Heartbeat line transforming into a digital AI code, AI role in real-time patient monitoring and heart health management. Advanced AI technology for cardiac care
Généré par l'IA / Generated using AI
π Health and biotech π Science and technology
Digital innovations for better health

From cure to prediction: the algorithmic transformation of healthcare

Etienne Minvielle, Director of the Centre de Recherche en Gestion at Ecole Polytechnique (IP Paris)
On February 26th, 2025 |
3 min reading time
Etienne Minvielle
Etienne Minvielle
Director of the Centre de Recherche en Gestion at Ecole Polytechnique (IP Paris)
Key takeaways
  • Algorithmic prevention differs from traditional prevention through its personalised and dynamic monitoring.
  • The Interception programme shows, for example, that 40% of severe forms of cancer could have been identified earlier thanks to algorithmic processes.
  • Innovation is essential to support an effective prevention policy in the face of new challenges (ageing population, climate issues, etc.).
  • It is important to transform our medical financing models to better support prevention, which is often neglected in favour of cure.
  • To demonstrate the value of prediction in the medical field, sufficient evidence of its effectiveness must be provided.

“A few years ago, we came togeth­er as part of a group of researchers from the Man­age­ment Research Cen­tre at Ecole Poly­tech­nique work­ing in the health­care sec­tor,” explains Éti­enne Min­vielle, CNRS research direc­tor (IP Paris). “One of the objec­tives was to think about how to bring tech­no­log­i­cal inno­va­tions into dia­logue with the needs of the health­care sys­tem.” This meet­ing launched a series of sem­i­nars on algo­rith­mic pre­ven­tion. “Two years ago, I per­son­al­ly didn’t know much about this top­ic,” he admits. “To tell the truth, I didn’t real­ly see what could be said about it. How­ev­er, after hav­ing led these sem­i­nars, I realise how impor­tant this sub­ject is for improv­ing prevention.”

Because, although ini­tial­ly lit­tle was known about this sub­ject, even among pro­fes­sion­als in the field, these dis­cus­sions have high­light­ed the fact that algo­rith­mic pre­ven­tion affects almost all areas of med­i­cine (oncol­o­gy, geri­atrics, psy­chi­a­try, neu­rol­o­gy, etc.).

From theory to practice, the algorithm prevents disease

From dig­i­tal twins to the pre­ven­tion of epi­demics, age­ing well and aug­ment­ed psy­chi­a­try, these sem­i­nars show that algo­rith­mic pre­ven­tion is not lim­it­ed to a spe­cif­ic field. It paves the way for a sys­temic trans­for­ma­tion of med­i­cine, link­ing tech­no­log­i­cal inno­va­tions to soci­etal issues. Health pre­ven­tion can now take two forms: con­ven­tion­al pre­ven­tion, which is aimed at a large group of the pop­u­la­tion, and so-called algo­rith­mic pre­ven­tion, which is more per­son­alised. “Algo­rith­mic pre­ven­tion dif­fers from con­ven­tion­al pre­ven­tion in that it is per­son­alised and accom­pa­nied by dynam­ic mon­i­tor­ing,” says Éti­enne Min­vielle. “This involves the col­lec­tion of sub­stan­tial data on genet­ic, but also socio-eco­nom­ic and behav­iour­al, factors.”

___________________________________________________________________________________________

Read also: How dig­i­tal tech­nol­o­gy will per­son­alise healthcare

___________________________________________________________________________________________

Once this data has been col­lect­ed, cou­pled with a more in-depth knowl­edge of the devel­op­ment of the dis­ease, it becomes pos­si­ble to make bet­ter pre­dic­tions. “For exam­ple, the Inter­cep­tion pro­gramme at Gus­tave Roussy is based on the obser­va­tion that 40% of severe forms of can­cer could have been iden­ti­fied ear­li­er by these algo­rith­mic process­es,” he explains. “Tests are thus car­ried out to iden­ti­fy genet­ic poly­mor­phisms, i.e. com­bi­na­tions of genet­ic muta­tions, in peo­ple iden­ti­fied as being at risk. Cou­pled with an analy­sis of envi­ron­men­tal risk fac­tors, they make it pos­si­ble to pre­dict the risk of can­cer occur­ring and to “inter­cept” it even before it can devel­op, thanks to per­son­alised monitoring.” 

40% of can­cers could there­fore be avoid­ed, as Fab­rice Bar­lesi, CEO of Gus­tave Roussy, is well aware: “Once we know this, we can­not fail to recog­nise the impor­tance of pre­ven­tion. But we must also ask our­selves why pre­ven­tion is not work­ing today – smok­ing is a case in point. More­over, our screen­ing pro­grammes, i.e. ear­ly detec­tion of the dis­ease, are also strug­gling. To rem­e­dy this, we will need to be able to iden­ti­fy the peo­ple at high­est risk with a view to inter­cept­ing this disease.”

A sim­i­lar pat­tern is found in the pre­ven­tion estab­lished by the ICOPE pro­gramme in its quest for healthy age­ing, in the pre­ven­tion of cog­ni­tive decline (such as with Alzheimer’s dis­ease), and in oth­er con­di­tions (car­di­ol­o­gy, men­tal health, well-being).

The science behind the algorithm

How­ev­er, exam­ples of the appli­ca­tion of this type of pre­ven­tion high­light its depen­dence on our sci­en­tif­ic, tech­no­log­i­cal and organ­i­sa­tion­al advances. “Today, we can see that inno­va­tion is a major lever for con­tribut­ing to an effec­tive pre­ven­tion pol­i­cy,” says Lise Alter, for­mer direc­tor gen­er­al of the Health Inno­va­tion Agency. “And, between an age­ing pop­u­la­tion, which means an increase in the preva­lence of chron­ic dis­eases, the diverse and var­ied chal­lenges of cli­mate change, and the lim­it­ing fac­tor of human resources in the health­care sec­tor, we are going to have to face major chal­lenges that will require the trans­for­ma­tion of our health­care system.”

And it is these major chal­lenges that make the promis­es of algo­rith­mic pre­ven­tion so appeal­ing. “When we talk about “trans­for­ma­tions” it means “changes” in our financ­ing mod­els, which are main­ly based on cura­tive rather than pre­ven­tive care. Eval­u­a­tion and also demon­stra­tion of val­ue – requir­ing appli­ca­tion on a pop­u­la­tion scale suf­fi­cient to have a pow­er of demon­stra­tion.” Above all, the demon­stra­tion of effec­tive­ness must not stop at the clin­i­cal aspect but must also focus on the impact of such a change on the organ­i­sa­tion of care or on the qual­i­ty of life of health­care per­son­nel. “These are there­fore much broad­er con­sid­er­a­tions than the sim­ple clin­i­cal impact on the patient, even if this remains a fun­da­men­tal point.”

For his part, Nico­las Rev­el, Direc­tor Gen­er­al of AP-HP, Assis­tance Publique – Hôpi­taux de Paris, is clear: “I am con­vinced that we are going to have to turn pre­ven­tion, which is a great idea, into a real­i­ty. This will require the removal of a few obsta­cles, both eco­nom­ic and finan­cial. And, indeed, at a time when we are seek­ing to reduce expen­di­ture, inno­va­tion will be the key to con­vinc­ing deci­sion-mak­ers to invest and to suc­cess­ful­ly imple­ment­ing it.” One of the lines of attack could also be to demon­strate effec­tive­ness, for pri­ma­ry as well as sec­ondary and ter­tiary pre­ven­tion. “Although pri­ma­ry pre­ven­tion requires long-term invest­ment, it cre­ates ben­e­fits that have an impact on sec­ondary and ter­tiary pre­ven­tion. This would enable us to bring the health­care sys­tem clos­er to the patient.”

This trans­for­ma­tion can­not hap­pen overnight. As Lise Alter right­ly points out: “Before any changes can be made, suf­fi­cient evi­dence is need­ed to pro­vide these ele­ments of objectivity.”

Pablo Andres

Our world explained with science. Every week, in your inbox.

Get the newsletter