1
|
Huang K, Li H, Tu S, Du J, Yao W, Liu R, Han Y, Ye R, Suo S, Zhu W, Liu X. Angiography‑based quantitative flow ratio for functional assessment of intracranial atherosclerotic disease. EUROINTERVENTION 2024; 20:e312-e321. [PMID: 38436369 PMCID: PMC10905197 DOI: 10.4244/eij-d-23-00611] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 07/30/2023] [Accepted: 12/04/2023] [Indexed: 03/05/2024]
Abstract
BACKGROUND Intracranial atherosclerotic stenosis (ICAS), an important cause of stroke, is associated with a considerable stroke recurrence rate despite optimal medical treatment. Further assessment of the functional significance of ICAS is urgently needed to enable individualised treatment and, thus, improve patient outcomes. AIMS We aimed to evaluate the haemodynamic significance of ICAS using the quantitative flow ratio (QFR) technique and to develop a risk stratification model for ICAS patients. METHODS Patients with moderate to severe stenosis of the middle cerebral artery, as shown on angiography, were retrospectively enrolled. For haemodynamic assessment, the Murray law-based QFR (μQFR) was performed on eligible patients. Multivariate logistic regression models composed of μQFR and other risk factors were developed and compared for the identification of symptomatic lesions. Based on the superior model, a nomogram was established and validated by calibration. RESULTS Among 412 eligible patients, symptomatic lesions were found in 313 (76.0%) patients. The μQFR outperformed the degree of stenosis in discriminating culprit lesions (area under the curve [AUC]: 0.726 vs 0.631; DeLong test p-value=0.001), and the model incorporating μQFR and conventional risk factors also performed better than that containing conventional risk factors only (AUC: 0.850 vs 0.827; DeLong test p-value=0.034; continuous net reclassification index=0.620, integrated discrimination improvement=0.057; both p<0.001). The final nomogram showed good calibration (p for Hosmer-Lemeshow test=0.102) and discrimination (C-statistic 0.850, 95% confidence interval: 0.812-0.883). CONCLUSIONS The μQFR was significantly associated with symptomatic ICAS and outperformed the angiographic stenosis severity. The final nomogram effectively discriminated symptomatic lesions and may provide a useful tool for risk stratification in ICAS patients.
Collapse
Affiliation(s)
- Kangmo Huang
- Department of Neurology, Nanjing Jinling Hospital, Affiliated Hospital of Medical School, Nanjing University, Nanjing, China
| | - Haotao Li
- Department of Neurology, Changshu No.2 People's Hospital, Changshu, China
| | - Shengxian Tu
- Biomedical Instrument Institute, School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai, China
| | - Juan Du
- Department of Neurology, Nanjing Jinling Hospital, Affiliated Hospital of Medical School, Nanjing University, Nanjing, China
| | - Weihe Yao
- Department of Neurology, Nanjing Jinling Hospital, Affiliated Hospital of Medical School, Nanjing University, Nanjing, China
| | - Rui Liu
- Department of Neurology, Nanjing Jinling Hospital, Affiliated Hospital of Medical School, Nanjing University, Nanjing, China
| | - Yunfei Han
- Department of Neurology, Nanjing Jinling Hospital, Affiliated Hospital of Medical School, Nanjing University, Nanjing, China
| | - Ruidong Ye
- Department of Neurology, Nanjing Jinling Hospital, Affiliated Hospital of Medical School, Nanjing University, Nanjing, China
| | - Shiteng Suo
- Biomedical Instrument Institute, School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai, China
- Department of Radiology, Renji Hospital, School of Medicine, Shanghai Jiao Tong University, Shanghai, China
| | - Wusheng Zhu
- Department of Neurology, Nanjing Jinling Hospital, Affiliated Hospital of Medical School, Nanjing University, Nanjing, China
| | - Xinfeng Liu
- Department of Neurology, Nanjing Jinling Hospital, Affiliated Hospital of Medical School, Nanjing University, Nanjing, China
- Stroke Center & Department of Neurology, The First Affiliated Hospital of USTC, Division of Life Sciences and Medicine, University of Science and Technology of China, Hefei, China
| |
Collapse
|
2
|
Rusche T, Wasserthal J, Breit HC, Fischer U, Guzman R, Fiehler J, Psychogios MN, Sporns PB. Machine Learning for Onset Prediction of Patients with Intracerebral Hemorrhage. J Clin Med 2023; 12:jcm12072631. [PMID: 37048712 PMCID: PMC10094957 DOI: 10.3390/jcm12072631] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/16/2023] [Revised: 03/13/2023] [Accepted: 03/30/2023] [Indexed: 04/03/2023] Open
Abstract
Objective: Intracerebral hemorrhage (ICH) has a high mortality and long-term morbidity and thus has a significant overall health–economic impact. Outcomes are especially poor if the exact onset is unknown, but reliable imaging-based methods for onset estimation have not been established. We hypothesized that onset prediction of patients with ICH using artificial intelligence (AI) may be more accurate than human readers. Material and Methods: A total of 7421 computed tomography (CT) datasets between January 2007–July 2021 from the University Hospital Basel with confirmed ICH were extracted and an ICH-segmentation algorithm as well as two classifiers (one with radiomics, one with convolutional neural networks) for onset estimation were trained. The classifiers were trained based on the gold standard of 644 datasets with a known onset of >1 and <48 h. The results of the classifiers were compared to the ratings of two radiologists. Results: Both the AI-based classifiers and the radiologists had poor discrimination of the known onsets, with a mean absolute error (MAE) of 9.77 h (95% CI (confidence interval) = 8.52–11.03) for the convolutional neural network (CNN), 9.96 h (8.68–11.32) for the radiomics model, 13.38 h (11.21–15.74) for rater 1 and 11.21 h (9.61–12.90) for rater 2, respectively. The results of the CNN and radiomics model were both not significantly different to the mean of the known onsets (p = 0.705 and p = 0.423). Conclusions: In our study, the discriminatory power of AI-based classifiers and human readers for onset estimation of patients with ICH was poor. This indicates that accurate AI-based onset estimation of patients with ICH based only on CT-data may be unlikely to change clinical decision making in the near future. Perhaps multimodal AI-based approaches could improve ICH onset prediction and should be considered in future studies.
Collapse
Affiliation(s)
- Thilo Rusche
- Department of Neuroradiology, Clinic of Radiology & Nuclear Medicine, University Hospital Basel, 4031 Basel, Switzerland
- Correspondence:
| | - Jakob Wasserthal
- Department of Neuroradiology, Clinic of Radiology & Nuclear Medicine, University Hospital Basel, 4031 Basel, Switzerland
| | - Hanns-Christian Breit
- Department of Neuroradiology, Clinic of Radiology & Nuclear Medicine, University Hospital Basel, 4031 Basel, Switzerland
| | - Urs Fischer
- Department of Neurology, University Hospital Basel, 4031 Basel, Switzerland
| | - Raphael Guzman
- Department of Neurosurgery, University Hospital Basel, 4031 Basel, Switzerland
| | - Jens Fiehler
- Department of Diagnostic and Interventional Neuroradiology, University Medical Center Hamburg-Eppendorf, 55131 Hamburg, Germany
| | - Marios-Nikos Psychogios
- Department of Neuroradiology, Clinic of Radiology & Nuclear Medicine, University Hospital Basel, 4031 Basel, Switzerland
| | - Peter B. Sporns
- Department of Neuroradiology, Clinic of Radiology & Nuclear Medicine, University Hospital Basel, 4031 Basel, Switzerland
- Department of Diagnostic and Interventional Neuroradiology, University Medical Center Hamburg-Eppendorf, 55131 Hamburg, Germany
- Department of Radiology and Neuroradiology, Stadtspital Zürich, 8063 Zürich, Switzerland
| |
Collapse
|
3
|
Visco V, Izzo C, Mancusi C, Rispoli A, Tedeschi M, Virtuoso N, Giano A, Gioia R, Melfi A, Serio B, Rusciano MR, Di Pietro P, Bramanti A, Galasso G, D’Angelo G, Carrizzo A, Vecchione C, Ciccarelli M. Artificial Intelligence in Hypertension Management: An Ace up Your Sleeve. J Cardiovasc Dev Dis 2023; 10:jcdd10020074. [PMID: 36826570 PMCID: PMC9963880 DOI: 10.3390/jcdd10020074] [Citation(s) in RCA: 6] [Impact Index Per Article: 6.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/27/2022] [Revised: 02/05/2023] [Accepted: 02/07/2023] [Indexed: 02/11/2023] Open
Abstract
Arterial hypertension (AH) is a progressive issue that grows in importance with the increased average age of the world population. The potential role of artificial intelligence (AI) in its prevention and treatment is firmly recognized. Indeed, AI application allows personalized medicine and tailored treatment for each patient. Specifically, this article reviews the benefits of AI in AH management, pointing out diagnostic and therapeutic improvements without ignoring the limitations of this innovative scientific approach. Consequently, we conducted a detailed search on AI applications in AH: the articles (quantitative and qualitative) reviewed in this paper were obtained by searching journal databases such as PubMed and subject-specific professional websites, including Google Scholar. The search terms included artificial intelligence, artificial neural network, deep learning, machine learning, big data, arterial hypertension, blood pressure, blood pressure measurement, cardiovascular disease, and personalized medicine. Specifically, AI-based systems could help continuously monitor BP using wearable technologies; in particular, BP can be estimated from a photoplethysmograph (PPG) signal obtained from a smartphone or a smartwatch using DL. Furthermore, thanks to ML algorithms, it is possible to identify new hypertension genes for the early diagnosis of AH and the prevention of complications. Moreover, integrating AI with omics-based technologies will lead to the definition of the trajectory of the hypertensive patient and the use of the most appropriate drug. However, AI is not free from technical issues and biases, such as over/underfitting, the "black-box" nature of many ML algorithms, and patient data privacy. In conclusion, AI-based systems will change clinical practice for AH by identifying patient trajectories for new, personalized care plans and predicting patients' risks and necessary therapy adjustments due to changes in disease progression and/or therapy response.
Collapse
Affiliation(s)
- Valeria Visco
- Department of Medicine, Surgery and Dentistry, University of Salerno, 84081 Baronissi, Italy
| | - Carmine Izzo
- Department of Medicine, Surgery and Dentistry, University of Salerno, 84081 Baronissi, Italy
| | - Costantino Mancusi
- Department of Advanced Biomedical Sciences, Federico II University of Naples, 80138 Naples, Italy
| | - Antonella Rispoli
- Department of Medicine, Surgery and Dentistry, University of Salerno, 84081 Baronissi, Italy
| | - Michele Tedeschi
- Department of Medicine, Surgery and Dentistry, University of Salerno, 84081 Baronissi, Italy
| | - Nicola Virtuoso
- Cardiology Unit, University Hospital “San Giovanni di Dio e Ruggi d’Aragona”, 84131 Salerno, Italy
| | - Angelo Giano
- Department of Medicine, Surgery and Dentistry, University of Salerno, 84081 Baronissi, Italy
| | - Renato Gioia
- Department of Medicine, Surgery and Dentistry, University of Salerno, 84081 Baronissi, Italy
| | - Americo Melfi
- Cardiology Unit, University Hospital “San Giovanni di Dio e Ruggi d’Aragona”, 84131 Salerno, Italy
| | - Bianca Serio
- Hematology and Transplant Center, University Hospital “San Giovanni di Dio e Ruggi d’Aragona”, 84131 Salerno, Italy
| | - Maria Rosaria Rusciano
- Department of Medicine, Surgery and Dentistry, University of Salerno, 84081 Baronissi, Italy
| | - Paola Di Pietro
- Department of Medicine, Surgery and Dentistry, University of Salerno, 84081 Baronissi, Italy
| | - Alessia Bramanti
- Department of Medicine, Surgery and Dentistry, University of Salerno, 84081 Baronissi, Italy
| | - Gennaro Galasso
- Department of Medicine, Surgery and Dentistry, University of Salerno, 84081 Baronissi, Italy
| | - Gianni D’Angelo
- Department of Computer Science, University of Salerno, 84084 Fisciano, Italy
| | - Albino Carrizzo
- Department of Medicine, Surgery and Dentistry, University of Salerno, 84081 Baronissi, Italy
- Vascular Physiopathology Unit, IRCCS Neuromed, 86077 Pozzilli, Italy
| | - Carmine Vecchione
- Department of Medicine, Surgery and Dentistry, University of Salerno, 84081 Baronissi, Italy
- Vascular Physiopathology Unit, IRCCS Neuromed, 86077 Pozzilli, Italy
| | - Michele Ciccarelli
- Department of Medicine, Surgery and Dentistry, University of Salerno, 84081 Baronissi, Italy
- Correspondence:
| |
Collapse
|
4
|
Chen H, Su T, Wang Q, Zheng Z, Li H, Li J. Comparison of thrombosis risk in an abdominal aortic dissection aneurysm with a double false lumen using computational fluid dynamic simulation method. Technol Health Care 2022; 31:1003-1015. [PMID: 36442166 DOI: 10.3233/thc-220481] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/23/2022]
Abstract
BACKGROUND: Aneurysms are associated with a mortality rate of 81% or more in cases of rupture. OBJECTIVE: To analyse the haemodynamic indices and compare the thrombosis risk in a double false lumen abdominal aortic dissection aneurysm using computational fluid dynamics (CFD). METHODS: Computer tomography angiography (CTA) imaging data were collected from a patient with a double false lumen abdominal aortic dissection aneurysm, and three different lesion morphology aneurysm models were established, double false lumen abdominal aortic dissection aneurysm, single false lumen abdominal aortic dissection aneurysm and saccular abdominal aortic aneurysm, in order to analyse the flow velocity, time-averaged shear stress (TAWSS), oscillatory shear index (OSI), relative residence time (RRT) of blood flow, and endothelial cell activation potential (ECAP). RESULTS: All three aneurysms were in a low-flow state within the body, and the low-flow velocity flow in the proximal vessel wall extended to the right common iliac artery; the vortex intensity was more intense in the abdominal aortic dissection aneurysm than in the saccular abdominal aortic aneurysm. The risk area for thrombosis was concentrated in the expansion part of the aneurysm and the false lumen. The RRT and ECAP maxima of the double false lumen abdominal aortic dissection aneurysm were much greater than those of the single false lumen dissection aneurysm and saccular aortic aneurysm. CONCLUSION: Low-velocity blood flow, high OSI, low TAWSS, high RRT, and high ECAP regions correlate with the risk of thrombosis. The double false lumen type of abdominal aortic dissection aneurysm had some specificity in this case. The risk of thrombosis in the patient was extremely high, and the largest risk zone was within the smaller false lumen, which could be because the smaller false lumen was connected to the true lumen by only one breach. The results of the study provide some guidance in the early screening and development of treatment plans.
Collapse
Affiliation(s)
- Hongbing Chen
- Department of Forensic Medicine, College of Basic Medicine, Chongqing Medical University, Chongqing, China
| | - Tong Su
- Department of Radiology, The First Affiliated Hospital of Chongqing Medical University, Chongqing, China
| | - Qi Wang
- Department of Forensic Medicine, College of Basic Medicine, Chongqing Medical University, Chongqing, China
| | - Zhe Zheng
- Department of Forensic Medicine, College of Basic Medicine, Chongqing Medical University, Chongqing, China
| | - Hongwei Li
- Institute of Forensic Science, Chongqing Public Security Bureau, Chongqing, China
| | - Jianbo Li
- Department of Forensic Medicine, College of Basic Medicine, Chongqing Medical University, Chongqing, China
| |
Collapse
|
5
|
Wang Y, Fan H, Duan W, Ren Z, Liu X, Liu T, Li Y, Zhang K, Fan H, Ren J, Li J, Li X, Wu X, Niu X. Elevated stress hyperglycemia and the presence of intracranial artery stenosis increase the risk of recurrent stroke. Front Endocrinol (Lausanne) 2022; 13:954916. [PMID: 36699024 PMCID: PMC9868694 DOI: 10.3389/fendo.2022.954916] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 05/27/2022] [Accepted: 12/12/2022] [Indexed: 01/11/2023] Open
Abstract
BACKGROUND Stress hyperglycemia has served as a reliable biomarker to predict poor outcomes after ischemic stroke. However, recent studies have reported some contrary conclusions. Different stroke subtypes may respond inconsistently to stress hyperglycemia. The progression of intracranial atherosclerotic stenosis (ICAS) is tightly related to hyperglycemia. Thus, this study aims to determine the relationship between stress hyperglycemia and recurrent stroke in ischemic stroke patients with or without intracranial atherosclerotic stenosis. METHODS This is a multicenter retrospective observational cohort study. Patients with acute minor ischemic stroke and eligible computed tomography and magnetic resonance imaging data were enrolled. The severity of stress hyperglycemia is measured by the stress hyperglycemia ratio (SHR). SHR was calculated based on fasting plasma glucose (FPG) and hemoglobin A1c (HbA1c) levels. The primary outcome was stroke recurrence during hospitalization. The interaction of SHR levels with the presence of ICAS on the primary outcome was investigated using univariable and multivariable Cox proportional hazards models. Restricted cubic splines were applied to determine the nonlinear relationship between SHR and primary outcome. A two-piecewise linear regression model was used to identify the threshold of SHR. RESULTS A total of 610 participants were included in the study. The average age of the patients was 61.4 ± 12.9 years old, and approximately 70% of participants were males. A total of 189 (30.98%) patients had ICAS. The patients were categorized into 3 groups based on the tertiles of SHR. Compared with the group with a lower SHR, a higher SHR was significantly associated with the risk of stroke recurrence in the ICAS group (hazard ratio [HR], 8.52, 95% confidence interval [CI], 3.16-22.96, P<0.001). When SHR was treated as a continuous variable, each 0.1-unit increase in SHR in the ICAS group was associated with a 1.63-fold increase in the risk of recurrence (HR, 1.63, 95% CI, 1.39-1.9, P<0.001) with a threshold of 0.75. FPG but not HbA1c was associated with stroke recurrence in ICAS patients (HR, 1.17, 95% CI, 1.08-1.26, P<0.001). Sensitive analyses showed consistent results after adjusting for previous diabetes mellitus, oral hypoglycemic agents and insulin injection. CONCLUSIONS SHR represents a better biomarker to predict the risk of stroke recurrence in patients with ICAS than FPG and HbA1c regardless of previous diabetes mellitus. TRIAL REGISTRATION https://www.chictr.org.cn/showproj.aspx?proj=125817; Identifier, [ChiCTR2100046958].
Collapse
Affiliation(s)
- Yongle Wang
- Department of Neurology, First Hospital of Shanxi Medical University, Taiyuan, Shanxi, China
- Clinical College, Shanxi Medical University, Taiyuan, Shanxi, China
| | - Hongxuan Fan
- Clinical College, Shanxi Medical University, Taiyuan, Shanxi, China
- Department of Cardiology, Second Hospital of Shanxi Medical University, Taiyuan, Shanxi, China
| | - Weiying Duan
- Clinical College, Shanxi Medical University, Taiyuan, Shanxi, China
| | - Zhaoyu Ren
- Clinical College, Shanxi Medical University, Taiyuan, Shanxi, China
| | - Xuchang Liu
- Clinical College, Shanxi Medical University, Taiyuan, Shanxi, China
| | - Tingting Liu
- Department of Neurology, First Hospital of Shanxi Medical University, Taiyuan, Shanxi, China
- Clinical College, Shanxi Medical University, Taiyuan, Shanxi, China
| | - Yanan Li
- Department of Neurology, First Hospital of Shanxi Medical University, Taiyuan, Shanxi, China
| | - Kaili Zhang
- Department of Neurology, The Bethune Hospital of Shanxi Province, Taiyuan, Shanxi, China
| | - Haimei Fan
- Department of Neurology, Sixth Hospital of Shanxi Medical University (General Hospital of Tisco), Taiyuan, Shanxi, China
| | - Jing Ren
- Department of Neurology, First Hospital of Shanxi Medical University, Taiyuan, Shanxi, China
| | - Juan Li
- Department of Neurology, First Hospital of Shanxi Medical University, Taiyuan, Shanxi, China
| | - Xinyi Li
- Department of Neurology, The Bethune Hospital of Shanxi Province, Taiyuan, Shanxi, China
| | - Xuemei Wu
- Department of Neurology, Sixth Hospital of Shanxi Medical University (General Hospital of Tisco), Taiyuan, Shanxi, China
| | - Xiaoyuan Niu
- Department of Neurology, First Hospital of Shanxi Medical University, Taiyuan, Shanxi, China
- *Correspondence: Xiaoyuan Niu,
| |
Collapse
|