Automated decision-support system for prediction of treatment responders in acute ischemic stroke

You will need to find out how your hospital uses such a system to relegate you to a treatment protocol. This will be needed to be done in advance since if you are locked in and the lockedin protocol leads to minimal supportive treatment you are screwed. You can't allow the medical staff to determine this.
http://www.frontiersin.org/Journal/10.3389/fneur.2013.00140/full?utm_source=newsletter&utm_medium=email&utm_campaign=Neurology-w46-2013

Kartheeban Nagenthiraja^1,2*, Brian P. Walcott^3,4, Mikkel B. Hansen¹, Leif Østergaard¹ and Kim Mouridsen¹

• ¹Center of Functionally Integrative Neuroscience and MINDLab, Aarhus University, Aarhus, Denmark
• ²Athinoula A. Martinos Center for Biomedical Imaging, Massachusetts General Hospital and Harvard Medical School, Boston, MA, USA
• ³Department of Neurosurgery, Massachusetts General Hospital and Harvard Medical School, Boston, MA, USA
• ⁴Cardiovascular Research Center, Massachusetts General Hospital and Harvard Medical School, Charlestown, MA, USA

MRI is widely used in the assessment of acute ischemic stroke. In particular, it identifies the mismatch between hypoperfused and the permanently damaged tissue, the PWI-DWI mismatch volume. It is used to help triage patients into active or supportive treatment pathways. COMBAT Stroke is an automated software tool for estimating the mismatch volume and ratio based on MRI. Herein, we validate the decision made by the software with actual clinical decision rendered. Furthermore, we evaluate the association between treatment decisions (both automated and actual) and outcomes. COMBAT Stroke was used to determine PWI-DWI mismatch volume and ratio in 228 patients from two European multi-center stroke databases. We performed confusion matrix analysis to summarize the agreement between the automated selection and the clinical decision. Finally, we evaluated the clinical and imaging outcomes of the patients in the four entries of the confusion matrix (true positive, true negative, false negative, and false positive). About 186 of 228 patients with acute stroke underwent thrombolytic treatment, with the remaining 42 receiving supportive treatment only. Selection based on radiographic criteria using COMBAT Stroke classified 142 patients as potential candidates for thrombolytic treatment and 86 for supportive treatment; 60% sensitivity and 29% specificity. The patients deemed eligible for thrombolytic treatment by COMBAT Stroke demonstrated significantly higher rates of compromised tissue salvage, less neurological deficit, and were more likely to experience thrombus dissolving and reestablishment of normal blood flow at 24 h follow-up compared to those who were treated without substantial PWI-DWI mismatch. These results provide evidence that COMBAT Stroke, in addition to clinical assessment, may offer an optimal framework for a fast, efficient, and standardized clinical support tool to select patients for thrombolysis in acute ischemic stroke. (Once again proving that tPA is truly a goldilocks question)

More at link.

The goldilocks dilemma in acute ischemic stroke

They miss the point that tPA is basically a failure since only the 'right candidates' benefit. Not until we publicly call it a failure will there be a concerted effort to find something better and maybe go down the route of stopping the neuronal cascade of death.
http://www.frontiersin.org/Journal/10.3389/fneur.2013.00164/full?utm_source=newsletter&utm_medium=email&utm_campaign=Neurology-w46-2013
Aaron P. Tansy and David S. Liebeskind*

• Department of Neurology, UCLA Stroke Center, University of California, Los Angeles, CA, USA

Despite the advent of and exciting advances in novel endovascular therapies, t-PA remains the only proven treatment for acute ischemic stroke to date. Although a variety of reasons likely underlie why past trials of endovascular strategies have been unsuccessful, we address in this perspective piece one critical unknown for which a solution is undoubtedly necessary if future ones are to meet with success: determination and selection of patients that are “just right” for endovascular treatments, or the Goldilocks dilemma. Key clinical criteria highlighted in past trials may help provide a solution to this critical problem. However, for them to do so, we propose that they must be applied in service of a model that accounts for the nuanced, dynamic nature of acute ischemic stroke better than the prevailing “time is brain” model. We provide and examine three clinical cases to illustrate this proposal towards solving the Goldilocks dilemma and advancing treatment in acute ischemic stroke. Further, we address our field’s ongoing challenge and mission in the meantime to best care for the “not-so-right” patients, by far the majority of the affected stroke population.

The introduction of intravenous tissue plasminogen activator (t-PA) heralded a sea change in the management of acute ischemic stroke (AIS). For the first time ever, a medical therapy for acute stroke was proven effective in reducing long-term impairment (1). Since that landmark event nearly two decades ago, the AIS field has witnessed the exciting development of novel endovascular strategies and heightened hopes of potentially improving upon t-PA’s clinical efficacy (2–7). The Goldilocks dilemma, or finding the ideal patient who is “just right,” remains the most formidable challenge in establishing new therapies for AIS.

Unfortunately, as of yet, no endovascular method has demonstrated itself more clinically effective than t-PA either in head-to-head comparison or in combination with it (5–7). Why is this? This question is an undoubtedly challenging and complex one, but also an undoubtedly necessary one to answer. Indeed, continued progress in AIS treatment and any potential role that endovascular methods may play in it rests in the balance. We address the Goldilocks dilemma as a key unsolved piece of this larger problem that has already received a great deal of attention in the stroke community: identifying the ideal patients and enrolling them in clinical trials seeking to prove efficacy of endovascular treatments.

The recent disappointing outcomes in related trials are a reflection not necessarily of flawed endovascular therapies, but, rather, of flawed selection of candidates likely to benefit from them. We also propose that improvement of the theoretical framework of ischemic stroke on which the criteria for determination of “just right” trial-eligibility is based may allow future trials to finally achieve success. Finally, we emphasize that, although our Goldilocks search for the “just right” acute stroke patient is necessary for future improvement in care, we must not be distracted and neglect our primary mission to care for all stroke patients including those “not-so-right” – by far, the vast majority for whom we neurointensivists and neurohospitalists currently provide acute stroke care.

More at link.