mp_3_PassageChezMedecin
π Health and biotech
Personalised medicine: custom healthcare on a national scale?

“Let’s personalise healthcare pathways, too”

with Agnès Vernet, Science journalist
On February 2nd, 2021 |
3min reading time
Etienne Minvielle
Etienne Minvielle
Director of the Centre de Recherche en Gestion at Ecole Polytechnique (IP Paris)
Key takeaways
  • Personalised medicine doesn’t just involve treatments, it could also incorporate the entire healthcare setting and patient experience.
  • Étienne Minvielle explains that better patient care means extra-medical assistance must also be personalised.
  • Patients have different needs, desires, personalities, and lifestyles. Taking these differences into account could improve treatment outcomes.
  • Personalised healthcare pathways could be developed with the aid of digital tools, similar to those used in e-commerce.
  • The title of this Braincamp is inspired by Étienne Minvielle's thesis at École polytechnique: "Managing singularity on a large scale".

Just as the prac­tice of medi­cine is more than pres­cri­bing medi­ca­tion, per­so­na­li­sed medi­cine more than tar­ge­ted treat­ments. Étienne Min­vielle, pro­fes­sor at École Poly­tech­nique is wor­king on more per­so­na­li­sed heal­th­care path­ways. His aim is to consi­der patients as a whole, taking into account their social context, habits and even beliefs.

“We’re tal­king about a per­so­na­li­sed approach throu­ghout the the entire jour­ney of a patient through the heal­th­care sys­tem. From hos­pi­tal to home, inclu­ding prac­ti­tio­ners such as inde­pendent nurses and phar­ma­cists,” Min­vielle explains. 

Offer patients the best guidance

The idea is to draw on tools deve­lo­ped in the ser­vice and e‑commerce sec­tors to tai­lor cus­to­mer expe­rience. Howe­ver, ins­tead of offe­ring dis­counts based on shop­ping habits, per­so­na­li­sed care means taking into account the patient’s social deter­mi­nants and psy­cho­so­cial needs.

“Once diag­no­sed with a chro­nic ill­ness, a patient will require ser­vices and non-medi­cal inter­ven­tions to improve their qua­li­ty of life. This could involve get­ting a pet-sit­ter during treat­ment ses­sions, help with paper­work to report their long-term condi­tion, or orga­ni­sing trans­port,” he adds.

A patient’s beha­viour and per­so­na­li­ty also affect the way they relate to heal­th­care. They might, for example, have a habit of resear­ching health-rela­ted infor­ma­tion online, tend to engage in ris­ky beha­viour, have a posi­tive or nega­tive out­look, be intro­ver­ted, extro­ver­ted, etc. “All of these fac­tors influence the patient’s res­ponse,” Min­vielle says. In order to take them into account, he is deve­lo­ping patient-cen­tred mana­ge­ment models.

These tools require data, and AI can faci­li­tate data col­lec­tion and help build rele­vant pro­files. “But in health, much of the data is high­ly com­plex,” he says. “We’ll need new pro­fes­sio­nals, such as coor­di­na­ting nurses, to make sense if it.” Connec­ted objects, such as pill dis­pen­sers, could also be used ; blood tests could be pres­cri­bed to check for meta­bo­lites so as to moni­tor patient com­pliance. “These solu­tions must go hand in hand with ethi­cal consi­de­ra­tions. How far can we go without intru­ding on patients’ lives?”

Pre­ser­ving patient autonomy

When it comes to ethics, vigi­lance is requi­red on seve­ral fronts. “Per­so­na­li­sed medi­cine must not res­trict access to care,” Min­vielle stresses. “There are risks per­tai­ning to access to per­so­na­li­sa­tion, as well as mino­ri­ty repre­sen­ta­tion in our models.” In a sys­tem that adapts patient care path­ways to their spe­ci­fic pro­file, digi­tal models could be used to orga­nise care options into broad cate­go­ries. This would stream­line care path­ways, res­tric­ting them in a way that may omit less popu­lar pre­fe­rences within the patient population.

Last­ly, per­so­na­li­sa­tion must not come at the expense of patient auto­no­my. Min­vielle believes that “patients should be able to opt out of care path­way per­so­na­li­sa­tion, and choose their own per­so­na­li­sa­tion path­way, even if it is not optimal.” 

Human and arti­fi­cial intelligence

Given what’s at stake, such a pro­gram can­not sole­ly rely on digi­tal tools. Human intel­li­gence is requi­red. Min­vielle reminds us that “AI can­not yet detect its own errors, whe­reas a human will imme­dia­te­ly notice if a patient has been given the wrong advice.”

Will this sys­tem save money ? “It remains to be seen. On the one hand, it should reduce waste ; on the other, we would be crea­ting a more com­plex sys­tem of care.” Min­vielle agrees that more research is nee­ded, and tru­ly per­so­na­li­sed care path­ways are still some time off.

“The main dif­fi­cul­ty is brin­ging eve­ry­thing toge­ther”, he says. The indi­vi­dua­li­sa­tion model is based on research from a num­ber of fields : public health (inte­gra­ting socioe­co­no­mic deter­mi­nants); psy­cho­lo­gy (ana­ly­sing patient beha­viour and demands); and medi­cal research (exa­mi­ning the effi­ca­cy of treat­ments on various patient pro­files). Yet “all of these groups are wor­king in iso­la­tion. If we are to deve­lop a culture of per­so­na­li­sa­tion within the health sys­tem, we have to demons­trate its feasibility.”

Support accurate information rooted in the scientific method.

Donate