The healthcare industry should use clinician data scientists to evaluate electronic health record data for the purpose of improving patient quality and safety, according to a viewpoint published recently on the Agency for Healthcare Research and Quality's (AHRQ) Patient Safety Network.
In the article, Alvin Rajkomar, an assistant professor at the University of California San Francisco, notes that EHRs hold a vast amount of valuable data, but says that piecing it together to track medications or other uses is complex and not optimal. For instance, he says, while such work generally is done by report writers, if they don’t have a clinical background, they may not appreciate a request for clinician data. That, Rajkomar says, could lead to a failure to provide correct, complete or the most accurate information.
He says that during his training to pull and analyze data, he found it hard to piece together raw data, especially with poor user interfaces and taking into account the different ways clinicians use and input data.
Rajkomar suggests, as a result, that there is a need for clinician data “translators” with core skills that include:
- Domain expertise in clinical systems
- Computer science with the ability to extract data from large electronic stores and of statistics
- A thorough understanding of how to analyze large databases
“With a foot in both the clinical and data science realms, clinician data scientists are best positioned to determine which questions warrant significant investment to answer and, just as importantly, how to integrate them into workflows,” he says.
Rajkomar acknowledges that there are no current pathways to train such clinician data scientists. For those who are available, such personnel should not be used just for precision medicine, but also to improve quality and safety.
“In medicine, accepting a suggested clinical intervention generated by a flawed algorithm carries significant risk to patients and even clinicians, who might be operating in a busy environment where second guessing every decision is impractical," he says. "Clinician data scientists can help bridge the gap of where to apply novel algorithms and how to design safeguards to prevent mistaken applications of algorithms."