Digital twins and prevention: a new era in medicine

Dig­i­tal twins are gain­ing ground in the indus­tri­al world. The doors that this kind of tool opens up allow it to be extend­ed into the field of health­care; in par­tic­u­lar with the use of dig­i­tal lungs for per­son­alised care. Being able to mod­el an organ, per­son­alise this mod­el using patient data, and sim­u­late its func­tion­ing could lead us to plan, antic­i­pate and pre­dict its devel­op­ment and ageing.

After all, as Claire Biot, Vice-Pres­i­dent of the Health Indus­try at Das­sault Sys­tèmes, right­ly points out, “today, by hav­ing the dig­i­tal twin of a Rafale, as well as lots of flight data – the equiv­a­lent of bio­mark­ers in aero­nau­tics – we can car­ry out pre­dic­tive main­te­nance in oper­a­tion. This means mov­ing from the dig­i­tal twin of a con­cept, the air­craft, to the per­son­alised dig­i­tal twin of each Rafale in operation.”

This rais­es the ques­tion: what role can dig­i­tal twins play in pre­ven­tive health­care? A ques­tion that was at the heart of the dis­cus­sions at the 5^th sem­i­nar of the Poly­tech­nique health group, coor­di­nat­ed by the Cen­tre de recherche en ges­tion de l’École poly­tech­nique (IP Paris), and led by Éti­enne Min­vielle (CNRS Research Direc­tor)¹.

Health pre­ven­tion is often seen as a sub­ject that was neglect­ed until recent­ly. Stan­ley Dur­rle­man, research direc­tor at Inria, is quick to point this out. “Talk­ing about pre­ven­tion is still uncom­mon in France, because first and fore­most we have a care sys­tem rather than a health sys­tem.” In his opin­ion, the cur­rent mot­to in research is more along the lines of “bet­ter to cure than to prevent.”

At Das­sault Sys­tèmes, dig­i­tal twins have been in use for some time. “Our ambi­tion is to help peo­ple live health­i­er lives at a cost that is sus­tain­able for health­care sys­tems, and we place dig­i­tal twins at the heart of our strat­e­gy,” explains Claire Biot, “because they make it pos­si­ble to rep­re­sent the invis­i­ble and get sev­er­al dis­ci­plines to work togeth­er.” A new project has been launched: “Med­iTwin was launched by Das­sault Sys­tèmes to cre­ate dif­fer­ent dig­i­tal twins in three ther­a­peu­tic areas: oncol­o­gy, neu­rol­o­gy and car­di­ol­o­gy,” she explains. “These dig­i­tal twins will pri­mar­i­ly be used for treat­ment or diag­no­sis, guid­ing med­ical decisions”.

There are two types of pre­ven­tion: pri­ma­ry pre­ven­tion (put in place to avoid catch­ing the dis­ease) and sec­ondary pre­ven­tion, which stops or slows down the devel­op­ment of the dis­ease. Pri­ma­ry pre­ven­tion applies in par­tic­u­lar to com­mu­ni­ca­ble dis­eases, with con­doms and quar­an­tine as exam­ples. It is there­fore cer­tain that, for cer­tain dis­eases, pri­ma­ry pre­ven­tion is com­pli­cat­ed. The sec­ond form of pre­ven­tion has a num­ber of con­straints, in par­tic­u­lar the need for rapid diag­no­sis and long-term patient man­age­ment. “How can I fol­low patients for decades to see if, in the end, my pre­ven­tion mea­sure was effec­tive?” won­ders Stan­ley Dur­rle­man. This is where a dig­i­tal mod­el­ling sys­tem that faith­ful­ly sim­u­lates the func­tion­ing of a per­son­alised bio­log­i­cal sys­tem using patient data comes into its own.

When it comes to illus­trat­ing the com­ple­men­tar­i­ty between pre­ven­tion and the pre­dic­tive algo­rith­mic sys­tems pro­posed by dig­i­tal twins, Stan­ley Dur­rle­man con­sid­ers Alzheimer’s dis­ease to be the prime exam­ple. Alzheimer’s dis­ease is cur­rent­ly not far behind can­cer as one of the biggest areas of med­ical research. “Despite colos­sal invest­ments in research, we haven’t had a pos­i­tive clin­i­cal tri­al for this dis­ease for 20 years,” explains the researcher. “And prac­ti­tion­ers still have vir­tu­al­ly noth­ing to pre­scribe to their patients” [editor’s note: the drug in ques­tion is cur­rent­ly only avail­able in the Unit­ed States, and the appli­ca­tion to mar­ket it in Europe is still being exam­ined by the authorities].

This treat­ment tar­gets the accu­mu­la­tion of amy­loid plaques in the patient’s brain, which begins 10–15 years before the first symp­toms of the dis­ease appear. “How­ev­er, the effects of the treat­ment on the patient’s cog­ni­tive decline remain rel­a­tive­ly minor,” he admits. “The change in our treat­ment plan is sub­stan­tial. We are no longer look­ing for drugs to cure the dis­ease, but rather to pre­vent it.”

It is there­fore impor­tant to under­stand how this dis­ease devel­ops and what the first signs are, in order to make an ear­ly diag­no­sis. To this end, Stan­ley Dur­rle­man’s research team has estab­lished pre­dic­tive mod­els – dig­i­tal twins – that can deter­mine the course of the dis­ease in dif­fer­ent peo­ple. After pre­sent­ing this mod­el, Claire Biot asked: “Are we ready for mass-test­ing for Alzheimer’s dis­ease?” Stan­ley Dur­rle­man replies that there is still progress to be made. “For a non-com­mu­ni­ca­ble dis­ease, it’s more accu­rate to talk about screen­ing,” explains the researcher. In gen­er­al, for this type of ill­ness, the patient will a doc­tor fol­low­ing the first symptoms.

Iden­ti­fi­ca­tion there­fore depends on the patient tak­ing action, and this first step must not be missed. “Giv­en the issues we have already dis­cussed, I think there is still a lot of work to be done to improve the detec­tion of cog­ni­tive dis­or­ders in the gen­er­al pop­u­la­tion,” he con­cludes. One of the areas to be devel­oped would be the iden­ti­fi­ca­tion of bio­mark­ers spe­cif­ic to the devel­op­ment of Alzheimer’s dis­ease. How­ev­er, just as the accu­mu­la­tion of amy­loid plaques in a patien­t’s brain is not always syn­ony­mous with the first signs of the dis­ease, pre­ven­tion will always depend on our abil­i­ty to predict.

These find­ings con­firm that, even if ques­tions remain, the dig­i­tal twin is like­ly to play an impor­tant role in the com­ing years. It could her­ald a new form of health pre­ven­tion, more algo­rith­mic, more per­son­alised and offer­ing pre­vi­ous­ly unimag­in­able detec­tion capabilities.

Pablo Andres