1 of 27

J

AI for clinical trial design, clinical applications and future developments

Jean-Philippe Vert, PhD

Owkin

2 of 27

Conflict of Interest

DISCLOSURE 

I have the following potential conflict(s) of interest to report

Type of affiliation / financial interest                                         Name of commercial company

Employee and shareholder Owkin

President and shareholder Bioptimus

3 of 27

>90% of drugs fail in clinical trial

Probability of success for oncology vs non-oncology drugs in the U.S. in the different development phases from 2011 to 2020

Source: https://www.statista.com/statistics/597819/drug-development-phases-probability-of-success-oncology-nononcology-drugs/

4 of 27

AI can optimize every clinical phase

Phase 1 / 2

Phase 3

(Federated) external control arms

Prognostic & predictive enrichment

Phase 2 / 3

Data-driven covariate adjustment

Gain early estimates of efficacy for single-arm phase I/II clinical trials to inform phase transition decisions

Inform trial recruitment and better define patient populations

Better measure treatment effect by increasing clinical trial statistical power without adding more patients

5 of 27

AI can optimize every clinical phase

Phase 1 / 2

Phase 3

(Federated) external control arms

Prognostic & predictive enrichment

Phase 2 / 3

Data-driven covariate adjustment

Gain early estimates of efficacy for single-arm phase I/II clinical trials to inform phase transition decisions

Inform trial recruitment and better define patient populations

Better measure treatment effect by increasing clinical trial statistical power without adding more patients

6 of 27

Motivation

  • Half of phase 3 CT fail for lack of efficacy

  • What if we could estimate efficacy earlier to better inform phase transition decision?

7 of 27

Standard RCT (phase 3)

8 of 27

External control arm (ECA)

Phase 1/2

RWD, other CT

9 of 27

External control arm (ECA)

Phase 1/2

RWD, other CT

Need to correct for lack of randomization

  • Matching
  • IPTW

10 of 27

Inverse Probability of Treatment Weighting

(IPTW)

2) Use weights to compare arms

  1. Reweight patients to match distributions

10

11 of 27

But… data are siloed

12 of 27

FedECA overcomes the challenge of pooling data

13 of 27

Real data: FedECA detects effect that individual study don’t

Center

n

GEN+NAB

n

FOLFIRINOX

HR (95% CI)

p

FFCD

55

92

1.13 (0.80, 1.61)

0.480

IDIBGI

144

22

0.74 (0.40, 1.37)

0.342

PANCAN

94

101

0.80 (0.55, 1.16)

0.234

FedECA

293

215

0.75 (0.62, 0.92)

0.005

  • 3 centers in 3 countries
  • Metastatic pancreatic cancer
  • FOLFIRINOX vs gemcitabine + nab-paclitaxel

Pancan

FedECA

14 of 27

AI can optimize every clinical phase

Phase 1 / 2

Phase 3

(Federated) external control arms

Prognostic & predictive enrichment

Phase 2 / 3

Data-driven covariate adjustment

Gain early estimates of efficacy for single-arm phase I/II clinical trials to inform phase transition decisions

Inform trial recruitment and better define patient populations

Better measure treatment effect by increasing clinical trial statistical power without adding more patients

15 of 27

Motivation

What if we could accelerate the enrollment process and include the right patients in your phase II/III trial to increase success rates?

  • Bad prognosis to increase events and reduce n
  • Good responders

16 of 27

Prognostic enrichment in heart failure

Risk profile in past HF trials

Risk profile in HF cohorts

Risk profile in an hypothetical trial with prognostic enrichment

Hypothetical uniform risk profile population

Sample size needed

17 of 27

Biomarkers for patient selection

PoS is doubled with biomarkers

18 of 27

Ex: AI biomarkers from pathology slides

[*] Saillard C et al. “Pacpaint: a histology-based deep learning model uncovers the extensive intratumor molecular heterogeneity of pancreatic adenocarcinoma”. �Nature Comms 2023.

[**] Schmauch B et al. “A deep learning model to predict RNA-Seq expression of tumours from whole slide images”. Nature Comms 2020.

[***] Saillard et al. “Validation of MSIntuit as an AI-based pre-screening tool for MSI detection from colorectal cancer histology slides”. Nature Comms 2023.

HE2RNA model [**]�Predicts gene expression�from H&E images

H&E slide

Predicted genes expression

PACpAInt model [*]�Predicts molecular subtypes�from H&E images in pancreatic cancer

H&E slide

Neoplastic region segmentation

MSIntuit Dx tool [***]�Pre-screen MSI from H&E images in colorectal cancer

H&E slide�CRC

19 of 27

Next frontier: few-short learning with foundation models

20 of 27

AI can optimize every clinical phase

Phase 1 / 2

Phase 3

(Federated) external control arms

Prognostic & predictive enrichment

Phase 2 / 3

Data-driven covariate adjustment

Gain early estimates of efficacy for single-arm phase I/II clinical trials to inform phase transition decisions

Inform trial recruitment and better define patient populations

Better measure treatment effect by increasing clinical trial statistical power without adding more patients

21 of 27

Motivation

  • >50% of phase 3 trials fail, mainly for efficacy reasons, due to underpowered CT

  • What if we could increase the power of CT with AI?

22 of 27

Covariate adjustment

Survival rate

Time (years)

Control arm Treatment arm

Challenge

Treatment effect signal is impacted by prognostic heterogeneity

Solution

Adjust for data-driven AI-discovered prognostic covariates in the statistical analysis of your trial

Result

Optimized treatment effect estimation

→ Increased statistical power

→ Better adjustment for covariates

Time (years)

Survival rate

23 of 27

Ex: HCCnet

A deep learning prognostic model for resected hepatocellular carcinoma

Saillard , C., et al. Predicting Survival After Hepatocellular Carcinoma Resection Using Deep Learning on Histological Slides. Hepatology 72, 6 (2020) https://doi.org/10.1002/hep.31207

24 of 27

Using HCCnet decreases by 12% the size of the CT needed to reach 80% power

25 of 27

EMA supports AI-based covariate adjustment

“A main potential strength of the artificial intelligence (AI) models is the gain in prognostic performance compared to an adjustment with covariates used in current practice in clinical trial settings. This gain in performance could translate to gains in statistical power.”

26 of 27

Conclusion

Phase 1 / 2

Phase 3

(Federated) external control arms

Prognostic & predictive enrichment

Phase 2 / 3

Data-driven covariate adjustment

Gain early estimates of efficacy for single-arm phase I/II clinical trials to inform phase transition decisions

Inform trial recruitment and better define patient populations

Better measure treatment effect by increasing clinical trial statistical power without adding more patients

27 of 27

Thank you