Industry Insight

Study Evaluates Whether CDS Can Prevent Medication-Prescribing Errors

Prescription drug errors are a leading source of harm in health care, resulting in substantial morbidity, mortality, and health care costs estimated at more than $20 billion annually in the United States.

Currently, clinical decision support (CDS) alerting tools—computerized alerts and reminders—are widely used to identify and reduce medication errors. However, CDS systems have a variety of limitations, including that they are rule based and can identify only medication errors that have been previously identified and programmed into the alerting logic.

A new study published in the January 2020 issue of The Joint Commission Journal on Quality and Patient Safety used retrospective data to evaluate the ability of a machine learning system—a platform that applies and automates advanced machine learning algorithms—to identify and prevent medication prescribing errors not previously identified by and programmed into the existing CDS system.

In the study “Using a Machine Learning System to Identify and Prevent Medication Prescribing Errors: A Clinical and Cost Analysis Evaluation,” alerts were generated retrospectively by a machine learning system using existing outpatient data from Brigham and Women’s Hospital and Massachusetts General Hospital in Boston from 2009 through 2013.

The study analyzed whether the system generated clinically valid alerts and its estimated cost savings associated with potentially prevented adverse events. These alerts were compared with alerts in the CDS system, using a random sample of 300 alerts selected for medical record review.

Findings showed a total of 10,668 alerts during the five-year period. Overall, 68.2% of the alerts would not have been generated by the existing CDS system. Ninety-two percent of a random sample of the chart-reviewed alerts was accurate based on structured data available in the record, and 80% were clinically valid. The estimated cost of adverse events potentially prevented in an outpatient setting was more than $60 per drug alert and $1.3 million when extrapolating the study’s findings to the full patient population.

“The authors of this study successfully provide a glimpse into a new world of safety for medication ordering augmented by machine learning,” says David M. Liebovitz, MD, an associate professor of medicine in the division of general internal medicine and geriatrics at the Feinberg School of Medicine at Northwestern University in Chicago, in an accompanying editorial. “Validation across different populations may reveal site-specific differences requiring unique models, and/or warrant identification and capture of new descriptive features.”

— Source: The Joint Commission

ONC Awards The Sequoia Project a Cooperative Agreement for TEFCA

The Office of the National Coordinator for Health Information Technology (ONC) has announced that The Sequoia Project has been awarded a cooperative agreement to serve as the Recognized Coordinating Entity (RCE). The RCE will be responsible for developing, updating, implementing, and maintaining the Common Agreement component of the Trusted Exchange Framework and Common Agreement (TEFCA). The Common Agreement will create the baseline technical and legal requirements for health information networks to share electronic health information and is part of ONC’s implementation of the 21st Century Cures Act (Cures Act).

“The Sequoia Project was selected through a competitive process to help with the interoperable flow of health information. We look forward to working in close collaboration with The Sequoia Project and across the broader health system to create a common agreement that best serves the needs of all stakeholders,” says Don Rucker, MD, national coordinator for health information technology.

In the Cures Act, Congress directed Health and Human Services to advance trusted exchange of electronic health information among health information networks through TEFCA. The Cures Act’s focus on trusted exchange is an important step toward fostering transparency and competition throughout the health care delivery system by addressing the technical barriers and business practices that impede the secure and appropriate sharing of electronic health information.

In addition to the Common Agreement, the RCE will collaborate with ONC to designate and monitor Qualified Health Information Networks (QHIN), modify and update accompanying QHIN technical requirements, engage with stakeholders through virtual public listening sessions, adjudicate noncompliance with the Common Agreement, and propose sustainability strategies to support TEFCA beyond the cooperative agreement’s period of performance.

— Source: The Sequoia Project

Telemedicine Engages Newly Postpartum Women in Cardiovascular Monitoring

America has the highest maternal mortality rate in the developed world, and it’s getting worse. As cardiovascular disease is the primary cause, researchers at the University of Pittsburgh (Pitt) School of Medicine and the Magee-Womens Research Institute announce a blood pressure home-monitoring program to rapidly detect concerning trends in postpartum women before their situation becomes critical.

To address the rising maternal mortality rate, the American College of Obstetricians and Gynecologists (ACOG) recently upped their recommended frequency for postpartum checkups, starting within three weeks of birth. But right now, only about 66% of new mothers diagnosed with a hypertensive disorder are making it back to the clinic for what is usually a single follow-up appointment around six weeks postpartum. That figure jumped to 88% when the researchers gave women a blood pressure cuff and periodically prompted them to text their readings to a nurse, according to a study published in the journal Obstetrics & Gynecology.

“We’re meeting women where they are instead of saying they have to come to the hospital for all these blood pressure checks when they have a new baby,” says lead author Alisse Hauspurg, MD, an assistant professor of obstetrics, gynecology, and reproductive sciences at Pitt. “I think this is supported by recent ACOG recommendations and is an opportunity to improve care for high-risk women.”

Between February 2018 and January 2019, the researchers enrolled 499 patients with preeclampsia; eclampsia; or chronic, gestational, or postpartum hypertension. Each was discharged from the postpartum unit with an automatic blood pressure cuff and instructions on how to take their own readings at home.

A computerized system integrated with the participants’ EHRs prompts them to take their own blood pressure and heart rate readings once a day for five days. If their readings are normal, their one-week follow-up appointment is automatically cancelled, as was the case for 43% of the women. Patients taking blood pressure medications start to taper down, and patients who aren’t taking any medications decrease the frequency of their readings.

Abnormal readings lead to an increase in monitoring frequency and automatically notify the patient’s health care provider. Dangerously high readings trigger a trip to the emergency department.

Overall, 83% of participants continued the program beyond three weeks postpartum and 74% continued for four weeks or more.

According to the researchers, this study demonstrates feasibility and high levels of engagement in the program, which should be straightforward to expand.

“One of the big advantages here is scalability,” says senior author Hyagriv Simhan, MD, a professor of obstetrics, gynecology, and reproductive sciences at Pitt and executive vice chair of obstetrical services at University of Pittsburgh Medical Center (UPMC) Magee-Womens Hospital. “Connecting women in their ‘fourth trimester’ to online care allows us to engage a larger number of patients over a larger geography with the infrastructure and workforce we already have.”

Of the 250 women who filled out a postprogram survey, 94% said they were satisfied with the experience and 82% said they were more comfortable knowing that a nurse was checking on their health every day.

One goal of the program is to bridge care from obstetricians to ongoing—albeit less intensive—cardiovascular monitoring. So far, 63% of the study participants have either scheduled an appointment or established care with a primary care provider.

“Home blood pressure monitoring gives patients ownership. They’re texting their numbers in,” Hauspurg says. “Hypertensive disorders of pregnancy impact women for the rest of their lives, so to have ownership over their own health is really important. We’re empowering them to know their numbers.”

Additional authors on the study include Laura Lemon, PharmD, PhD; Beth Quinn, RN; Anna Binstock, MD; Jacob Larkin, MD; Richard Beigi, MD; and Andrew Watson, MD, all of UPMC Magee-Womens Hospital and Pitt.

The remote monitoring platform integral to the program was supplied by Vivify Health. UPMC was an investor in Vivify at the time of the study.

— Source: The University of Pittsburgh Medical Center