Predicting the clinical prognosis of acute ischemic stroke using machine learning: an application of radiomic biomarkers on non-contrast CT after intravascular interventional treatment

 Predicting failure to recover is ABSOLUTELY FUCKING USELESS! When the hell will you do the research that produces recovery? Maybe when you are the 1 in 4 per WHO that has a stroke?

Predicting the clinical prognosis of acute ischemic stroke using machine learning: an application of radiomic biomarkers on non-contrast CT after intravascular interventional treatment

Hongxian Gu¹Yuting Yan²Xiaodong He²Yuyun Xu²Yuguo Wei³Yuan Shao^2*

• ¹Department of Radiology, The People's Hospital of Jianyang City, Jianyang, Sichuan Province, China
• ²Center for Rehabilitation Medicine, Department of Radiology, Zhejiang Provincial People's Hospital, Hangzhou, Zhejiang, China
• ³GE Healthcare Life Sciences, Hangzhou, Jiangsu, China

Purpose: This study aimed to develop a radiomic model based on non-contrast computed tomography (NCCT) after interventional treatment to predict the clinical prognosis of acute ischemic stroke (AIS) with large vessel occlusion.

Methods: We retrospectively collected 141 cases of AIS from 2016 to 2020 and analyzed the patients' clinical data as well as NCCT data after interventional treatment. Then, the total dataset was divided into training and testing sets according to the subject serial number. The cerebral hemispheres on the infarct side were segmented for radiomics signature extraction. After radiomics signatures were standardized and dimensionality reduced, the training set was used to construct a radiomics model using machine learning. The testing set was then used to validate the prediction model, which was evaluated based on discrimination, calibration, and clinical utility. Finally, a joint model was constructed by incorporating the radiomics signatures and clinical data.

Results: The AUCs of the joint model, radiomics signature, NIHSS score, and hypertension were 0.900, 0.863, 0.727, and 0.591, respectively, in the training set. In the testing set, the AUCs of the joint model, radiomics signature, NIHSS score, and hypertension were 0.885, 0.840, 0.721, and 0.590, respectively.

Conclusion: Our results provided evidence that using post-interventional NCCT for a radiomic model could be a valuable tool in predicting the clinical prognosis of AIS with large vessel occlusion.(So you're going to tell your patients they are not going to recover because you incompetently never did the research on getting survivors recovered? Good luck listening to the screaming.)

Introduction

AIS is a neurological emergency with high rates of disability and mortality (Regenhardt et al., 2018). According to statistics, ~25–35% of strokes manifest as large vessel occlusion, and this group is the main target for intravascular interventional therapy (Kidwell et al., 2013). However, the hyperdense areas on postoperative NCCT often confuse clinicians as to whether it was a hemorrhage or contrast agent and affect subsequent treatment and clinical prognosis.

The relationship between the hyperdense area and clinical outcomes remains uncertain. Some studies have shown that patients with the hyperdense area had a higher score on the modified Rankin Scale (mRS) score at discharge or 90 days than those without the hyperdense area (Payabvash et al., 2014, 2015; Rouchaud et al., 2014; Chen et al., 2019, 2020), while others indicated that it did not affect functional outcomes (Lummel et al., 2014; An et al., 2019). We would like to use a new machine learning tool that could obtain more information, including the area of the hyperdense area, the area of concomitant hypodense infarction, the histogram of CT value distribution, and the degree of brain parenchyma swelling to make a one-stop prediction of clinical outcomes.

Radiomics, as a new technology, transforms subjective visual interpretation into image data-driven objective evaluation in a non-invasive way. It can extract a large number of quantitative features, such as shape, intensity, and texture, from images and further reflect more biological information related to the disease (Lambin et al., 2012; Yip and Aerts, 2016; Avanzo et al., 2017). Radiomics has successfully demonstrated the potential for multiple applications in stroke, and the extracted features can be used to diagnose stroke lesions, predict early transformation, and assess the long-term prognosis after stroke onset (Chen et al., 2021; Jiang et al., 2021). Peter et al. (2017) identified six texture features from NCCT images that could differentiate ischemic lesions from their contralateral normal tissues. In addition, Tang et al. (2020) quantified the penumbra and core area from both the apparent diffusion coefficient and cerebral blood flow maps in patients with AIS (< 9 h) using radiomic analysis, and in the external dataset, the constructed radiomic nomogram could strongly predict favorable clinical outcomes at 7 days and 3 months. Clinically, NCCT is the first choice for AIS patients after intervention because it is efficient, non-invasive, and low in cost. Nevertheless, little is known about the relationship between the radiomics signatures based on NCCT after AIS intervention and the clinical prognosis.

Therefore, we aimed to develop a radiomics model to predict the clinical prognosis of AIS patients with interventional treatment. Then, the correlation between texture features and clinical outcome was further elucidated to identify potential biomarkers for clinical prognosis.

More at link.

The use of accelerometer bracelets to evaluate arm motor function over a stroke rehabilitation period – an explorative observational study

 Assessments are completely worthless unless they point directly to the 100% recovery protocols. I see nothing here that suggests you go from the assessment to the chosen 100% recovery protocol. When the hell will the stroke medical world do ANYTHING TO GET STROKE SOLVED? I'd have you all fired! A lot of dead wood needs to removed in stroke and until that occurs stroke will never be solved!

Look how bad this is; NOT EVEN MEASURING 100% RECOVERY!

Are you that blitheringly stupid? 100% recovery is the only goal in stroke, if you don't measure that you'll never get there!

 You measure RESULTS AND RECOVERY! Not this accelerometer crap!

“What's measured, improves.” So said management legend and author Peter F. Drucker 

The latest crapola here:

The use of accelerometer bracelets to evaluate arm motor function over a stroke rehabilitation period – an explorative observational study

• Eric Lyckegård Finn,
• Håkan Carlsson,
• Petter Ericson,
• Kalle Åström,
• Christina Brogårdh &
• Johan Wasselius 

Journal of NeuroEngineering and Rehabilitation volume 21, Article number: 82 (2024) Cite this article

• Metrics details

Abstract

Background

Assessments of arm motor function are usually based on clinical examinations or self-reported rating scales. Wrist-worn accelerometers can be a good complement to measure movement patterns after stroke. Currently there is limited knowledge of how accelerometry correlate to clinically used scales. The purpose of this study was therefore to evaluate the relationship between intermittent measurements of wrist-worn accelerometers and the patient’s progression of arm motor function assessed by routine clinical outcome measures during a rehabilitation period.

Methods

Patients enrolled in in-hospital rehabilitation following a stroke were invited. Included patients were asked to wear wrist accelerometers for 24 h at the start (T1) and end (T2) of their rehabilitation period. On both occasions arm motor function was assessed by the modified Motor Assessment Scale (M_MAS) and the Motor Activity Log (MAL). The recorded accelerometry was compared to M_MAS and MAL.

Results

20 patients were included, of which 18 completed all measurements and were therefore included in the final analysis. The resulting Spearman’s rank correlation coefficient showed a strong positive correlation between measured wrist acceleration in the affected arm and M-MAS and MAL values at T1, 0.94 (p < 0.05) for M_MAS and 0.74 (p < 0.05) for the MAL values, and a slightly weaker positive correlation at T2, 0.57 (p < 0.05) for M_MAS and 0.46 − 0.45 (p = 0.06) for the MAL values. However, no correlation was seen for the difference between the two sessions.

Conclusions

The results confirm that the wrist acceleration can differentiate between the affected and non-affected arm, and that there is a positive correlation between accelerometry and clinical measures. Many of the patients did not change their M-MAS or MAL scores during the rehabilitation period, which may explain why no correlation was seen for the difference between measurements during the rehabilitation period. Further studies should include continuous accelerometry throughout the rehabilitation period to reduce the impact of day-to-day variability.

Introduction

Assessment of motor function and motion pattern is a central part of evaluation of neurological conditions.(NO, it's not you blithering idiots, it's completely useless without having protocols to followup!) Currently, such evaluation is largely based on self-reported rating scales and clinical examination by healthcare professionals. However, clinical examination is limited to assessing impairments or activity limitations but not the motion pattern in an objective way. Another limiting factor is that currently it is not possible to evaluate the patients in an in-home environment apart from self-reporting rating scales.

With the introduction of comfortable and affordable wearable sensors, detailed kinetic data can be a useful complement to clinical outcome measures, and continuously recorded with a low level of intrusiveness for the patient in an in-home environment. Such sensors include accelerometers [1,2,3,4], EMG sensors [5, 6] and magnets [7]. Sensors can be worn on the body [1, 8, 9], integrated in bracelets [2, 3, 7], or in gloves [10]. Sensors can be used for many purposes, such as activity monitoring of elderly [11], oncology patients [12], or to monitor vital signs in surgical patients [13].

One field where measurement of motor function with sensors is of great importance is within stroke rehabilitation, where long-term improvements may be difficult to quantify and separate from compensatory movement patterns and a learned non-use behavior [14]. Wearable sensors have been used within rehabilitation to monitor gait [8, 15], fall risk [1] and arm motor function [1, 6, 7] and are shown to be appreciated by rehabilitation professionals as well as by patients [16]. Sensors have also been combined with in-app training programs for home rehabilitation [2, 17] of chronic stroke patients to improve participation. Such in-app training programs can help measure and improve adherence to the training by providing instructions and guidance, but also providing an accessible communication platform with the rehabilitation team. Potentially, it could measure the training dose as well as the use of the affected arm in daily activities during the rehabilitation.

Sensors have also been used in stroke care, for diagnostic purposes by identifying unliteral arm motor deficit [3, 18,19,20], and for monitoring and evaluation of rehabilitation following stroke [21,22,23,24]. However, a study by Rand et al. 2012 on 60 stroke patients receiving rehabilitation, showed that upper extremity activity measured by activity monitors was not correlated to increased functional status of the affected arm [21]. Similar result has been seen in several other studies where functional recovery has not been correlated to increased arm movement as measured by accelerometry [23, 24]. Contradictory to this, Gohlke et al. showed that functional recovery was associated with increased arm movement when measured by bilateral wrist accelerometry at multiple times during the rehabilitation of 14 stroke patients [22]. Since the results of the various studies differ, more studies are needed within this area.

The purpose of this study was to evaluate the relationship between intermittent measurements of wrist-worn accelerometers and the patient’s progression of arm motor function as assessed by the clinical outcome measures Motor Assessment Scale (MAS) [25, 26] and Motor Activity Log (MAL) [27, 28] during an active rehabilitation period.

Our hypothesis was that an improvement in MAL and MAS would correlate with an increase in upper limb activity, as measured by the accelerometers, and normalization in the balance between right and left arm activity.

More at link.

Non-contrast head CT-based thrombolysis for wake-up/unknown onset stroke is safe: A single-center study and meta-analysis

Really, your tyranny of low expectations is so fucking low that you consider this a success? Talk to survivors sometime, they want 100% recovery. WHEN THE HELL WILL YOU GET THERE?

Non-contrast head CT-based thrombolysis for wake-up/unknown onset stroke is safe: A single-center study and meta-analysis

Show all authors

Alicia M Zha*, Haris Kamal*, Jerome A Jeevarajan, ...

First Published April 4, 2021 Review Article Find in PubMed 

https://doi.org/10.1177/17474930211006305

Article information

 

Abstract

Background

Recent studies have shown that tPA can be safely administered past the standard 4.5 h window with good outcomes when selected with multi-model imaging, which is often lacking outside of comprehensive stroke centers.

Aim

We aim to analyze the safety and outcomes of wake up/unknown onset (WUS/UNK) patients treated based on non-contrast head CT (NCCT) at our institution and in the literature.

Methods

Suspected stroke patients from January 2015 to December 2018 receiving tPA within 4.5 h (standard window-SW) and with WUS/UNK based on NCCT and clinical-imaging mismatch were identified. We compared baseline characteristics, tPA metrics, and outcome data, with primary outcome as symptomatic intracerebral hemorrhage (sICH). A meta-analysis was performed evaluating NCCT-based treatment of WUS/UNK patients.

Results

Of 1827 patients treated at our hub or through telestroke, 93 underwent WUS/UNK-based treatment. There was no statistical difference in sICH between WUS/UNK and SW: 1% vs. 4% (OR 0.3; 95% confidence interval 0.0–1.9). 90-day modified Rankin scale outcomes were similar between SW and WUS/UNK-treated patients. Seven studies encompassing 485 WUS/UNK patients were included in a pooled analysis with a 2.1% incidence of sICH. In our meta-analysis, three studies compared NCCT-based treated WUS/UNK patients with SW patients with no difference in rate of hemorrhage: 2.1% vs 3.4% (OR 1.01; 95% confidence interval 0.45–2.28).

Interpretation

Our single-center analysis and meta-analysis suggest that tPA can be safely administered based on NCCT with comparable rates of sICH for select WUS/UNK stroke patients.

Keywords Wake up stroke, thrombolysis, telestroke

Access Options

 

ASPECTS-based selection for late endovascular treatment: a retrospective two-site cohort study

 What you consider a 'better outcome' is still failure by any survivors reckoning. 100% recovery is the only goal in stroke. WHEN THE HELL ARE YOU GOING TO ACTUALLY GET AROUND TO SOLVING STROKE? This chipping at the edges is barely helping.

ASPECTS-based selection for late endovascular treatment: a retrospective two-site cohort study

Show all authors

Stefania Nannoni*, Johannes Kaesmacher*, Federico Ricciardi, ...

First Published April 22, 2021 Research Article Find in PubMed 

https://doi.org/10.1177/17474930211009806

Article information

Abstract

Introduction

The DAWN trial demonstrated the effectiveness of late endovascular treatment in acute ischemic stroke patients selected on the basis of a clinical-core mismatch. We explored in a real-world sample of endovascular treatment patients if a clinical-ASPECTS (Alberta Stroke Program Early CT Score) mismatch was associated with an outcome benefit after late endovascular treatment.

Methods

We retrospectively analyzed all consecutive acute ischemic stroke patients admitted 6–24 h after last proof of good health in two stroke centers, with initial National Institutes of Health Stroke Scale (NIHSS) ≥10 and an internal carotid artery or M1 occlusion. We defined clinical-ASPECTS mismatch as NIHSS ≥ 10 and ASPECTS ≥ 7, or NIHSS ≥ 20 and ASPECTS ≥ 5. We assessed the interaction between the presence of the clinical-ASPECTS mismatch and late endovascular treatment using ordinal shift analysis of the three-month modified Rankin Scale and adjusting for multiple confounders.

Results

The included 337 patients had a median age of 73 years (IQR = 61–82), admission NIHSS of 18 (15–22), and baseline ASPECTS of 7 (5–9). Out of 196 (58.2%) patients showing clinical-ASPECTS mismatch, 146 (74.5%) underwent late endovascular treatment. Among 141 (41.8%) mismatch negative patients, late endovascular treatment was performed in 72 (51.1%) patients. In the adjusted analysis, late endovascular treatment was significantly associated with a better outcome in the presence of clinical-ASPECTS mismatch (adjusted odd ratio, aOR = 2.83; 95% confidence interval, CI: 1.48–5.58) but not in its absence (aOR = 1.32; 95%CI: 0.61–2.84). The p-value for the interaction term between clinical-ASPECTS mismatch and late endovascular treatment was 0.073.

Conclusions

In our retrospective two-site analysis, late endovascular treatment seemed effective(Since you didn't get to 100% recovery, in no sense of the word can it be considered effective.) in the presence of a clinical-ASPECTS mismatch, but not in its absence. If confirmed in randomized trials, this finding could support the use of an ASPECTS-based selection for late endovascular treatment decisions, obviating the need for advanced imaging.

Keywords Acute ischemic stroke, late time window, endovascular treatment, ASPECTS

Introduction

Recent randomized clinical trials have provided class I evidence for the efficacy of endovascular treatment (EVT) in acute ischemic stroke (AIS) patients from proximal anterior circulation large vessel occlusion (LVO) in the late-time window, if properly selected based on their neuroimaging profile.^1–3 However, we previously demonstrated that the proportion of late-admitted AIS eligible for EVT according to strict trial criteria was low in the real-life scenario.⁴

Enlarging the selection criteria for late EVT could allow a larger population of AIS patients to benefit from the revascularization procedures. Notably, the use of a simpler neuroimaging protocol could help with the decision to proceed with mechanical thrombectomy in case of absent, failed or contraindicated advanced imaging, or in situations of discordant imaging profile.⁵

The Alberta Stroke Program Early CT Score (ASPECTS) is an easily applicable tool to estimate the amount of irreversibly damaged brain tissue in the middle cerebral artery (MCA) territory strokes.⁶ Originally designed for non-contrast CT scan (NCCT), it has been also applied to diffusion-weighted imaging (DWI) sequences, after one-point adjustment.⁷ However, the role of ASPECTS in selecting patients who are most likely to benefit from EVT is not clearly established in the late time window.^8,9 Also, to the best of our knowledge, its use in association of clinical stroke severity as a surrogate of the core-penumbra mismatch¹ has not been evaluated.

The main aim of our study was to analyze the clinical outcome of late-arriving AIS patients with proximal anterior circulation LVO depending on the presence of a clinical-ASPECTS mismatch and of treatment with mechanical thrombectomy in two comprehensive stroke centers.

More at link.

 

EXPRESS: Clinical Effectiveness of Endovascular Stroke Treatment in the Early and Extended Time Windows

But you didn't measure and report on 100% recovery so you didn't even have the correct objective for your research. 'Good outcome' is NOT GOOD ENOUGH!  When the hell will you start shooting for 100% recovery? The only goal in stroke!

EXPRESS: Clinical Effectiveness of Endovascular Stroke Treatment in the Early and Extended Time Windows

Show all authors

Raul Nogueira, Diogo C. Haussen, David S. Liebeskind, ...

First Published March 11, 2021 Research Article 

https://doi.org/10.1177/17474930211005740

Article information

   

Abstract

Background

The clinical efficacy of mechanical thrombectomy (MT) has been unequivocally demonstrated in multiple randomized clinical trials (RCTs). However, these studies were performed in carefully selected centers and utilized strict inclusion criteria.

Aim

We aimed to assess the clinical effectiveness of MT in a prospective registry.

Methods

A total of 2008 patients from 76 sites across 12 countries were enrolled in a prospective open-label MT registry. Patients were categorized into the corresponding cohorts of the SWIFT-Prime, DAWN, and DEFUSE 3 trials according to the basic demographic and clinical criteria without considering specific parenchymal imaging findings. Baseline and outcome variables were compared across the corresponding groups.

Results

As compared to the treated patients in the actual trials, registry-derived patients tended to be younger and had lower baseline ASPECTS. In addition, time to treatment was earlier and the use of IV-tPA and general anesthesia were higher in DAWN- and DEFUSE 3-registry derived patients versus their corresponding trials. Reperfusion rates were higher in the registry patients. The rates of 90-day good outcome (mRS0-2) in registry-derived patients were comparable to those of the patients treated in the corresponding RCTs (SWIFT-Prime,64.5% vs 60.2%; DAWN,50.4% vs 48.6%; Beyond-DAWN:52.4% vs 48.6%; DEFUSE 3, 52% vs 44.6%, respectively; all P>0.05). Registry-derived patients had significant less disability than the corresponding RCT controls (ordinal mRS shift OR, P<0.05 for all).

Conclusion

Our study provides favorable generalizability data for the safety and efficacy of thrombectomy in the €œreal-world€ setting and supports that patients may be safely treated outside the constraints of RCTs.

Keywords Acute stroke therapy, Stroke, Treatment, registry, thrombectomy, time

Access Options

 

Stroke Imaging Selection Modality and Endovascular Therapy Outcomes in the Early and Extended Time Windows

NOT GOOD ENOUGH! 'Better outcomes' is the tyranny of low expectations in full display. The goal is 100% recovery. WHEN THE HELL WILL YOU EVEN TRY TO GET THERE?

Stroke Imaging Selection Modality and Endovascular Therapy Outcomes in the Early and Extended Time Windows

Raul G. Nogueira

,

Diogo C. Haussen

,

David Liebeskind

,

Tudor G. Jovin

,

Rishi Gupta

,

Ashutov Jadhav

,

Ron F. Budzik

,

Blaise Baxter

,

Antonin Krajina

,

Alain Bonafe

,

Ali Malek

, … See all authors

Originally published12 Jan 2021https://doi.org/10.1161/STROKEAHA.120.031685Stroke. 2021;52:491–497

Abstract

Background and Purpose:

Advanced imaging has been increasingly used for patient selection in endovascular stroke therapy. The impact of imaging selection modality on endovascular stroke therapy clinical outcomes in extended time window remains to be defined. We aimed to study this relationship and compare it to that noted in early-treated patients.

Methods:

Patients from a prospective multicentric registry (n=2008) with occlusions involving the intracranial internal carotid or the M1- or M2-segments of the middle cerebral arteries, premorbid modified Rankin Scale score 0 to 2 and time to treatment 0 to 24 hours were categorized according to treatment times within the early (0–6 hour) or extended (6–24 hour) window as well as imaging modality with noncontrast computed tomography (NCCT)±CT angiography (CTA) or NCCT±CTA and CT perfusion (CTP). The association between imaging modality and 90-day modified Rankin Scale, analyzed in ordinal (modified Rankin Scale shift) and dichotomized (functional independence, modified Rankin Scale score 0–2) manner, was evaluated and compared within and across the extended and early windows.

Results:

In the early window, 332 patients were selected with NCCT±CTA alone while 373 also underwent CTP. After adjusting for identifiable confounders, there were no significant differences in terms of 90-day functional disability (ordinal shift: adjusted odd ratio [aOR], 0.936 [95% CI, 0.709–1.238], P=0.644) or independence (aOR, 1.178 [95% CI, 0.833–1.666], P=0.355) across the CTP and NCCT±CTA groups. In the extended window, 67 patients were selected with NCCT±CTA alone while 180 also underwent CTP. No significant differences in 90-day functional disability (aOR, 0.983 [95% CI, 0.81–1.662], P=0.949) or independence (aOR, 0.640 [95% CI, 0.318–1.289], P=0.212) were seen across the CTP and NCCT±CTA groups. There was no interaction between the treatment time window (0–6 versus 6–24 hours) and CT selection modality (CTP versus NCCT±CTA) in terms of functional disability at 90 days (P=0.45).

Conclusions:

CTP acquisition was not associated with better outcomes in patients treated in the early or extended time windows. While confirmatory data is needed, our data suggests that extended window endovascular stroke therapy may remain beneficial even in the absence of advanced imaging.

 

Combination of Serum Neurofilament Light Chain Levels and MRI Markers to Predict Cognitive Function in Ischemic Stroke

Survivors don't give a crap about your fucking failure to recover predictions. They want specific recovery rehab options. 

WHEN THE HELL WILL YOU DO THAT?

 Combination of Serum Neurofilament Light Chain Levels and MRI Markers to Predict Cognitive Function in Ischemic Stroke

Show all authors

Yuan Peng, MD, PhD*, Qianfeng Li, MD*, Lei Qin, PhD, ...

First Published February 1, 2021 Research Article 

https://doi.org/10.1177/1545968321989354

Article information

 

Abstract

Background:

It is important to predict poststroke cognitive outcome to guide individualized treatment and prevention strategy. We aimed to evaluate the predictive value of the combination of a serum biomarker for axonal damage (neurofilament light chain [NfL]) and neuroimaging markers (volume of infarction and white matter hyperintensities [WMH]) for neuronal abnormality in poststroke cognitive outcome.

Methods:

A total of 1028 patients were screened; among them, 144 patients with acute ischemic stroke (stroke group) and 30 patients without stroke (control group) were enrolled. Serum NfL levels of samples obtained from both groups were measured through single molecule array assay. Neuroimaging markers of neuroaxonal injury, including infarct volume and WMH in the stroke group were quantified on magnetic resonance images using an in-house MATLAB code (MATLAB 2017; MathWorks). The primary outcome was the functional independence measure (FIM) cognitive subscores on discharge. We assessed the association of serum NfL levels and neuroimaging markers with cognitive outcome. The prognosis value of the combination of serum NfL levels and imaging markers for predicting FIM cognitive subscores on discharge was calculated using the area under curve (AUC) of the receiver operating characteristic.

Results:

Serum NfL levels of the stroke group were 9-fold higher than those of the control group (1449.7 vs 157.2 pg/mL, n = 144/30, P < .001). There was a correlation of serum NfL levels with infarct volume (r = 0.530, P < .001) and functional outcome, including FIM cognitive subscores (r = −0.387, P < .001) and FIM motor subscores on admission (r = −0.306, P < .001), but not with WMH volume after adjusting for infarct volume (r = −0.196, P = .245). Serum NfL levels on admission independently predicted poststroke FIM cognitive subscores on discharge (AUC = 0.672, P < .001). The predictive value for poststroke cognitive outcome was improved by combining serum NfL levels with infarct and WMH volume (AUC = 0.760, P < .001).

Conclusion:

The combination of serum NfL levels with volume of infarct and WMH shows an improved predictive value for cognitive function during acute rehabilitation phase after stroke, providing a promising panel of biomarkers for prognosis and guidance of treatment.(But you give us no guidance. Useless crapola here.)

Keywords ischemic stroke, cognitive function, FIM, functional independence measure, infarct volume, white matter hyperintensities, neurofilament light chain

Access Options