Higher percentages of saturated fat in low-carb diets may not harm cholesterol levels, new analysis suggests

Useless, NO PROTOCOL. 

Higher percentages of saturated fat in low-carb diets may not harm cholesterol levels, new analysis suggests

Author Hanae ArmitagePublished on January 16, 2019

In the debate of low-fat versus low-carb diets, both can help you shed unwanted weight equally, as long as you’re choosing healthy options. But it turns out a diet composed of fewer carbs and higher percentages of saturated fat might actually have health benefits outside of weight loss — better blood cholesterol levels.
This finding came from a follow up analysis of the DIETFITS study, which set out to contrast the effects of low-carb versus low-fat dieting and determine which was better for losing weight. In a subgroup of 210 low-carb dieters, those who consumed a higher percent of saturated fats as part of their overall diet had better levels of blood lipids, including both higher HDLs (good cholesterol) and lower triglycerides, which are the main type of fat in the blood and in body fat storage.
That's not to say that saturated fats are suddenly exonerated — there's a bit of a catch, said Christopher Gardner, PhD, nutrition expert and senior author of the analysis. Those with the best lipid levels and highest percent of saturated fat intake also ate fewer carbohydrates, particularly added sugars and refined grains.
So the lesson here isn't that saturated fats are good for you, it's that they're not going to topple a good dieting effort that's low in carbs and refined sugars and high in whole foods and vegetables.
A secondary analysis paper detailing the findings appears in The American Journal of Clinical Nutrition. Cindy Shih, former research assistant at Stanford, is the first author.
"The people who were assigned to the low-carb group did a great job at cutting carbs, particularly from added sugars and refined grains. They didn’t get specific guidance about how much fat to eat, and according to their diet records, they didn't eat very differently in terms of the amount of fat intake," said Gardner.
The national guideline for saturated fat consumption is 10 percent of your diet, but since these folks consumed fewer calories from carbohydrates, the percent of fat, including saturated fat, technically increased, since it accounted for a higher proportion of their diet.
"So if one of these people were to go to their doctor the doctor might see an increase in saturated fat percent from 10 to 15 and be concerned. But if you look more closely, you see that the grams of fat they're eating didn't change much, and you see that they have higher HDL levels, stable LDL levels and lower levels of triglycerides."
This, Gardner says, is the punchline: Low-carb dieters with the highest saturated fat percentage had modestly better, not worse, blood lipid levels. But the actual amount of saturated fat they ate wasn’t much different — the high percentage was primarily due to the fact that these folks cut back the most on their carbohydrate intake.
"I want this finding to put people who are on a low-carb diet, and their doctors, more at ease about the percent of saturated fat consumption," said Gardner. "An increase to 15 percent exceeds the guidelines, but what matters most is the grams of fat and carbs, and the weight loss. If you or your patient is more successful at losing weight with a low-carb diet, you might not have to worry so much about the percent of saturated fat."

Toque installation challenges

My stroke was in May so nothing about winter weather was covered. The only way I can get a toque on is to put the bottom edge against a wall, put my forehead against that edge and use the good hand to pull it down around my ears.  Luckily my daughter knitted one that is quite roomy, all my tight fitting ones are impossible without someone else. I do despise the ushanka hats because the ear flaps have to be tied

Ushanka or trappers hat

Toque/Canadian or tassel hat

The Rise of Pseudomedicine for Dementia and Brain Health

Rather than just railing against this stuff, why don't you set up clinical research trials to prove one way or the other?  Or is that too fucking hard? Complaining is much easier and you can sit on your high horse looking down on the riff raff. 

The Rise of Pseudomedicine for Dementia and Brain Health

Joanna Hellmuth, MD, MHS¹; Gil D. Rabinovici, MD¹; Bruce L. Miller, MD¹

Author Affiliations Article Information

JAMA. Published online January 25, 2019. doi:10.1001/jama.2018.21560

The US population is aging, and with it is an increasing prevalence of Alzheimer disease, which lacks effective approaches for prevention or a cure.¹ Many individuals are concerned about developing cognitive changes and dementia. With increasing amounts of readily accessible information, people independently seek and find material about brain health interventions, although not all sources contain quality medical information.

This landscape of limited treatments for dementia, concern about Alzheimer disease, and wide access to information have brought a troubling increase in “pseudomedicine.” Pseudomedicine refers to supplements and medical interventions that exist within the law and are often promoted as scientifically supported treatments, but lack credible efficacy data. Practitioners of pseudomedicine often appeal to health concerns, promote individual testimony as established fact, advocate for unproven therapies, and achieve financial gains.

With neurodegenerative disease, the most common example of pseudomedicine is the promotion of dietary supplements to improve cognition and brain health. This $3.2-billion industry promoting brain health benefits from high-penetration consumer advertising through print media, radio, television, and the internet.² No known dietary supplement prevents cognitive decline or dementia, yet supplements advertised as such are widely available and appear to gain legitimacy when sold by major US retailers. Consumers are often unaware that dietary supplements do not undergo US Food and Drug Administration (FDA) testing for safety or review for efficacy. Indeed, supplements may cause harm, as has been shown with vitamin E, which may increase risk of hemorrhagic stroke, and, in high doses, increase risk of death.^3,4 The Alzheimer’s Association highlights these concerns, noting that many of these supplements are promoted by testimony rather than science.⁵ These brain health supplements can also be costly, and discussion of them in clinical settings can subvert valuable time needed for clinicians and patients to review other interventions.

Patients and caregivers encounter sophisticated techniques that supply false “scientific” backing for brain health interventions. For example, referring to scientific integrity, Feynman coined the term “cargo cult science” to describe endeavors that follow “…the apparent precepts and forms of scientific investigation, but they’re missing something essential….”⁶ Cargo cult science is apparent in material promoting some brain health supplements; “evidence” is presented in a scientific-appearing format that lacks actual substance and rigor. Feynman suggested 1 feature of scientific integrity is “bending over backwards to show how [the study] may be wrong…,” which is a feature that is often lacking when interventions are promoted for financial gain.⁶

A similarly concerning category of pseudomedicine involves interventions promoted by licensed medical professionals that target unsubstantiated etiologies of neurodegenerative disease (eg, metal toxicity; mold exposure; infectious causes, such as Lyme disease). Some of these practitioners may stand to gain financially by promoting interventions that are not covered by insurance, such as intravenous nutrition, personalized detoxification, chelation therapy, antibiotics, or stem cell therapy. These interventions lack a known mechanism for treating dementia and are costly, unregulated, and potentially harmful.

Recently, detailed protocols to reverse cognitive changes have been promoted, but these protocols merely repackage known dementia interventions (eg, cognitive training, exercise, a heart-healthy diet) and add supplements and other lifestyle changes. Such protocols are promoted by medical professionals with legitimate credentials, offer a unique holistic and personal approach, and are said to be based on rigorous data published in reputable journals. However, when examining the primary data, the troubling and familiar patterns of testimony and cargo cult science emerge. The primary scientific articles superficially appear valid, yet lack essential features, such as sufficient participant characterization, uniform interventions, or treatment randomization with control or placebo groups, and may fail to include sufficient study limitations. Some of these poor-quality studies may be published in predatory open access journals.⁷

An argument can be made that even though pseudomedicine may be ethically questionable, these interventions are relatively benign and offer hope for patients facing an incurable disease. However, these interventions are not ethically, medically, or financially benign for patients or their families. While appealing to a sense of hope can be a motivating factor for clinical trials or complementary or alternative practices, the difference is in how these circumstances are framed. Complementary or alternative practices are often adjunct treatments and might not result in direct financial gain by the practitioner recommending the therapy. Further, in clinical trials, there are structured conversations between researchers and participants (such as during the informed consent process) that include research coordinators explaining that any studied interventions are experimental, may result in no gain, and can cause harm. In contrast, pseudomedicine may involve unethical gain for practitioners and manufactured illusion of benefit for patients.

What Can Be Done?

Health care professionals have the responsibility to learn about common pseudomedicine interventions. If a patient or family member inquiries about such an intervention, clinicians can take several steps:

• Understand that motivations to pursue such interventions often come from a desire to obtain the best medical care, and convey that understanding to the patients.
• Provide honest scientific interpretation of any supporting evidence, along with the associated risks and costs. This approach creates a productive dialogue, rather than dismissing any inquiries outright.
• Appropriately label pseudomedicine interventions as such.
• Differentiate testimony from data, and assess whether studies display scientific integrity by “bending over backward” to address any limitations.
• Suggest an exploration of the financial interests behind the intervention (eg, the sale of supplements, out-of-pocket payments to a clinician or organization, book sales). Note that the gain may not only be financial, but also temporary fame that can accompany spearheading a new protocol.⁶
• Provide education on the US Dietary Supplement Health and Education Act that limits FDA testing and regulation of supplements.
• Point out that any effective interventions for common diseases would already be widely used.
• Express a willingness to continue to partner with patients in their medical care even if opinions and interpretations about pseudomedicine differ.

Conclusions

It is disheartening that patients with dementia and their family members are targeted by practitioners and companies motivated by self-interest. Physicians have an ethical mandate to protect patients who may be vulnerable to promotion by these entities. More needs to be done on a national level to limit the claims of benefit for interventions that lack proven efficacy. Clinicians must distinguish testimony and cargo cult science from quality medical research and explain when interventions may appear to represent pseudomedicine. While unethical forces promote the existence of pseudomedicine, an educated community of physicians and patients is the starting point to counteract these practices.

Back to top

Article Information

Corresponding Author: Joanna Hellmuth, MD, MHS, 675 Nelson Rising Ln, Ste 190, San Francisco, CA 94158 (Joanna.Hellmuth@ucsf.edu).

Published Online: January 25, 2019. doi:10.1001/jama.2018.21560

Blood-brain barrier test may predict dementia

There is this damage to the blood brain barrier from your stroke, so ask your doctor what exactly they are doing to fix that problem.  Inflammatory action leaking through the blood brain barrier from the neuronal cascade of death in the first week. How soon does this damage need to be fixed to prevent dementia?

 

Blood-brain barrier test may predict dementia

 

At a Glance

• A study shows that people with early cognitive impairment develop damage to the blood-brain barrier.
• Measuring the breakdown of this barrier could be an early way to test for cognitive impairment in dementia, including Alzheimer’s disease.

Researchers have been looking for ways to test for early signs of dementias and develop strategies that prevent disease progression.Skynesher / E+ / Getty Images

Cognitive impairment is when a person has problems remembering, learning, concentrating, or making decisions that affect everyday life. Millions of people in the U.S. show some sort of cognitive impairment. People with cognitive impairment are at higher risk for developing dementia, which is the loss of cognitive functioning. Alzheimer's disease is the most common dementia diagnosis.
Researchers have been looking for ways to test for early signs of cognitive impairment and dementia. Early detection could open the door to strategies that prevent disease progression. Potential biomarkers include changes in the size and function of the brain and its parts, as well as levels of certain proteins seen on brain scans, in cerebrospinal fluid, and in blood. People with Alzheimer’s disease, for example, have abnormally high levels of plaques made up of beta-amyloid and tangles made of tau proteins.
To look for earlier biomarkers of cognitive decline, a team led by Dr. Berislav V. Zlokovic at the University of Southern California, Los Angeles, examined two markers involved in the breakdown of the blood-brain barrier. This barrier controls the movement of cells and molecules between the blood and the fluid that surrounds the brain’s nerve cells. Past studies have found that abnormalities in the small blood vessels (capillaries) of the brain often contribute to dementia.
The team enrolled more than 160 people with and without cognitive impairment. They measured levels of the soluble form of a protein called platelet-derived growth factor receptor beta (PDGFRβ). PDGFRβ is found in the capillaries that maintain the blood-brain barrier’s integrity. Levels of the soluble form rise in cerebrospinal fluid when the blood-brain barrier is compromised. The team also tracked the integrity of the blood-brain barrier in 73 participants using an MRI-based technique they’d previously developed. The study was supported in part by NIH’s National Institute on Aging (NIA) and National Institute of Neurological Disorders and Stroke (NINDS). Results were published online on January 14, 2018, in Nature Medicine.
The researchers found that, compared with those without cognitive impairment, those with cognitive impairment had higher levels of soluble PDGFRβ and a greater breakdown in the blood-brain barrier of certain brain regions. Notably, both these measures were independent of beta-amyloid and tau protein levels. The findings suggest these measurements could pave the way for an early diagnostic test for cognitive impairment from Alzheimer’s disease as well as other causes.
“This is a solid step towards an accurate and reliable test that could be an earliest sign of critical brain damage in some people with Alzheimer’s disease and related dementias” says Dr. Roderick Corriveau, a program director at NINDS.
“Because of our aging population and growing public health concerns, efforts to find a reliable and accurate predictor of cognitive impairment and dementia are very important to researchers and the public,” explains Dr. Suzana Petanceska, a program director at NIA. “These early results are showing one possible, promising way to quantify risk.”
The researchers are planning to further validate these results by conducting a second trial with more participants.

Adaptive CSP for user independence in MI-BCI paradigm for upper limb stroke rehabilitation

Have your doctor explain how these calculations will get you 100% recovered.  You'll have to go to the link to see them properly.

Adaptive CSP for user independence in MI-BCI paradigm for upper limb stroke rehabilitation

Ana P. Costa, Jakob S. Møller, Helle K. Iversen and Sadasivan PuthusserypadyAbstract—A 3-class motor imagery (MI) Brain-ComputerInterface (BCI) system, that implements subject adaptationwith short to non-existing calibration sessions is proposed. Theproposed adaptive common spatial patterns (ACSP) algorithmwas tested on two datasets (an open source data set (4-class MI),and an in-house data set (3-class MI)). Results show that whenlong calibration data is available, the ACSP performs only slightlybetter (4%) than the CSP, but for short calibration sessions, theACSP significantly improved the performance (up to 4-fold). Aninvestigation into class separability of the in-house data set wasperformed and was concluded that the “Pinch”movement wasmore easily discriminated than “Grasp” and “Elbow Flexion”.The proposed paradigm proved feasible and provided insights tohelp choose the motor tasks leading to best results in potentialreal-life applications. The ACSP enabled a successful semi userindependent scenario and showed potential to be a tool towardsan improved, personalized stroke rehabilitation protocol.Index Terms—Brain-computer interface (BCI), Stroke rehabil-itation, Sensorimotor rhythms (SMR), Adaptive Common SpatialPatterns (ACSP)I. 

INTRODUCTION 

Brain-Computer Interface (BCI) technology allows for brainsignals to be recorded and translated into output commands,which can be used in various applications. In electroencephalogram (EEG) setups, sensorimotor rhythms (SMRs) are someof the signals of interest which can be measured. SMRs are tuned by motor intentions, such as motor imagery (MI), and are characterized by a modulation of the amplitudes of the measured electrical potentials.One area where MI-BCI systems have real-world applications is in neuro-rehabilitation, namely in stroke cases. Current stroke rehabilitation therapies present some limitations [1]–[3]and different enhancing strategies are emerging, of which BCIs are a promising one [4]. Rehabilitative BCIs aim at exploiting brain plasticity to improve motor recovery in patients. MI is used in most studies for this purpose, as it is hypothesized that it promotes neuroplasticity-related repair of the damaged brain areas [5]. The basis of MI-BCI systems for stroke rehabilitation has been laid by studies reporting an increasein motor cortex excitability as well as topographical changesafter training [6]. Preliminary results such as [7], [8] indicate the feasibility of incorporating BCI in post-stroke hand rehabilitation. Nevertheless, more large, randomized clinical trialsare necessary to confirm the advantages and reliability of themethod.Another issue to consider, is that individual stroke characteristics lead to different consequent neuroplastic changes during recovery, which indicates that an ideal system should be tailored for each patient [9]. This is related to one ofthe disadvantages of many BCI systems, which is subject-dependence: systems require data from a long training session for each subject, where no feedback is given to the user. This is impractical and particularly undesirable in the context ofstroke rehabilitation, where it is important that the patients start receiving feedback as soon as possible.A. Adaptive Spatial FiltersA commonly used strategy for source localization in MI-BCI systems is the common spatial pattern (CSP) filters.However, it presents some setbacks, namely that (i) it requireslarge data to avoid overfitting and generate robust projectingvectors, while being quite sensitive to outliers and (ii) it istypically subject-dependent and has no ability to adapt tothe non-stationarities that are characteristic of EEG signals[10]. These characteristics imply that long subject dependent calibration sessions are needed for computing the filter coefficients. Therefore, variations of the algorithm are needed to solve these problems and improve its performance. There aretwo ways to incorporate new data in order to handle changes that occur between distinct EEGs: block-wise [10], [11] and sample-wise. Here, a Recursive Least Squares (RLS) approach was implemented for sample-wise adaptation of the CSP filter,similar to the method used by [12] for the axDAWN filter.II. 

 MATERIALS AND METHODS

 A. Signal Processing1) The CSP Filter:LetXj∈RCn×Nbe thejthEEGtrial, whereNis the number of samples/trial and Cn is the number of channels. Then, the filtered trialZj,CSP∈RCn×N=W Xj, whereW∈RCn×Cnis the matrixparameterizing the signal decomposition. Here, we denote each column (wi,i=1,2,...,Cn) ofWas a spatial filter, andeach column ofW−1as a spatial pattern. The normalizedcovariance matrix for classkis defined as:Ck=1TnTn∑j=1Xj(k)XTj(k)trace{Xj(k)XTj(k)},(1)whereTnis the number of trials,Xj(k)is the jth trial belonging to classk∈[1,K]andK= 2for the binary classification case, which we will use, for simplicity, to explain420978-1-7281-1295-4/18/$31.00 ©2018 IEEEGlobalSIP 2018
the algorithm. In [13], the CSP is described with a discrimina-tive view, which was useful to derive the ACSP. Considering Cd=C1−C2andCc=C1+C2as the discriminative activity (Cd),i.e.the band-power modulation between the two classes, and the common activity (Cc), the solution to the following maximization problem can be achieved by solving the GED problem:argmaxWWTCdWWTCcW.(2)A One-Versus-All (OVA) multiclass version of the CSP was used so that the algorithm can be used to distinguish between nmore than two classes [14]. Finally, to get a system that is trainable on a small amount of data, the CSP was regularized with Diagonal Loading (DLCSP algorithm) [15].2) Adaptive Spatial Filter (ACSP):A sample-wise adaptive approach to the CSP algorithm based on the RLS method forGED is introduced here [16]. A training set is used to initializethe CSP matrix. Expanding Eq.(2), it can be deducted that:argmaxWWTCdWWTCcW= argmaxWWTC1WWTCcW.(3)BothC1andCcrepresent full normalized covariancematrices of stationary signals with zero mean. Rearranging the solution to the GED problem as in [16], we obtain the basis for the iterative algorithm:W=WTCcWWTC1WC−1cC1W.(4)A temporal discrete variablen is now introduced and an estimate of the primal eigenvectorw1(n)is computed as:ˆw1(n) =wT1(n′)Cc(n)w1(n′)wT1(n′)C1(n)w1(n′)C1c(n)−1C11(n)w1(n′)(5)where n′=n−1. Some comments about Eq.(5):1)Iterative computation of class covariance matrices:Here,we have not prioritized an asynchronous, self-paced systemwhich results in an advantage for the development of the ACSP, specifically in this step, because we always know the true label of each samplex(n). Therefore, we can iteratively update the normalizedC1(n)only whenx(n)∈class1, whileCc(n)is always updated:C1(n) =C1(n′) +x1(n)xT1(n)trace{x1(n)xT1(n)}andCc(n) =Cc(n′) +x(n)xT(n)trace{x(n)xT(n)},(6)wherex(n)is any data sample taken at timenandx1(n)represents the data belonging only to class 1.2)Iterative computation of the inverse ofCc(n):This stepin Eq.(5) would imply a very high computational effort whichis not feasible for an online application. Therefore, as in [12],[16], the Sherman-Morrison-Woodbury formula is used for theiterative update ofC−1c(n)[17]:C−1c(n) =C−1c(n′)−C−1c(n′)x(n)xT(n)C−1c(n′)1 +xT(n)C−1c(n′)x(n).(7)It is advantageous to use Eq.(7) since only C−1c(n′)needs to be stored and only simple matrix operations are required for each iteration. Finally, a deflation technique [16] is used to iteratively estimate the remaining eigenvectors (wi’s).Ci1(n) =[I−Ci−11(n)wi−1(n)wTi−1(n)wTi−1(n)Ci−11(n)wi−1(n)]Ci−11(n),Cic(n) =Ci−11(n).(8)To computew′is, Eq.(5) is used with the respectiveCi1(n)andCic(n)computed as in Eq.(8). As in [12], thew′is are normalized for numerical reasons.wi(n) =ˆwi(n)[ˆwTi(n)Cic(n)ˆwi(n)]12.(9)After all the spatial filters of trialnhave been computed,the first and lastmvectors are stored to classify trial n+ 1.3) Classification Algorithm:Discriminant Analysis (DA)was the chosen method to perform the classification, due to itslow computational complexity and comparable performances to more complex approaches [12], [18], [19]. To overcome some of the limitations of DA, Friedman’s regularized version of DA [20] (RDA) was implemented [21].B. Dataset Description and Experimental Design1) Dataset 1: 4-class MI of different body parts:This dataset belongs to the BCI competition IV [22] (dataset 2a)and comprises of the EEG recordings on 9 subjects of four classes of MI from distinct body parts (left and right hand,feet and tongue). For each subject, two sessions of 288 trialswere recorded, namely a calibration session without feedbackand an evaluation session with feedback.2) Dataset 2: 3-class MI of single upper limb:This dataset was recorded in our laboratory and was obtained in two differ-ent days: a short calibration session recorded without feedback and a longer session with feedback. The three motor tasks (Fig.1) were performed with the right arm. A goal-oriented visualinterface was implemented, as it has been proven to improve classification results [18]. For the calibration day, each sessionof MI consisted of 6 runs of 18 trials. Each trial started with a warning sound and a fixation cross, for the subject to mentally prepare for the task (2 seconds). Then, it was replaced by a visual cue indicating which of the three motor tasks the subjectshould imagine (4 seconds). Finally, the screen became blankand the subject could rest (2 seconds). In the online session,a vertical green bar positioned on the right side of each cuedisplayed real-time feedback (the bar grew from bottom totop, one fragment at a time for correct classifications). Theuser started receiving feedback after 1 second.The recordings were done on 14 healthy subjects agedbetween 20-31. The subjects were sitting comfortably in achair placed approximately one meter from the screen display-ing the visual interface. During the experiment, the subjects421(a)(b)(c)Fig. 1. Visual interface of the BCI system. (a) Palmar grasp (Class 1) -engaging all fingers and palm to hold an imaginary object between them. (b)Pinch (Class 2) - collecting the fingertips of the thumb, index and middlefinger. (c) Elbow Flexion (Class 3) - flexing the elbow while maintainingthe wrist aligned with the arm, with the thumb directed upwards/towards thesubject as the forearm is lifted.placed their right hand comfortably on the table in frontof them and kept all movements to a minimum. 16 activeAg/AgCl electrodes were used spanning the motor cortexarea. All procedures involving human subjects were performedin accordance to the ethical standards of the 1964 Helsinkideclaration and of the national research committee.C. Data Analysis SetupBefore analysis, the data was band-pass (7-30 Hz) filteredusing a4thorder zero-phase Butterworth filter. Two distinctstrategies were used to asses the performance of the ACSPfilter on dataset 1: (1)User dependent strategy:one CSP filterand RDA classifier were trained for each subject using all thedata from the calibration session and tested on the evaluationdata, and (2)Semi user independent strategy:shorter calibra-tion sessions were used to initialize the feature extraction andclassification parameters. This allows for potential customiza-tion of the BCI system for the individual needs of each patient.After testing the ACSP on dataset 1, it was used on dataset2, where the training size was short and determined based onthe previous results.III. 

RESULTS AND DISCUSSION 

A. Dataset 1: 4-class MI of different body parts1) User dependent strategy:An investigation of the con-vergence of the adaptive filter was made prior to the analysis of the classification performances. In Table I, the classification performances of the CSP and ACSP in the unseen evaluation data are displayed and compared to the results of the winningalgorithm (filter bank CSP (FBCSP)) of the BCI competition[14], with the best performance for each subject highlightedin bold. While a one-sided paired t-test indicated that thedifference between the performance of the FBCSP and thatof the ACSP algorithm was non-significant (p-value of 0.141at a confidence level ofα= 0.05), the first still outperformedthe latter in all subjects except three. A similar paired t-test revealed that there is no significant difference between the CSP and the ACSP (p= 0.294). These results indicate that there is little advantage in using the ACSP algorithmwhen sufficient training data is available. Finally, the scalptopographies were analyzed and it was concluded that the ACSP lead to physiologically significant patterns similar tothe ones obtained by the regular CSP algorithm.TABLE ICLASSIFICATIONPERFORMANCE(ASMAXIMUMKAPPAVALUE)OFACSP, CSPAND THEWINNER(FBCSP)OF THEBCI COMPETITIONIVIN THEUNSEENEVALUATIONDATA OFDATASET1.SubjectsCSPACSPFBCSP [14]10.6770.6830.67620.3630.2310.41730.6020.6770.74540.4650.3770.48150.2460.3300.39860.2430.3660.27370.6120.5680.77380.7490.7040.75590.5650.7710.606Mean0.5020.5230.569Median0.5650.5680.6062) Semi user independent strategy:In this approach, thenumber of trials per class was made to vary from 15 to 65 insteps of 15 and the resulting kappa values corresponding tothe classification performances on the evaluation dataset were calculated for each case. The trials chosen for each class weretaken randomly. The result is presented in Fig. 2. It is clear2030405060700.250.350.450.50.55Kappa valueAdaptive CSPfixed CSPFig. 2.Evolution of classification performance on evaluation dataset for different sizes on the training session (online simulation). Samples of growing size from the calibration dataset were used to train the CSP, for each subject, and evaluated on the corresponding evaluation dataset, using the same procedure as in section III-A1. The average maximum kappa value of all subjects is used as evaluation performance.that the performance of the CSP decreases significantly withsmaller training sizes. The ACSP, however, results in kappavalues similar to the final one already from a very small set.While the difference in performance kappa between algorithmsfor a training size of 72 is only 0.021, for a training size of 35the difference is 0.115. This represents a 1.28-fold increase.Based on this analysis, the training sizes for dataset 2 were chosen to be 36.B. Dataset 2: 3-class MI of single upper limbA similar convergence analysis was made for dataset 2and it indicated convergence around 17 trials per class. In Table II, the classification performances obtained during the online feedback session in terms of average maximum kappavalues for the MI are summarized. We conclude that the422TABLE IIPERFORMANCES FROM THEMI ONLINESESSION OFDATASET2WITHREALTIMEFEEDBACKGIVEN ASAVERAGEMAXIMUMKAPPAVALUE.Subjects124567891011121314MeanMedianDLCSPFixed0.100.080.050.190.050.100.080.050.210.050.300.130.080.110.08Adaptive0.360.490.520.460.490.650.500.710.6510.480.330.330.220.470.49ACSP resulted in a 4-fold increase in performance of theDLCSP, which is a significant result (p= 5×10−5). Theperformance of the ACSP is comparable with the literaturefor similar problems [18], [23]. Finally, an investigation intoclass separability was made, by extracting and combining thebinary confusion matrices for each class (Table III). The resultssuggest that class 2 (Pinch) was the easiest to discriminate, andclass 3 (Elbow Flexion) the hardest. 

TABLE 

IIICLASSIFICATION PERFORMANCES FOR PAIRWISE CLASS DISCRIMINATION,FOR THE ONLINE FEEDBACK SESSION.Class combination1 vs 21 vs 32 vs 3Kappa value0.6320.5160.579IV. 

 CONCLUSION 

The feasibility of a 3-class MI-BCI paradigm which could be employed for enhancement to the current stroke rehabilitation therapies has been studied.(Who the fuck cares about study? We need solutions.) The RLS-based ACSP seems to   overcome one of the main disadvantages of the CSPfilter, allowing for personalized training programs based on short calibration sessions. The ACSP provided only slightly better results than the CSP when there was plenty training data, but performed up to 4 times better when not. The classification performances are lower in the second dataset,confirming that it is a harder task to distinguish between motor tasks performed by the same limb. An investigation onthe separability of the chosen motor tasks indicates that the“Pinch” movement was the easiest to discriminate, which can suggest a direction for class choice in future similar studies.The system here implemented could be(Once again followup needed) a step towards a potential application of MI-BCI technology for enhancementof current post-stroke neuro-rehabilitation. Overall, there isstill room for improvement towards practical applicability,such as channel reduction and development of an unsupervisedversion of the algorithm. Large and randomized clinical trialsare also necessary to confirm the advantages and reliability of the method.