A group of hospitals in Paris is exploring the use of data analytics and machine learning to predict patient admissions down to the hour.
Four hospitals within the city’s public hospital system are trialing a new data-driven approach that combs through 10 years of admissions data and deploys refined algorithms to predict admissions rates during certain times of the day, according to Forbes' contributed post.
The project is expected to be rolled out to all 44 public hospitals in Paris, which meant data scientists had to create a scalable, open-sourced framework from scratch, while also considering the need for cloud-based storage to house additional data in the future.
Although privacy laws in France presented some barriers, the model has helped hospitals adjust staffing levels during periods of heavy admissions. Clinical and administrative staff members use a simple, web-based to review predicted admission rates 15 days out.
In the United States, hospitals have been using predictive modeling to reduce readmissions, identify population health needs, improve the efficiency and safety of patient care, bolster precision medicine efforts and more.
RELATED: Christiana Care's Terri Steinberg: Analytics vital to successful population health
Readmissions and chronic care patients are particularly costly pain points—and analytics are not a cure-all.
“When you’re looking at a patient population with chronic conditions, you’re not going to get 100 percent accuracy. But when it comes to a root cause, there are certain specific factors that put a patient at higher risk of readmission,” Asif “A.J.” Ally, vice president of clinical affairs for Argus Health Systems, a Kansas City, Missouri-based company that provides pharmacy management services to health insurers, said in a recent interview for the FierceHealthPayer eBook, The Expanding Role of Pharmacy to Cut Readmissions.
Data points that can help predict readmission risks, according to the eBook, include:
- Patients who take 5 or more medications
- Low-income patients who may not have resources to pay for their prescriptions or to access caregivers
- Elderly patients who are living alone and may not have a support system to make follow-up appointments
- Patients with specific conditions including heart failure, sepsis or congestive obstructive pulmonary disorder
- Patients who struggle with substance abuse
- Patients with low literacy and numeracy skills