1
|
Zeng M, Smith L, Bird A, Trinh VQN, Bacchi S, Harvey J, Jenkinson M, Scroop R, Kleinig T, Jannes J, Palmer LJ. Predictions for functional outcome and mortality in acute ischaemic stroke following successful endovascular thrombectomy. BMJ Neurol Open 2024; 6:e000707. [PMID: 38932996 PMCID: PMC11202712 DOI: 10.1136/bmjno-2024-000707] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/07/2024] [Accepted: 06/10/2024] [Indexed: 06/28/2024] Open
Abstract
Background Accurate outcome predictions for patients who had ischaemic stroke with successful reperfusion after endovascular thrombectomy (EVT) may improve patient treatment and care. Our study developed prediction models for key clinical outcomes in patients with successful reperfusion following EVT in an Australian population. Methods The study included all patients who had ischaemic stroke with occlusion in the proximal anterior cerebral circulation and successful reperfusion post-EVT over a 7-year period. Multivariable logistic regression and Cox regression models, incorporating bootstrap and multiple imputation techniques, were used to identify predictors and develop models for key clinical outcomes: 3-month poor functional status; 30-day, 1-year and 3-year mortality; survival time. Results A total of 978 patients were included in the analyses. Predictors associated with one or more poor outcomes include: older age (ORs for every 5-year increase: 1.22-1.40), higher premorbid functional modified Rankin Scale (ORs: 1.31-1.75), higher baseline National Institutes of Health Stroke Scale (ORs: 1.05-1.07) score, higher blood glucose (ORs: 1.08-1.19), larger core volume (ORs for every 10 mL increase: 1.10-1.22), pre-EVT thrombolytic therapy (ORs: 0.44-0.56), history of heart failure (outcome: 30-day mortality, OR=1.87), interhospital transfer (ORs: 1.42 to 1.53), non-rural/regional stroke onset (outcome: functional dependency, OR=0.64), longer onset-to-groin puncture time (outcome: 3-year mortality, OR=1.08) and atherosclerosis-caused stroke (outcome: functional dependency, OR=1.68). The models using these predictors demonstrated moderate predictive abilities (area under the receiver operating characteristic curve range: 0.752-0.796). Conclusion Our models using real-world predictors assessed at hospital admission showed satisfactory performance in predicting poor functional outcomes and short-term and long-term mortality for patients with successful reperfusion following EVT. These can be used to inform EVT treatment provision and consent.
Collapse
Affiliation(s)
- Minyan Zeng
- School of Public Health, Faculty of Health and Medical Sciences, The University of Adelaide, Adelaide, South Australia, Australia
- Australian Institute for Machine Learning, Adelaide, South Australia, Australia
| | - Luke Smith
- School of Public Health, Faculty of Health and Medical Sciences, The University of Adelaide, Adelaide, South Australia, Australia
- Australian Institute for Machine Learning, Adelaide, South Australia, Australia
| | - Alix Bird
- School of Public Health, Faculty of Health and Medical Sciences, The University of Adelaide, Adelaide, South Australia, Australia
- Australian Institute for Machine Learning, Adelaide, South Australia, Australia
| | - Vincent Quoc-Nam Trinh
- School of Public Health, Faculty of Health and Medical Sciences, The University of Adelaide, Adelaide, South Australia, Australia
- Australian Institute for Machine Learning, Adelaide, South Australia, Australia
| | - Stephen Bacchi
- Royal Adelaide Hospital, Adelaide, South Australia, Australia
| | - Jackson Harvey
- Royal Adelaide Hospital, Adelaide, South Australia, Australia
| | - Mark Jenkinson
- Australian Institute for Machine Learning, Adelaide, South Australia, Australia
- School of Computer and Mathematical Sciences, Faculty of Sciences, Engineering and Technology, The University of Adelaide, Adelaide, South Australia, Australia
- South Australian Health and Medical Research Institute, Adelaide, South Australia, Australia
| | - Rebecca Scroop
- Royal Adelaide Hospital, Adelaide, South Australia, Australia
| | - Timothy Kleinig
- Royal Adelaide Hospital, Adelaide, South Australia, Australia
| | - Jim Jannes
- Royal Adelaide Hospital, Adelaide, South Australia, Australia
| | - Lyle J Palmer
- School of Public Health, Faculty of Health and Medical Sciences, The University of Adelaide, Adelaide, South Australia, Australia
- Australian Institute for Machine Learning, Adelaide, South Australia, Australia
| |
Collapse
|
2
|
Marburg M, Rudolf LF, Matthis C, Neumann A, Schareck C, Schacht H, Schulz R, Machner B, Schramm P, Royl G, Koch PJ. The lesion core extent modulates the impact of early perfusion mismatch imaging on outcome variability after thrombectomy in stroke. Front Neurol 2024; 15:1366240. [PMID: 38841692 PMCID: PMC11150589 DOI: 10.3389/fneur.2024.1366240] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/05/2024] [Accepted: 04/29/2024] [Indexed: 06/07/2024] Open
Abstract
Introduction Despite profitable group effects on functional outcomes after mechanical thrombectomy (MT) in large vessel occlusion (LVO), many patients with successful reperfusion show a non-favorable long-term outcome, highlighting the necessity to identify potential biomarkers predicting outcome variability. In this regard, the role of perfusion mismatch imaging for outcome variability in the early time window within 6 h after symptom onset is a matter of debate. We attempted to investigate under which conditions early perfusion mismatch imaging accounts for variability in functional outcomes after mechanical thrombectomy. Patients and methods In a retrospective single-center study, we examined 190 consecutive patients with LVO who were admitted to the Medical Center Lübeck within 6 h after symptom onset, all of whom underwent MT. Perfusion mismatch was quantified by applying the Alberta Stroke Program Early CT score (ASPECTS) on CT-measured cerebral blood flow (CBF-ASPECTS) and subtracting it from an ASPECTS application on cerebral blood volume (CBV-ASPECTS), i.e., ASPECTS mismatch. Using multivariate ordinal regression models, associations between ASPECTS mismatch and modified Rankin Scale (mRS) after 90 days were assessed. Furthermore, the interaction between ASPECTS mismatch and the core lesion volume was calculated to evaluate conditional associations. Results ASPECTS mismatch did not correlate with functional outcomes when corrected for multiple influencing covariables. However, interactions between ASPECTS mismatch and CBV-ASPECTS [OR: 1.12 (1.06-1.18), p-value < 0.001], as well as NCCT-ASPECTS [OR: 1.15 (1.06-1.25), p-value < 0.001], did show a significant association with functional outcomes. Model comparisons revealed that, profoundly, in patients with large core lesion volumes (CBV-ASPECTS < 6 or NCCT-ASPECTS < 6), perfusion mismatch showed a negative correlation with the mRS. Discussion and conclusion Perfusion mismatch imaging within the first 6 h of symptom onset provides valuable insights into the outcome variability of LVO stroke patients receiving thrombectomy but only in patients with large ischemic core lesions.
Collapse
Affiliation(s)
- Maria Marburg
- Department of Neurology, University Hospital Schleswig-Holstein, Lübeck, Germany
| | - Linda F. Rudolf
- Department of Neuroradiology, University Hospital Schleswig-Holstein, Lübeck, Germany
| | - Christine Matthis
- Department of Social Medicine and Epidemiology, University Hospital Schleswig-Holstein, Lübeck, Germany
| | - Alexander Neumann
- Department of Neuroradiology, University Hospital Schleswig-Holstein, Lübeck, Germany
| | - Constantin Schareck
- Department of Radiology, University Hospital Schleswig-Holstein, Lübeck, Germany
| | - Hannes Schacht
- Department of Neuroradiology, University Hospital Schleswig-Holstein, Lübeck, Germany
| | - Robert Schulz
- Department of Neurology, University Medical Center Hamburg Eppendorf, Hamburg, Germany
| | - Björn Machner
- Department of Neurology, Schoen Clinic Neustadt, Neustadt in Holstein, Germany
| | - Peter Schramm
- Department of Neuroradiology, University Hospital Schleswig-Holstein, Lübeck, Germany
| | - Georg Royl
- Department of Neurology, University Hospital Schleswig-Holstein, Lübeck, Germany
- Center of Brain, Behavior and Metabolism, University of Lübeck, Lübeck, Germany
| | - Philipp J. Koch
- Department of Neurology, University Hospital Schleswig-Holstein, Lübeck, Germany
- Center of Brain, Behavior and Metabolism, University of Lübeck, Lübeck, Germany
| |
Collapse
|
3
|
Diprose JP, Diprose WK, Chien TY, Wang MTM, McFetridge A, Tarr GP, Ghate K, Beharry J, Hong J, Wu T, Campbell D, Barber PA. Deep learning on pre-procedural computed tomography and clinical data predicts outcome following stroke thrombectomy. J Neurointerv Surg 2024:jnis-2023-021154. [PMID: 38527795 DOI: 10.1136/jnis-2023-021154] [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: 10/18/2023] [Accepted: 02/23/2024] [Indexed: 03/27/2024]
Abstract
BACKGROUND Deep learning using clinical and imaging data may improve pre-treatment prognostication in ischemic stroke patients undergoing endovascular thrombectomy (EVT). METHODS Deep learning models were trained and tested on baseline clinical and imaging (CT head and CT angiography) data to predict 3-month functional outcomes in stroke patients who underwent EVT. Classical machine learning models (logistic regression and random forest classifiers) were constructed to compare their performance with the deep learning models. An external validation dataset was used to validate the models. The MR PREDICTS prognostic tool was tested on the external validation set, and its performance was compared with the deep learning and classical machine learning models. RESULTS A total of 975 patients (550 men; mean±SD age 67.5±15.1 years) were studied with 778 patients in the model development cohort and 197 in the external validation cohort. The deep learning model trained on baseline CT and clinical data, and the logistic regression model (clinical data alone) demonstrated the strongest discriminative abilities for 3-month functional outcome and were comparable (AUC 0.811 vs 0.817, Q=0.82). Both models exhibited superior prognostic performance than the other deep learning (CT head alone, CT head, and CT angiography) and MR PREDICTS models (all Q<0.05). CONCLUSIONS The discriminative performance of deep learning for predicting functional independence was comparable to logistic regression. Future studies should focus on whether incorporating procedural and post-procedural data significantly improves model performance.
Collapse
Affiliation(s)
| | - William K Diprose
- Department of Medicine, Faculty of Medical and Health Sciences, University of Auckland, Auckland, New Zealand
| | | | - Michael T M Wang
- Department of Medicine, Faculty of Medical and Health Sciences, University of Auckland, Auckland, New Zealand
| | - Andrew McFetridge
- Department of Radiology, Auckland City Hospital, Auckland, New Zealand
| | - Gregory P Tarr
- Department of Radiology, Auckland City Hospital, Auckland, New Zealand
| | - Kaustubha Ghate
- Department of Neurology, Auckland City Hospital, Auckland, New Zealand
| | - James Beharry
- Department of Neurology, Christchurch Hospital, Christchurch, New Zealand
| | - JaeBeom Hong
- Department of Neurology, Auckland City Hospital, Auckland, New Zealand
| | - Teddy Wu
- Department of Neurology, Christchurch Hospital, Christchurch, New Zealand
| | - Doug Campbell
- Department of Anaesthesia and Perioperative Medicine, Auckland City Hospital, Auckland, New Zealand
| | - P Alan Barber
- Department of Medicine, Faculty of Medical and Health Sciences, University of Auckland, Auckland, New Zealand
- Department of Neurology, Auckland City Hospital, Auckland, New Zealand
| |
Collapse
|
4
|
Nie X, Yang J, Li X, Zhan T, Liu D, Yan H, Wei Y, Liu X, Chen J, Gong G, Wu Z, Yang Z, Wen M, Gu W, Pan Y, Jiang Y, Meng X, Liu T, Cheng J, Li Z, Miao Z, Liu L. Prediction of futile recanalisation after endovascular treatment in acute ischaemic stroke: development and validation of a hybrid machine learning model. Stroke Vasc Neurol 2024:svn-2023-002500. [PMID: 38336369 DOI: 10.1136/svn-2023-002500] [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: 03/29/2023] [Accepted: 01/23/2024] [Indexed: 02/12/2024] Open
Abstract
BACKGROUND Identification of futile recanalisation following endovascular therapy (EVT) in patients with acute ischaemic stroke is both crucial and challenging. Here, we present a novel risk stratification system based on hybrid machine learning method for predicting futile recanalisation. METHODS Hybrid machine learning models were developed to address six clinical scenarios within the EVT and perioperative management workflow. These models were trained on a prospective database using hybrid feature selection technique to predict futile recanalisation following EVT. The optimal model was validated and compared with existing models and scoring systems in a multicentre prospective cohort to develop a hybrid machine learning-based risk stratification system for futile recanalisation prediction. RESULTS Using a hybrid feature selection approach, we trained and tested multiple classifiers on two independent patient cohorts (n=1122) to develop a hybrid machine learning-based prediction model. The model demonstrated superior discriminative ability compared with other models and scoring systems (area under the curve=0.80, 95% CI 0.73 to 0.87) and was transformed into a web application (RESCUE-FR Index) that provides a risk stratification system for individual prediction (accessible online at fr-index.biomind.cn/RESCUE-FR/). CONCLUSIONS The proposed hybrid machine learning approach could be used as an individualised risk prediction model to facilitate adherence to clinical practice guidelines and shared decision-making for optimal candidate selection and prognosis assessment in patients undergoing EVT.
Collapse
Affiliation(s)
- Ximing Nie
- Department of Neurology, Capital Medical University, Beijing, China
- China National Clinical Research Center for Neurological Diseases, Beijing Tiantan Hospital, Beijing, China
| | - Jinxu Yang
- School of Computer and Communication Engineering, University of Science and Technology, Beijing, China
| | - Xinxin Li
- China National Clinical Research Center for Neurological Diseases, Beijing Tiantan Hospital, Beijing, China
| | - Tianming Zhan
- China National Clinical Research Center for Neurological Diseases, Beijing Tiantan Hospital, Beijing, China
| | - Dongdong Liu
- China National Clinical Research Center for Neurological Diseases, Beijing Tiantan Hospital, Beijing, China
| | - Hongyi Yan
- China National Clinical Research Center for Neurological Diseases, Beijing Tiantan Hospital, Beijing, China
| | - Yufei Wei
- Department of Neurology, Capital Medical University, Beijing, China
- China National Clinical Research Center for Neurological Diseases, Beijing Tiantan Hospital, Beijing, China
| | - Xiran Liu
- Department of Neurology, Capital Medical University, Beijing, China
- China National Clinical Research Center for Neurological Diseases, Beijing Tiantan Hospital, Beijing, China
| | - Jiaping Chen
- Department of Neurology, Capital Medical University, Beijing, China
- China National Clinical Research Center for Neurological Diseases, Beijing Tiantan Hospital, Beijing, China
| | - Guoyang Gong
- China National Clinical Research Center for Neurological Diseases, Beijing Tiantan Hospital, Beijing, China
| | - Zhenzhou Wu
- China National Clinical Research Center for Neurological Diseases, Beijing Tiantan Hospital, Beijing, China
| | - Zhonghua Yang
- Department of Neurology, Capital Medical University, Beijing, China
- China National Clinical Research Center for Neurological Diseases, Beijing Tiantan Hospital, Beijing, China
| | - Miao Wen
- Department of Neurology, Capital Medical University, Beijing, China
- China National Clinical Research Center for Neurological Diseases, Beijing Tiantan Hospital, Beijing, China
| | - Weibin Gu
- Department of Radiology, Beijing Tiantan Hospital, Beijing, China
| | - Yuesong Pan
- Department of Neurology, Capital Medical University, Beijing, China
- China National Clinical Research Center for Neurological Diseases, Beijing Tiantan Hospital, Beijing, China
| | - Yong Jiang
- Department of Neurology, Capital Medical University, Beijing, China
- China National Clinical Research Center for Neurological Diseases, Beijing Tiantan Hospital, Beijing, China
| | - Xia Meng
- Department of Neurology, Capital Medical University, Beijing, China
- China National Clinical Research Center for Neurological Diseases, Beijing Tiantan Hospital, Beijing, China
| | - Tao Liu
- Key Laboratory of Biomechanics and Mechanobiology, Ministry of Education, School of Biological Science and Medical Engineering International Research Institute for Multidisciplinary Science, Beihang University, Beijing, China
- Beijing Advanced Innovation Center for Big Data-Based Precision Medicine, School of Computer Science and Engineering, Beihang University, Beijing, China
| | - Jian Cheng
- Key Laboratory of Biomechanics and Mechanobiology, Ministry of Education, School of Biological Science and Medical Engineering International Research Institute for Multidisciplinary Science, Beihang University, Beijing, China
- Beijing Advanced Innovation Center for Big Data-Based Precision Medicine, School of Computer Science and Engineering, Beihang University, Beijing, China
| | - Zixiao Li
- Department of Neurology, Capital Medical University, Beijing, China
- China National Clinical Research Center for Neurological Diseases, Beijing Tiantan Hospital, Beijing, China
| | - Zhongrong Miao
- Department of Interventional Neuroradiology, Beijing Tiantan Hospital, Capital Medical University, Beijing, China
| | - Liping Liu
- Department of Neurology, Capital Medical University, Beijing, China
- China National Clinical Research Center for Neurological Diseases, Beijing Tiantan Hospital, Beijing, China
| |
Collapse
|
5
|
Nozoe M, Kubo H, Yamamoto M, Ikeji R, Seike H, Majima K, Shimada S. Muscle weakness is more strongly associated with functional outcomes in patients with stroke than sarcopenia or muscle wasting: an observational study. Aging Clin Exp Res 2024; 36:4. [PMID: 38261059 PMCID: PMC10806041 DOI: 10.1007/s40520-023-02672-9] [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: 06/14/2023] [Accepted: 11/21/2023] [Indexed: 01/24/2024]
Abstract
BACKGROUND Stroke-related sarcopenia is an important prognosis factor and an intervention target for improving outcomes in patients with stroke. AIM This study aimed to identify the association between sarcopenia, possible sarcopenia, muscle weakness, muscle mass and calf circumference, and the functional outcomes 3 months after stroke. METHODS In this single-centre prospective observational study, muscle strength, muscle mass, and calf circumference were measured in patients with acute stroke at hospital discharge. Diagnosis of sarcopenia, possible sarcopenia, muscle weakness, low muscle mass, and low calf circumference were defined according to the 2019 Asian Working Group for Sarcopenia criteria. The primary outcome measure was the modified Rankin Scale (mRS) score at 3 months, with an mRS score of 3 or higher indicating a poor outcome. Logistic regression analysis was conducted to examine independent associations between each assessment and functional outcomes. RESULTS A total of 247 patients (median age: 73 years) were included in this study. The prevalence of sarcopenia was 28% (n = 70), and in the adjusted model, sarcopenia (aOR = 2.60, 95% CI 1.07-6.31, p = 0.034), muscle weakness (aOR = 3.40, 95% CI 1.36-8.52, p = 0.009), and low muscle mass (aOR = 2.61, 95% CI 1.04-6.52) were significantly associated with poor functional outcome. Nevertheless, other evaluations did not demonstrate an independent association with the outcome. CONCLUSION Sarcopenia, muscle weakness, and low muscle mass were found to be independently associated with functional outcomes 3 months after stroke, and muscle weakness exhibited the strongest association with outcomes among them.
Collapse
Affiliation(s)
- Masafumi Nozoe
- Department of Physical Therapy, Faculty of Rehabilitation, Kansai Medical University, 18-89 Uyamahigashicho, Hirakata, Osaka, Japan.
| | - Hiroki Kubo
- Department of Physical Therapy, Faculty of Nursing and Rehabilitation, Konan Women's University, Kobe, Japan
| | - Miho Yamamoto
- Department of Rehabilitation Medicine, Nishiyamato Rehabilitation Hospital, Nara, Japan
| | - Rio Ikeji
- Department of Rehabilitation, Itami Kousei Neurosurgical Hospital, Itami, Japan
| | - Haruka Seike
- Department of Rehabilitation, Itami Kousei Neurosurgical Hospital, Itami, Japan
| | - Kazuki Majima
- Department of Rehabilitation, Itami Kousei Neurosurgical Hospital, Itami, Japan
| | - Shinichi Shimada
- Department of Neurosurgery, Itami Kousei Neurosurgical Hospital, Itami, Japan
| |
Collapse
|
6
|
Li X, Li C, Liu AF, Jiang CC, Zhang YQ, Liu YE, Zhang YY, Li HY, Jiang WJ, Lv J. Application of a nomogram model for the prediction of 90-day poor outcomes following mechanical thrombectomy in patients with acute anterior circulation large-vessel occlusion. Front Neurol 2024; 15:1259973. [PMID: 38313559 PMCID: PMC10836145 DOI: 10.3389/fneur.2024.1259973] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/17/2023] [Accepted: 01/02/2024] [Indexed: 02/06/2024] Open
Abstract
Background The past decade has witnessed advancements in mechanical thrombectomy (MT) for acute large-vessel occlusions (LVOs). However, only approximately half of the patients with LVO undergoing MT show the best/independent 90-day favorable outcome. This study aimed to develop a nomogram for predicting 90-day poor outcomes in patients with LVO treated with MT. Methods A total of 187 patients who received MT were retrospectively analyzed. Factors associated with 90-day poor outcomes (defined as mRS of 4-6) were determined by univariate and multivariate logistic regression analyzes. One best-fit nomogram was established to predict the risk of a 90-day poor outcome, and a concordance index was utilized to evaluate the performance of the model. Additionally, 145 patients from a single stroke center were retrospectively recruited as the validation cohort to test the newly established nomogram. Results The overall incidence of 90-day poor outcomes was 45.16%, affecting 84 of 186 patients in the training set. Moreover, five variables, namely, age (odds ratio [OR]: 1.049, 95% CI [1.016-1.083]; p = 0.003), glucose level (OR: 1.163, 95% CI [1.038-1.303]; p = 0.009), baseline National Institute of Health Stroke Scale (NIHSS) score (OR: 1.066, 95% CI [0.995-1.142]; p = 0.069), unsuccessful recanalization (defined as a TICI grade of 0 to 2a) (OR: 3.730, 95% CI [1.688-8.245]; p = 0.001), and early neurological deterioration (END, defined as an increase of ≥4 points between the baseline NIHSS score and the NIHSS score at 24 h after MT) (OR: 3.383, 95% CI [1.411-8.106]; p = 0.006), were included in the nomogram to predict the potential risk of poor outcomes at 90 days following MT in LVO patients, with a C-index of 0.763 (0.693-0.832) in the training set and 0.804 (0.719-0.889) in the validation set. Conclusion The proposed nomogram provided clinical evidence for the effective control of these risk factors before or during the process of MT surgery in LVO patients.
Collapse
Affiliation(s)
- Xia Li
- The PLA Rocket Force Characteristic Medical Center, Beijing, China
- Department of Neurology, Baotou Center Hospital, Neurointerventional Medical Center of Inner Mongolia Medical University, Institute of Cerebrovascular Disease in Inner Mongolia, Inner Mongolia, China
| | - Chen Li
- The PLA Rocket Force Characteristic Medical Center, Beijing, China
| | - Ao-Fei Liu
- The PLA Rocket Force Characteristic Medical Center, Beijing, China
| | - Chang-Chun Jiang
- Department of Neurology, Baotou Center Hospital, Neurointerventional Medical Center of Inner Mongolia Medical University, Institute of Cerebrovascular Disease in Inner Mongolia, Inner Mongolia, China
| | - Yi-Qun Zhang
- The PLA Rocket Force Characteristic Medical Center, Beijing, China
| | - Yun-E Liu
- The PLA Rocket Force Characteristic Medical Center, Beijing, China
| | - Ying-Ying Zhang
- The PLA Rocket Force Characteristic Medical Center, Beijing, China
| | - Hao-Yang Li
- Department of Psychiatric Specialty, Capital Medical University, Beijing, China
| | - Wei-Jian Jiang
- The PLA Rocket Force Characteristic Medical Center, Beijing, China
| | - Jin Lv
- The PLA Rocket Force Characteristic Medical Center, Beijing, China
| |
Collapse
|
7
|
Koch PJ, Rudolf LF, Schramm P, Frontzkowski L, Marburg M, Matthis C, Schacht H, Fiehler J, Thomalla G, Hummel FC, Neumann A, Münte TF, Royl G, Machner B, Schulz R. Preserved Corticospinal Tract Revealed by Acute Perfusion Imaging Relates to Better Outcome After Thrombectomy in Stroke. Stroke 2023; 54:3081-3089. [PMID: 38011237 DOI: 10.1161/strokeaha.123.044221] [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: 06/15/2023] [Accepted: 10/04/2023] [Indexed: 11/29/2023]
Abstract
BACKGROUND The indication for mechanical thrombectomy (MT) in stroke patients with large vessel occlusion has been constantly expanded over the past years. Despite remarkable treatment effects at the group level in clinical trials, many patients remain severely disabled even after successful recanalization. A better understanding of this outcome variability will help to improve clinical decision-making on MT in the acute stage. Here, we test whether current outcome models can be refined by integrating information on the preservation of the corticospinal tract as a functionally crucial white matter tract derived from acute perfusion imaging. METHODS We retrospectively analyzed 162 patients with stroke and large vessel occlusion of the anterior circulation who were admitted to the University Medical Center Lübeck between 2014 and 2020 and underwent MT. The ischemic core was defined as fully automatized based on the acute computed tomography perfusion with cerebral blood volume data using outlier detection and clustering algorithms. Normative whole-brain structural connectivity data were used to infer whether the corticospinal tract was affected by the ischemic core or preserved. Ordinal logistic regression models were used to correlate this information with the modified Rankin Scale after 90 days. RESULTS The preservation of the corticospinal tract was associated with a reduced risk of a worse functional outcome in large vessel occlusion-stroke patients undergoing MT, with an odds ratio of 0.28 (95% CI, 0.15-0.53). This association was still significant after adjusting for multiple confounding covariables, such as age, lesion load, initial symptom severity, sex, stroke side, and recanalization status. CONCLUSIONS A preinterventional computed tomography perfusion-based surrogate of corticospinal tract preservation or disconnectivity is strongly associated with functional outcomes after MT. If validated in independent samples this concept could serve as a novel tool to improve current outcome models to better understand intersubject variability after MT in large vessel occlusion stroke.
Collapse
Affiliation(s)
- Philipp J Koch
- Department of Neurology (P.J.K., M.M., G.R., B.M.), University Hospital Schleswig-Holstein, Campus Lübeck, Germany
- Center of Brain, Behavior and Metabolism (CBBM), University of Lübeck, Germany (P.J.K., T.F.M., G.R., B.M.)
| | - Linda F Rudolf
- Department of Neuroradiology (L.F.R., P.S., H.S., A.N.), University Hospital Schleswig-Holstein, Campus Lübeck, Germany
| | - Peter Schramm
- Department of Neuroradiology (L.F.R., P.S., H.S., A.N.), University Hospital Schleswig-Holstein, Campus Lübeck, Germany
| | - Lukas Frontzkowski
- Department of Neurology (L.F., G.T., R.S.) University Medical Center Hamburg Eppendorf, Germany
| | - Maria Marburg
- Department of Neurology (P.J.K., M.M., G.R., B.M.), University Hospital Schleswig-Holstein, Campus Lübeck, Germany
| | - Christine Matthis
- Department of Social Medicine and Epidemiology (C.M.), University Hospital Schleswig-Holstein, Campus Lübeck, Germany
| | - Hannes Schacht
- Department of Neuroradiology (L.F.R., P.S., H.S., A.N.), University Hospital Schleswig-Holstein, Campus Lübeck, Germany
| | - Jens Fiehler
- Department of Neuroradiology (J.F.) University Medical Center Hamburg Eppendorf, Germany
| | - Götz Thomalla
- Department of Neurology (L.F., G.T., R.S.) University Medical Center Hamburg Eppendorf, Germany
| | - Friedhelm C Hummel
- Neuro-X Institute and Brain Mind Institute, Swiss Federal Institute of Technology, Geneva, Switzerland (F.C.H.)
- Neuro-X Institute and Brain Mind Institute, Swiss Federal Institute of Technology (EPFL Valais), Clinique Romande de Réadaptation, Sion, Switzerland (F.C.H.)
- Clinical Neuroscience, University of Geneva Medical School, Switzerland (F.C.H.)
| | - Alexander Neumann
- Department of Neuroradiology (L.F.R., P.S., H.S., A.N.), University Hospital Schleswig-Holstein, Campus Lübeck, Germany
| | - Thomas F Münte
- Center of Brain, Behavior and Metabolism (CBBM), University of Lübeck, Germany (P.J.K., T.F.M., G.R., B.M.)
| | - Georg Royl
- Department of Neurology (P.J.K., M.M., G.R., B.M.), University Hospital Schleswig-Holstein, Campus Lübeck, Germany
- Center of Brain, Behavior and Metabolism (CBBM), University of Lübeck, Germany (P.J.K., T.F.M., G.R., B.M.)
| | - Björn Machner
- Department of Neurology (P.J.K., M.M., G.R., B.M.), University Hospital Schleswig-Holstein, Campus Lübeck, Germany
- Center of Brain, Behavior and Metabolism (CBBM), University of Lübeck, Germany (P.J.K., T.F.M., G.R., B.M.)
- Department of Neurology, Schoen Clinic Neustadt, Holstein, Germany (B.M.)
| | - Robert Schulz
- Department of Neurology (L.F., G.T., R.S.) University Medical Center Hamburg Eppendorf, Germany
| |
Collapse
|
8
|
Yao Z, Mao C, Ke Z, Xu Y. An explainable machine learning model for predicting the outcome of ischemic stroke after mechanical thrombectomy. J Neurointerv Surg 2023; 15:1136-1141. [PMID: 36446552 PMCID: PMC10579503 DOI: 10.1136/jnis-2022-019598] [Citation(s) in RCA: 7] [Impact Index Per Article: 7.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/03/2022] [Accepted: 11/01/2022] [Indexed: 12/02/2022]
Abstract
BACKGROUND There is high variability in the clinical outcomes of patients with acute ischemic stroke (AIS) after mechanical thrombectomy (MT). METHODS 217 consecutive patients with anterior circulation large vessel occlusion who underwent MT between August 2018 and January 2022 were analysed. The primary outcome was functional independence defined as a modified Rankin Scale score of 0-2 at 3 months. In the derivation cohort (August 2018 to December 2020), 7 ensemble ML models were trained on 70% of patients and tested on the remaining 30%. The model's performance was further validated on the temporal validation cohort (January 2021 to January 2022). The SHapley Additive exPlanations (SHAP) framework was applied to interpret the prediction model. RESULTS Derivation analyses generated a 9-item score (PFCML-MT) comprising age, National Institutes of Health Stroke Scale score, collateral status, and postoperative laboratory indices (albumin-to-globulin ratio, estimated glomerular filtration rate, blood neutrophil count, C-reactive protein, albumin and serum glucose levels). The area under the curve was 0.87 for the test set and 0.84 for the temporal validation cohort. SHAP analysis further determined the thresholds for the top continuous features. This model has been translated into an online calculator that is freely available to the public (https://zhelvyao-123-60-sial5s.streamlitapp.com). CONCLUSIONS Using ML and readily available features, we developed an ML model that can potentially be used in clinical practice to generate real-time, accurate predictions of the outcome of patients with AIS treated with MT.
Collapse
Affiliation(s)
- Zhelv Yao
- Department of Neurology, Nanjing University Medical School Affiliated Nanjing Drum Tower Hospital, Nanjing, Jiangsu, China
- Jiangsu Key Laboratory for Molecular Medicine, Nanjing University Medical School, Nanjing, China
- Nanjing Medicine Center For Neurological Diseases, Nanjing, China
| | - Chenglu Mao
- Department of Neurology, Nanjing University Medical School Affiliated Nanjing Drum Tower Hospital, Nanjing, Jiangsu, China
- Jiangsu Key Laboratory for Molecular Medicine, Nanjing University Medical School, Nanjing, China
- Nanjing Medicine Center For Neurological Diseases, Nanjing, China
| | - Zhihong Ke
- Jiangsu Key Laboratory for Molecular Medicine, Nanjing University Medical School, Nanjing, China
- Nanjing Medicine Center For Neurological Diseases, Nanjing, China
- Department of Neurology, Nanjing Drum Tower Hospital, Clinical College of Nanjing Medical University, Nanjing, China
| | - Yun Xu
- Department of Neurology, Nanjing University Medical School Affiliated Nanjing Drum Tower Hospital, Nanjing, Jiangsu, China
- Jiangsu Key Laboratory for Molecular Medicine, Nanjing University Medical School, Nanjing, China
- Nanjing Medicine Center For Neurological Diseases, Nanjing, China
| |
Collapse
|
9
|
Reyes-Esteves S, Kumar M, Kasner SE, Witsch J. Clinical Grading Scales and Neuroprognostication in Acute Brain Injury. Semin Neurol 2023; 43:664-674. [PMID: 37788680 DOI: 10.1055/s-0043-1775749] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/05/2023]
Abstract
Prediction of neurological clinical outcome after acute brain injury is critical because it helps guide discussions with patients and families and informs treatment plans and allocation of resources. Numerous clinical grading scales have been published that aim to support prognostication after acute brain injury. However, the development and validation of clinical scales lack a standardized approach. This in turn makes it difficult for clinicians to rely on prognostic grading scales and to integrate them into clinical practice. In this review, we discuss quality measures of score development and validation and summarize available scales to prognosticate outcomes after acute brain injury. These include scales developed for patients with coma, cardiac arrest, ischemic stroke, nontraumatic intracerebral hemorrhage, subarachnoid hemorrhage, and traumatic brain injury; for each scale, we discuss available validation studies.
Collapse
Affiliation(s)
- Sahily Reyes-Esteves
- Department of Neurology, Hospital of the University of Pennsylvania, Philadelphia, Pennsylvania
| | - Monisha Kumar
- Department of Neurology, Hospital of the University of Pennsylvania, Philadelphia, Pennsylvania
| | - Scott E Kasner
- Department of Neurology, Hospital of the University of Pennsylvania, Philadelphia, Pennsylvania
| | - Jens Witsch
- Department of Neurology, Hospital of the University of Pennsylvania, Philadelphia, Pennsylvania
| |
Collapse
|
10
|
Chalos V, Venema E, Mulder MJHL, Roozenbeek B, Steyerberg EW, Wermer MJH, Lycklama à Nijeholt GJ, van der Worp HB, Goyal M, Campbell BCV, Muir KW, Guillemin F, Bracard S, White P, Dávalos A, Jovin TG, Hill MD, Mitchell PJ, Demchuk AM, Saver JL, van der Lugt A, Brown S, Dippel DWJ, Lingsma HF. Development and Validation of a Postprocedural Model to Predict Outcome After Endovascular Treatment for Ischemic Stroke. JAMA Neurol 2023; 80:2807606. [PMID: 37523199 PMCID: PMC10391355 DOI: 10.1001/jamaneurol.2023.2392] [Citation(s) in RCA: 3] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/10/2023] [Accepted: 05/19/2023] [Indexed: 08/01/2023]
Abstract
Importance Outcome prediction after endovascular treatment (EVT) for ischemic stroke is important to patients, family members, and physicians. Objective To develop and validate a model based on preprocedural and postprocedural characteristics to predict functional outcome for individual patients after EVT. Design, Setting, and Participants A prediction model was developed using individual patient data from 7 randomized clinical trials, performed between December 2010 and December 2014. The model was developed within the Highly Effective Reperfusion Evaluated in Multiple Endovascular Stroke Trials (HERMES) collaboration and external validation in data from the Dutch Multicenter Randomized Clinical Trial of Endovascular Treatment for Acute Ischemic Stroke in the Netherlands (MR CLEAN) Registry of patients treated in clinical practice between March 2014 and November 2017. Participants included patients from multiple centers throughout different countries in Europe, North America, East Asia, and Oceania (derivation cohort), and multiple centers in the Netherlands (validation cohort). Included were adult patients with a history of ischemic stroke from an intracranial large vessel occlusion in the anterior circulation who underwent EVT within 12 hours of symptom onset or last seen well. Data were last analyzed in July 2022. Main Outcome(s) and Measure(s) A total of 19 variables were assessed by multivariable ordinal regression to predict functional outcome (modified Rankin Scale [mRS] score) 90 days after EVT. Variables were routinely available 1 day after EVT. Akaike information criterion (AIC) was used to optimize model fit vs model complexity. Probabilities for functional independence (mRS 0-2) and survival (mRS 0-5) were derived from the ordinal model. Model performance was expressed with discrimination (C statistic) and calibration. Results A total of 781 patients (median [IQR] age, 67 [57-76] years; 414 men [53%]) constituted the derivation cohort, and 3260 patients (median [IQR] age, 72 [61-80] years; 1684 men [52%]) composed the validation cohort. Nine variables were included in the model: age, baseline National Institutes of Health Stroke Scale (NIHSS) score, prestroke mRS score, history of diabetes, occlusion location, collateral score, reperfusion grade, NIHSS score at 24 hours, and symptomatic intracranial hemorrhage 24 hours after EVT. External validation in the MR CLEAN Registry showed excellent discriminative ability for functional independence (C statistic, 0.91; 95% CI, 0.90-0.92) and survival (0.89; 95% CI, 0.88-0.90). The proportion of functional independence in the MR CLEAN Registry was systematically higher than predicted by the model (41% vs 34%), whereas observed and predicted survival were similar (72% vs 75%). The model was updated and implemented for clinical use. Conclusion and relevance The prognostic tool MR PREDICTS@24H can be applied 1 day after EVT to accurately predict functional outcome for individual patients at 90 days and to provide reliable outcome expectations and personalize follow-up and rehabilitation plans. It will need further validation and updating for contemporary patients.
Collapse
Affiliation(s)
- Vicky Chalos
- Department of Neurology, Erasmus MC University Medical Center, Rotterdam, the Netherlands
- Department of Public Health, Erasmus MC University Medical Center, Rotterdam, the Netherlands
- Department of Radiology and Nuclear Medicine, Erasmus MC University Medical Center, Rotterdam, the Netherlands
| | - Esmee Venema
- Department of Public Health, Erasmus MC University Medical Center, Rotterdam, the Netherlands
- Department of Emergency Medicine, Erasmus MC University Medical Center, Rotterdam, the Netherlands
| | - Maxim J. H. L. Mulder
- Department of Neurology, Erasmus MC University Medical Center, Rotterdam, the Netherlands
| | - Bob Roozenbeek
- Department of Neurology, Erasmus MC University Medical Center, Rotterdam, the Netherlands
| | - Ewout W. Steyerberg
- Department of Biomedical Data Sciences, Leiden University Medical Center, Leiden, the Netherlands
| | - Marieke J. H. Wermer
- Department of Neurology, Leiden University Medical Center, Leiden, the Netherlands
| | | | - H. Bart van der Worp
- Department of Neurology and Neurosurgery, University Medical Center Utrecht, Brain Center, Utrecht University, Utrecht, the Netherlands
| | - Mayank Goyal
- Departments of Clinical Neuroscience and Radiology, Hotchkiss Brain Institute, Cumming School of Medicine, University of Calgary, Calgary, Alberta, Canada
| | - Bruce C. V. Campbell
- Department of Medicine and Neurology, Royal Melbourne Hospital, University of Melbourne, Melbourne, Victoria, Australia
| | - Keith W. Muir
- Institute of Neuroscience & Psychology, University of Glasgow, Queen Elizabeth University Hospital, Glasgow, United Kingdom
| | - Francis Guillemin
- CHRU Nancy, Inserm, Université de Lorraine, CIC Clinical Epidemiology, Nancy, France
| | - Serge Bracard
- Department of Diagnostic and Interventional Neuroradiology, University of Lorraine and University Hospital of Nancy, Nancy, France
| | - Philip White
- Translational and Clinical Research Institute, Newcastle University, Newcastle upon Tyne, United Kingdom
| | - Antoni Dávalos
- Department of Neuroscience, Hospital Germans Trias y Pujol, Barcelona, Spain
| | - Tudor G. Jovin
- Stroke Institute, Department of Neurology, University of Pittsburgh Medical Center Stroke Institute, Presbyterian University Hospital, Pittsburgh, Pennsylvania
| | - Michael D. Hill
- Departments of Clinical Neuroscience and Radiology, Hotchkiss Brain Institute, Cumming School of Medicine, University of Calgary, Calgary, Alberta, Canada
| | - Peter J. Mitchell
- Department of Radiology, Royal Melbourne Hospital, University of Melbourne, Melbourne, Victoria, Australia
| | - Andrew M. Demchuk
- Departments of Clinical Neuroscience and Radiology, Hotchkiss Brain Institute, Cumming School of Medicine, University of Calgary, Calgary, Alberta, Canada
| | - Jeffrey L. Saver
- Department of Neurology and Comprehensive Stroke Center, David Geffen School of Medicine, University of Los Angeles, Los Angeles, California
| | - Aad van der Lugt
- Department of Radiology and Nuclear Medicine, Erasmus MC University Medical Center, Rotterdam, the Netherlands
| | - Scott Brown
- Altair Biostatistics, Mooresville, North Carolina
| | - Diederik W. J. Dippel
- Department of Neurology, Erasmus MC University Medical Center, Rotterdam, the Netherlands
| | - Hester F. Lingsma
- Department of Public Health, Erasmus MC University Medical Center, Rotterdam, the Netherlands
| |
Collapse
|
11
|
Pluta R, Miziak B, Czuczwar SJ. Apitherapy in Post-Ischemic Brain Neurodegeneration of Alzheimer's Disease Proteinopathy: Focus on Honey and Its Flavonoids and Phenolic Acids. Molecules 2023; 28:5624. [PMID: 37570596 PMCID: PMC10420307 DOI: 10.3390/molecules28155624] [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: 06/30/2023] [Revised: 07/20/2023] [Accepted: 07/22/2023] [Indexed: 08/13/2023] Open
Abstract
Neurodegeneration of the brain after ischemia is a major cause of severe, long-term disability, dementia, and mortality, which is a global problem. These phenomena are attributed to excitotoxicity, changes in the blood-brain barrier, neuroinflammation, oxidative stress, vasoconstriction, cerebral amyloid angiopathy, amyloid plaques, neurofibrillary tangles, and ultimately neuronal death. In addition, genetic factors such as post-ischemic changes in genetic programming in the expression of amyloid protein precursor, β-secretase, presenilin-1 and -2, and tau protein play an important role in the irreversible progression of post-ischemic neurodegeneration. Since current treatment is aimed at preventing symptoms such as dementia and disability, the search for causative therapy that would be helpful in preventing and treating post-ischemic neurodegeneration of Alzheimer's disease proteinopathy is ongoing. Numerous studies have shown that the high contents of flavonoids and phenolic acids in honey have antioxidant, anti-inflammatory, anti-apoptotic, anti-amyloid, anti-tau protein, anticholinesterase, serotonergic, and AMPAK activities, influencing signal transmission and neuroprotective effects. Notably, in many preclinical studies, flavonoids and phenolic acids, the main components of honey, were also effective when administered after ischemia, suggesting their possible use in promoting recovery in stroke patients. This review provides new insight into honey's potential to prevent brain ischemia as well as to ameliorate damage in advanced post-ischemic brain neurodegeneration.
Collapse
Affiliation(s)
- Ryszard Pluta
- Department of Pathophysiology, Medical University of Lublin, 20-090 Lublin, Poland; (B.M.); (S.J.C.)
| | | | | |
Collapse
|
12
|
Liao YC, Wang JW, Guo C, Bai M, Ran Z, Wen LM, Ju BW, Ding Y, Hu JP, Yang JH. Cistanche tubulosa alleviates ischemic stroke-induced blood-brain barrier damage by modulating microglia-mediated neuroinflammation. JOURNAL OF ETHNOPHARMACOLOGY 2023; 309:116269. [PMID: 36863639 DOI: 10.1016/j.jep.2023.116269] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 12/06/2022] [Revised: 02/08/2023] [Accepted: 02/11/2023] [Indexed: 06/18/2023]
Abstract
ETHNOPHARMACOLOGICAL RELEVANCE Ischemic stroke (IS) has both high morbidity and mortality. Previous research conducted by our group demonstrated that the bioactive ingredients of the traditional medicinal and edible plant Cistanche tubulosa (Schenk) Wight (CT) have various pharmacological effects in treating nervous system diseases. However, the effect of CT on the blood-brain barrier (BBB) after IS are still unknown. AIM OF THE STUDY This study aimed to identify CT's curative effect on IS and explore its underlying mechanism. MATERIALS AND METHODS IS injury was established in a rat model of middle cerebral artery occlusion (MCAO). Gavage administration of CT at dosages of 50, 100, and 200 mg/kg/day was carried out for seven consecutive days. Network pharmacology was used for predicting the pathways and potential targets of CT against IS, and subsequent studies confirmed the relevant targets. RESULTS According to the results, both neurological dysfunction and BBB disruption were exacerbated in the MCAO group. Moreover, CT improved BBB integrity and neurological function and protected against cerebral ischemia injury. Network pharmacology revealed that IS might involve neuroinflammation mediated by microglia. Extensive follow-up studies verified that MCAO caused IS by stimulating the production of inflammatory factors and microglial infiltration. CT was found to influence neuroinflammation via microglial M1-M2 polarization. CONCLUSION These findings suggested that CT may regulate microglia-mediated neuroinflammation by reducing MCAO-induced IS. The results provide theoretical and experimental evidence for the efficacy of CT therapy and novel concepts for the prevention and treatment of cerebral ischemic injuries.
Collapse
Affiliation(s)
- Yu-Cheng Liao
- College of Pharmacy, Xinjiang Medical University, Urumqi, 830054, China; Department of Pharmacy, Xijing Hospital, Fourth Military Medical University, Xi'an, 710032, China
| | - Jing-Wen Wang
- Department of Pharmacy, Xijing Hospital, Fourth Military Medical University, Xi'an, 710032, China
| | - Chao Guo
- Department of Pharmacy, Xijing Hospital, Fourth Military Medical University, Xi'an, 710032, China
| | - Min Bai
- Department of Pharmacy, Xijing Hospital, Fourth Military Medical University, Xi'an, 710032, China
| | - Zheng Ran
- College of Pharmacy, Xinjiang Medical University, Urumqi, 830054, China
| | - Li-Mei Wen
- Department of Pharmacy, The First Affiliated Hospital, Xinjiang Medical University, Urumqi, 830011, China
| | - Bo-Wei Ju
- College of Pharmacy, Xinjiang Medical University, Urumqi, 830054, China; Department of Pharmacy, The Fifth Affiliated Hospital, Xinjiang Medical University, Urumqi, 830011, China
| | - Yi Ding
- Department of Pharmacy, Xijing Hospital, Fourth Military Medical University, Xi'an, 710032, China.
| | - Jun-Ping Hu
- College of Pharmacy, Xinjiang Medical University, Urumqi, 830054, China.
| | - Jian-Hua Yang
- Department of Pharmacy, The First Affiliated Hospital, Xinjiang Medical University, Urumqi, 830011, China.
| |
Collapse
|
13
|
Mujanovic A, Brigger R, Kurmann CC, Ng F, Branca M, Dobrocky T, Meinel TR, Windecker D, Almiri W, Grunder L, Beyeler M, Seiffge DJ, Pilgram-Pastor S, Arnold M, Piechowiak EI, Campbell B, Gralla J, Fischer U, Kaesmacher J. Prediction of delayed reperfusion in patients with incomplete reperfusion following thrombectomy. Eur Stroke J 2023; 8:456-466. [PMID: 37231686 DOI: 10.1177/23969873231164274] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 05/27/2023] Open
Abstract
BACKGROUND The clinical course of patients with incomplete reperfusion after thrombectomy, defined as an expanded Thrombolysis in Cerebral Infarction (eTICI) score of 2a-2c, is heterogeneous. Patients showing delayed reperfusion (DR) have good clinical outcomes, almost comparable to patients with ad-hoc TICI3 reperfusion. We aimed to develop and internally validate a model that predicts DR occurrence in order to inform physicians about the likelihood of a benign natural disease progression. PATIENTS AND METHODS Single-center registry analysis including all consecutive, study-eligible patients admitted between 02/2015 and 12/2021. Preliminary variable selection for the prediction of DR was performed using bootstrapped stepwise backward logistic regression. Interval validation was performed with bootstrapping and the final model was developed using a random forests classification algorithm. Model performance metrics are reported with discrimination, calibration, and clinical decision curves. Primary outcome was concordance statistics as a measure of goodness of fit for the occurrence of DR. RESULTS A total of 477 patients (48.8% female, mean age 74 years) were included, of whom 279 (58.5%) showed DR on 24 follow-up. The model's discriminative ability for predicting DR was adequate (C-statistics 0.79 [95% CI: 0.72-0.85]). Variables with strongest association with DR were: atrial fibrillation (aOR 2.06 [95% CI: 1.23-3.49]), Intervention-To-Follow-Up time (aOR 1.06 [95% CI: 1.03-1.10]), eTICI score (aOR 3.49 [95% CI: 2.64-4.73]), and collateral status (aOR 1.33 [95% CI: 1.06-1.68]). At a risk threshold of R = 30%, use of the prediction model could potentially reduce the number of additional attempts in one out of four patients who will have spontaneous DR, without missing any patients who do not show spontaneous DR on follow-up. CONCLUSIONS The model presented here shows fair predictive accuracy for estimating chances of DR after incomplete thrombectomy. This may inform treating physicians on the chances of a favorable natural disease progression if no further reperfusion attempts are made.
Collapse
Affiliation(s)
- Adnan Mujanovic
- Department of Diagnostic and Interventional Neuroradiology, University Hospital of Bern, University of Bern, Bern, Switzerland
| | - Robin Brigger
- Department of Diagnostic and Interventional Neuroradiology, University Hospital of Bern, University of Bern, Bern, Switzerland
| | - Christoph C Kurmann
- Department of Diagnostic and Interventional Neuroradiology, University Hospital of Bern, University of Bern, Bern, Switzerland
- Department of Diagnostic, Interventional and Pediatric Radiology, University Hospital of Bern, University of Bern, Bern, Switzerland
| | - Felix Ng
- Department of Medicine and Neurology, Melbourne Brain Centre at The Royal Melbourne Hospital, University of Melbourne, Parkville, VIC, Australia
| | | | - Tomas Dobrocky
- Department of Diagnostic and Interventional Neuroradiology, University Hospital of Bern, University of Bern, Bern, Switzerland
| | - Thomas R Meinel
- Department of Neurology, University Hospital of Bern, University of Bern, Bern, Switzerland
| | - Daniel Windecker
- Department of Diagnostic and Interventional Neuroradiology, University Hospital of Bern, University of Bern, Bern, Switzerland
| | - William Almiri
- Department of Diagnostic and Interventional Neuroradiology, University Hospital of Bern, University of Bern, Bern, Switzerland
| | - Lorenz Grunder
- Department of Diagnostic and Interventional Neuroradiology, University Hospital of Bern, University of Bern, Bern, Switzerland
| | - Morin Beyeler
- Department of Neurology, University Hospital of Bern, University of Bern, Bern, Switzerland
| | - David J Seiffge
- Department of Neurology, University Hospital of Bern, University of Bern, Bern, Switzerland
| | - Sara Pilgram-Pastor
- Department of Diagnostic and Interventional Neuroradiology, University Hospital of Bern, University of Bern, Bern, Switzerland
| | - Marcel Arnold
- Department of Neurology, University Hospital of Bern, University of Bern, Bern, Switzerland
| | - Eike I Piechowiak
- Department of Diagnostic and Interventional Neuroradiology, University Hospital of Bern, University of Bern, Bern, Switzerland
| | - Bruce Campbell
- Department of Medicine and Neurology, Melbourne Brain Centre at The Royal Melbourne Hospital, University of Melbourne, Parkville, VIC, Australia
| | - Jan Gralla
- Department of Diagnostic and Interventional Neuroradiology, University Hospital of Bern, University of Bern, Bern, Switzerland
| | - Urs Fischer
- Department of Neurology, University Hospital of Bern, University of Bern, Bern, Switzerland
- Department of Neurology, University Hospital of Basel, University of Basel, Basel, Switzerland
| | - Johannes Kaesmacher
- Department of Diagnostic and Interventional Neuroradiology, University Hospital of Bern, University of Bern, Bern, Switzerland
| |
Collapse
|
14
|
Karamchandani RR, Satyanarayana S, Yang H, Rhoten JB, Strong D, Patel NM, Clemente JD, Defilipp G, Bernard JD, Stetler WR, Parish JM, Asimos AW. The Charlotte Large Artery Occlusion Endovascular Therapy Outcome Score Predicts Poor Outcomes 1 Year After Endovascular Thrombectomy. World Neurosurg 2023; 173:e415-e421. [PMID: 36805504 DOI: 10.1016/j.wneu.2023.02.066] [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: 11/08/2022] [Revised: 02/12/2023] [Accepted: 02/13/2023] [Indexed: 02/22/2023]
Abstract
OBJECTIVE We evaluated the ability of several outcome prognostic scales to predict poor 1-year outcomes and mortality after endovascular thrombectomy. METHODS In this retrospective analysis from the stroke registry of a large integrated health system, consecutive patients presenting from August 2020 to September 2021 with an anterior circulation large-vessel occlusion stroke treated with endovascular thrombectomy were included. Multivariable logistic regression was performed to determine the ability of each scale to predict the primary outcome (1-year modified Rankin Scale [mRS] score of 4-6) and the secondary outcome (1-year mortality). Area under the curve analyses were performed for each scale. RESULTS In 237 included patients (mean age 68 [±15] years; median National Institutes of Health Stroke Scale score 16 [11-21]), poor 1-year outcomes were present in 116 patients (49%) and 1-year mortality was 34%. The CLEOS (Charlotte Large Artery Occlusion Endovascular Therapy Outcome Score), which incorporates age, baseline National Institutes of Health Stroke Scale score, initial glucose level, and computed tomography perfusion cerebral blood volume index, had a significant association with poor 1-year outcomes (per 25-point increase; odds ratio, 1.0134; P = 0.02). CLEOS and PRE (Pittsburgh Response to Endovascular Therapy) were both significantly associated with 1-year mortality. Area under the curve values were comparable for CLEOS, PRE, Houston Intra-Arterial Therapy 2, and Totaled Health Risks in Vascular Events to predict 1-year mRS score 4-6 and mortality. Only 1 of 18 patients with CLEOS ≥690 had a 1-year mRS score of 0-3. CONCLUSIONS CLEOS can predict poor 1-year outcomes and mortality for patients with anterior circulation large-vessel occlusion using prethrombectomy variables.
Collapse
Affiliation(s)
- Rahul R Karamchandani
- Department of Neurology, Neurosciences Institute, Atrium Health, Charlotte, North Carolina, USA.
| | - Sagar Satyanarayana
- Information and Analytics Services, Atrium Health, Charlotte, North Carolina, USA
| | - Hongmei Yang
- Information and Analytics Services, Atrium Health, Charlotte, North Carolina, USA
| | - Jeremy B Rhoten
- Department of Neurology, Neurosciences Institute, Atrium Health, Charlotte, North Carolina, USA
| | - Dale Strong
- Information and Analytics Services, Atrium Health, Charlotte, North Carolina, USA
| | - Nikhil M Patel
- Department of Internal Medicine, Pulmonary and Critical Care, Neurosciences Institute, Charlotte, North Carolina, USA
| | - Jonathan D Clemente
- Charlotte Radiology, Neurosciences Institute, Atrium Health, Charlotte, North Carolina, USA
| | - Gary Defilipp
- Charlotte Radiology, Neurosciences Institute, Atrium Health, Charlotte, North Carolina, USA
| | - Joe D Bernard
- Carolina Neurosurgery and Spine Associates, Neurosciences Institute, Atrium Health, Charlotte, North Carolina, USA
| | - William R Stetler
- Carolina Neurosurgery and Spine Associates, Neurosciences Institute, Atrium Health, Charlotte, North Carolina, USA
| | - Jonathan M Parish
- Carolina Neurosurgery and Spine Associates, Neurosciences Institute, Atrium Health, Charlotte, North Carolina, USA
| | - Andrew W Asimos
- Department of Emergency Medicine, Neurosciences Institute, Atrium Health, Charlotte, North Carolina, USA
| |
Collapse
|
15
|
Nie X, Leng X, Miao Z, Fisher M, Liu L. Clinically Ineffective Reperfusion After Endovascular Therapy in Acute Ischemic Stroke. Stroke 2023; 54:873-881. [PMID: 36475464 DOI: 10.1161/strokeaha.122.038466] [Citation(s) in RCA: 32] [Impact Index Per Article: 32.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/12/2022]
Abstract
Endovascular treatment is a highly effective therapy for acute ischemic stroke due to large vessel occlusion. However, in clinical practice, nearly half of the patients do not have favorable outcomes despite successful recanalization of the occluded artery. This unfavorable outcome can be defined as having clinically ineffective reperfusion. The objective of the review is to describe clinically ineffective reperfusion after endovascular therapy and its underlying risk factors and mechanisms, including initial tissue damage, cerebral edema, the no-reflow phenomenon, reperfusion injury, procedural features, and variations in postprocedural management. Further research is needed to more accurately identify patients at a high risk of clinically ineffective reperfusion after endovascular therapy and to improve individualized periprocedural management strategies, to increase the chance of achieving favorable clinical outcomes.
Collapse
Affiliation(s)
- Ximing Nie
- Department of Neurology (X.N., L.L.), Beijing Tiantan Hospital, Capital Medical University, China.,China National Clinical Research Center for Neurological Diseases, Beijing (X.N., L.L.)
| | - Xinyi Leng
- Department of Medicine and Therapeutics, Prince of Wales Hospital, Chinese University of Hong Kong, SAR (X.L.)
| | - Zhongrong Miao
- Department of Interventional Neuroradiology (Z.M.), Beijing Tiantan Hospital, Capital Medical University, China
| | - Marc Fisher
- Department of Neurology, Beth Israel Deaconess Medical Center, Harvard Medical School, Boston, MA (M.F.)
| | - Liping Liu
- Department of Neurology (X.N., L.L.), Beijing Tiantan Hospital, Capital Medical University, China.,China National Clinical Research Center for Neurological Diseases, Beijing (X.N., L.L.)
| |
Collapse
|
16
|
Karamchandani RR, Yang H, Rhoten JB, Strong D, Satyanarayana S, Asimos AW. Validation of the Charlotte large artery occlusion endovascular therapy outcome score using Viz.ai-derived cerebral blood volume index. Interv Neuroradiol 2023:15910199221149563. [PMID: 36617962 DOI: 10.1177/15910199221149563] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/10/2023] Open
Abstract
BACKGROUND The Charlotte large artery occlusion endovascular therapy outcome score (CLEOS) predicts poor 90-day outcomes for patients presenting with internal carotid artery (ICA) or middle cerebral artery (MCA) occlusions. It incorporates RAPID-derived cerebral blood volume (CBV) index, a marker of collateral circulation. We validated the predictive ability of CLEOS with Viz.ai-processed computed tomography perfusion (CTP) imaging. METHODS The original CLEOS derivation cohort was compared to a validation cohort consisting of all ICA and MCA thrombectomy patients treated at a large health system with Viz.ai-processed CTP. Rates of poor 90-day outcome (mRS 4-6) were compared in the derivation and validation cohorts, stratified by CLEOS. CLEOS was compared to previously described prediction models using area under the curve (AUC) analyses. Calibration of CLEOS was performed to compare predicted risk of poor outcomes with observed outcomes. RESULTS One-hundred eighty-one patients (mean age 66.4 years, median NIHSS 16) in the validation cohort were included. The validation cohort had higher median CTP core volumes (24 vs 8 ml) and smaller median mismatch volumes (81 vs 101 ml) than the derivation cohort. CLEOS-predicted poor outcomes strongly correlated with observed outcomes (R2 = 0.82). AUC for CLEOS in the validation cohort (0.72, 95% CI 0.64-0.80) was similar to the derivation cohort (AUC 0.75, 95% CI 0.70-0.80) and was comparable or superior to previously described prognostic models. CONCLUSIONS CLEOS can predict risk of poor 90-day outcomes in ICA and MCA thrombectomy patients evaluated with pre-intervention, Viz.ai-processed CTP.
Collapse
Affiliation(s)
| | - Hongmei Yang
- Information and Analytics Services, 2351Atrium Health, Charlotte, NC, USA
| | - Jeremy B Rhoten
- Neurology, Neurosciences Institute, 2351Atrium Health, Charlotte, NC, USA
| | - Dale Strong
- Information and Analytics Services, 2351Atrium Health, Charlotte, NC, USA
| | | | - Andrew W Asimos
- Emergency Medicine, Neurosciences Institute, 2351Atrium Health, Charlotte, NC, USA
| |
Collapse
|
17
|
Quandt F, Meißner N, Wölfer TA, Flottmann F, Deb-Chatterji M, Kellert L, Fiehler J, Goyal M, Saver JL, Gerloff C, Thomalla G, Tiedt S. RCT versus real-world cohorts: Differences in patient characteristics drive associations with outcome after EVT. Eur Stroke J 2022; 8:231-240. [PMID: 37021166 PMCID: PMC10069173 DOI: 10.1177/23969873221142642] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/25/2022] [Accepted: 11/09/2022] [Indexed: 12/23/2022] Open
Abstract
Background: The selection of patients with large-vessel occlusion (LVO) stroke for endovascular treatment (EVT) depends on patient characteristics and procedural metrics. The relation of these variables to functional outcome after EVT has been assessed in numerous datasets from both randomized controlled trials (RCT) and real-world registries, but whether differences in their case mix modulate outcome prediction is unknown. Methods: We leveraged data from individual patients with anterior LVO stroke treated with EVT from completed RCTs from the Virtual International Stroke Trials Archive ( N = 479) and from the German Stroke Registry ( N = 4079). Cohorts were compared regarding (i) patient characteristics and procedural pre-EVT metrics, (ii) these variables’ relation to functional outcome, and (iii) the performance of derived outcome prediction models. Relation to outcome (functional dependence defined by a modified Rankin Scale score of 3–6 at 90 days) was analyzed by logistic regression models and a machine learning algorithm. Results: Ten out of 11 analyzed baseline variables differed between the RCT and real-world cohort: RCT patients were younger, had higher admission NIHSS scores, and received thrombolysis more often (all p < 0.0001). Largest differences at the level of individual outcome predictors were observed for age (RCT: adjusted odds ratio (aOR), 1.29 (95% CI, 1.10–1.53) vs real-world aOR, 1.65 (95% CI, 1.54–1.78) per 10-year increments, p < 0.001). Treatment with intravenous thrombolysis was not significantly associated with functional outcome in the RCT cohort (aOR, 1.64 (95 % CI, 0.91–3.00)), but in the real-world cohort (aOR, 0.81 (95% CI, 0.69–0.96); p for cohort heterogeneity = 0.056). Outcome prediction was more accurate when constructing and testing the model using real-world data compared to construction with RCT data and testing on real-world data (area under the curve, 0.82 (95% CI, 0.79–0.85) vs 0.79 (95% CI, 0.77–0.80), p = 0.004). Conclusions: RCT and real-world cohorts considerably differ in patient characteristics, individual outcome predictor strength, and overall outcome prediction model performance.
Collapse
Affiliation(s)
- Fanny Quandt
- Department of Neurology, University Medical Center Hamburg-Eppendorf, Hamburg, Germany
| | - Nina Meißner
- Institute for Stroke and Dementia Research, University Hospital, LMU Munich, Munich, Germany
| | - Teresa A Wölfer
- Institute for Stroke and Dementia Research, University Hospital, LMU Munich, Munich, Germany
| | - Fabian Flottmann
- Department of Diagnostic and Interventional Neuroradiology, University Medical Center Hamburg-Eppendorf, Hamburg, Germany
| | - Milani Deb-Chatterji
- Department of Neurology, University Medical Center Hamburg-Eppendorf, Hamburg, Germany
| | - Lars Kellert
- Department of Neurology, University Hospital, LMU Munich, Munich, Germany
| | - Jens Fiehler
- Department of Diagnostic and Interventional Neuroradiology, University Medical Center Hamburg-Eppendorf, Hamburg, Germany
| | - Mayank Goyal
- Department of Radiology, University of Calgary, Foothills Medical Centre, Calgary, AB, Canada
| | - Jeffrey L Saver
- Department of Neurology and Comprehensive Stroke Center, David Geffen School of Medicine, University of California Los Angeles, Los Angeles, CA, USA
| | - Christian Gerloff
- Department of Neurology, University Medical Center Hamburg-Eppendorf, Hamburg, Germany
| | - Götz Thomalla
- Department of Neurology, University Medical Center Hamburg-Eppendorf, Hamburg, Germany
| | - Steffen Tiedt
- Institute for Stroke and Dementia Research, University Hospital, LMU Munich, Munich, Germany
| |
Collapse
|
18
|
Ordies S, Lesenne A, Bekelaar K, Demeestere J, Lemmens R, Vanacker P, Mesotten D. Multicentric validation of a reduced features case-mix set for predicting functional outcome after ischemic stroke in Belgium. Acta Neurol Belg 2022; 123:545-551. [PMID: 36409450 DOI: 10.1007/s13760-022-02142-5] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/08/2022] [Accepted: 11/06/2022] [Indexed: 11/22/2022]
Abstract
INTRODUCTION Ischemic stroke is the second cause of death and leading cause of severe disability worldwide. A reduced features set of CT-DRAGON (age, NIHSS on admission and pre-stroke mRS) predicts 90-day functional outcome after stroke in a single center. The current study was designed to validate this adapted CT-DRAGON score in three major Belgian hospitals, in the framework of future case-mix adjustment. METHODS This retrospective study included stroke patients, treated by thrombolysis, thrombectomy, a combination of both or neither thrombolysis or thrombectomy (conservative treatment) in 2019. Patient characteristics and 90-day mRS were collected. Multivariable logistic regression analysis of 90-day mRS 0-2 vs. 3-6 and 0-5 vs. 6 with the reduced features set was performed. Discriminative performance was assessed by the area under the receiver operating characteristic curve (AUROC). RESULTS Thirty-three percent of patients (413/1243) underwent treatment. Majority of strokes was treated conservatively (n = 830, 67%), 18% (n = 225) was treated by thrombolysis, 7% (n = 88) by thrombectomy and 8% (n = 100) by thrombolysis and thrombectomy. Age, NIHSS and pre-stroke mRS were independently associated with 90-day mRS 0-2 (all p ≤ 0.0001, AUROC 0.88). When treatment modality was added in the model, age, NIHSS, pre-stroke mRS and treatment modality were independently associated with 90-day mRS 0-2 (p < 0.0001, p < 0.0001, p < 0.0001 and p = 0.0001) AUROC 0.89). Age, NIHSS, pre-stroke mRS and treatment modality were independently associated with 90-day survival (p = 0.0001, p < 0.0001, p < 0.0001 and p = 0.008, AUROC 0.86). DISCUSSION The reduced features set (age, NIHSS and pre-mRS) was independently associated with long-term functional outcome in a Belgian multicentric cohort, making it useful for case-mix adjustments in Belgian stroke centers. Treatment modality was associated with long-term outcome.
Collapse
Affiliation(s)
- Sofie Ordies
- Department of Anesthesiology, Intensive Care Medicine, Emergency Medicine and Pain Therapy, Ziekenhuis Oost-Limburg Genk, Genk, Belgium
- Department of Anesthesiology, University Hospitals Leuven, Leuven, Belgium
| | - Anouk Lesenne
- Department of Anesthesiology, Intensive Care Medicine, Emergency Medicine and Pain Therapy, Ziekenhuis Oost-Limburg Genk, Genk, Belgium
- Department of Anesthesiology and Perioperative Medicine, Ghent University Hospital, Ghent, Belgium
| | - Kim Bekelaar
- Department of Neurology, Ziekenhuis Oost-Limburg Genk, Genk, Belgium
| | - Jelle Demeestere
- Department of Neurology, University Hospitals Leuven, Leuven, Belgium
| | - Robin Lemmens
- Department of Neurology, University Hospitals Leuven, Leuven, Belgium
| | - Peter Vanacker
- Department of Neurology, AZ Groeninge Kortrijk, Kortrijk, Belgium
- Neurovascular Center and Stroke Unit Antwerp, Antwerp University Hospital, Antwerp, Belgium
- Faculty of Medicine and Health Sciences, University of Antwerp, Antwerp, Belgium
| | - Dieter Mesotten
- Department of Anesthesiology, Intensive Care Medicine, Emergency Medicine and Pain Therapy, Ziekenhuis Oost-Limburg Genk, Genk, Belgium.
- Faculty of Medicine and Life Sciences, University of Hasselt, Diepenbeek, Belgium.
| |
Collapse
|
19
|
Zeng M, Oakden-Rayner L, Bird A, Smith L, Wu Z, Scroop R, Kleinig T, Jannes J, Jenkinson M, Palmer LJ. Pre-thrombectomy prognostic prediction of large-vessel ischemic stroke using machine learning: A systematic review and meta-analysis. Front Neurol 2022; 13:945813. [PMID: 36158960 PMCID: PMC9495610 DOI: 10.3389/fneur.2022.945813] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/17/2022] [Accepted: 08/18/2022] [Indexed: 11/20/2022] Open
Abstract
Introduction Machine learning (ML) methods are being increasingly applied to prognostic prediction for stroke patients with large vessel occlusion (LVO) treated with endovascular thrombectomy. This systematic review aims to summarize ML-based pre-thrombectomy prognostic models for LVO stroke and identify key research gaps. Methods Literature searches were performed in Embase, PubMed, Web of Science, and Scopus. Meta-analyses of the area under the receiver operating characteristic curves (AUCs) of ML models were conducted to synthesize model performance. Results Sixteen studies describing 19 models were eligible. The predicted outcomes include functional outcome at 90 days, successful reperfusion, and hemorrhagic transformation. Functional outcome was analyzed by 10 conventional ML models (pooled AUC=0.81, 95% confidence interval [CI]: 0.77–0.85, AUC range: 0.68–0.93) and four deep learning (DL) models (pooled AUC=0.75, 95% CI: 0.70–0.81, AUC range: 0.71–0.81). Successful reperfusion was analyzed by three conventional ML models (pooled AUC=0.72, 95% CI: 0.56–0.88, AUC range: 0.55–0.88) and one DL model (AUC=0.65, 95% CI: 0.62–0.68). Conclusions Conventional ML and DL models have shown variable performance in predicting post-treatment outcomes of LVO without generally demonstrating superiority compared to existing prognostic scores. Most models were developed using small datasets, lacked solid external validation, and at high risk of potential bias. There is considerable scope to improve study design and model performance. The application of ML and DL methods to improve the prediction of prognosis in LVO stroke, while promising, remains nascent. Systematic review registration https://www.crd.york.ac.uk/prospero/display_record.php?ID=CRD42021266524, identifier CRD42021266524
Collapse
Affiliation(s)
- Minyan Zeng
- Australian Institute for Machine Learning, University of Adelaide, Adelaide, SA, Australia
- School of Public Health, University of Adelaide, Adelaide, SA, Australia
- *Correspondence: Minyan Zeng
| | - Lauren Oakden-Rayner
- Australian Institute for Machine Learning, University of Adelaide, Adelaide, SA, Australia
- School of Public Health, University of Adelaide, Adelaide, SA, Australia
- Department of Radiology, Royal Adelaide Hospital, Adelaide, SA, Australia
| | - Alix Bird
- Australian Institute for Machine Learning, University of Adelaide, Adelaide, SA, Australia
- School of Public Health, University of Adelaide, Adelaide, SA, Australia
| | - Luke Smith
- Australian Institute for Machine Learning, University of Adelaide, Adelaide, SA, Australia
- School of Public Health, University of Adelaide, Adelaide, SA, Australia
| | - Zimu Wu
- School of Public Health and Preventive Medicine, Monash University, Melbourne, VIC, Australia
| | - Rebecca Scroop
- Department of Radiology, Royal Adelaide Hospital, Adelaide, SA, Australia
- Faculty Health and Medical Science, School of Medicine, University of Adelaide, Adelaide, SA, Australia
| | - Timothy Kleinig
- Faculty Health and Medical Science, School of Medicine, University of Adelaide, Adelaide, SA, Australia
- Department of Neurology, Royal Adelaide Hospital, Adelaide, SA, Australia
| | - Jim Jannes
- Faculty Health and Medical Science, School of Medicine, University of Adelaide, Adelaide, SA, Australia
- Department of Neurology, Royal Adelaide Hospital, Adelaide, SA, Australia
| | - Mark Jenkinson
- Australian Institute for Machine Learning, University of Adelaide, Adelaide, SA, Australia
- Functional Magnetic Resonance Imaging of the Brain Centre, University of Oxford, Oxford, United Kingdom
| | - Lyle J. Palmer
- Australian Institute for Machine Learning, University of Adelaide, Adelaide, SA, Australia
- School of Public Health, University of Adelaide, Adelaide, SA, Australia
| |
Collapse
|