Paris Hospitals Use Big Data To Predict Admissions

Here’s a fascinating story in from Paris (or par-ee, if you’re a Francophile), courtesy of Forbes. The article details how a group of top hospitals there are running a trial of big data and machine learning tech designed to predict admission rates. The hospitals’ predictive model, which is being tested at four of the hospitals which make up the Assistance Publiq-Hopitaux de Paris (AP-HP), is designed to predict admission rates as much as 15 days in advance.

The four hospitals participating in the project have pulled together a massive trove of data from both internal and external sources, including 10 years’ worth of hospital admission records. The goal is to forecast admissions by the day and even by the hour for the four facilities participating in the test.

According to Forbes contributor Bernard Marr, the project involves using time series analysis techniques which can detect patterns in the data useful for predicting admission rates at different times.  The hospitals are also using machine learning to determine which algorithms are likely to make good predictions from old hospital data.

The system the hospitals are using is built on the open source Trusted Analytics Platform. According to Marr, the partners felt that the platform offered a particularly strong capacity for ingesting and crunching large amounts of data. They also built on TAP because it was geared towards open, collaborative development environments.

The pilot system is accessible via a browser-based interface, designed to be simple enough that data science novices like doctors, nurses and hospital administration staff could use the tool to forecast visit and admission rates. Armed with this knowledge, hospital leaders can then pull in extra staffers when increased levels of traffic are expected.

Being able to work in a distributed environment will be key if AP-HP decides to roll the pilot out to all of its 44 hospitals, so developers built with that in mind. To be prepared for the future, which might call for adding a great deal of storage and processing power, they designed distributed, cloud-based system.

“There are many analytical solutions for these type of problems, [but] none of them have been implemented in a distributed fashion,” said Kyle Ambert, an Intel data scientist and TAP contributor who spoke with Marr. “Because we’re interested in scalability, we wanted to make sure we could implement these well-understood algorithms in such a way that they work over distributed systems.”

To make this happen, however, Ambert and the development team have had to build their own tools, an effort which resulted in the first contribution to an open-source framework of code designed to carry out analysis over scalable, distributed framework, one which is already being deployed in other healthcare environments, Marr reports.

My feeling is that there’s no reason American hospitals can’t experiment with this approach. In fact, maybe they already are. Readers, are you aware of any US facilities which are doing something similar? (Or are most still focused on “skinny” data?)

About the author

Anne Zieger

Anne Zieger

Anne Zieger is a healthcare journalist who has written about the industry for 30 years. Her work has appeared in all of the leading healthcare industry publications, and she's served as editor in chief of several healthcare B2B sites.

3 Comments

  • It helps if you have a single-payer system, and a health care system that focuses on rational results rather than maximum profit.

    Actually, in countries with a less profit-focused health care system, EHRs have been working well for over a decade (with the exception of the UK). There is just not the same level of frustration and refusal to comply as I have observed here in this country.

    There is also not the same manic level of everyone and his cousin trying to cash in by implementing EHRs at breakneck speed.

    There are a few larger systems in this country though that have done a fairly good job of implementing, using, and upgrading over the years. Two of them that I am familiar with are in Ohio: the Ohio State University Wexner Medical Center and the Cleveland Clinic. Think what you will about the latter’s empire building around the world, but the powers that be there did implement (after a few serious glitches) Epic over a number of years to a point where it actually works. I still remember being astonished to hear that they had not had any telephone or verbal orders there for five years – and that was five years ago. Who cares if the docs put in orders on their tablets from the golf course? Given the amount of money there I am sure they have already begun making use of Big Date platforms…Ohio State took the same slow and careful approach as the Clinic, and Epic works there, too, pretty well, in spite of a LOT of initial resistance. In that facility, it was primarily the nurse managers that took the lead during implementation and saw to it that things remained on track, even to the point of overriding providers’ initial resistance…

    Let’s join the rest of the world, America. EHRs can work, but it needs everyone on board. It IS possible. How about if we all just shut up and get on with it?

  • Is this any different from how store chains estimate sales levels and therefore staffing levels for a given day based on the like day in previous years? Plus hospitals know that weekend nights ramp up certain health issues (like getting shot in a violence prone area), more ortho injuries on ski or baseball or football weekend afternoons and the like. The only reason that this is just beginning is that hospitals are finally getting fairly comfortable with EHR’s and are beginning to try and see what they can do with the data. Hospital systems that got up on EHR years or even decades ago are likely to be far more advanced with predictions. FWIW, I believe that one hospital system in Montreal (heavy government push for efficiencies in socialized medicine) is already using its data to predict OR utilization and staff scheduling to go with the predictions and to make better use of staff and facilities. This is certainly a good thing for ER’s, which can use a combination of history, weather conditions, scheduled events and like factors to predict needed staffing levels.

  • R Troy,
    You’re right. This is just the beginning of us trying to figure out all the amazing things we’ll be able to do with EHR data. I’ve seen dozens of companies that are using data as you describe.

Click here to post a comment
   

Categories