Navigate the healthcare industry
Healthcare Brew covers pharmaceutical developments, health startups, the latest tech, and how it impacts hospitals and providers to keep administrators and providers informed.
Schedulers at Mass General Brigham (MGB) are turning to artificial intelligence (AI) for help managing late arrivals and no-show appointments.
Partnering with GE HealthCare, the Massachusetts-based health system rolled out an AI-enabled schedule predictions dashboard earlier this month that uses an algorithm and historical data to anticipate “missed care opportunities,” such as late patient arrivals or no-shows. The scheduling algorithm has the potential to reduce health system costs and find patients who may require help getting to appointments.
“Utilizing operational AI and machine learning can bring providers together and streamline data sets,” Keith Dreyer, MGB’s chief data science officer, said in a statement. “This technology has the potential to reduce burnout and allow physicians to spend more time with patients, which may ultimately lead to better outcomes.”
The AI-driven schedule predictions tool, which is an add-on to GE HealthCare’s commercially available digital imaging module, is the first development that is part of a 10-year partnership between GE HealthCare and MGB. The pair signed the contract in 2017 to incorporate new technology across healthcare specialties.
During preliminary testing at a MGB hospital, the AI algorithm successfully predicted a missed care opportunity between 67% and 96% of the time, GE HealthCare found. The algorithm takes into account factors such as patient attendance record, length of exam, seasonal scheduling patterns, and hospital capacity, Oleg Pianykh, director of medical analytics for MGB’s radiology department, told Healthcare Brew in an email.
But providers still need to exercise caution when using scheduling algorithms, as they may be biased. One scheduling algorithm used by a large specialty clinic gave Black patients a higher no-show probability than non-Black patients, based on factors such as ability to afford transportation or childcare, Healthcare Brew previously reported.
Even still, the scheduling algorithm can be used to identify patients who may need assistance with things such as transportation coordination, Efrén Flores, MGB’s vice chair for radiology diversity, equity, and inclusion, told Healthcare Brew via email.
“This algorithm allows us to use these existing resources more efficiently because we now have a clearer picture of this road map by identifying who is at risk and tailor how we assist them with the programs we have,” Flores said.
Missed appointments can add up for hospitals and care centers.
Each no-show cost a practice $200 on average, which can lead to about $150 billion in lost revenue across the healthcare industry each year, healthcare communications platform Artera found in 2017.
Health systems can use scheduling algorithms like this to identify and address the factors behind missed care, Pianykh said.
“This creates real opportunities for not only avoiding the bias, but also for developing practical, targeted improvements, eliminating the very sources of [missed care opportunities],” Pianykh said.