Mining the mind: Machine learning in brain research Matthias Treder - - PowerPoint PPT Presentation

▶
mining the mind machine learning in brain research
SMART_READER_LITE
LIVE PREVIEW

Mining the mind: Machine learning in brain research Matthias Treder - - PowerPoint PPT Presentation

Nov 17, 2022 237 likes •676 views

Introduction ML in BCI ML in brain research Ethics Mining the mind: Machine learning in brain research Matthias Treder 2016-12-16 Introduction ML in BCI ML in brain research Ethics Introduction ML in BCI ML in brain research Ethics M

slide-1
SLIDE 1

Introduction ML in BCI ML in brain research Ethics

Mining the mind: Machine learning in brain research

Matthias Treder 2016-12-16

slide-2
SLIDE 2

Introduction ML in BCI ML in brain research Ethics

slide-3
SLIDE 3

Introduction ML in BCI ML in brain research Ethics

MEASURING BRAIN ACTIVITY

image taken from: Astrand E, Wardak C and Ben Hamed S (2014). “Selective visual attention to drive cognitive brain–machine interfaces: from concepts to neurofeedback and rehabilitation applications” Front. Syst. Neurosci. 8:144

slide-4
SLIDE 4

Introduction ML in BCI ML in brain research Ethics

BCI = MACHINE LEARNING + REAL-TIME

NEUROIMAGING

slide-5
SLIDE 5

Introduction ML in BCI ML in brain research Ethics

BCI = MACHINE LEARNING + REAL-TIME

NEUROIMAGING

slide-6
SLIDE 6

Introduction ML in BCI ML in brain research Ethics

BCI = MACHINE LEARNING + REAL-TIME

NEUROIMAGING

slide-7
SLIDE 7

Introduction ML in BCI ML in brain research Ethics

BCI = MACHINE LEARNING + REAL-TIME

NEUROIMAGING

slide-8
SLIDE 8

Introduction ML in BCI ML in brain research Ethics

CORRECTING ERRORS IN MENTAL TYPEWRITERS

Schmidt, Blankertz, Treder (2012), BMC Neuroscience

slide-9
SLIDE 9

Introduction ML in BCI ML in brain research Ethics

CORRECTING ERRORS IN MENTAL TYPEWRITERS

Schmidt, Blankertz, Treder (2012), BMC Neuroscience

C A F

T i m e

Stimulation

slide-10
SLIDE 10

Introduction ML in BCI ML in brain research Ethics

CORRECTING ERRORS IN MENTAL TYPEWRITERS

Schmidt, Blankertz, Treder (2012), BMC Neuroscience

C A F

T i m e

Stimulation Classification

  • utput

C

correct error

slide-11
SLIDE 11

Introduction ML in BCI ML in brain research Ethics

CORRECTING ERRORS IN MENTAL TYPEWRITERS

−100 100 200 300 400 500 600 700 800 900 1000 10 20 [µV]

error correct fi fi

slide-12
SLIDE 12

Introduction ML in BCI ML in brain research Ethics

CORRECTING ERRORS IN MENTAL TYPEWRITERS

−100 100 200 300 400 500 600 700 800 900 1000 10 20 [µV]

error correct

Mean 0.1 0.2 0.3 0.4 0.5 0.6 0.7 0.8 0.9 1

AUC

Participant

Accuracy

ClassifierA ClassifierB 0.2 0.4 0.6 0.8 1 0.1 0.2 0.3 0.4 0.5 0.6 0.7 0.8 0.9 1 gbo / auc: 0.83 bad / auc: 0.85 iae / auc: 0.75 gbq / auc: 0.62 gbt / auc: 0.8 iac / auc: 0.83 gbn / auc: 0.82 gbw / auc: 0.87 iau / auc: 0.69 mk / auc: 0.69 fat / auc: 0.95 0.2 0.4 0.6 0.8 1 0.1 0.2 0.3 0.4 0.5 0.6 0.7 0.8 0.9 1 gbo / auc: 0.97 bad / auc: 0.97 iae / auc: 0.96 gbq / auc: 0.96 gbt / auc: 0.93 iac / auc: 0.91 gbn / auc: 0.87 gbw / auc: 0.84 iau / auc: 0.79 mk / auc: 0.75 fat / auc: 0.99

ROC classifier A ROC classifier B

False alarm rate False alarm rate Hit rate Hit rate

slide-13
SLIDE 13

Introduction ML in BCI ML in brain research Ethics

ML IN MEMORY RESEARCH

slide-14
SLIDE 14

Introduction ML in BCI ML in brain research Ethics

ML IN MEMORY RESEARCH

10 72 31 71 84 18 10 33 98 70 7 89 23 22 92 13 34 83 37 40 49 6 77 2 49 12

later forgotten later remembered later forgotten later remembered

?

Pre- encoding Encoding Post- encoding Retrieval

?

remembered remembered forgotten forgotten

slide-15
SLIDE 15

Introduction ML in BCI ML in brain research Ethics

ML IN MEMORY RESEARCH

slide-16
SLIDE 16

Introduction ML in BCI ML in brain research Ethics

NEUROETHICS

◮ Cellular, molecular, cognitive neuroscience

slide-17
SLIDE 17

Introduction ML in BCI ML in brain research Ethics

NEUROETHICS

◮ Cellular, molecular, cognitive neuroscience ◮ Incidental findings in healthy participants

slide-18
SLIDE 18

Introduction ML in BCI ML in brain research Ethics

NEUROETHICS

◮ Cellular, molecular, cognitive neuroscience ◮ Incidental findings in healthy participants ◮ Altering brain function (eg deep brain stimulation)

slide-19
SLIDE 19

Introduction ML in BCI ML in brain research Ethics

NEUROETHICS

◮ Cellular, molecular, cognitive neuroscience ◮ Incidental findings in healthy participants ◮ Altering brain function (eg deep brain stimulation) ◮ Brain enhancement

slide-20
SLIDE 20

Introduction ML in BCI ML in brain research Ethics

ETHICS IN BCI: EXPECTATIONS

◮ Traumatic brain injury: impaired capacity to judge costs/benefits

slide-21
SLIDE 21

Introduction ML in BCI ML in brain research Ethics

ETHICS IN BCI: EXPECTATIONS

◮ Traumatic brain injury: impaired capacity to judge costs/benefits ◮ Motor skills automatic, BCI operation requires sustained attention

and cognitive effort

slide-22
SLIDE 22

Introduction ML in BCI ML in brain research Ethics

ETHICS IN BCI: EXPECTATIONS

◮ Traumatic brain injury: impaired capacity to judge costs/benefits ◮ Motor skills automatic, BCI operation requires sustained attention

and cognitive effort

◮ High expectations due to media bias

slide-23
SLIDE 23

Introduction ML in BCI ML in brain research Ethics

ETHICS IN BCI: EXPECTATIONS

◮ Traumatic brain injury: impaired capacity to judge costs/benefits ◮ Motor skills automatic, BCI operation requires sustained attention

and cognitive effort

◮ High expectations due to media bias ◮ Psychological harm: distress, loss of behavioral control

slide-24
SLIDE 24

Introduction ML in BCI ML in brain research Ethics

ETHICS IN BCI: EXPECTATIONS

◮ Traumatic brain injury: impaired capacity to judge costs/benefits ◮ Motor skills automatic, BCI operation requires sustained attention

and cognitive effort

◮ High expectations due to media bias ◮ Psychological harm: distress, loss of behavioral control ◮ Selection: Equal opportunity for all vs failed expectations

slide-25
SLIDE 25

Introduction ML in BCI ML in brain research Ethics

ETHICS IN BCI: RESEARCH VS CLINICAL PRACTICE

slide-26
SLIDE 26

Introduction ML in BCI ML in brain research Ethics

ETHICS IN BCI: RESEARCH VS CLINICAL PRACTICE

slide-27
SLIDE 27

Introduction ML in BCI ML in brain research Ethics

ETHICS IN BCI: RESEARCH VS CLINICAL PRACTICE

Improvement: proof-of-concept and parameter tuning with volunteers, transfer to patients

image taken from: McCullagh P, Lightbody G, Zygierewicz J, Kernohan W. (2014). “Ethical challenges associated with the development and deployment of brain computer interface technology.” Neuroethics 7:109–122.

slide-28
SLIDE 28

Introduction ML in BCI ML in brain research Ethics

ETHICS IN BCI: BENEFITS AND RISKS

Trade-off: Levels of invasiveness

◮ EEG (noninvasive): e.g. motor cortex signals smeared

slide-29
SLIDE 29

Introduction ML in BCI ML in brain research Ethics

ETHICS IN BCI: BENEFITS AND RISKS

Trade-off: Levels of invasiveness

◮ EEG (noninvasive): e.g. motor cortex signals smeared ◮ ECog (epidural implant): risk of infection and hemorrhage

slide-30
SLIDE 30

Introduction ML in BCI ML in brain research Ethics

ETHICS IN BCI: BENEFITS AND RISKS

Trade-off: Levels of invasiveness

◮ EEG (noninvasive): e.g. motor cortex signals smeared ◮ ECog (epidural implant): risk of infection and hemorrhage ◮ Microelectrode array (subdural implant): risk of tissue death

slide-31
SLIDE 31

Introduction ML in BCI ML in brain research Ethics

ETHICS IN BCI: COMMUNICATION

◮ Patient groups

slide-32
SLIDE 32

Introduction ML in BCI ML in brain research Ethics

ETHICS IN BCI: COMMUNICATION

◮ Patient groups

◮ Minimally conscious: residual awareness

slide-33
SLIDE 33

Introduction ML in BCI ML in brain research Ethics

ETHICS IN BCI: COMMUNICATION

◮ Patient groups

◮ Minimally conscious: residual awareness ◮ Locked in: conscious but lack capacity for voluntary body motion

slide-34
SLIDE 34

Introduction ML in BCI ML in brain research Ethics

ETHICS IN BCI: COMMUNICATION

◮ Patient groups

◮ Minimally conscious: residual awareness ◮ Locked in: conscious but lack capacity for voluntary body motion

◮ Informed consent

slide-35
SLIDE 35

Introduction ML in BCI ML in brain research Ethics

ETHICS IN BCI: COMMUNICATION

◮ Patient groups

◮ Minimally conscious: residual awareness ◮ Locked in: conscious but lack capacity for voluntary body motion

◮ Informed consent

◮ ‘Talking’ via ML algorithm, rather than to the patient directly

slide-36
SLIDE 36

Introduction ML in BCI ML in brain research Ethics

ETHICS IN BCI: COMMUNICATION

◮ Patient groups

◮ Minimally conscious: residual awareness ◮ Locked in: conscious but lack capacity for voluntary body motion

◮ Informed consent

◮ ‘Talking’ via ML algorithm, rather than to the patient directly ◮ Caregivers might overestimate system (yes-no responses)

slide-37
SLIDE 37

Introduction ML in BCI ML in brain research Ethics

MINING THE BRAIN USING ML

slide-38
SLIDE 38

Introduction ML in BCI ML in brain research Ethics

MINING THE BRAIN USING ML

Privacy of thoughts

◮ unconscious intentions [Zander et al., Dec 2016, PNAS]

slide-39
SLIDE 39

Introduction ML in BCI ML in brain research Ethics

MINING THE BRAIN USING ML

Privacy of thoughts

◮ unconscious intentions [Zander et al., Dec 2016, PNAS] ◮ psychological traits

slide-40
SLIDE 40

Introduction ML in BCI ML in brain research Ethics

MINING THE BRAIN USING ML

Privacy of thoughts

◮ unconscious intentions [Zander et al., Dec 2016, PNAS] ◮ psychological traits ◮ neuromarketing

slide-41
SLIDE 41

Introduction ML in BCI ML in brain research Ethics

MINING THE BRAIN USING ML

Privacy of thoughts

◮ unconscious intentions [Zander et al., Dec 2016, PNAS] ◮ psychological traits ◮ neuromarketing ◮ brain fingerprinting

slide-42
SLIDE 42

Introduction ML in BCI ML in brain research Ethics

MINING THE BRAIN USING ML

Privacy of thoughts

◮ unconscious intentions [Zander et al., Dec 2016, PNAS] ◮ psychological traits ◮ neuromarketing ◮ brain fingerprinting ◮ ‘thought police’?

slide-43
SLIDE 43

Introduction ML in BCI ML in brain research Ethics

REFERENCES

Glannon W (2014). “Ethical issues with brain-computer interfaces.” Front Syst Neurosci 8:136. McCullagh P, Lightbody G, Zygierewicz J, Kernohan W. (2014). “Ethical challenges associated with the development and deployment

  • f brain computer interface technology.” Neuroethics 7:109–122.

Vlek RJ, Steines D, Szibbo D, Kübler A, Schneider M-J, Haselager P, Nijboer F (2012). “Ethical Issues in Brain–Computer Interface Research, Development, and Dissemination.” JNPT 36:94–99.