Habibi MA, Fakhfouri A, Mirjani MS, Razavi A, Mortezaei A, Soleimani Y, Lotfi S, Arabi S, Heidaresfahani L, Sadeghi S, Minaee P, Eazi S, Rashidi F, Shafizadeh M, Majidi S. Prediction of cerebral aneurysm rupture risk by machine learning algorithms: a systematic review and meta-analysis of 18,670 participants. Neurosurg Rev. 2024 Jan 6;47(1):34. doi: 10.1007/s10143-023-02271-2. PMID: 38183490.
\n\"It is possible to identify unruptured intracranial aneurysms (UIA) using machine learning (ML) algorithms, which can be a life-saving strategy, especially in high-risk populations. To better understand the importance and effectiveness of ML algorithms in practice, a systematic review and meta-analysis were conducted to predict cerebral aneurysm rupture risk.\"
\n\"Eligibility criteria included studies that used ML approaches in patients with cerebral aneurysms confirmed by DSA, CTA, or MRI.\"
\n\"Out of 35 studies included, 33 were cohort, and 11 used digital subtraction angiography (DSA) as their reference imaging modality. Middle cerebral artery (MCA) and anterior cerebral artery (ACA) were the commonest locations of aneurysmal vascular involvement-51% and 40%, respectively.\"
\n\"The aneurysm morphology was saccular in 48% of studies. Ten of 37 studies (27%) used deep learning techniques such as CNNs and ANNs. Meta-analysis was performed on 17 studies: sensitivity of 0.83 (95% confidence interval (CI), 0.77-0.88); specificity of 0.83 (95% CI, 0.75-0.88); positive DLR of 4.81 (95% CI, 3.29-7.02) and the negative DLR of 0.20 (95% CI, 0.14-0.29); a diagnostic score of 3.17 (95% CI, 2.55-3.78); odds ratio of 23.69 (95% CI, 12.75-44.01).\"
\n\"ML algorithms can effectively predict the risk of rupture in cerebral aneurysms with good levels of accuracy, sensitivity, and specificity. However, further research is needed to enhance their diagnostic performance in predicting the rupture status of IA.\"
\nhttps://pubmed.ncbi.nlm.nih.gov/38183490/
", "messages": [ { "id": 3255564, "postDate": "2025-07-29T00:55:13.867Z", "content": "Habibi MA, Fakhfouri A, Mirjani MS, Razavi A, Mortezaei A, Soleimani Y, Lotfi S, Arabi S, Heidaresfahani L, Sadeghi S, Minaee P, Eazi S, Rashidi F, Shafizadeh M, Majidi S. Prediction of cerebral aneurysm rupture risk by machine learning algorithms: a systematic review and meta-analysis of 18,670 participants. Neurosurg Rev. 2024 Jan 6;47(1):34. doi: 10.1007/s10143-023-02271-2. PMID: 38183490.
\n\"It is possible to identify unruptured intracranial aneurysms (UIA) using machine learning (ML) algorithms, which can be a life-saving strategy, especially in high-risk populations. To better understand the importance and effectiveness of ML algorithms in practice, a systematic review and meta-analysis were conducted to predict cerebral aneurysm rupture risk.\"
\n\"Eligibility criteria included studies that used ML approaches in patients with cerebral aneurysms confirmed by DSA, CTA, or MRI.\"
\n\"Out of 35 studies included, 33 were cohort, and 11 used digital subtraction angiography (DSA) as their reference imaging modality. Middle cerebral artery (MCA) and anterior cerebral artery (ACA) were the commonest locations of aneurysmal vascular involvement-51% and 40%, respectively.\"
\n\"The aneurysm morphology was saccular in 48% of studies. Ten of 37 studies (27%) used deep learning techniques such as CNNs and ANNs. Meta-analysis was performed on 17 studies: sensitivity of 0.83 (95% confidence interval (CI), 0.77-0.88); specificity of 0.83 (95% CI, 0.75-0.88); positive DLR of 4.81 (95% CI, 3.29-7.02) and the negative DLR of 0.20 (95% CI, 0.14-0.29); a diagnostic score of 3.17 (95% CI, 2.55-3.78); odds ratio of 23.69 (95% CI, 12.75-44.01).\"
\n\"ML algorithms can effectively predict the risk of rupture in cerebral aneurysms with good levels of accuracy, sensitivity, and specificity. However, further research is needed to enhance their diagnostic performance in predicting the rupture status of IA.\"
\nhttps://pubmed.ncbi.nlm.nih.gov/38183490/
", "rawMarkdown": "## Prediction of cerebral aneurysm rupture risk by machine learning algorithms\n\n### Citation:\n\nHabibi MA, Fakhfouri A, Mirjani MS, Razavi A, Mortezaei A, Soleimani Y, Lotfi S, Arabi S, Heidaresfahani L, Sadeghi S, Minaee P, Eazi S, Rashidi F, Shafizadeh M, Majidi S. **Prediction of cerebral aneurysm rupture risk by machine learning algorithms**: a systematic review and meta-analysis of 18,670 participants. Neurosurg Rev. 2024 Jan 6;47(1):34. doi: 10.1007/s10143-023-02271-2. PMID: 38183490.\n\n\"It is possible to identify **unruptured intracranial aneurysms** (UIA) using machine learning (ML) algorithms, which can be a life-saving strategy, especially in high-risk populations. To better understand the importance and effectiveness of ML algorithms in practice, a systematic review and meta-analysis were conducted to predict cerebral aneurysm rupture risk.\"\n\n\"Eligibility criteria included studies that used ML approaches in patients with cerebral aneurysms confirmed by DSA, CTA, or MRI.\"\n\n\"Out of 35 studies included, 33 were cohort, and 11 used digital subtraction angiography (DSA) as their reference imaging modality. **Middle cerebral artery (MCA) and anterior cerebral artery (ACA)** were the commonest locations of aneurysmal vascular involvement-51% and 40%, respectively.\"\n\n\"The aneurysm morphology was saccular in 48% of studies. Ten of 37 studies (**27%) used deep learning** techniques such as CNNs and ANNs. **Meta-analysis** was performed on 17 studies: sensitivity of 0.83 (95% confidence interval (CI), 0.77-0.88); specificity of 0.83 (95% CI, 0.75-0.88); positive DLR of 4.81 (95% CI, 3.29-7.02) and the negative DLR of 0.20 (95% CI, 0.14-0.29); a diagnostic score of 3.17 (95% CI, 2.55-3.78); odds ratio of 23.69 (95% CI, 12.75-44.01).\"\n\n\"ML algorithms can effectively predict the risk of rupture in cerebral aneurysms with good levels of accuracy, sensitivity, and specificity. However, further research is needed to enhance their diagnostic performance in predicting the rupture status of IA.\"\n\nhttps://pubmed.ncbi.nlm.nih.gov/38183490/", "votes": 17 }, { "id": 3258164, "postDate": "2025-07-30T08:36:47.323Z", "content": "Good stuffs again @mpwolke
", "rawMarkdown": "Good stuffs again @mpwolke ", "votes": 1, "replies": [ { "id": 3258291, "postDate": "2025-07-30T13:51:26.220Z", "content": "We're always learning a little bit more Tom99763. Besides, only after Calabrese comment above, I realized that the Competition subject of attention is to Detect IAs (locations), and not their rupture risk.
\nThank you again : )
Thanks for sharing this reference. Please note that this competition focuses on detection, not rupture risk. This citation is still very relevant. Also, we did not exclude ruptured aneurysms as long as they were still clearly visible on imaging (as confirmed by multiple expert readers).
", "rawMarkdown": "Thanks for sharing this reference. Please note that this competition focuses on detection, not rupture risk. This citation is still very relevant. Also, we did not exclude ruptured aneurysms as long as they were still clearly visible on imaging (as confirmed by multiple expert readers).", "votes": 1, "replies": [ { "id": 3255873, "postDate": "2025-07-29T15:37:07.163Z", "content": "Hi Calabrese,
\nI posted this topic since it was the most recent paper that I found about IA (Intracranial Aneurysm) .
\nIn a hurry, I didn't noticed that the object of the competition was just IA detection and Not rupture.
\nMy bad, that's the issue when we try to be pro-active : (
\nBest regards,
\nMarília Prata.
Still very relevant! And a really interesting paper.
", "rawMarkdown": "Still very relevant! And a really interesting paper. ", "votes": 1 } ] } ] } ], "comments": [ { "id": 3258164, "author_name": "Tom", "author_url": "", "post_date": "2025-07-30T08:36:47.323000", "content": "Good stuffs again @mpwolke
", "votes": 1, "replies": [ { "id": 3258291, "author_name": "Marília Prata", "author_url": "", "post_date": "2025-07-30T13:51:26.220000", "content": "We're always learning a little bit more Tom99763. Besides, only after Calabrese comment above, I realized that the Competition subject of attention is to Detect IAs (locations), and not their rupture risk.
\nThank you again : )
Thanks for sharing this reference. Please note that this competition focuses on detection, not rupture risk. This citation is still very relevant. Also, we did not exclude ruptured aneurysms as long as they were still clearly visible on imaging (as confirmed by multiple expert readers).
", "votes": 1, "replies": [ { "id": 3255873, "author_name": "Marília Prata", "author_url": "", "post_date": "2025-07-29T15:37:07.163000", "content": "Hi Calabrese,
\nI posted this topic since it was the most recent paper that I found about IA (Intracranial Aneurysm) .
\nIn a hurry, I didn't noticed that the object of the competition was just IA detection and Not rupture.
\nMy bad, that's the issue when we try to be pro-active : (
\nBest regards,
\nMarília Prata.
Still very relevant! And a really interesting paper.
", "votes": 1, "replies": [] } ] } ] } ], "raw_markdown_by_id": { "3255564": "## Prediction of cerebral aneurysm rupture risk by machine learning algorithms\n\n### Citation:\n\nHabibi MA, Fakhfouri A, Mirjani MS, Razavi A, Mortezaei A, Soleimani Y, Lotfi S, Arabi S, Heidaresfahani L, Sadeghi S, Minaee P, Eazi S, Rashidi F, Shafizadeh M, Majidi S. **Prediction of cerebral aneurysm rupture risk by machine learning algorithms**: a systematic review and meta-analysis of 18,670 participants. Neurosurg Rev. 2024 Jan 6;47(1):34. doi: 10.1007/s10143-023-02271-2. PMID: 38183490.\n\n\"It is possible to identify **unruptured intracranial aneurysms** (UIA) using machine learning (ML) algorithms, which can be a life-saving strategy, especially in high-risk populations. To better understand the importance and effectiveness of ML algorithms in practice, a systematic review and meta-analysis were conducted to predict cerebral aneurysm rupture risk.\"\n\n\"Eligibility criteria included studies that used ML approaches in patients with cerebral aneurysms confirmed by DSA, CTA, or MRI.\"\n\n\"Out of 35 studies included, 33 were cohort, and 11 used digital subtraction angiography (DSA) as their reference imaging modality. **Middle cerebral artery (MCA) and anterior cerebral artery (ACA)** were the commonest locations of aneurysmal vascular involvement-51% and 40%, respectively.\"\n\n\"The aneurysm morphology was saccular in 48% of studies. Ten of 37 studies (**27%) used deep learning** techniques such as CNNs and ANNs. **Meta-analysis** was performed on 17 studies: sensitivity of 0.83 (95% confidence interval (CI), 0.77-0.88); specificity of 0.83 (95% CI, 0.75-0.88); positive DLR of 4.81 (95% CI, 3.29-7.02) and the negative DLR of 0.20 (95% CI, 0.14-0.29); a diagnostic score of 3.17 (95% CI, 2.55-3.78); odds ratio of 23.69 (95% CI, 12.75-44.01).\"\n\n\"ML algorithms can effectively predict the risk of rupture in cerebral aneurysms with good levels of accuracy, sensitivity, and specificity. However, further research is needed to enhance their diagnostic performance in predicting the rupture status of IA.\"\n\nhttps://pubmed.ncbi.nlm.nih.gov/38183490/", "3258164": "Good stuffs again @mpwolke ", "3255835": "Thanks for sharing this reference. Please note that this competition focuses on detection, not rupture risk. This citation is still very relevant. Also, we did not exclude ruptured aneurysms as long as they were still clearly visible on imaging (as confirmed by multiple expert readers)." } }