Class: PerformanceMetric

One reported performance measure of a decoding analysis, and its value.

URI: neurostudy:PerformanceMetric

 classDiagram
    class PerformanceMetric
    click PerformanceMetric href "../PerformanceMetric/"
      PerformanceMetric : name

      PerformanceMetric : reference_value

      PerformanceMetric : relation





        PerformanceMetric --> "0..1" PerformanceRelation : relation
        click PerformanceRelation href "../PerformanceRelation/"



      PerformanceMetric : value

Slots

Name	Cardinality and Range	Description	Inheritance
name	1 String	The measure as the source names it, such as accuracy, balanced accuracy, AUC,...	direct
value	0..1 Float	The value as reported, in the source's own scale: a percentage and a proporti...	direct
reference_value	0..1 Float	Numeric reference this measure was compared against, when reported -- chance ...	direct
relation	0..1 PerformanceRelation	Direction of this measure relative to its own reference_value	direct

Usages

used by	used in	type	used
DecodingDetails	performance_metrics	range	PerformanceMetric

Identifier and Mapping Information

Schema Source

• from schema: https://neurostuff.org/schemas/neuroimaging-study-storage

Mappings

Mapping Type	Mapped Value
self	neurostudy:PerformanceMetric
native	neurostudy:PerformanceMetric

LinkML Source

Direct

name: PerformanceMetric
description: One reported performance measure of a decoding analysis, and its value.
from_schema: https://neurostuff.org/schemas/neuroimaging-study-storage
rank: 1000
attributes:
  name:
    name: name
    description: The measure as the source names it, such as accuracy, balanced accuracy,
      AUC, d-prime, sensitivity, specificity, or a correlation between predicted and
      observed scores.
    in_subset:
    - mvp
    - model_extracted
    from_schema: https://neurostuff.org/schemas/neuroimaging-study-storage/analysis_details
    domain_of:
    - Arm
    - Timepoint
    - Group
    - Task
    - Condition
    - Assessment
    - Region
    - Analysis
    - ModelTerm
    - ExternalDataset
    - PerformanceMetric
    range: string
    required: true
  value:
    name: value
    description: 'The value as reported, in the source''s own scale: a percentage
      and a proportion are both recorded as written rather than converted, since the
      scale is not always stated and converting would invent precision.'
    in_subset:
    - mvp
    - model_extracted
    from_schema: https://neurostuff.org/schemas/neuroimaging-study-storage/analysis_details
    rank: 1000
    domain_of:
    - PerformanceMetric
    range: float
  reference_value:
    name: reference_value
    description: 'Numeric reference this measure was compared against, when reported
      -- chance for an accuracy, zero for a correlation. Each measure carries its
      own: accuracy against chance and AUC against 0.5 are two references, not one.
      `relation` says which side of it the measure fell on.'
    in_subset:
    - model_extracted
    from_schema: https://neurostuff.org/schemas/neuroimaging-study-storage/analysis_details
    rank: 1000
    domain_of:
    - PerformanceMetric
    range: float
  relation:
    name: relation
    description: Direction of this measure relative to its own reference_value.
    in_subset:
    - model_extracted
    from_schema: https://neurostuff.org/schemas/neuroimaging-study-storage/analysis_details
    rank: 1000
    domain_of:
    - PerformanceMetric
    range: PerformanceRelation

Induced

name: PerformanceMetric
description: One reported performance measure of a decoding analysis, and its value.
from_schema: https://neurostuff.org/schemas/neuroimaging-study-storage
rank: 1000
attributes:
  name:
    name: name
    description: The measure as the source names it, such as accuracy, balanced accuracy,
      AUC, d-prime, sensitivity, specificity, or a correlation between predicted and
      observed scores.
    in_subset:
    - mvp
    - model_extracted
    from_schema: https://neurostuff.org/schemas/neuroimaging-study-storage/analysis_details
    owner: PerformanceMetric
    domain_of:
    - Arm
    - Timepoint
    - Group
    - Task
    - Condition
    - Assessment
    - Region
    - Analysis
    - ModelTerm
    - ExternalDataset
    - PerformanceMetric
    range: string
    required: true
  value:
    name: value
    description: 'The value as reported, in the source''s own scale: a percentage
      and a proportion are both recorded as written rather than converted, since the
      scale is not always stated and converting would invent precision.'
    in_subset:
    - mvp
    - model_extracted
    from_schema: https://neurostuff.org/schemas/neuroimaging-study-storage/analysis_details
    rank: 1000
    owner: PerformanceMetric
    domain_of:
    - PerformanceMetric
    range: float
  reference_value:
    name: reference_value
    description: 'Numeric reference this measure was compared against, when reported
      -- chance for an accuracy, zero for a correlation. Each measure carries its
      own: accuracy against chance and AUC against 0.5 are two references, not one.
      `relation` says which side of it the measure fell on.'
    in_subset:
    - model_extracted
    from_schema: https://neurostuff.org/schemas/neuroimaging-study-storage/analysis_details
    rank: 1000
    owner: PerformanceMetric
    domain_of:
    - PerformanceMetric
    range: float
  relation:
    name: relation
    description: Direction of this measure relative to its own reference_value.
    in_subset:
    - model_extracted
    from_schema: https://neurostuff.org/schemas/neuroimaging-study-storage/analysis_details
    rank: 1000
    owner: PerformanceMetric
    domain_of:
    - PerformanceMetric
    range: PerformanceRelation