WellSpan Health discovers missing drug history near home to improve patient safety
AI, EHR Legacy Data Conversion, and Local Pharmacy Connections Deliver 97% of Medicines to Patients Over 65
WellSpan Health is a nonprofit, integrated health system that serves communities in central Pennsylvania and northern Maryland. This eight-hospital health system was recognized with an Eisenberg Award for innovation in patient safety and quality, and achieved HIMSS Stage 7 status for the inpatient electronic medical records adoption model and ambulatory (EMRAM and O-EMRAM). In late 2020, WellSpan was certified as Acute Level 8 in the CHIME Digital Health Most Wired, a program designed to improve the health and care of communities around the world by encouraging the optimal use of information technology.
Discrepancies in a patient’s medication history can have serious downstream consequences. Up to 70% of patients have errors on their medication list when admitted to hospital by the emergency department (ED), and up to 59% of these errors can cause harm.1In addition, one-third of inpatient orders have errors, 85% of which stem from medication history collected during the admission process.2
WellSpan Health encountered similar issues. Missing, incomplete, and inconsistent patient data from external sources of medication history led to unnecessary complications and delays in the medication reconciliation process. As a result, clinical staff had to call pharmacies and providers to collect, confirm, and manually enter medication data, opening the door to transcription errors and potential adverse drug events (ADRs).
In addition to gaps in the medication history stream, medication data from their converted old EHR systems was essentially unusable in the current EHR. This would require manual intervention and corrections each time a patient presented to a WellSpan facility. Seeing this as a barrier to quality patient care, WellSpan management sought a solution through a partnership with DrFirst and its AI-powered SmartProcessor.SM Solution.
“We launched Epic in 2017 and used another medication history provider as our data source. We had high hopes to improve our medication reconciliation process, but quickly realized that we were still missing a lot of information about our patients,” said Donald “Chip” Gerhart, R.Ph., Director clinical informatics in pharmacy.
In addition to the lack of medication history, WellSpan also had difficulty with consistency in medication instruction (sig) terminology and variations in terms used between different data sources. Where one prescription might use the word “orally,” another said “by mouth,” which caused import and mapping issues that clinicians had to manually resolve in each patient record.
“We first tried to do some mapping on our own to deal with the variation in signature terms and how they were translated in our Epic system, but quickly realized there was a significant amount of work involved. in progress that we had to do,” explained Gerhart. “At a certain point we realized that we were fighting a losing battle, and it was something that we were going to have to constantly manage with dedicated internal resources and that we still could not achieve 90% and more. “
To improve access to accurate and actionable patient medication histories, WellSpan began conversations with DrFirst in 2019. MedHxSM provides a combination of local and national medication history sources directly into the native Epic workflow for the most comprehensive medication history database available. In addition to providing data from HIEs and other EHR partners, DrFirst identifies and connects local pharmacies for healthcare organizations that share common patients and makes refills dispensed under MedHx available.
“One of the things we were particularly drawn to was DrFirst’s ability to connect with local pharmacies to get more information for our patients outside of PBMs,” Gerhart said.
With additional data sources more closely aligned with the patient population in Pennsylvania and Maryland, WellSpan also leveraged SmartSigSM, a patented artificial intelligence (AI) solution included in MedHx, to standardize signature information in consistent terms, securely infer missing information, and pre-populate drug information and signatures into its Epic EHR.
In addition to improving access to patient medication histories, WellSpan used SmartProcessor in late 2020 to standardize medication data across three legacy systems (NextGen, MEDENT, and MEDITECH) when transitioning multiple facilities to one. only Epic system.
WellSpan integrated MedHx with SmartSig into its Epic EHR in late 2020. As a result, when WellSpan clinicians search a patient’s medication history, they find usable data on 93% of patients and 97% of patients over 65 years. In the first six months, 73 local pharmacies began sharing medication history data, providing 2.4 million additional prescriptions that would otherwise have to be entered manually. Pre-populating signaling information has dramatically increased access to local patient histories, improving the quality of data imported into Epic and saving more than seven clicks per medication.
“By partnering with local pharmacies and DrFirst, we receive more complete and accurate prescription fill information, which means our staff don’t have to manually collect this data or fill in these fields in the history.” medication for each patient. We are saving time previously spent calling pharmacies and confirming missing medications and signature information, reducing errors associated with manual entry and improving patient safety,” said Gerhart.
Along with upgrading their external medication history source, WellSpan’s efforts to improve quality and access to legacy data have yielded impressive results. SmartProcessor has converted data from over 270,000 patient records from legacy NextGen, MEDENT and MEDITECH systems, representing over 5.5 million medication records. Of these records, 88% were normalized and imported into WellSpan’s enterprise-wide Epic system. Access to this data saved five to seven minutes per patient record while avoiding countless opportunities for transcription and ADR errors and subsequent readmissions.
“To save time and improve the quality of medication history data when consolidating three EHRs into a network-wide implementation of Epic, we developed a data conversion process using the DrFirst’s SmartProcessor AI engine that cleans and structures data beyond standard Neuro Linguistic Programming (NLP) using clinical and statistical context.This standardized drug data for use in our Epic system while addressing discrepancies and variations from older EHRs, inferring missing data with context from medication histories to avoid blank fields while avoiding laborious manual entry.
– Robert Lackey, MD, FAAFP Director of Medical Information, WellSpan Health
1 Tam, VC, Knowles, SR, Cornish, PL, Fine, N., Marchesano, R., & Etchells, EE (2005). Frequency, type, and clinical significance of medication history errors at hospital admission: a systematic review. At CMAJ. https://doi.org/10.1503/cmaj.045311
2 Gleason, KM, McDaniel, MR, Feinglass, J., Baker, DW, Lindquist, L., Liss, D. and Noskin, GA (2010). Medication Study Results During Clinical Transitions and Transfers (Matching): An Analysis of Medication Reconciliation Errors and Risk Factors at Hospital Admission. Journal of General Internal Medicine. https://doi.org/10.1007/s11606-010-1256-6