vocab

Question 1

What term describes having multiple long-term conditions?

Answer 1

Multimorbidity

Question 2

What was the Turing test?

Answer 2

Game where interrogator differentiates between a human and a computer based on questions

Question 3

What did the Turing test predict?

Answer 3

Within 50 years, computers would win 70% of the time

Question 4

What does MAAS stand for?

Answer 4

Multi-agency advice service

Question 5

What 4 organizations does MAAS join together?

Answer 5

NICE, MHRA, HRA, CQC

Question 6

What is it called when too many different variables affect predictions?

Answer 6

Overfitting

Question 7

What is synthetic data and what’s its purpose?

Answer 7

Fake data to protect privacy

Question 8

What are 2 examples of front-end?

Answer 8

Patient registration and insurance verification

Question 9

What is included in the mid-cycle?

Answer 9

Coding of claims

Question 10

What is included in the back-end?

Answer 10

Billing and collections

Question 11

What is the reconciliation of different data sources into a single output called?

Answer 11

Data harmonization

Question 12

What is palliative care?

Answer 12

Care for patients with serious illnesses

Question 13

What does ICO stand for? what does it do?

Answer 13

Information commissioner’s office; makes guidelines on how data can be collected and used

Question 14

What is frailty (as defined by British Geriatrics Society)?

Answer 14

State of health in aging where body systems lose their in-built reserves and cannot cope with illnesses

Question 15

Is frailty higher in men or women?

Answer 15

Women

Question 16

Are frailty and prefrailty higher in older adults in upper middle-income countries or high-income countries?

Answer 16

Upper middle

Question 17

What is brittleness as it refers to algorithms?

Answer 17

When algorithms cannot generalize outside a narrow set of conditions

Question 18

What is digital exclusion?

Answer 18

When people don’t have the skills to use digital devices or access to technology

Question 19

What is semi supervised learning?

Answer 19

Using a small, labelled dataset to learn and apply those to a larger unlabelled dataset

Question 20

What is drift?

Answer 20

AI could change due to the learning nature of the algorithms, so you need to constantly update it

Question 21

What is generalisability?

Answer 21

applicability of a study to other contexts (refers to the extent to which a model made in one place can be run in another place)

Question 22

What is interopability?

Answer 22

not being limited to a certain vendor’s predictive model (which may have been trained with a specific set of data)

Question 23

What is cardioversion?

Answer 23

a procedure to restore the normal rhythm of the heart; nurse needs to be there before and after to take the measurement but if they miss it, they lose the patient from clinical studies

Question 24

What is metadata?

Answer 24

references and information about the characteristics of data

Question 25

What is transfer learning?
how was it used?

Answer 25

training on a large dataset and then retraining the model on a smaller specific dataset → improves generalization of an AI

Researchers in India used transfer learning to identify kidneys in ultrasound scans using only 45 training examples

Question 26

what is good about dynamic procurement systems (DPS)?

Answer 26

align better with the fast-changing environment of AI digital solutions

Question 27

DAIS

Answer 27

data, analysis, and intelligence service

Question 28

OMOP data model

Answer 28

structures and harmonizes healthcare data sources (e.g. EHRs) into a database