- Data ON, Intel Partnership to Support EHR Database Workloads
- Google Cloud Partners with Meditech to Offer EHR through Public Cloud
These are the only vendors with complete voice assistance and navigation capabilities available to consumers and are in the process of developing computerized virtual scribes.
Epic is using AI to predict hospital readmissions, patient risk levels, mortality, ED utilization, at-home fall risk, sepsis, hospital-acquired disease, and patient deterioration, KLAS stated.
Epic enables EHR customers to access AI capabilities without having to look towards another vendor, the market research firm also found.
Meanwhile, Cerner is using AI for A1c predictions for outpatient populations, readmission predictions, and heart failure predictions. It is the only vendor with coding and documentation assistance, KLAS reported.
Other AI applications within Cerner’s EHR include:
· Charge Assist (helps with accurate coding for E&M codes)
· Chart Assist (helps with documentation improvement)
· Chart Search (NLP-driven search engine spanning EMR and PHM records)
· Virtual Scribe (alpha phase; transcribes clinician/patient conversations)
· Voice Assist (proof-of-concept phase; enables completion of certain tasks via voice command)
But among both of the top EHR vendors, there have been no financial use cases yet and limited operational use cases.
Additionally, Allscripts is the only vendor that has prebuilt machine learning models generally available or piloting. The vendor has been working with a partner customer on a model to predict acute kidney injury and developing ambient AI to reduce the clinician workload, KLAS said.
MEDITECH focuses on AI capabilities beyond an AI platform or machine learning models. The vendor’s main area of focus is virtual assistant to enable voice navigation within patient charts and ambient listening.
Overall, KLAS indicated that EMR customers should invest in the additional capabilities beyond the out-of-the-box machine learning models as long as an organization has already reached a certain level of AI maturity.
“…Including good internal data science team or interdisciplinary team capable of validating and managing the models, the appetite to build/deploy their own models and customize/tweak Epic’s prebuilt models, and a great process for operationalizing the new models Epic continues to release,” the report stated.
By 