Tweet
Tweet

Slide 1

Slide 1 text

Denis A. Engemann, PhD 6/22/20 CBU Cambridge Challenges of building clinical biomarkers from M/EEG Multimodal modeling with missing data and robust regression on power spectra [email protected] www.denis-engemann.de github: @dengemann twitter: @dngman

Slide 2

Slide 2 text

Woo et al. 2017 Nat Neuro Rev. Predicting clinical endpoints from multiple brain signals Mass-Univariate statistics Combine multiple inputs into single prediction

Slide 3

Slide 3 text

Predicting clinical endpoints from multiple brain signals

Slide 4

Slide 4 text

Predicting clinical endpoints from multiple brain signals NO T SO FAST !!

Slide 5

Slide 5 text

Caveat: Prediction accuracy depend on sample size. Often in a bad way … Varoquaux 2017, Neuroimage

Slide 6

Slide 6 text

Varoquaux, Raamana, Engemann et al. 2016, Neuroimage Caveat: Cross-validation can be too optimistic.

Slide 7

Slide 7 text

Varoquaux, Raamana, Engemann et al. 2016, Neuroimage Caveat: Cross-validation can be too optimistic. good news for M/EEG

Slide 8

Slide 8 text

Bzdok, Engemann et al. 2018 bioRxiv [https://github.com/banilo/inf_vs_pred_2018/] Caveat: inference is not prediction Significance does not imply that prediction will work!

Slide 9

Slide 9 text

Caveat: generative mechanism often unknown Jonas & Kording 2017, PLOS Comp. Biol.

Slide 10

Slide 10 text

Caveat: generative mechanism often unknown Jonas & Kording 2017, PLOS Comp. Biol. Different imaging modality, Different generative mechanism …

Slide 11

Slide 11 text

Caveat: Too few samples of the clinical outcome •Problem: few data on precious endpoint, e.g, cognitive decline •Brain Age Delta = predicted age (PAD) - passport age
 •Precocious aging induces cognitive dysfunction (CD) and risk of mortality
 •Typically estimated with MRI!

Slide 12

Slide 12 text

Caveat: Too few samples of the clinical outcome •Problem: few data on precious endpoint, e.g, cognitive decline •Idea: Predict endpoint that’s widely available and exploit its correlation with the actual endpoint of interest, e.g. age •Brain Age Delta = predicted age (PAD) - passport age
 •Precocious aging induces cognitive dysfunction (CD) and risk of mortality
 •Typically estimated with MRI! Solution: Surrogate biomarker.

Slide 13

Slide 13 text

Surrogate biomarkers: Brain Age Cole et al. Mol. Psych. 2018 •Problem: few data on precious endpoint, e.g, cognitive decline •Idea: Predict endpoint that’s widely available and exploit its correlation with the actual endpoint of interest, e.g. age •Brain Age Delta = predicted age (PAD) - passport age
 •Precocious aging induces cognitive dysfunction (CD) and risk of mortality
 •Typically estimated with MRI!

Slide 14

Slide 14 text

Surrogate biomarkers: Brain Age Cole et al. Mol. Psych. 2018 •Problem: few data on precious endpoint, e.g, cognitive decline •Idea: Predict endpoint that’s widely available and exploit its correlation with the actual endpoint of interest, e.g. age •Brain Age Delta = predicted age (PAD) - passport age
 •Precocious aging induces cognitive dysfunction (CD) and risk of mortality
 •Typically estimated with MRI!

Slide 15

Slide 15 text

Surrogate biomarkers: Brain Age •Problem: few data on precious endpoint, e.g, cognitive decline •Idea: Predict endpoint that’s widely available and exploit its correlation with the actual endpoint of interest, e.g. age •Brain Age Delta = predicted age (PAD) - passport age
 •Precocious aging induces cognitive dysfunction (CD) and risk of mortality
 Liem et al 2017 NIMG Cole et al. Mol. Psych. 2018

Slide 16

Slide 16 text

Surrogate biomarkers: Brain Age •Problem: few data on precious endpoint, e.g, cognitive decline •Idea: Predict endpoint that’s widely available and exploit its correlation with the actual endpoint of interest, e.g. age •Brain Age Delta = predicted age (PAD) - passport age
 •Precocious aging induces cognitive dysfunction (CD) and risk of mortality
 •Typically estimated with MRI! Cole et al. Mol. Psych. 2018 Liem et al 2017 NIMG Liem et al 2017 NIMG

Slide 17

Slide 17 text

Shall we bother about M/EEG? Brookes et al. 2011, PNAS fMRI resting state networks can be reconstructed from MEG

Slide 18

Slide 18 text

Shall we bother about M/EEG? Hipp & Siegel 2015, Curr. Biol. BOLD and MEG show spatial correlations across many frequency bands.

Slide 19

Slide 19 text

Perhaps … Kumral et al. 2020 NIMG BOLD and EEG signal variability at rest differently relate to aging

Slide 20

Slide 20 text

Perhaps we should … Nentwich et al. 2020 NIMG fMRI and EEG connectivity is different.

Slide 21

Slide 21 text

Perhaps we should bother … Gaubert et al. 2019 Brain EEG-signatures in preclincal Alzheimer’s disease

Slide 22

Slide 22 text

Joint predictive modeling with MEG, fMRI and MRI Is it worth the effort? Multimodal input data anatomical MRI functional MRI MEG Layer I: Ridge Regression Age predictions Missing value coding Layer II: Random Forest Regressor tree = 1 tree = 1 subject #i age = 50 age #i = 53 age = 57 age = 5 tree = ... tree = B Multimodal input data anatomical MRI functional MRI MEG Layer I: Ridge Regression Age predictions Missing value coding Layer II: Random Forest Regressor tree = 1 tree = 1 subject #i age = 50 age #i = 53 age = 57 age = 5 tree = ... tree = B 2 1 2 21 A A A A 1 2 2 2 21 1 1 2 1 1e 1e 1e 1e 1 2 2 2 21 1 1 2 1 1e 1e 1e 1e 1 2 2 2 21 1 1 true age 2 21 true age 2 1 A A A A 1 2 2 2 21 1 1 2 1 1e 1e 1e 1e 1 2 2 2 21 1 1 2 1 1e 1e 1e 1e 1 2 2 2 21 1 1 Engemann et al. 2020 eLife

Slide 23

Slide 23 text

How to get M/EEG signals?

Slide 24

Slide 24 text

MEG system at Neurospin … not very different form the one at CBU How to get M/EEG signals?

Slide 25

Slide 25 text

Python code How to get M/EEG signals?

Slide 26

Slide 26 text

How to get M/EEG signals?

Slide 27

Slide 27 text

1e−28 1e−27 1e−26 1 3 10 30 Frequecy (Hz) log10(MEG2) age group (17.9,28] (28,38] (38,48] (48,58] (58,68] (68,78] (78,88.1] What MEG features shall we use?

Slide 28

Slide 28 text

1e−28 1e−27 1e−26 1 3 10 30 Frequecy (Hz) log10(MEG2) age group (17.9,28] (28,38] (38,48] (48,58] (58,68] (68,78] (78,88.1] α-power Engemann 2018 Brain What MEG features shall we use?

Slide 29

Slide 29 text

1e−28 1e−27 1e−26 1 3 10 30 Frequecy (Hz) log10(MEG2) age group (17.9,28] (28,38] (38,48] (48,58] (58,68] (68,78] (78,88.1] α-peak α-power Babiloni 2006 HBM Engemann 2018 Brain What MEG features shall we use?

Slide 30

Slide 30 text

1e−28 1e−27 1e−26 1 3 10 30 Frequecy (Hz) log10(MEG2) age group (17.9,28] (28,38] (38,48] (48,58] (58,68] (68,78] (78,88.1] α-peak Power topography Gaubert 2019 Brain Fruehwirt 2017 NeurIPS workshop α-power Babiloni 2006 HBM Engemann 2018 Brain What MEG features shall we use?

Slide 31

Slide 31 text

1e−28 1e−27 1e−26 1 3 10 30 Frequecy (Hz) log10(MEG2) age group (17.9,28] (28,38] (38,48] (48,58] (58,68] (68,78] (78,88.1] 1/f fits Voytek et al. 2015 JoN α-peak Power topography Gaubert 2019 Brain Fruehwirt 2017 NeurIPS workshop α-power Babiloni 2006 HBM Engemann 2018 Brain What MEG features shall we use?

Slide 32

Slide 32 text

1e−28 1e−27 1e−26 1 3 10 30 Frequecy (Hz) log10(MEG2) age group (17.9,28] (28,38] (38,48] (48,58] (58,68] (68,78] (78,88.1] 1/f fits Voytek et al. 2015 JoN α-peak Power topography Gaubert 2019 Brain Fruehwirt 2017 NeurIPS workshop α-power Babiloni 2006 HBM Engemann 2018 Brain Other classical features • Evoked latency (Price 2017 Nat Coms) • 1/f topography Enhancements • Source power (Sabbagh 2019 NeurIPS) • Power Envelope Correlations (Khan 2018 NIMG) • A few options: orthogonalization, covariance • Power envelope power … What MEG features shall we use?

Slide 33

Slide 33 text

1e−28 1e−27 1e−26 1 3 10 30 Frequecy (Hz) log10(MEG2) age group (17.9,28] (28,38] (38,48] (48,58] (58,68] (68,78] (78,88.1] 1/f fits Voytek et al. 2015 JoN α-peak Power topography Gaubert 2019 Brain Fruehwirt 2017 NeurIPS workshop α-power Babiloni 2006 HBM Engemann 2018 Brain Other classical features • Evoked latency (Price 2017 Nat Coms) • 1/f topography Enhancements: Source Analysis • Source power (Sabbagh 2019 NeurIPS) • Power Envelope Correlations (Khan 2018 NIMG) • A few options: orthogonalization, covariance • Power envelope power … What MEG features shall we use?

Slide 34

Slide 34 text

How to build an MEG-base regression model? MEG at Neurospin … not very different form the one at CBU

Slide 35

Slide 35 text

How to build an MEG-base regression model? Objective: predict target fro x Sabbagh et al. 2019 (NeurIPS) 2020 (NIMG)

Slide 36

Slide 36 text

How to build an MEG-base regression model? Objective: predict target fro x Sabbagh et al. 2019 (NeurIPS) 2020 (NIMG) Use AI ?

Slide 37

Slide 37 text

How to build an MEG-base regression model? Objective: predict target fro x Sabbagh et al. 2019 (NeurIPS) 2020 (NIMG) Use AI ? NOPE

Slide 38

Slide 38 text

How to build an MEG-base regression model? z ? Objective: predict target from M/EEG Neurophysiological genera or Maxwell's eq. neural mechanism Sabbagh et al. 2019 (NeurIPS) 2020 (NIMG)

Slide 39

Slide 39 text

How to build an MEG-base regression model? z ? Objective: predict target from M/EEG Neurophysiological genera or Maxwell's eq. neural mechanism Sabbagh et al. 2019 (NeurIPS) 2020 (NIMG)

Slide 40

Slide 40 text

How to build an MEG-base regression model? z ? Objective: predict target from M/EEG Neurophysiological genera or Maxwell's eq. neural mechanism Sabbagh et al. 2019 (NeurIPS) 2020 (NIMG) Primary currents

Slide 41

Slide 41 text

How to build an MEG-base regression model? z s ? Objective: predict target from M/EEG Neurophysiological genera or a is ical o el statistical sources Maxwell's eq. neural mechanism Sabbagh et al. 2019 (NeurIPS) 2020 (NIMG)

Slide 42

Slide 42 text

How to build an MEG-base regression model? z s ? Objective: predict target from M/EEG Neurophysiological genera or a is ical o el statistical sources M/EEG signals Maxwell's eq. neural mechanism Sabbagh et al. 2019 (NeurIPS) 2020 (NIMG)

Slide 43

Slide 43 text

How to build an MEG-base regression model? z s ? Objective: predict target from M/EEG Neurophysiological genera or a is ical o el biomedical outcome statistical sources M/EEG signals Maxwell's eq. neural mechanism Sabbagh et al. 2019 (NeurIPS) 2020 (NIMG)

Slide 44

Slide 44 text

How to build an MEG-base regression model? z s ? Objective: predict target from M/EEG Neurophysiological genera or a is ical o el biomedical outcome statistical sources M/EEG signals Maxwell's eq. neural mechanism f log s Sabbagh et al. 2019 (NeurIPS) 2020 (NIMG)

Slide 45

Slide 45 text

Overview on all features Engemann et al. 2020 eLife Liem et al 2017 NIMG NEW!

Slide 46

Slide 46 text

Joint predictive modeling with MEG, fMRI and MRI Is it worth the effort? Multimodal input data anatomical MRI functional MRI MEG Layer I: Ridge Regression Age predictions Missing value coding Layer II: Random Forest Regressor tree = 1 tree = 1 subject #i age = 50 age #i = 53 age = 57 age = 5 tree = ... tree = B Multimodal input data anatomical MRI functional MRI MEG Layer I: Ridge Regression Age predictions Missing value coding Layer II: Random Forest Regressor tree = 1 tree = 1 subject #i age = 50 age #i = 53 age = 57 age = 5 tree = ... tree = B 2 1 2 21 A A A A 1 2 2 2 21 1 1 2 1 1e 1e 1e 1e 1 2 2 2 21 1 1 2 1 1e 1e 1e 1e 1 2 2 2 21 1 1 true age 2 21 true age 2 1 A A A A 1 2 2 2 21 1 1 2 1 1e 1e 1e 1e 1 2 2 2 21 1 1 2 1 1e 1e 1e 1e 1 2 2 2 21 1 1 Engemann et al. 2020 eLife

Slide 47

Slide 47 text

Joint predictive modeling with MEG, fMRI and MRI Is it worth the effort? Multimodal input data anatomical MRI functional MRI MEG Layer I: Ridge Regression Age predictions Missing value coding Layer II: Random Forest Regressor tree = 1 tree = 1 subject #i age = 50 age #i = 53 age = 57 age = 5 tree = ... tree = B Multimodal input data anatomical MRI functional MRI MEG Layer I: Ridge Regression Age predictions Missing value coding Layer II: Random Forest Regressor tree = 1 tree = 1 subject #i age = 50 age #i = 53 age = 57 age = 5 tree = ... tree = B 2 1 2 21 A A A A 1 2 2 2 21 1 1 2 1 1e 1e 1e 1e 1 2 2 2 21 1 1 2 1 1e 1e 1e 1e 1 2 2 2 21 1 1 true age 2 21 true age 2 1 A A A A 1 2 2 2 21 1 1 2 1 1e 1e 1e 1e 1 2 2 2 21 1 1 2 1 1e 1e 1e 1e 1 2 2 2 21 1 1 Engemann et al. 2020 eLife

Slide 48

Slide 48 text

Joint predictive modeling with MEG, fMRI and MRI Is it worth the effort? Multimodal input data anatomical MRI functional MRI MEG Layer I: Ridge Regression Age predictions Missing value coding Layer II: Random Forest Regressor tree = 1 tree = 1 subject #i age = 50 age #i = 53 age = 57 age = 5 tree = ... tree = B Multimodal input data anatomical MRI functional MRI MEG Layer I: Ridge Regression Age predictions Missing value coding Layer II: Random Forest Regressor tree = 1 tree = 1 subject #i age = 50 age #i = 53 age = 57 age = 5 tree = ... tree = B 2 1 2 21 A A A A 1 2 2 2 21 1 1 2 1 1e 1e 1e 1e 1 2 2 2 21 1 1 2 1 1e 1e 1e 1e 1 2 2 2 21 1 1 true age 2 21 true age 2 1 A A A A 1 2 2 2 21 1 1 2 1 1e 1e 1e 1e 1 2 2 2 21 1 1 2 1 1e 1e 1e 1e 1 2 2 2 21 1 1 Engemann et al. 2020 eLife

Slide 49

Slide 49 text

Joint predictive modeling with MEG, fMRI and MRI Is it worth the effort? Multimodal input data anatomical MRI functional MRI MEG Layer I: Ridge Regression Age predictions Missing value coding Layer II: Random Forest Regressor tree = 1 tree = 1 subject #i age = 50 age #i = 53 age = 57 age = 5 tree = ... tree = B Multimodal input data anatomical MRI functional MRI MEG Layer I: Ridge Regression Age predictions Missing value coding Layer II: Random Forest Regressor tree = 1 tree = 1 subject #i age = 50 age #i = 53 age = 57 age = 5 tree = ... tree = B 2 1 2 21 A A A A 1 2 2 2 21 1 1 2 1 1e 1e 1e 1e 1 2 2 2 21 1 1 2 1 1e 1e 1e 1e 1 2 2 2 21 1 1 true age 2 21 true age 2 1 A A A A 1 2 2 2 21 1 1 2 1 1e 1e 1e 1e 1 2 2 2 21 1 1 2 1 1e 1e 1e 1e 1 2 2 2 21 1 1 Engemann et al. 2020 eLife

Slide 50

Slide 50 text

Joint predictive modeling with MEG, fMRI and MRI Is it worth the effort? Multimodal input data anatomical MRI functional MRI MEG Layer I: Ridge Regression Age predictions Missing value coding Layer II: Random Forest Regressor tree = 1 tree = 1 subject #i age = 50 age #i = 53 age = 57 age = 5 tree = ... tree = B Multimodal input data anatomical MRI functional MRI MEG Layer I: Ridge Regression Age predictions Missing value coding Layer II: Random Forest Regressor tree = 1 tree = 1 subject #i age = 50 age #i = 53 age = 57 age = 5 tree = ... tree = B 2 1 2 21 A A A A 1 2 2 2 21 1 1 2 1 1e 1e 1e 1e 1 2 2 2 21 1 1 2 1 1e 1e 1e 1e 1 2 2 2 21 1 1 true age 2 21 true age 2 1 A A A A 1 2 2 2 21 1 1 2 1 1e 1e 1e 1e 1 2 2 2 21 1 1 2 1 1e 1e 1e 1e 1 2 2 2 21 1 1 Engemann et al. 2020 eLife

Slide 51

Slide 51 text

Can we enhance age prediction? by combining MEG,fMRI & MRI 4.7 5.1 5.2 6.0 −3.0 −2.5 −2.0 −1.5 −1.0 −0.5 0.0 0.5 1.0 1.5 MAE difference (years) Multimodal stacking m ro ement o er anatomical M M fM ME M fM M ME M no M anat. M anat. added 0 10 20 30 0 10 20 30 0 10 20 30 MAEfM (years) MAEME (years) age 20 40 60 0 A B Engemann et al. 2020 eLife

Slide 52

Slide 52 text

Can we enhance age prediction? by combining MEG,fMRI & MRI 4.7 5.1 5.2 6.0 −3.0 −2.5 −2.0 −1.5 −1.0 −0.5 0.0 0.5 1.0 1.5 MAE difference (years) Multimodal stacking m ro ement o er anatomical M M fM ME M fM M ME M no M anat. M anat. added 0 10 20 30 0 10 20 30 0 10 20 30 MAEfM (years) MAEME (years) age 20 40 60 0 A B Engemann et al. 2020 eLife

Slide 53

Slide 53 text

Can we enhance brain age as an index of cognitive aging? by combining MEG,fMRI & MRI FluidIntelligence Depression MMSE PicturePriming1 Proverbs PSQI VSTMcolour4 ACER FluidIntelligence FamousFaces Depression VSTMcolour4 FluidIntelligence MMSE VSTMcolour4 CardioMeasures1 CardioMeasures FluidIntelligence EmotionalMemor 1 FamousFaces Depression otel PicturePriming1 Proverbs FluidIntelligence PicturePriming1 VSTMcolour FluidIntelligence MMSE 1 4 ME MRI MRI MRI MRI MRI MRI ME MRI ME −log1 (p) FluidIntelligence Depression MMSE PicturePriming1 Proverbs PSQI VSTMcolour4 ACER FluidIntelligence FamousFaces Depression VSTMcolour4 FluidIntelligence MMSE VSTMcolour4 CardioMeasures1 CardioMeasures FluidIntelligence EmotionalMemor 1 FamousFaces Depression otel PicturePriming1 Proverbs FluidIntelligence PicturePriming1 VSTMcolour FluidIntelligence MMSE 1 1 ME MRI MRI MRI MRI MRI MRI ME MRI ME β A B Engemann et al. 2020 eLife

Slide 54

Slide 54 text

Can we enhance brain age as an index of cognitive aging? by combining MEG,fMRI & MRI FluidIntelligence Depression MMSE PicturePriming1 Proverbs PSQI VSTMcolour4 ACER FluidIntelligence FamousFaces Depression VSTMcolour4 FluidIntelligence MMSE VSTMcolour4 CardioMeasures1 CardioMeasures FluidIntelligence EmotionalMemor 1 FamousFaces Depression otel PicturePriming1 Proverbs FluidIntelligence PicturePriming1 VSTMcolour FluidIntelligence MMSE 1 1 ME MRI MRI MRI MRI MRI MRI ME MRI ME β B Engemann et al. 2020 eLife

Slide 55

Slide 55 text

What aspects of MEG are most influential? Peaks - Latencies - 1/f - Power - Connectivity Engemann et al. 2020 eLife 10 15 0.01 0.1 Variable impo MAE (years) family source activity source connectivity sensor mixed A B . . . . 11. predictin y 5 ME stac in models ull ombined ource ource Activity ource onnectivity ensor Mixed 10 11 1 1 1 15 1 MAE (years)

Slide 56

Slide 56 text

What aspects of MEG are most influential? Peaks - Latencies - 1/f - Power - Connectivity Engemann et al. 2020 eLife α βlow βlow βlow Ecat Pcat 10 15 0.01 0.10 1.00 Variable importance (MAE) MAE (years) family source activity source connectivity sensor mixed input/feature si nal envelope 1 f slope α pea E lat B predictin y ensor Mixed 1 15 1

Slide 57

Slide 57 text

What if some modalities are (sometimes) missing? opportunistic missing value handling Engemann et al. 2020 eLife on Age predictions Missing value coding Layer II: Random Forest Regressor on Age predictions Missing value coding Layer II: Random Forest Regressor 2 1 2 21 A A A A 1 2 2 2 21 1 1 2 1 1e 1e 1e 1e 1 2 2 2 21 1 1 2 1 1e 1e 1e 1e 1 2 2 2 21 1 1 true age 2 21 true age 2 1 A A A A 1 2 2 2 21 1 1 2 1 1e 1e 1e 1e 1 2 2 2 21 1 1 2 1 1e 1e 1e 1e 1 2 2 2 21 1 1

Slide 58

Slide 58 text

What if some modalities are (sometimes) missing? opportunistic missing value handling 4.4 4.6 4.6 4.7 8.6 14.6 MRI fMRI fMRI MEGsens MRI fMRI MEG MRI fMRI MEGsens MEG MEGsens 0 10 20 30 MAE Available inputs 4.5 5.0 5.5 6.0 6.5 7.0 4.5 5.0 5.5 6.0 6.5 7.0 MAEavailable MAEopportunistic stackin o el MRI fMRI MEG MRI fMRI MRI MEG MRI fMRI MEG co parison co on co on e tra full vs re uce A B Engemann et al. 2020 eLife

Slide 59

Slide 59 text

Interim-Summary 1. MEG contains unique information on age and cognitive aging 2. MEG source power is a potent feature for predictive modeling 3. Tree-based methods bring flexible missing value handling

Slide 60

Slide 60 text

Interim-Summary 1. MEG contains unique information on age and cognitive aging 2. MEG source power is a potent feature for predictive modeling 3. Tree-based methods bring flexible missing value handling Limitations: Do I need MEG + Source Localization ? What we find in most hospitals looks a bit different …

Slide 61

Slide 61 text

WHAT IF I TOLD YOU … … that no MRI is needed.

Slide 62

Slide 62 text

… hack the Covariance Matrix !

Slide 63

Slide 63 text

M/EEG Covariance Matrix

Slide 64

Slide 64 text

M/EEG Covariance Matrix Ci = Xi X⊤/T ∈ ℝP×P

Slide 65

Slide 65 text

M/EEG Covariance Matrix: Ci = Xi X⊤ i /T ∈ ℝP×P

Slide 66

Slide 66 text

M/EEG Covariance Matrix: var(Xi ) = diag(Ci ) ∈ ℝP Power is variance Ci = Xi X⊤ i /T ∈ ℝP×P

Slide 67

Slide 67 text

M/EEG Covariance Matrix: Power is variance var(Xi ) = diag(Ci ) ∈ ℝP Ci = Xi X⊤ i /T ∈ ℝP×P

Slide 68

Slide 68 text

Predicting from M/EEG source power Without biophysical source localization z s ? Objective: predict target from M/EEG Neurophysiological genera or a is ical o el biomedical outcome statistical sources M/EEG signals Maxwell's eq. neural mechanism f log s Problem: volume conductions is evil. Sabbagh et al. 2019 (NeurIPS) 2020 (NIMG) Ci = Xi X⊤ i /T ∈ ℝP×P Use cov. as representation

Slide 69

Slide 69 text

Predicting from M/EEG source power Without biophysical source localization z s ? Objective: predict target from M/EEG Neurophysiological genera or a is ical o el biomedical outcome statistical sources M/EEG signals Maxwell's eq. neural mechanism f log s Problem: volume conductions is evil. Idea: get immunized against this evil Sabbagh et al. 2019 (NeurIPS) 2020 (NIMG) Ci = Xi X⊤ i /T ∈ ℝP×P Use cov. as representation logm ( ¯ C−1/2Ci ¯ C−1/2)

Slide 70

Slide 70 text

Predicting from M/EEG source power Without biophysical source localization z s ? Objective: predict target from M/EEG Neurophysiological genera or a is ical o el biomedical outcome statistical sources M/EEG signals Maxwell's eq. neural mechanism f log s Problem: volume conductions is evil. Idea: get immunized against this evil Sabbagh et al. 2019 (NeurIPS) 2020 (NIMG) Take out volume conduction using Riemannian embeddings, or spatial filters Ci = Xi X⊤ i /T ∈ ℝP×P Use cov. as representation logm ( ¯ C−1/2Ci ¯ C−1/2)

Slide 71

Slide 71 text

Simulations Are shortcuts — in principle — possible? Sabbagh et al. 2019 (NeurIPS) 2020 (NIMG) distance from identity chance level 0.00 0.25 0.50 0.75 1.00 0.0 0.5 1.0 1.5 2.0 2.5 3.0 µ Normalized MAE noise on target 0.00 0.25 0.50 0.75 1.00 0.01 0.10 1.00 10.00 σ 0.00 0.25 0.50 0.75 1.00 upper diag S o iemann noise on mi ing matri 0.01 0.10 1.00 σ z s ? Objective: predict target from M/EEG Neurophysiological genera or a is ical o el biomedical outcome statistical sources M/EEG signals Maxwell's eq. neural mechanism f log s

Slide 72

Slide 72 text

Empirical benchmarks How do these models compare with real data and unknown degrees model violations? Sabbagh et al. 2020 (NIMG) 7.98 8.11 8.76 8.76 9.17 10.89 predicting age Riemann53 Riemann SPoC67 SPoC diag upper 8 10 12 14 16 MAE upper diag SPoC Riemann MEG — sensor space MEG — source space

Slide 73

Slide 73 text

Empirical benchmarks How do these models compare with real data and unknown degrees model violations? Sabbagh et al. 2020 (NIMG) 7.98 8.11 8.76 8.76 9.17 10.89 predicting age Riemann53 Riemann SPoC67 SPoC diag upper 8 10 12 14 16 MAE upper diag SPoC Riemann MEG — sensor space MEG — source space Q: Do we expect the same ranking?

Slide 74

Slide 74 text

Empirical benchmarks How do these models compare with real data and unknown degrees model violations? Sabbagh et al. 2020 (NIMG) 7.69 9.50 10.98 11.67 11.86 12.46 predicting age diag Riemann11 Riemann upper SPoC20 SPoC 5.0 7.5 10.0 12.5 15.0 17.5 MAE upper diag SPoC Riemann 7.98 8.11 8.76 8.76 9.17 10.89 predicting age Riemann53 Riemann SPoC67 SPoC diag upper 8 10 12 14 16 MAE upper diag SPoC Riemann MEG — sensor space MEG — source space

Slide 75

Slide 75 text

Empirical benchmarks How do these models compare with real data and unknown degrees model violations? Sabbagh et al. 2020 (NIMG) 7.69 9.50 10.98 11.67 11.86 12.46 predicting age diag Riemann11 Riemann upper SPoC20 SPoC 5.0 7.5 10.0 12.5 15.0 17.5 MAE upper diag SPoC Riemann 7.98 8.11 8.76 8.76 9.17 10.89 predicting age Riemann53 Riemann SPoC67 SPoC diag upper 8 10 12 14 16 MAE upper diag SPoC Riemann MEG — sensor space MEG — source space Observations: (1) the baseline model is the best in source space

Slide 76

Slide 76 text

Empirical benchmarks How do these models compare with real data and unknown degrees model violations? Sabbagh et al. 2020 (NIMG) 7.69 9.50 10.98 11.67 11.86 12.46 predicting age diag Riemann11 Riemann upper SPoC20 SPoC 5.0 7.5 10.0 12.5 15.0 17.5 MAE upper diag SPoC Riemann 7.98 8.11 8.76 8.76 9.17 10.89 predicting age Riemann53 Riemann SPoC67 SPoC diag upper 8 10 12 14 16 MAE upper diag SPoC Riemann MEG — sensor space MEG — source space Observations: (1) the baseline model is the best in source space (2) Riemannian embeddings get closest to results with source localization

Slide 77

Slide 77 text

Empirical benchmarks How do these models compare with real data and unknown degrees model violations? Sabbagh et al. 2020 (NIMG) 7.98 8.11 8.76 8.76 9.17 10.89 predicting age Riemann53 Riemann SPoC67 SPoC diag upper 8 10 12 14 16 MAE upper diag SPoC Riemann MEG — sensor space EEG— sensor space (TUH data, n=1385) Q: Can we get similar results on 21-chan. EEG as compared to 306-chan. MEG?

Slide 78

Slide 78 text

Empirical benchmarks How do these models compare with real data and unknown degrees model violations? Sabbagh et al. 2020 (NIMG) 8.21 8.27 9.63 10.72 predicting age Riemann19 Riemann SPoC21 diag upper 5.0 7.5 10.0 12.5 15.0 MAE upper diag SPoC Riemann 7.98 8.11 8.76 8.76 9.17 10.89 predicting age Riemann53 Riemann SPoC67 SPoC diag upper 8 10 12 14 16 MAE upper diag SPoC Riemann MEG — sensor space EEG— sensor space (TUH data, n=1385) EEG can in principle be substituted for MEG

Slide 79

Slide 79 text

1) Université Paris-Saclay, Inria, CEA, Palaiseau, France, 2) Inserm, UMRS-942, Paris Diderot University, Paris, France, 3) Department of Anaesthesiology and Critical Care, Lariboisière Hospital, Assistance Publique Hôpitaux de Paris, Paris, France, 4) Max Planck Institute for Human Cognitive and Brain Sciences, Department of Neurology, D-04103, Leipzig, Germany NeurIPS Twitter NeuroImage 8.21 8.27 9.63 10.72 predicting age Riemann19 Riemann SPoC21 diag upper 5.0 7.5 10.0 12.5 15.0 MAE 7.98 8.11 8.76 8.76 9.17 10.89 predicting age Riemann53 Riemann SPoC67 SPoC diag upper 8 10 12 14 16 MAE upper diag SPoC Riemann raw raw raw Riemann53 SPoC67 diag env eog ecg eo/cg rej env eog ecg eo/cg rej env eog ecg eo/cg rej 6 7 8 9 10 11 12 13 14 Preprocessing steps MAE SSS SSP David Sabbagh1,2,3, Pierre Ablin1, Gaël Varoquaux1, Alexandre Gramfort1, Denis A. Engemann1,4 Correspondendce: david.sabbagh inria.fr, denis-alexander.engemann inria.fr z s bjective: predict outcome from M/EEG Neurophysiological generator Statistical model biomedical outcome statistical sources M/EEG signals Maxwell s eq. neural mechanism 1 2 x y f log s ) MEG - Cam-CAN n 600) EEG - Temple Univ. Hospital n 1385) ξ M M T M M M' Log M Ex M Predictive regression modeling with MEG/EEG: From source power to signals and cognitive states P1609 When prediction performance is the priority iemannian em eddings may eat source localization Riemannian embeddings perform best on real data. Volume conduction prevents classical linear modeling when predicting from source power. Simulations: SF RE yield consistent regression. RE were more robust to model violations. RE yielded robust regression models. dea hen using a linear model like Ridge regression to predict outcomes y) from M/EEG ), replace biophysical source model with mathematical-statistical transformation to regress out volume conduction. e considered spatial lters SF) and Riemannian embeddings RE). Baseline: sensor space power upper) and log-power diag). Note For prediction at the subject-level we encounter severe model violations as each individual has her own head and brain. This breaks mathematical guarantees. See R code for NeurIPS paper) Note e benchmarked methods against age-prediction with ridge regression. ith source localization MNE) as transformation, diag performed best 7.7 yrs mean absolute error MAE) Note e compared regression models across different combinations of preprocessing steps: denoising SSP/SSS), ECG/E G artifacts, rejection of bad segments. e even ran models with no preprocessing at all. RE is a clear winner. Caveat: Additional analyses also suggest that RE is most in uenced by anatomical factors. distance from identity chance level 0.00 0.25 0.50 0.75 1.00 0.0 0.5 1.0 1.5 2.0 2.5 3.0 Normalized MAE noise on target 0.00 0.25 0.50 0.75 1.00 0.01 0.10 1.00 10.00 σ 0.00 0.25 0.50 0.75 1.00 upper diag SPoC Riemann noise on mixing matrix 0.01 0.10 1.00 σ OHBM 2020 Poster 1609

Slide 80

Slide 80 text

Summary What shall I remember?

Slide 81

Slide 81 text

Summary What shall I remember? 1. MEG contains unique information on age and cognitive aging

Slide 82

Slide 82 text

Summary What shall I remember? 1. MEG contains unique information on age and cognitive aging 2. MEG source power is a potent feature for predictive modeling

Slide 83

Slide 83 text

Summary What shall I remember? 1. MEG contains unique information on age and cognitive aging 2. MEG source power is a potent feature for predictive modeling 3. Tree-based methods bring flexible missing value handling

Slide 84

Slide 84 text

Summary What shall I remember? 1. MEG contains unique information on age and cognitive aging 2. MEG source power is a potent feature for predictive modeling 3. Tree-based methods bring flexible missing value handling 4. Statistical-mathematical shortcuts can help avoid source localization

Slide 85

Slide 85 text

Summary What shall I remember? 1. MEG contains unique information on age and cognitive aging 2. MEG source power is a potent feature for predictive modeling 3. Tree-based methods bring flexible missing value handling 4. Statistical-mathematical shortcuts can help avoid source localization 5. EEG may be substituted for MEG in age-prediction.

Slide 86

Slide 86 text

Thank you! Oleh Kozynets Guillaume Lemaître David Sabbagh Pierre Ablin Franz Liem Gaël Varoquaux Alexandre Gramfort Contact [email protected] www.denis-engemann.de github: @dengemann twitter: @dngman