Artificial Intelligence Flashcards

1
Q

TRUE or FALSE: artificial intelligence (AI) exists

A

FALSE: AI does not exist, and may never exist

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

What is machine learning (ML)?

A

“a logical contradiction, and thus nonsense”

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

What is deep learning?

A

“learning”

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

Arrange the following from oldest to newest (in terms of when these concepts came into existence): artificial intelligence, deep learning, machine learning

A

artificial intelligence > machine learning > deep learning

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

How many people are challenged by mental illness in Canada? Provide a number and a percentage.

A
  • 20-25%
  • 6.7 million +
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

How many people are challenged by mental illness in Alberta? Provide a number and a percentage.

A
  • 25%
  • 1 million +
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

TRUE or FALSE: there are more people with heart disease and diabetes in Canada than there are people with mental illness.

A

FALSE: there are MORE people with MENTAL ILLNESS than there are people with heart disease and diabetes in Canada

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

What are the limits in mental health services?

A
  • symptom-biased diagnosis
  • low-efficiency high-cost treatment (trial and error)
  • lack of accessible long-term support
  • complexity of mental illness and limited information (personal, populational, longitudinal level)
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

How does machine learning work? Provide an example.

A
  1. models are inputted (e.g. atrophied and normal brains)
  2. put a line in the space between the distinct models (i.e. line = modifier)
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

what is the difference between supervised and unsupervised learning?

A
  • supervised: human teaches the machine to label clusters (e.g. apples and strawberries)
  • unsupervised: no human labelling; machine defines distinct groups as clusters (e.g. cluster 1 and cluster 2)
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

Why use machine learning? (i.e. what are the benefits?)

A
  1. predictivity (individual-level prediction)
  2. generalizability (cross-validation, avoid over-fitting)
  3. finding the best features
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

TRUE or FALSE: in machine learning, significance = individual prediction

A

FALSE: significance does NOT equal individual prediction

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

TRUE or FALSE: machine learning can predict treatment response to ECT with hippocampal subfield volumes

A

TRUE

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

Machine learning can be used to identify life-time suicide attempters. What percentage of predicted non-attempters are actual non-attempters?

A

69%

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

Machine learning can be used to identify life-time suicide attempters. What percentage of predicted non-attempters are actual attempters?

A

31%

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q

Machine learning can be used to identify life-time suicide attempters. What percentage of predicted attempters are actual non-attempters?

A

28%

17
Q

Machine learning can be used to identify life-time suicide attempters. What percentage of predicted attempters are actual attempters?

A

72%

18
Q

TRUE or FALSE: machine learning is used in administrative health data

A

TRUE

19
Q

In collaboration with Alberta Health, machine learning has been used to predict what mental health data? The preliminary analysis achieved what percentage of accuracy of individual prediction of OUD?

A

opioid use disorder (OUD); 86%

20
Q

What percentage of predicted non-OUD individuals are actual non-OUD individuals?

A

79%

21
Q

What percentage of predicted non-OUD individuals are actual OUD individuals?

A

7%

22
Q

What percentage of predicted OUD individuals are actual non-OUD individuals?

A

21%

23
Q

What percentage of predicted OUD individuals are actual OUD individuals?

A

93%

24
Q

What are some ongoing machine learning projects?

A
  1. health administration data and medical records
  2. clinical trials
  3. genetic imaging
  4. aging
25
Q

What are the 2 components of computational psychiatry?

A

theory driven and data driven