ONE3A: one-against-all authentication model for smartphone using GAN network and optimization techniques.

This study focuses on addressing computational limits in smartphones by proposing an efficient authentication model that enables implicit authentication without requiring additional hardware and incurring less computational cost. The research explores various wrapper feature selection strategies and classifiers to enhance authentication accuracy while considering smartphone limitations such as hardware constraints, battery life, and memory size. However, the available dataset is small; thus, it cannot support a general conclusion. In this article, a novel implicit authentication model for smartphone users is proposed to address the one-against-all classification problem in smartphone authentication. This model depends on the integration of the conditional tabular generative adversarial network (CTGAN) to generate synthetic data to address the imbalanced dataset and a new proposed feature selection technique based on the Whale Optimization Algorithm (WOA). The model was evaluated using a public dataset (RHU touch mobile keystroke dataset), and the results showed that the WOA with the random forest (RF) classifier achieved the best reduction rate compared to the Harris Hawks Optimization (HHO) algorithm. Additionally, its classification accuracy was found to be the best in mobile user authentication from their touch behavior data. WOA-RF achieved an average accuracy of 99.62 ± 0.40% with a reduction rate averaging 87.85% across ten users, demonstrating its effectiveness in smartphone authentication.

Pattern of Post COVID Fatigue in Elderly Patients.

The incidence of Long COVID (LC) increases with age but then drops sharply in over 70-year-olds. The prevailing explanation is that different biases in data collection such as reluctance to report symptoms or attributing them to comorbidities may explain this pattern in this age group. Our local data suggested a similar pattern confirming the rarity of LC symptoms especially fatigue in the over 70s. Our data have also showed a different phenotype of post COVID fatigue which is not commonly associated with post exertional symptoms bringing into question the suggestion that bias in collecting data is the main cause. We explore several immunological, metabolic and epigenetic factors associated with aging that may explain such phenomenon.

An improved long short term memory network for intrusion detection.

Over the years, intrusion detection system has played a crucial role in network security by discovering attacks from network traffics and generating an alarm signal to be sent to the security team. Machine learning methods, e.g., Support Vector Machine, K Nearest Neighbour, have been used in building intrusion detection systems but such systems still suffer from low accuracy and high false alarm rate. Deep learning models (e.g., Long Short-Term Memory, LSTM) have been employed in designing intrusion detection systems to address this issue. However, LSTM needs a high number of iterations to achieve high performance. In this paper, a novel, and improved version of the Long Short-Term Memory (ILSTM) algorithm was proposed. The ILSTM is based on the novel integration of the chaotic butterfly optimization algorithm (CBOA) and particle swarm optimization (PSO) to improve the accuracy of the LSTM algorithm. The ILSTM was then used to build an efficient intrusion detection system for binary and multi-class classification cases. The proposed algorithm has two phases: phase one involves training a conventional LSTM network to get initial weights, and phase two involves using the hybrid swarm algorithms, CBOA and PSO, to optimize the weights of LSTM to improve the accuracy. The performance of ILSTM and the intrusion detection system were evaluated using two public datasets (NSL-KDD dataset and LITNET-2020) under nine performance metrics. The results showed that the proposed ILSTM algorithm outperformed the original LSTM and other related deep-learning algorithms regarding accuracy and precision. The ILSTM achieved an accuracy of 93.09% and a precision of 96.86% while LSTM gave an accuracy of 82.74% and a precision of 76.49%. Also, the ILSTM performed better than LSTM in both datasets. In addition, the statistical analysis showed that ILSTM is more statistically significant than LSTM. Further, the proposed ISTLM gave better results of multiclassification of intrusion types such as DoS, Prob, and U2R attacks.

A novel CNN gap layer for growth prediction of palm tree plantlings.

Monitoring palm tree seedlings and plantlings presents a formidable challenge because of the microscopic size of these organisms and the absence of distinguishing morphological characteristics. There is a demand for technical approaches that can provide restoration specialists with palm tree seedling monitoring systems that are high-resolution, quick, and environmentally friendly. It is possible that counting plantlings and identifying them down to the genus level will be an extremely time-consuming and challenging task. It has been demonstrated that convolutional neural networks, or CNNs, are effective in many aspects of image recognition; however, the performance of CNNs differs depending on the application. The performance of the existing CNN-based models for monitoring and predicting plantlings growth could be further improved. To achieve this, a novel Gap Layer modified CNN architecture (GL-CNN) has been proposed with an IoT effective monitoring system and UAV technology. The UAV is employed for capturing plantlings images and the IoT model is utilized for obtaining the ground truth information of the plantlings health. The proposed model is trained to predict the successful and poor seedling growth for a given set of palm tree plantling images. The proposed GL-CNN architecture is novel in terms of defined convolution layers and the gap layer designed for output classification. There are two 64×3 conv layers, two 128×3 conv layers, two 256×3 conv layers and one 512×3 conv layer for processing of input image. The output obtained from the gap layer is modulated using the ReLU classifier for determining the seedling classification. To evaluate the proposed system, a new dataset of palm tree plantlings was collected in real time using UAV technology. This dataset consists of images of palm tree plantlings. The evaluation results showed that the proposed GL-CNN model performed better than the existing CNN architectures with an average accuracy of 95.96%.

Efficient thermal face recognition method using optimized curvelet features for biometric authentication.

Biometric technology is becoming increasingly prevalent in several vital applications that substitute traditional password and token authentication mechanisms. Recognition accuracy and computational cost are two important aspects that are to be considered while designing biometric authentication systems. Thermal imaging is proven to capture a unique thermal signature for a person and thus has been used in thermal face recognition. However, the literature did not thoroughly analyse the impact of feature selection on the accuracy and computational cost of face recognition which is an important aspect for limited resources applications like IoT ones. Also, the literature did not thoroughly evaluate the performance metrics of the proposed methods/solutions which are needed for the optimal configuration of the biometric authentication systems. This paper proposes a thermal face-based biometric authentication system. The proposed system comprises five phases: a) capturing the user's face with a thermal camera, b) segmenting the face region and excluding the background by optimized superpixel-based segmentation technique to extract the region of interest (ROI) of the face, c) feature extraction using wavelet and curvelet transform, d) feature selection by employing bio-inspired optimization algorithms: grey wolf optimizer (GWO), particle swarm optimization (PSO) and genetic algorithm (GA), e) the classification (user identification) performed using classifiers: random forest (RF), k-nearest neighbour (KNN), and naive bayes (NB). Upon the public dataset, Terravic Facial IR, the proposed system was evaluated using the metrics: accuracy, precision, recall, F-measure, and receiver operating characteristic (ROC) area. The results showed that the curvelet features optimized using the GWO and classified with random forest could help in authenticating users through thermal images with performance up to 99.5% which is better than the results of wavelet features by 10% while the former used 5% fewer features. In addition, the statistical analysis showed the significance of our proposed model. Compared to the related works, our system showed to be a better thermal face authentication model with a minimum set of features, making it computational-friendly.

Prioritized and predictive intelligence of things enabled waste management model in smart and sustainable environment.

Collaborative modelling of the Internet of Things (IoT) with Artificial Intelligence (AI) has merged into the Intelligence of Things concept. This recent trend enables sensors to track required parameters and store accumulated data in cloud storage, which can be further utilized by AI based predictive models for automatic decision making. In a smart and sustainable environment, effective waste management is a concern. Poor regulation of waste in surrounding areas leads to rapid spread of contagious disease risks. Traditional waste object management requires more working staff, increases effort, consumes time and is relatively ineffective. In this research, an Intelligence of Things Enabled Smart Waste Management (IoT-SWM) model with predictive capabilities is developed. Here, local sinks (LS) are deployed in specified locations. At every instant, the current status of smart bins in each LS is notified to users to determine the priority level of LS to be emptied. Based on aggregated sensor values for the three smart bins, LS weight and poison gas value, the priority order of emptying LS is computed, and decision is made whether to notify the users with an alert message or not. It also helps in predicting the LS, which is likely to be filled up at a faster rate based on assigned timestamp. This model is implemented in real time with many LS and it was observed that bins, which were close to more crowded sites filled up faster compared to sparse populated areas. Random forest algorithm was used to predict whether an alert notification is to be sent or not. An average mean of 95.8% accuracy was noted while using 60 decision trees in random forest algorithm. The average mean execution latency recorded for training and testing sets is 13.06 sec and 14.39 sec respectively. Observed accuracy rate, precision, recall and f1-score parameters were 95.8%, 96.5%, 98.5% and 97.2% respectively. Model buildup and the validation time computed were 3.26 sec and 4.25 sec respectively. It is also noted that at a threshold value of 0.93 in LS level, the maximum accuracy rate reached was 95.8%. Thus, based on the prediction of random forest approach, a decision to notify the users is taken. Obtained outcome indicates that the waste level can be efficiently determined, and the overflow of dustbins can be easily checked in time.

A Novel CNN pooling layer for breast cancer segmentation and classification from thermograms.

Breast cancer is the second most frequent cancer worldwide, following lung cancer and the fifth leading cause of cancer death and a major cause of cancer death among women. In recent years, convolutional neural networks (CNNs) have been successfully applied for the diagnosis of breast cancer using different imaging modalities. Pooling is a main data processing step in CNN that decreases the feature maps' dimensionality without losing major patterns. However, the effect of pooling layer was not studied efficiently in literature. In this paper, we propose a novel design for the pooling layer called vector pooling block (VPB) for the CCN algorithm. The proposed VPB consists of two data pathways, which focus on extracting features along horizontal and vertical orientations. The VPB makes the CNNs able to collect both global and local features by including long and narrow pooling kernels, which is different from the traditional pooling layer, that gathers features from a fixed square kernel. Based on the novel VPB, we proposed a new pooling module called AVG-MAX VPB. It can collect informative features by using two types of pooling techniques, maximum and average pooling. The VPB and the AVG-MAX VPB are plugged into the backbone CNNs networks, such as U-Net, AlexNet, ResNet18 and GoogleNet, to show the advantages in segmentation and classification tasks associated with breast cancer diagnosis from thermograms. The proposed pooling layer was evaluated using a benchmark thermogram database (DMR-IR) and its results compared with U-Net results which was used as base results. The U-Net results were as follows: global accuracy = 96.6%, mean accuracy = 96.5%, mean IoU = 92.07%, and mean BF score = 78.34%. The VBP-based results were as follows: global accuracy = 98.3%, mean accuracy = 97.9%, mean IoU = 95.87%, and mean BF score = 88.68% while the AVG-MAX VPB-based results were as follows: global accuracy = 99.2%, mean accuracy = 98.97%, mean IoU = 98.03%, and mean BF score = 94.29%. Other network architectures also demonstrate superior improvement considering the use of VPB and AVG-MAX VPB.

Deep learning model for fully automated breast cancer detection system from thermograms.

Breast cancer is one of the most common diseases among women worldwide. It is considered one of the leading causes of death among women. Therefore, early detection is necessary to save lives. Thermography imaging is an effective diagnostic technique which is used for breast cancer detection with the help of infrared technology. In this paper, we propose a fully automatic breast cancer detection system. First, U-Net network is used to automatically extract and isolate the breast area from the rest of the body which behaves as noise during the breast cancer detection model. Second, we propose a two-class deep learning model, which is trained from scratch for the classification of normal and abnormal breast tissues from thermal images. Also, it is used to extract more characteristics from the dataset that is helpful in training the network and improve the efficiency of the classification process. The proposed system is evaluated using real data (A benchmark, database (DMR-IR)) and achieved accuracy = 99.33%, sensitivity = 100% and specificity = 98.67%. The proposed system is expected to be a helpful tool for physicians in clinical use.

Evaluation of the Addenbrooke's Cognitive Examination's validity in a brain injury rehabilitation setting.

BACKGROUND: Several reports have warned of the Mini Mental State Examination's (MMSE) inability to detect gross memory and high executive impairments. Addenbrooke's Cognitive Examination-Revised (ACE-R) has gained enormous popularity in dementia screening as it addresses the main shortcomings of MMSE. AIM: This study aimed at evaluating the use of ACE-R and to establish its sensitivity compared to MMSE in a cohort of brain injury patients. METHOD: ACE-R was administered to a cohort of chronic brain injury patients. All patients had a cognitive impairment which was severe enough to prevent them working or studying. Patients with significant mental health, sensory, communication or physical impairments were excluded. RESULTS: Thirty-six patients were recruited, 31 males with a mean age of 37 years. For an upper cut-off value of 27/30 for MMSE and 88/100 for ACE-R, their sensitivities were 36% and 72%, respectively. For a lower cut-off value of 24/30 and 82/100 the tests sensitivities were 11% and 56%, respectively. Analysis of the ACE-R sub-tests indicated that memory and verbal fluency sub-tests showed the most dramatic impairment. CONCLUSION: MMSE is insensitive as a screening test in brain injury patients. The results show ACE-R to be a sensitive, easily administered test.

Guidelines for prevention of venous thromboembolism in immobile patients secondary to neurological impairment.

BACKGROUND: Venous thromboembolism (VTE) is a major cause of morbidity and mortality in hospitalized patients and 7% of these cases are due to immobility secondary to a neurological impairment. Many guidelines are available to guide clinicians dealing with medical or surgical patients. However, and with the exception of spinal injuries, no guidelines are available to deal with other neurologically impaired patients at risk of VTE. AIM: Our study aimed at gathering evidence from the literature to enable us to deal with the main controversial issues of VTE prevention. Guidelines will be formulated. METHOD: A Clinical Standards Group is responsible for the development of clinical guidelines for the Greater Manchester Neurorehabilitation network with services covering a population of around 3 million. The development of VTE prevention guidelines started with the formulation of the main questions, then gathering evidence from the literature to address these questions. Wide consultation then took place. The guidelines were then put before the group for endorsement. RESULTS: Answers for the main questions such as duration of thromboprophylaxis, TEDS and antiplatelets drugs use were suggested. The resulting document was summarized as a flow chart for use. CONCLUSION: We feel that the proposed guidelines are a useful tool for clinicians as they reflect the evidence available from the literature at the moment.

Can physical assessment techniques aid diagnosis in people with chronic fatigue syndrome/myalgic encephalomyelitis? A diagnostic accuracy study.

OBJECTIVE: To assess five physical signs to see whether they can assist in the screening of patients with chronic fatigue syndrome/myalgic encephalomyelitis (CFS/ME) and potentially lead to quicker treatment. METHODS: This was a diagnostic accuracy study with inter-rater agreement assessment. Participants recruited from two National Health Service hospitals, local CFS/ME support groups and the community were examined by three practitioners on the same day in a randomised order. Two allied health professionals (AHPs) performed independent examinations of physical signs including: postural/mechanical disturbances of the thoracic spine, breast varicosities, tender Perrin's point, tender coeliac plexus and dampened cranial flow. A physician conducted a standard clinical neurological and rheumatological assessment while looking for patterns of illness behaviour. Each examination lasted approximately 20 min. RESULTS: Ninety-four participants were assessed, 52 patients with CFS/ME and 42 non-CFS/ME controls, aged 18-60. Cohen's kappa revealed that agreement between the AHPs was substantial for presence of the tender coeliac plexus (κ=0.65, p<0.001) and moderate for postural/mechanical disturbance of the thoracic spine (κ=0.57, p<0.001) and Perrin's point (κ=0.56, p<0.001). A McNemar's test found no statistically significant bias in the diagnosis by the experienced AHP relative to actual diagnosis (p=1.0) and a marginally non-significant bias by the newly trained AHP (p=0.052). There was, however, a significant bias in the diagnosis made by the physician relative to actual diagnosis (p<0.001), indicating poor diagnostic utility of the clinical neurological and rheumatological assessment. CONCLUSIONS: Using the physical signs appears to improve the accuracy of identifying people with CFS/ME and shows agreement with current diagnostic techniques. However, the present study concludes that only two of these may be needed. Examining for physical signs is both quick and simple for the AHP and may be used as an efficient screening tool for CFS/ME. This is a small single-centre study, and therefore, further validation in other centres and larger populations is needed.

Medico-legal and ethical aspects in the management of wandering patients following brain injury: questionnaire survey.

BACKGROUND: Different methods are often used to deter head injury patients, who have a tendency to wander, from leaving the rehabilitation wards. The extent to which these patients could be restrained is controversial. Despite the fact that the majority of these patients lack mental capacity, Mental Health Act sections are rarely invoked. Under common law, informal patients should have the right to refuse treatment and to leave the hospital whenever they like. OBJECTIVE: To examine the current practice in the management of wandering patients following brain injury in rehabilitation units in the UK and to formulate practical guidelines based on this common practice. METHODS: A postal survey in the form of a structured questionnaire was sent to 58 consultants in Rehabilitation Medicine and Neuropsychologists based at different neurological rehabilitation units in the UK. RESULTS: A total of 30 clinicians (52%) completed the questionnaire. One-to-one supervision was the method most commonly used to manage wandering patients (83%) followed by implementation of a structured daily routine (73%) and the use of different medications (70%). Only 17% would lock the door without giving the patient lock combination/key and another 17% would physically restrain the patient without invoking mental health act (MHA) section; 60% would consider MHA section with great variability in the mental health team response time and the place where patient is managed once under MHA section. CONCLUSIONS: The questionnaire showed great variations in the methods and the medico-legal framework used in the management of wandering patients. There was, however, a tendency to avoid physical restraint which may reflect the recognition of the unlawfulness of detaining informal patients.

Significant reduction of the risk of venous thromboembolism in all long-term immobile patients a few months after the onset of immobility.

Prophylactic anticoagulation is a standard practice in patients with sudden lower limbs paralysis. Thromboprophylaxis is usually continued until the patient regains independent mobility. The duration of anticoagulation in long-term immobile patients is unknown. Spinal cord injury patients are the only population that was comprehensively studied and prophylactic anticoagulation is discontinued after 4 months as the risk of venous thromboembolism drops dramatically after 3-4 months. Development of muscle spasticity has been traditionally considered to be the reason for this low risk as lower limbs spasticity/spasms might be able to improve the calf muscle pump action. We are presenting the evidence from physiological studies of the lower limbs vascular system that cast doubt over this explanation and present an alternative hypothesis backed by several clinical circumstantial evidence suggesting that the vascular changes following long term lower limbs inactivity which are universal to all immobile patients is probably the main protecting factor. We suggest that prophylactic anticoagulation is necessary only on the first 4 months following the acute onset of immobility in all neurologically impaired immobile patients regardless of their muscle tone state.

Thermogram breast cancer prediction approach based on Neutrosophic sets and fuzzy c-means algorithm.

The early detection of breast cancer makes many women survive. In this paper, a CAD system classifying breast cancer thermograms to normal and abnormal is proposed. This approach consists of two main phases: automatic segmentation and classification. For the former phase, an improved segmentation approach based on both Neutrosophic sets (NS) and optimized Fast Fuzzy c-mean (F-FCM) algorithm was proposed. Also, post-segmentation process was suggested to segment breast parenchyma (i.e. ROI) from thermogram images. For the classification, different kernel functions of the Support Vector Machine (SVM) were used to classify breast parenchyma into normal or abnormal cases. Using benchmark database, the proposed CAD system was evaluated based on precision, recall, and accuracy as well as a comparison with related work. The experimental results showed that our system would be a very promising step toward automatic diagnosis of breast cancer using thermograms as the accuracy reached 100%.

Multiple Sclerosis/Chronic Fatigue Syndrome overlap: When two common disorders collide.

INTRODUCTION: Fatigue is a major cause of disability and handicap in Multiple Sclerosis (MS) patients. The management of this common problem is often difficult. Chronic Fatigue Syndrome (CFS/ME) is another common cause of fatigue which is prevalent in the same population of middle aged females commonly affected by MS. AIM: This report aims at examining the potential coexistence of MS and CFS/ME in the same patients. METHOD: This is a retrospective study examining a cohort of MS patients referred for rehabilitation. The subjects were screened for CFS/ME symptoms. RESULTS: Sixty-four MS patients (43 females) were screened for CFS/ME. Nine patients (14%) with a mean age 52 (SD 9.7) who were all females fulfilled the Fukuda criteria for diagnosis of CFS/ME. Their symptoms, including muscular and joint pain, malaise and recurrent headaches, were not explained by the pattern of their MS. DISCUSSION: MS and CFS/ME are two common conditions with increased prevalence in middle aged females. As the diagnosis of CFS/ME is clinical with no positive clinical signs or investigations; it can be made with difficulty in the presence of another clear explanation for the disabling fatigue. Our results suggest that the two conditions may co-exist. Considering CFS/ME as a potential co-morbidity may lead to more focused and appropriate management.

Outcomes of inpatient rehabilitation of patients with multiple sclerosis.

BACKGROUND: Several trials have demonstrated improved outcomes following inpatient rehabilitation for Multiple Sclerosis patients. Two populations were studied: patients in relapse and patients with no active medical problems recruited from the community. In every day practice, most admissions for MS inpatient rehabilitation aim to improve function following sudden deterioration. The outcomes of inpatient rehabilitation for this population were never studied. METHOD: Retrospective case note analysis of consecutive admissions of MS patients from 2005 to 2009 to a specialist neurological rehabilitation unit. RESULTS: Forty-one cases were identified. 26 were females. Age 25-71 (mean 52 ± 12). Disease duration 0-39 years (mean 13 ± 11). 20 patients were admitted from the community and 21 were transferred from acute hospital beds. Length of stay ranged between 11 to 152 days (mean 49 ± 36). Mean length of stay for wheelchair dependent patients was approximately double the length of stay for ambulatory patients. Improving mobility, transfer or posture were the primary cause of admissions in 37 cases. Sixteen out of 21 ambulatory patients (76%) attained 100% mobility goals. Only 4 out of 20 wheelchair bound patients (20%) achieved 100% mobility goals (P 0.002). Neither the type of MS nor the duration of it influenced the overall outcome. CONCLUSION: Our results suggest that MS patients admitted for rehabilitation following deterioration secondary to a medical or surgical cause show the same favourable outcome that was demonstrated with MS stable patients or in relapse. Baseline mobility, but not type and duration of MS, seems to have a significant impact on the rehabilitation outcome in terms of gaol achievement.

Validation of the language component of the Addenbrooke's Cognitive Examination--Revised (ACE-R) as a screening tool for aphasia in stroke patients.

AIM: Several tests are available for aphasia screening following stroke. However, some of them have shortcomings such as need of specialist knowledge, low sensitivity and/or specificity and lengthy administration time. Our study aims to evaluate the language component of the Addenbrooke's Cognitive Examination--Revised (ACE-R) as a screening tool for aphasia in stroke patients. METHODS: The language component of ACE-R was administered to consecutive patients admitted to a post-acute stroke unit. Patients who were medically unstable or had a significant history of sensory impairment or mental health issues were excluded. The test was administered by two junior doctors with basic training in ACE-R administration. Patients recruited were also assessed by an experienced speech and language therapist (SLT). The results of the two assessments were documented by a different member of the team and the SLT results were used as the benchmark to calculate the ACE-R language component sensitivity and specificity. RESULTS: Fifty-nine participants were recruited and 27 of them were women. The mean age was 72 (SD 11.9). Thirty-four participants had left and 11 right hemisphere stroke. Fourteen had bilateral affection. Six participants were left handed. A cut-off value of 22/26 of ACE-R language component showed 100% specificity and 83.1% sensitivity, while a cut-off value of 16/26 had 88.2% specificity and 100% sensitivity. CONCLUSION: Our results suggest that the language component of ACE-R has a satisfactory sensitivity and specificity compared with other screening tests used in strokes. It is easy to administer and free to use.

Botulinum Toxin in the management of hitchhiker's toe.

INTRODUCTION: Hyperextension of the extensor hallucis longus (EHL) muscle is a well recognised disabling sequel of either pyramidal or extrapyramidal lesions causing what is known as striated or hitchhiker's toe. Surgery was the only effective strategy to manage EHL hyperextension before botulinum toxin's use to manage muscular dystonia and spasticity became widely popular. METHODS: A multicentre retrospective study. A standard proforma was sent to specialists in neurological rehabilitation dealing routinely with this problem. The data was analysed using descriptive statistics. RESULTS: Four consultants and two trainees representing five separate neurological rehabilitation services agreed to participate in the study. Full data was available from the 29 proformas completed. The subjects were 15 females with an age range between 20 and 78 years (mean 58.7). Stroke was the primary diagnosis in 18 subjects. Four subjects had bilateral involvement. 16 subjects had either an associated foot drop or equino varus deformity. Dysport® was used in 15 subjects with an average dose of 170 units per injection and Botox® in the other 14 with an average dose of 65 units. The treatment was effective in 24 subjects (83%). All patients receiving Dysport® responded to the treatment. Whilst 5 Botox® treated patients failed to respond to it (35% failure rate). Most of the non respondents seemed to receive insufficient doses of Botox® (below 60 units). Surgical management was successful in 3 out of the 5 non respondent cases. CONCLUSION: Botilinum Toxin is an effective and safe method to manage hitchhicker's toe. In our study the conversion ratio between Dysport® and Botox® was 2.5:1. Third of the patients receiving Botox® failed to respond to the treatment most probably due to insufficient doses used.