Intensive care: an app that saved lives

A major issue dur­ing the pan­dem­ic has been avail­ab­il­ity of crit­ic­al care beds in intens­ive care units. At vital points dur­ing the peak in num­bers of Cov­id-19 patients, many hos­pit­als were under pres­sure. The ser­vices needed to know where to send patients in order to pre­vent over-load­ing ICUs. 

Ini­tially, health­care staff were not­ing the num­ber of beds avail­able in dif­fer­ent hos­pit­als on Excel sheets, which they were send­ing to one anoth­er via What­s­App chats. Even though the crisis con­di­tions required fast action, it was neither the most effi­cient nor the most secure way to share data. Espe­cially since we are talk­ing about inform­a­tion that could have caused pan­ic had it been intercepted. 

I work with doc­tors and nurses in those ser­vices on a daily basis and, once we had dis­cussed the prob­lem, I knew we could auto­mate it. As a response, our team designed an easy-to-use digit­al tool to keep track of beds. At the begin­ning of the lock­down, we worked around the clock to turn out the tool in 3–4 days. The ICU Bed Avail­ab­il­ity Mon­it­or (ICUBAM) was imme­di­ately picked up by the loc­al health author­it­ies of the Grand Est – a region of France with a pop­u­la­tion of over 5.5 mil­lion people. 

The ICUBAM sends a text mes­sage to the mobile phones of ICU work­ers twice a day, with a link to a simple online form. In a mat­ter of seconds, the user can input the neces­sary inform­a­tion includ­ing the num­ber of avail­able beds, wheth­er they were equipped for COVID+ patients or not, and the num­ber of people discharged. 

Data was then col­lec­ted and cent­ral­ised, which we used to gen­er­ate mod­els and real-time ana­lyses of evol­u­tions in the pan­dem­ic. Through­out the crisis, we con­tin­ued to inter­act with doc­tors, present­ing them with the dash­boards of our mod­els and fig­ures. The data was there to help them make decisions but of course judge­ments calls remained their own responsibility. 

ICUBAM was rel­at­ively easy to put in place. All we really needed was a place to store the data – and some fund­ing to cov­er the cost of the text mes­sages. As the num­bers came in over time, we trans­formed the data into a visu­al map of the pan­dem­ic across the coun­try. From that, we were able to go fur­ther by com­bin­ing the data from dif­fer­ent hos­pit­als with epi­demi­olo­gic­al mod­els of the pan­dem­ic to pre­dict avail­ab­il­ity of beds in the com­ing days. Our goal was to provide vital inform­a­tion to doc­tors who were mak­ing dif­fi­cult decisions about where to send high-risk patients. 

After the lock­down peri­od at the begin­ning of sum­mer 2020 we stopped run­ning the ICUBAM. How­ever, we were later con­tac­ted by many intens­ive care health work­ers with requests for us to put it back into action in pre­par­a­tion for the second wave. On our side, we would like the author­it­ies on a nation­al level to take up the sys­tem; health work­ers in ICUs need it. To face the second wave, the ICUBAM has been put back into action by INRIA and four French regions. For me, this shows our capa­city to redeploy the tool when needed.

Digit­al tools like ICUBAM can provide real insights into pub­lic health issues by keep­ing track of import­ant data for doc­tors, but also so that we may ana­lyse it to bet­ter under­stand a situ­ation for oth­er stake­hold­ers. We cre­ated it in a mat­ter of days, and the format could eas­ily be adap­ted to oth­er crisis scen­ari­os. Depend­ing on the con­text, it could be used to track avail­ab­il­ity of med­ic­al mater­i­als, their stor­age loc­a­tions and so on. In devel­op­ing coun­tries, sim­il­ar data col­lect­ing sys­tems could help sup­port and track pub­lic health crises. 

On a pos­it­ive note, post-lock­down I have also noticed more PhD applic­a­tions in my field. It would seem that the pan­dem­ic offers an example of how stat­ist­ics can be applied to real-life situ­ations. Young sci­ent­ists want to apply their know­ledge and there are many oth­er excit­ing chal­lenges to tackle in the domain of arti­fi­cial intel­li­gence for health.