Researchers at Boston’s Beth Israel Deaconess Medical Center are sharing insights they gained while building a locally focused, AI-aided model for anticipating COVID-19’s next moves.
Jennifer Stevens, MD, MS, and colleagues had their case study published June 29 in Harvard Business Review.
Noting that the effort leaned heavily on Beth Israel’s own Center for Healthcare Delivery Science, of which Stevens is director, the team state their hope other provider institutions will see in their success story “a new opportunity in healthcare operations that is particularly useful in times of extreme uncertainty.”
Stevens et al. break out their key observations as four lessons learned:
1. National forecasting models broke down when predicting hospital capacity for Covid-19 patients because no local variables were included.
“[E]arly on our hospital was choosing to admit rather than send home many SARS-COV-2 positive patients, even with mild infections, because the clinical trajectory of the disease was so uncertain,” the authors write. “Thus we needed a dynamic hyper-local model.”
2. Local infection modeling required a range of different research methods, and the trust and commitment of operational leaders who recognized the value of the work.
“We gathered Covid-patient census data from multiple hospitals simultaneously, using a common machine-learning technique called multitask learning to capitalize on limited data,” they report. This and other AI methods helped the hospital predict demand to within five days of the true peak, allowing project leaders to model the slope more accurately than national models.
3. Effective modeling in confusing times may require rapidly developing new methods for predicting the next storm.
“[W]e created and validated a model for identifying such potential ‘super-spreader’ businesses in our service area. … Meanwhile, we can use our work with businesses to further inform our forecasting model by examining traffic in business locations we have identified as high-risk and assessing whether incorporating these data improves the ability of our model to predict the demand on hospital capacity.”
4. Given the profound future uncertainty in healthcare, small investments in trusted internal research groups that can answer operational questions with new methods can yield substantial returns.
“Our institution made a prescient investment in creating an embedded and trusted research group made up of clinicians, economists, and epidemiologists studying healthcare operations,” Stevens and colleagues underscore. “Other organizations can similarly unite the rigor and flexibility of methodological experts with the need to rapidly answer operational questions in dynamic and even chaotic environments.”
The team fleshes out these learnings in some detail, and HBR has posted the report in full for free.