Skip to main content

Table 3 PROBAST

From: Machine learning methods for functional recovery prediction and prognosis in post-stroke rehabilitation: a systematic review

Criteria

Specification of the review question

Step 1: Specify your systematic review question

 Intended use of the model:

Prediction of functional outcome after rehabilitation treatment of post-stroke patients

 Participants:

Adults post-stroke participants selected independently on the timing of the event or type of stroke

 Predictors:

Any kind of predictor was included, more specifically any type included in the following categories of stroke assessment: biomechanical assessment, functional assessment, demographic characteristics, medical history, stroke assessment and neurological assessment. The selected predictors are related to the admission or recovery phase only, excluding predictors variables collected at discharge

 Outcome:

Any kind of functional outcome, not exclusively cognitive or sensory-related was selected

Study

Outcome

Type of prediction study

Step 2: Classify the type of prediction model evaluation

 Almubark et al.

Upper extremity home use

Development only

 Bates et al.

Physical grade achievement

Development only

 Berlowitz et al.

Functional outcome

Development only

 Bland et al.

Walking ability

Development only

 Cheng et al.

Recovery

Development only

 Li et al.

Functional status

Development only

 De Marchis et al.

Unfavourable functional outcome

Development and validation

 De Ridder et al.

Disability and functional outcome

Development and validation

 George et al.

Extent of motor recovery after constraint-induced movement therapy

Development only

 König et al.

Functional independence

Development and validation

 Kuceyeski et al.

Clinical performance

Development only

 Abdel Majeed et al.

Change in clinical outcomes

Development only

 Masiero et al.

Ambulation

Development only

 Mostafavi et al.

Assessment of impairment

Development only

 Sale et al.

Motor improvement

Development only

 Scrutinio, Lanzillo, et al.

Functional status

Development only

 Scrutinio, Guida, et al.

Treatment failure

Development only

 Sonoda et al.

Stroke outcome

Development only

 Zariffa et al.

Measure of upper-limb function

Development only

Domain

Risk of bias (number of models)

Applicability (number of models)

Dev

Val

Dev

Val

Step 3: Assess risk of bias and applicability

 Participants

High = 0

Unclear = 0

Low = 174

High = 0

Unclear = 0

Low = 174

High = 0

Unclear = 0

Low = 174

High = 0

Unclear = 0

Low = 174

 Predictors

High = 1

Unclear = 0

Low = 173

High = 1

Unclear = 0

Low = 173

High = 1

Unclear = 0

Low = 173

High = 1

Unclear = 0

Low = 173

 Outcome

High = 24

Unclear = 120

Low = 30

High = 24

Unclear = 120

Low = 30

High = 24

Unclear = 119

Low = 31

High = 24

Unclear = 119

Low = 31

 Analysis

High = 77

Unclear = 8

Low = 89

 Overall

High = 85

Unclear = 67

Low = 22

High = 35

Unclear = 110

Low = 29

  1. A short table containing the details on the four steps of the evaluation is reported