Skip to main content
. 2024 Nov 15;35(1):3–16. doi: 10.1007/s00062-024-01474-4

Table 2.

Summary of findings for existing studies applying machine learning to predict unruptured intracranial aneurysm ‘stability’. The authors defined stability as a composite outcome which included rupture as well as aneurysm growth and/or presence of symptoms

Publication Study Design Modality Reference standard Time period of risk assessment Definition of stability Comparison to clinical practice Index test Model features Hold-out test set (n)
(or other specified dataset)
Hold-out test set performance accuracy
(or performance of other specified dataset)

Liu et al.

2019 [28]

Development and prospective validation DSA Comparison to result (stable/unstable) 1 month stability assessment (follow-up median: 11.5 months, range: 3–26 months)

1. Remained unruptured

2. No UIA growth

3. Asymptomatic

1. Generalized linear model*

2. Ridge regression

3. Logistic regression

(1) Clinical features

(2) Morphological features

IV: 124 AUC: 0.86

Zhu, et al.

2020 [29]

Development and retrospective validation 3D-DSA Comparison to result (stable/unstable) 1 month stability assessment (median follow up 15.6 months; range 5–39 months)

1. Remained unruptured

2. No UIA growth

1. Neural Network*

2. Random forest

3. SVM

(1) Clinical features

(2) Morphological features

IV: 411

Accuracy: 0.82

Balanced Accuracy: 0.72

Sensitivity: 0.52

Specificity: 0.93

AUC:0.87

PPV: 0.71

NPV: 0.85

F1 Score: 0.60

Yang, et al.

2021 [30]

Development and prospective validation CTA Comparison to result (stable/unstable) 3 years

1. Remained unruptured

2. UIA Growth ≤ 20%

Comparison made to PHASES, ELAPSS, UIATS and IARS Score 1. Neural network

(1) Clinical features

(2) Morphological features

(3) Hemodynamic features

IV: 37

(9-fold cross validation on training data, no hold-out test set per se)

AUC: 0.83
Liu, et al. 2022 [31] Development and prospective validation CTA Comparison to result (stable/unstable) 2 years

1. Remained unruptured

2. UIA of aneurysm < 20% or < 1 mm

Comparison made to PHASES and ELAPSS 1. Logistic regression

(1) Clinical features

(2) Morphological features

(3) Hemodynamic features

IV: 97 AUC: 0.94
Zhang, et al. 2023 [32] Development and retrospective validation

CTA/

MRA

Comparison to result (stable/unstable) 2 years

1. Remained unruptured

2. No IA growth

3. Asymptomatic

1. SVM*

2. Logistic regression

3. Adaboost

(1) Hemodynamic features EV: 54

Accuracy: 0.83

Balanced Accuracy: 0.83

Sensitivity: 0.83

Specificity: 0.83

AUC: 0.89

PPV: 0.71

NPV: 0.91

F1 Score: 0.77

Irfan, et al. 2023 [33] Development only DSA Comparison to risk interpretation of the UIAs was conducted by expert neurosurgeons Duration not stated Not defined Comparison to neurosurgeon expert opinions for reference standard

Combination model:

1. Neural network

2. Decision tree classifier

(1) Morphological features

(2) Hemodynamic features

IV: 141

Accuracy: 0.85

Balanced Accuracy: 0.85

Sensitivity: 0.84

Specificity: 0.86

AUC: 0.93

PPV: 0.82

NPV: 0.87

F1 Score: 0.83