|
1
|
Kim JY, Choi HJ, Kim SH, Ju H. Improved differentiation of cavernous malformation and acute intraparenchymal hemorrhage on CT using an AI algorithm. Sci Rep 2024; 14:11818. [PMID: 38782974 PMCID: PMC11116413 DOI: 10.1038/s41598-024-61960-0] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/19/2024] [Accepted: 05/13/2024] [Indexed: 05/25/2024] Open
Abstract
This study aimed to evaluate the utility of an artificial intelligence (AI) algorithm in differentiating between cerebral cavernous malformation (CCM) and acute intraparenchymal hemorrhage (AIH) on brain computed tomography (CT). A retrospective, multireader, randomized study was conducted to validate the performance of an AI algorithm in differentiating AIH from CCM on brain CT. CT images of CM and AIH (< 3 cm) were identified from the database. Six blinded reviewers, including two neuroradiologists, two radiology residents, and two emergency department physicians, evaluated CT images from 288 patients (CCM, n = 173; AIH, n = 115) with and without AI assistance, comparing diagnostic performance. Brain CT interpretation with AI assistance resulted in significantly higher diagnostic accuracy than without (86.92% vs. 79.86%, p < 0.001). Radiology residents and emergency department physicians showed significantly improved accuracy of CT interpretation with AI assistance than without (84.21% vs. 75.35%, 80.73% vs. 72.57%; respectively, p < 0.05). Neuroradiologists showed a trend of higher accuracy with AI assistance in the interpretation but lacked statistical significance (95.83% vs. 91.67%, p = 0.56). The use of an AI algorithm can enhance the differentiation of AIH from CCM in brain CT interpretation, particularly for nonexperts in neuroradiology.
Collapse
Affiliation(s)
- Jung Youn Kim
- Department of Radiology, CHA Bundang Medical Center, CHA University, 59 Yatap-Ro, Bundang, Seongnam, Gyeonggi-Do, 13496, Republic of Korea
| | - Hye Jeong Choi
- Department of Radiology, CHA Bundang Medical Center, CHA University, 59 Yatap-Ro, Bundang, Seongnam, Gyeonggi-Do, 13496, Republic of Korea.
| | - Sang Heum Kim
- Department of Radiology, CHA Bundang Medical Center, CHA University, 59 Yatap-Ro, Bundang, Seongnam, Gyeonggi-Do, 13496, Republic of Korea
| | - Hwangseon Ju
- Department of Radiology, CHA Bundang Medical Center, CHA University, 59 Yatap-Ro, Bundang, Seongnam, Gyeonggi-Do, 13496, Republic of Korea
| |
Collapse
|
|
2
|
Li X, Jones P, Zhao M. Identifying potential (re)hemorrhage among sporadic cerebral cavernous malformations using machine learning. Sci Rep 2024; 14:11022. [PMID: 38745042 PMCID: PMC11094099 DOI: 10.1038/s41598-024-61851-4] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/08/2023] [Accepted: 05/10/2024] [Indexed: 05/16/2024] Open
Abstract
The (re)hemorrhage in patients with sporadic cerebral cavernous malformations (CCM) was the primary aim for CCM management. However, accurately identifying the potential (re)hemorrhage among sporadic CCM patients in advance remains a challenge. This study aims to develop machine learning models to detect potential (re)hemorrhage in sporadic CCM patients. This study was based on a dataset of 731 sporadic CCM patients in open data platform Dryad. Sporadic CCM patients were followed up 5 years from January 2003 to December 2018. Support vector machine (SVM), stacked generalization, and extreme gradient boosting (XGBoost) were used to construct models. The performance of models was evaluated by area under receiver operating characteristic curves (AUROC), area under the precision-recall curve (PR-AUC) and other metrics. A total of 517 patients with sporadic CCM were included (330 female [63.8%], mean [SD] age at diagnosis, 42.1 [15.5] years). 76 (re)hemorrhage (14.7%) occurred during follow-up. Among 3 machine learning models, XGBoost model yielded the highest mean (SD) AUROC (0.87 [0.06]) in cross-validation. The top 4 features of XGBoost model were ranked with SHAP (SHapley Additive exPlanations). All-Elements XGBoost model achieved an AUROCs of 0.84 and PR-AUC of 0.49 in testing set, with a sensitivity of 0.86 and a specificity of 0.76. Importantly, 4-Elements XGBoost model developed using top 4 features got a AUROCs of 0.83 and PR-AUC of 0.40, a sensitivity of 0.79, and a specificity of 0.72 in testing set. Two machine learning-based models achieved accurate performance in identifying potential (re)hemorrhages within 5 years in sporadic CCM patients. These models may provide insights for clinical decision-making.
Collapse
Affiliation(s)
- Xiaopeng Li
- Department of Neurology, The First Affiliated Hospital of Henan University, Kaifeng, China
| | - Peng Jones
- Independent Researcher, Xinyang, Henan, China
| | - Mei Zhao
- Department of Neurology, The First Affiliated Hospital of Nanchang University, No. 17 Yongwai Street, Nanchang, 330006, Jiangxi, China.
| |
Collapse
|
|
3
|
Xu S, Yang L. Diagnosis and treatment status of suprasellar optic pathway cavernous malformations. J Int Med Res 2023; 51:3000605231219167. [PMID: 38147640 PMCID: PMC10752090 DOI: 10.1177/03000605231219167] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/11/2023] [Accepted: 11/17/2023] [Indexed: 12/28/2023] Open
Abstract
Cerebral cavernous malformations constitute a subtype of cerebral vascular malformation typically located in the cerebral cortex. However, their occurrence in the suprasellar optic pathway is relatively rare. There is some uncertainty surrounding the clinical diagnostic methods and optimal treatment strategies specific to suprasellar optic pathway cavernous malformations. In this narrative review, we retrospectively analyzed relevant literature related to suprasellar visual pathway cavernous malformations. We conducted a study involving 90 patients who were postoperatively diagnosed with cavernous malformations, including the 16-year-old male patient mentioned in this article. We have summarized crucial clinical data, including the patient age distribution, sex ratio, lesion locations, primary symptoms, and surgical approaches. The comprehensive analysis of this clinical information underscores the critical importance of timely intervention in relieving symptoms and improving neurological deficits in affected patients. These findings provide valuable guidance and insight for clinical practitioners and researchers dealing with this specific medical condition.
Collapse
Affiliation(s)
- Songbai Xu
- Department of Neurosurgery, The First Hospital of Jilin University, Changchun, Jilin, P.R. China
| | - Liu Yang
- Department of Neurosurgery, The First Hospital of Jilin University, Changchun, Jilin, P.R. China
| |
Collapse
|
|
4
|
Theodorou A, Palaiodimou L, Papagiannopoulou G, Kargiotis O, Psychogios K, Safouris A, Bakola E, Chondrogianni M, Kotsali-Peteinelli V, Melanis K, Tsibonakis A, Andreadou E, Vasilopoulou S, Lachanis S, Velonakis G, Tzavellas E, Tzartos JS, Voumvourakis K, Paraskevas GP, Tsivgoulis G. Clinical Characteristics, Neuroimaging Markers, and Outcomes in Patients with Cerebral Amyloid Angiopathy: A Prospective Cohort Study. J Clin Med 2023; 12:5591. [PMID: 37685658 PMCID: PMC10488273 DOI: 10.3390/jcm12175591] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/04/2023] [Revised: 08/23/2023] [Accepted: 08/25/2023] [Indexed: 09/10/2023] Open
Abstract
Background and purpose: Sporadic cerebral amyloid angiopathy (CAA) is a small vessel disease, resulting from progressive amyloid-β deposition in the media/adventitia of cortical and leptomeningeal arterioles. We sought to assess the prevalence of baseline characteristics, clinical and radiological findings, as well as outcomes among patients with CAA, in the largest study to date conducted in Greece. Methods: Sixty-eight patients fulfilling the Boston Criteria v1.5 for probable/possible CAA were enrolled and followed for at least twelve months. Magnetic Resonance Imaging was used to assess specific neuroimaging markers. Data regarding cerebrospinal fluid biomarker profile and Apolipoprotein-E genotype were collected. Multiple logistic regression analyses were performed to identify predictors of clinical phenotypes. Cox-proportional hazard regression models were used to calculate associations with the risk of recurrent intracerebral hemorrhage (ICH). Results: Focal neurological deficits (75%), cognitive decline (57%), and transient focal neurological episodes (TFNEs; 21%) were the most common clinical manifestations. Hemorrhagic lesions, including lobar cerebral microbleeds (CMBs; 93%), cortical superficial siderosis (cSS; 48%), and lobar ICH (43%) were the most prevalent neuroimaging findings. cSS was independently associated with the likelihood of TFNEs at presentation (OR: 4.504, 95%CI:1.258-19.088), while multiple (>10) lobar CMBs were independently associated with cognitive decline at presentation (OR:5.418, 95%CI:1.316-28.497). cSS emerged as the only risk factor of recurrent ICH (HR:4.238, 95%CI:1.509-11.900) during a median follow-up of 20 months. Conclusions: cSS was independently associated with TFNEs at presentation and ICH recurrence at follow-up, while a higher burden of lobar CMBs with cognitive decline at baseline. These findings highlight the prognostic value of neuroimaging markers, which may influence clinical decision-making.
Collapse
Affiliation(s)
- Aikaterini Theodorou
- Second Department of Neurology, “Attikon” University Hospital, School of Medicine, National and Kapodistrian University of Athens, 12462 Athens, Greece; (A.T.); (L.P.); (G.P.); (E.B.); (M.C.); (V.K.-P.); (K.M.); (A.T.); (J.S.T.); (K.V.); (G.P.P.)
| | - Lina Palaiodimou
- Second Department of Neurology, “Attikon” University Hospital, School of Medicine, National and Kapodistrian University of Athens, 12462 Athens, Greece; (A.T.); (L.P.); (G.P.); (E.B.); (M.C.); (V.K.-P.); (K.M.); (A.T.); (J.S.T.); (K.V.); (G.P.P.)
| | - Georgia Papagiannopoulou
- Second Department of Neurology, “Attikon” University Hospital, School of Medicine, National and Kapodistrian University of Athens, 12462 Athens, Greece; (A.T.); (L.P.); (G.P.); (E.B.); (M.C.); (V.K.-P.); (K.M.); (A.T.); (J.S.T.); (K.V.); (G.P.P.)
| | - Odysseas Kargiotis
- Stroke Unit, Metropolitan Hospital, 18547 Piraeus, Greece; (O.K.); (K.P.); (A.S.)
| | - Klearchos Psychogios
- Stroke Unit, Metropolitan Hospital, 18547 Piraeus, Greece; (O.K.); (K.P.); (A.S.)
| | - Apostolos Safouris
- Stroke Unit, Metropolitan Hospital, 18547 Piraeus, Greece; (O.K.); (K.P.); (A.S.)
| | - Eleni Bakola
- Second Department of Neurology, “Attikon” University Hospital, School of Medicine, National and Kapodistrian University of Athens, 12462 Athens, Greece; (A.T.); (L.P.); (G.P.); (E.B.); (M.C.); (V.K.-P.); (K.M.); (A.T.); (J.S.T.); (K.V.); (G.P.P.)
| | - Maria Chondrogianni
- Second Department of Neurology, “Attikon” University Hospital, School of Medicine, National and Kapodistrian University of Athens, 12462 Athens, Greece; (A.T.); (L.P.); (G.P.); (E.B.); (M.C.); (V.K.-P.); (K.M.); (A.T.); (J.S.T.); (K.V.); (G.P.P.)
| | - Vasiliki Kotsali-Peteinelli
- Second Department of Neurology, “Attikon” University Hospital, School of Medicine, National and Kapodistrian University of Athens, 12462 Athens, Greece; (A.T.); (L.P.); (G.P.); (E.B.); (M.C.); (V.K.-P.); (K.M.); (A.T.); (J.S.T.); (K.V.); (G.P.P.)
| | - Konstantinos Melanis
- Second Department of Neurology, “Attikon” University Hospital, School of Medicine, National and Kapodistrian University of Athens, 12462 Athens, Greece; (A.T.); (L.P.); (G.P.); (E.B.); (M.C.); (V.K.-P.); (K.M.); (A.T.); (J.S.T.); (K.V.); (G.P.P.)
| | - Athanasios Tsibonakis
- Second Department of Neurology, “Attikon” University Hospital, School of Medicine, National and Kapodistrian University of Athens, 12462 Athens, Greece; (A.T.); (L.P.); (G.P.); (E.B.); (M.C.); (V.K.-P.); (K.M.); (A.T.); (J.S.T.); (K.V.); (G.P.P.)
| | - Elissavet Andreadou
- First Department of Neurology, “Eginition” Hospital, School of Medicine, National and Kapodistrian University of Athens, 11528 Athens, Greece; (E.A.); (S.V.)
| | - Sofia Vasilopoulou
- First Department of Neurology, “Eginition” Hospital, School of Medicine, National and Kapodistrian University of Athens, 11528 Athens, Greece; (E.A.); (S.V.)
| | - Stefanos Lachanis
- Iatropolis Magnetic Resonance Diagnostic Centre, 15231 Athens, Greece;
| | - Georgios Velonakis
- Second Department of Radiology, “Attikon” University Hospital, School of Medicine, National and Kapodistrian University of Athens, 12462 Athens, Greece;
| | - Elias Tzavellas
- First Department of Psychiatry, “Aiginition” Hospital, School of Medicine, National and Kapodistrian University of Athens, 11528 Athens, Greece;
| | - John S. Tzartos
- Second Department of Neurology, “Attikon” University Hospital, School of Medicine, National and Kapodistrian University of Athens, 12462 Athens, Greece; (A.T.); (L.P.); (G.P.); (E.B.); (M.C.); (V.K.-P.); (K.M.); (A.T.); (J.S.T.); (K.V.); (G.P.P.)
| | - Konstantinos Voumvourakis
- Second Department of Neurology, “Attikon” University Hospital, School of Medicine, National and Kapodistrian University of Athens, 12462 Athens, Greece; (A.T.); (L.P.); (G.P.); (E.B.); (M.C.); (V.K.-P.); (K.M.); (A.T.); (J.S.T.); (K.V.); (G.P.P.)
| | - Georgios P. Paraskevas
- Second Department of Neurology, “Attikon” University Hospital, School of Medicine, National and Kapodistrian University of Athens, 12462 Athens, Greece; (A.T.); (L.P.); (G.P.); (E.B.); (M.C.); (V.K.-P.); (K.M.); (A.T.); (J.S.T.); (K.V.); (G.P.P.)
| | - Georgios Tsivgoulis
- Second Department of Neurology, “Attikon” University Hospital, School of Medicine, National and Kapodistrian University of Athens, 12462 Athens, Greece; (A.T.); (L.P.); (G.P.); (E.B.); (M.C.); (V.K.-P.); (K.M.); (A.T.); (J.S.T.); (K.V.); (G.P.P.)
- Department of Neurology, University of Tennessee Health Science Center, Memphis, TN 38163, USA
| |
Collapse
|
|
5
|
Szczygieł-Pilut E, Pilut D, Korostynski M, Kopiński P, Potaczek DP, Wypasek E. The First Potentially Causal Genetic Variant Documented in a Polish Woman with Multiple Cavernous Malformations of the Brain. Genes (Basel) 2023; 14:1535. [PMID: 37628586 PMCID: PMC10454152 DOI: 10.3390/genes14081535] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/29/2023] [Revised: 07/23/2023] [Accepted: 07/25/2023] [Indexed: 08/27/2023] Open
Abstract
Cerebral cavernous malformations (CCMs) are relatively common in the central nervous system. They occur in two forms, sporadic and familial (FCCMs). Three genes are recognized to be associated with FCCM, including CCM1, CCM2, and CCM3, the latter also called PDCD10. In this article, we describe a single-nucleotide variant in the PDCD10 gene in a 23-year-old Polish female with CCM. The NM_007217.4 (PDCD10): c.395+1G>A variant destroys the canonical splice donor site following exon 6. This is the first reported genetically characterized case of CCM (FCCM) in Poland.
Collapse
Affiliation(s)
- Elżbieta Szczygieł-Pilut
- Department of Neurology with the Stroke Unit and Sub-Department of Neurological Rehabilitation, John Paul II Hospital, 31-202 Krakow, Poland;
- Department of Psychology and Psychopathology of Human Development, Faculty of Philosophy, John Paul II Pontifical University, 31-002 Krakow, Poland
| | - Daniel Pilut
- Individual Clinical Practice, 31-534 Krakow, Poland;
| | - Michal Korostynski
- Laboratory of Pharmacogenomics, Department of Molecular Neuropharmacology, Maj Institute of Pharmacology, Polish Academy of Sciences, 31-343 Krakow, Poland;
| | - Piotr Kopiński
- Department of Lung Diseases, Cancer and Tuberculosis, Collegium Medicum, Nicolaus Copernicus University, 85-067 Bydgoszcz, Poland;
- Krakow Center for Medical Research and Technology, John Paul II Hospital, 31-202 Krakow, Poland
| | - Daniel P. Potaczek
- Translational Inflammation Research Division & Core Facility for Single Cell Multiomics, Medical Faculty, Philipps University Marburg, 35043 Marburg, Germany
- Center for Infection and Genomics of the Lung (CIGL), Universities of Giessen and Marburg Lung Center (UGMLC), 35392 Giessen, Germany
- Bioscientia MVZ Labor Mittelhessen GmbH, 35394 Giessen, Germany
| | - Ewa Wypasek
- Krakow Center for Medical Research and Technology, John Paul II Hospital, 31-202 Krakow, Poland
- Faculty of Medicine and Health Sciences, Andrzej Frycz Modrzewski Krakow University, 30-705 Kraków, Poland
| |
Collapse
|