogenomics in clinical practice with examples, view the pre-recorded webinar, Precision Medicine is Coming Soon… Are Your Records Ready?
