600+ algorithms cleared by FDA

Huge impact of multimodal for multiple clinical applications.

The talk with be on youtube.

The main paper cited during the talk:

Medical forecasting

  1. Define risk: Partitionning high risk patients
    1. Lifestylefactors : UPF in diet, exercise, air pollution, sleep
    2. Genetics : APOE
    3. Biomarkers : p-tau 217
    4. PRS
    5. Retina photo
      1. You can predict the future of alzheimer and parkinson disease years before with the retina photo
  2. Monitoring high risk people
    1. Assess them more frequently :
      1. check retina
      2. brain organ clocks.: Tony Risckerey (?), validated in UK biobank
      3. epigenetic
      4. biomarkers : p-tau 217
  3. Timing of intervention: when will it begin to manifest and develop?
    1. La place du multimodal AI
  4. Preventive therapy
    1. Anti-inflammatory : e.g. GLP1
    2. Anti-amyloid
      1. no simple drug
      2. we will hopefully have more drugs and more efficient → but we need step 1 2 and 3 to build accurate clinical trials!
      3. they also will help to assess the ruled-out drugs with greatest subgroup analysis
    3. Full court press Lifestyle factors

Challenges of multimodal AI

Medical education

Health inequity and biases