Multilayer perceptron-based self-care early prediction of children with disabilities.

Early identification of children with self-care impairments is one of the key challenges professional therapists face due to the complex and time-consuming detection process using relevant self-care activities. Due to the complex nature of the problem, machine-learning methods have been widely applied in this area. In this study, a feed-forward artificial neural network (ANN)-based self-care prediction methodology, called multilayer perceptron (MLP)-progressive, has been proposed. The proposed methodology integrates unsupervised instance-based resampling and randomizing preprocessing techniques to MLP for improved early detection of self-care disabilities in children. Preprocessing of the dataset affects the MLP performance; hence, randomization and resampling of the dataset improves the performance of the MLP model. To confirm the usefulness of MLP-progressive, three experiments were conducted, including validating MLP-progressive methodology over multi-class and binary-class datasets, impact analysis of the proposed preprocessing filters on the model performance, and comparing the MLP-progressive results with state-of-the-art studies. The evaluation metrics accuracy, precision, recall, F-measure, TP rate, FP rate, and ROC were used to measure performance of the proposed disability detection model. The proposed MLP-progressive model outperforms existing methods and attains a classification accuracy of 97.14% and 98.57% on multi-class and binary-class datasets, respectively. Additionally, when evaluated on the multi-class dataset, significant improvements in accuracies ranging from 90.00% to 97.14% were observed when compared to state-of-the-art methods.

Outcome Of The Distal Radius Fractures Managed With Across Wrist External Fixator Vs Buttress Plates.

BACKGROUND: Distal radius fracture is one of the most common injuries presented to emergency department and can be presented in any age group. In young patients the most common cause is Road Traffic Accident (RTA), while old patient history of fall is the most common cause. Different surgical options are available to treat this injury. This study aims to compare the outcome of volar buttress plate vs across wrist external fixator for Arbeitsgemeinschaft für Osteosynthesefragen (AO) type C2/C3 fracture of the distal radius. METHODS: A retrospective comparative study between July 2020 to June 2021 at Ghurki Trust Teaching Hospital was done and a total of 50 patients who underwent surgical intervention for AO C2/C3 fracture of the distal Radius, were included. The follow-up period was 12 weeks. QuickDASH score was used to find out patient's functional outcomes. Functional outcome was analyzed between the two groups using Mann-Whitney U test, using SPSS version 21. RESULTS: There was no significant statistical difference between the functional outcome of patients with distal radius fracture treated with across wrist external fixator vs volar buttress plate, in term of QuickDASH score. Furthermore, age and gender also were having no effect on functional outcome in our population. CONCLUSIONS: Across wrist external fixator is a reasonable option for AO C2/C3 type fractures of the distal radius with comparable results with volar buttress plate. It is the procedure of choice in high volume tertiary care hospitals like Gurki Trust Teaching hospital as it saves time, have similar functional outcome score, no need to re-open for removal of implant, less chances of tendon rupture as compared to volar buttress plate for distal radius fracture.

Magnetic Tile Surface Defect Detection Methodology Based on Self-Attention and Self-Supervised Learning.

As the core component of permanent magnet motor, the magnetic tile defects seriously affect the quality of industrial motor. Automatic recognition of the surface defects of the magnetic tile is a difficult job since the patterns of the defects are complex and diverse. The existing defect recognition methods result in difficulty in practical application due to the complicated system structure and the low accuracy of the image segmentation and the target detection for the diversity of the defect patterns. A self-supervised learning (SSL) method, which benefits from its nonlinear feature extraction performance, is proposed in this study to improve the existing approaches. We proposed an efficient multihead self-attention method, which can automatically locate single or multiple defect areas of magnetic tile and extract features of the magnetic tile defects. We also designed an accurate full-connection classifier, which can accurately classify different defects of magnetic tile defects. A knowledge distillation process without labeling is proposed, which simplifies the self-supervised training process. The process of our method is as follows. A feature extraction model consists of standard vision transformer (ViT) backbone, which is trained by contrast learning without labeled dataset that is used to extract global and local features from the input magnetic tile images. Then, we use a full-connection neural network, which is trained by using labeled dataset to classify the known defect types. Finally, we combined the feature extraction model and defect classification model together to form a relatively simple integrated system. The public magnetic tile surface defect dataset, which holds 5 defect categories and 1 nondefect category, is used in the process of training, validating, and testing. We also use online data augmentation techs to increase training samples to make the model converge and achieve high classification accuracy. The experimental results show that the features extracted by the SSL method can get richer and more detailed features than the supervised learning model gets. The composite model reaches to a high testing accuracy of 98.3%, and gains relatively strong robustness and good generalization ability.

Balancing Complex Signals for Robust Predictive Modeling.

Robust predictive modeling is the process of creating, validating, and testing models to obtain better prediction outcomes. Datasets usually contain outliers whose trend deviates from the most data points. Conventionally, outliers are removed from the training dataset during preprocessing before building predictive models. Such models, however, may have poor predictive performance on the unseen testing data involving outliers. In modern machine learning, outliers are regarded as complex signals because of their significant role and are not suggested for removal from the training dataset. Models trained in modern regimes are interpolated (over trained) by increasing their complexity to treat outliers locally. However, such models become inefficient as they require more training due to the inclusion of outliers, and this also compromises the models' accuracy. This work proposes a novel complex signal balancing technique that may be used during preprocessing to incorporate the maximum number of complex signals (outliers) in the training dataset. The proposed approach determines the optimal value for maximum possible inclusion of complex signals for training with the highest performance of the model in terms of accuracy, time, and complexity. The experimental results show that models trained after preprocessing with the proposed technique achieve higher predictive accuracy with improved execution time and low complexity as compared to traditional predictive modeling.

Data-driven knowledge acquisition, validation, and transformation into HL7 Arden Syntax.

OBJECTIVE: The objective of this study is to help a team of physicians and knowledge engineers acquire clinical knowledge from existing practices datasets for treatment of head and neck cancer, to validate the knowledge against published guidelines, to create refined rules, and to incorporate these rules into clinical workflow for clinical decision support. METHODS AND MATERIALS: A team of physicians (clinical domain experts) and knowledge engineers adapt an approach for modeling existing treatment practices into final executable clinical models. For initial work, the oral cavity is selected as the candidate target area for the creation of rules covering a treatment plan for cancer. The final executable model is presented in HL7 Arden Syntax, which helps the clinical knowledge be shared among organizations. We use a data-driven knowledge acquisition approach based on analysis of real patient datasets to generate a predictive model (PM). The PM is converted into a refined-clinical knowledge model (R-CKM), which follows a rigorous validation process. The validation process uses a clinical knowledge model (CKM), which provides the basis for defining underlying validation criteria. The R-CKM is converted into a set of medical logic modules (MLMs) and is evaluated using real patient data from a hospital information system. RESULTS: We selected the oral cavity as the intended site for derivation of all related clinical rules for possible associated treatment plans. A team of physicians analyzed the National Comprehensive Cancer Network (NCCN) guidelines for the oral cavity and created a common CKM. Among the decision tree algorithms, chi-squared automatic interaction detection (CHAID) was applied to a refined dataset of 1229 patients to generate the PM. The PM was tested on a disjoint dataset of 739 patients, which gives 59.0% accuracy. Using a rigorous validation process, the R-CKM was created from the PM as the final model, after conforming to the CKM. The R-CKM was converted into four candidate MLMs, and was used to evaluate real data from 739 patients, yielding efficient performance with 53.0% accuracy. CONCLUSION: Data-driven knowledge acquisition and validation against published guidelines were used to help a team of physicians and knowledge engineers create executable clinical knowledge. The advantages of the R-CKM are twofold: it reflects real practices and conforms to standard guidelines, while providing optimal accuracy comparable to that of a PM. The proposed approach yields better insight into the steps of knowledge acquisition and enhances collaboration efforts of the team of physicians and knowledge engineers.

Multi-model-based interactive authoring environment for creating shareable medical knowledge.

OBJECTIVE: Technologically integrated healthcare environments can be realized if physicians are encouraged to use smart systems for the creation and sharing of knowledge used in clinical decision support systems (CDSS). While CDSSs are heading toward smart environments, they lack support for abstraction of technology-oriented knowledge from physicians. Therefore, abstraction in the form of a user-friendly and flexible authoring environment is required in order for physicians to create shareable and interoperable knowledge for CDSS workflows. Our proposed system provides a user-friendly authoring environment to create Arden Syntax MLM (Medical Logic Module) as shareable knowledge rules for intelligent decision-making by CDSS. METHODS AND MATERIALS: Existing systems are not physician friendly and lack interoperability and shareability of knowledge. In this paper, we proposed Intelligent-Knowledge Authoring Tool (I-KAT), a knowledge authoring environment that overcomes the above mentioned limitations. Shareability is achieved by creating a knowledge base from MLMs using Arden Syntax. Interoperability is enhanced using standard data models and terminologies. However, creation of shareable and interoperable knowledge using Arden Syntax without abstraction increases complexity, which ultimately makes it difficult for physicians to use the authoring environment. Therefore, physician friendliness is provided by abstraction at the application layer to reduce complexity. This abstraction is regulated by mappings created between legacy system concepts, which are modeled as domain clinical model (DCM) and decision support standards such as virtual medical record (vMR) and Systematized Nomenclature of Medicine - Clinical Terms (SNOMED CT). We represent these mappings with a semantic reconciliation model (SRM). RESULTS: The objective of the study is the creation of shareable and interoperable knowledge using a user-friendly and flexible I-KAT. Therefore we evaluated our system using completeness and user satisfaction criteria, which we assessed through the system- and user-centric evaluation processes. For system-centric evaluation, we compared the implementation of clinical information modelling system requirements in our proposed system and in existing systems. The results suggested that 82.05% of the requirements were fully supported, 7.69% were partially supported, and 10.25% were not supported by our system. In the existing systems, 35.89% of requirements were fully supported, 28.20% were partially supported, and 35.89% were not supported. For user-centric evaluation, the assessment criterion was 'ease of use'. Our proposed system showed 15 times better results with respect to MLM creation time than the existing systems. Moreover, on average, the participants made only one error in MLM creation using our proposed system, but 13 errors per MLM using the existing systems. CONCLUSION: We provide a user-friendly authoring environment for creation of shareable and interoperable knowledge for CDSS to overcome knowledge acquisition complexity. The authoring environment uses state-of-the-art decision support-related clinical standards with increased ease of use.

Biomarkers for Diabetic Retinopathy - Could Endothelin 2 Be Part of the Answer?

PURPOSE: The endothelins are a family of three highly conserved and homologous vasoactive peptides that are expressed across all organ systems. Endothelin (Edn) dysregulation has been implicated in a number of pathophysiologies, including diabetes and diabetes-related complications. Here we examined Edn2 and endothelin receptor B (Endrb) expression in retinae of diabetic mouse models and measured serum Edn2 to assess its biomarker potential. MATERIALS AND METHODS: Edn2 and Ednrb mRNA and Edn2 protein expression were assessed in young (8wk) and mature (24wk) C57Bl/6 (wild type; wt), Kimba (model of retinal neovascularisation, RNV), Akita (Type 1 diabetes; T1D) and Akimba mice (T1D plus RNV) by qRT-PCR and immunohistochemistry. Edn2 protein concentration in serum was measured using ELISA. RESULTS: Fold-changes in Edn2 and Ednrb mRNA were seen only in young Kimba (Edn2: 5.3; Ednrb: 6.0) and young Akimba (Edn2: 7.9, Ednrb: 8.8) and in mature Kimba (Edn2:9.2, Ednrb:11.2) and mature Akimba (Edn2:14.0, Ednrb:17.5) mice. Co-localisation of Edn2 with Müller-cell-specific glutamine synthetase demonstrated Müller cells and photoreceptors as the major cell types for Edn2 expression in all animal models. Edn2 serum concentrations in young Kimba, Akita and Akimba mice were not elevated compared to wt. However, in mature mice, Edn2 serum concentration was increased in Akimba (6.9pg/mg total serum protein) compared to wt, Kimba and Akita mice (3.9, 4.6, and 3.8pg/mg total serum protein, respectively; p<0.05). CONCLUSIONS: These results demonstrated that long-term hyperglycaemia in conjunction with VEGF-driven RNV increased Edn2 serum concentration suggesting Edn2 might be a candidate biomarker for vascular changes in diabetic retinopathy.

Multimodal hybrid reasoning methodology for personalized wellbeing services.

A wellness system provides wellbeing recommendations to support experts in promoting a healthier lifestyle and inducing individuals to adopt healthy habits. Adopting physical activity effectively promotes a healthier lifestyle. A physical activity recommendation system assists users to adopt daily routines to form a best practice of life by involving themselves in healthy physical activities. Traditional physical activity recommendation systems focus on general recommendations applicable to a community of users rather than specific individuals. These recommendations are general in nature and are fit for the community at a certain level, but they are not relevant to every individual based on specific requirements and personal interests. To cover this aspect, we propose a multimodal hybrid reasoning methodology (HRM) that generates personalized physical activity recommendations according to the user׳s specific needs and personal interests. The methodology integrates the rule-based reasoning (RBR), case-based reasoning (CBR), and preference-based reasoning (PBR) approaches in a linear combination that enables personalization of recommendations. RBR uses explicit knowledge rules from physical activity guidelines, CBR uses implicit knowledge from experts׳ past experiences, and PBR uses users׳ personal interests and preferences. To validate the methodology, a weight management scenario is considered and experimented with. The RBR part of the methodology generates goal, weight status, and plan recommendations, the CBR part suggests the top three relevant physical activities for executing the recommended plan, and the PBR part filters out irrelevant recommendations from the suggested ones using the user׳s personal preferences and interests. To evaluate the methodology, a baseline-RBR system is developed, which is improved first using ranged rules and ultimately using a hybrid-CBR. A comparison of the results of these systems shows that hybrid-CBR outperforms the modified-RBR and baseline-RBR systems. Hybrid-CBR yields a 0.94% recall, a 0.97% precision, a 0.95% f-score, and low Type I and Type II errors.

GUDM: Automatic Generation of Unified Datasets for Learning and Reasoning in Healthcare.

A wide array of biomedical data are generated and made available to healthcare experts. However, due to the diverse nature of data, it is difficult to predict outcomes from it. It is therefore necessary to combine these diverse data sources into a single unified dataset. This paper proposes a global unified data model (GUDM) to provide a global unified data structure for all data sources and generate a unified dataset by a "data modeler" tool. The proposed tool implements user-centric priority based approach which can easily resolve the problems of unified data modeling and overlapping attributes across multiple datasets. The tool is illustrated using sample diabetes mellitus data. The diverse data sources to generate the unified dataset for diabetes mellitus include clinical trial information, a social media interaction dataset and physical activity data collected using different sensors. To realize the significance of the unified dataset, we adopted a well-known rough set theory based rules creation process to create rules from the unified dataset. The evaluation of the tool on six different sets of locally created diverse datasets shows that the tool, on average, reduces 94.1% time efforts of the experts and knowledge engineer while creating unified datasets.

H2RM: A Hybrid Rough Set Reasoning Model for Prediction and Management of Diabetes Mellitus.

Diabetes is a chronic disease characterized by high blood glucose level that results either from a deficiency of insulin produced by the body, or the body's resistance to the effects of insulin. Accurate and precise reasoning and prediction models greatly help physicians to improve diagnosis, prognosis and treatment procedures of different diseases. Though numerous models have been proposed to solve issues of diagnosis and management of diabetes, they have the following drawbacks: (1) restricted one type of diabetes; (2) lack understandability and explanatory power of the techniques and decision; (3) limited either to prediction purpose or management over the structured contents; and (4) lack competence for dimensionality and vagueness of patient's data. To overcome these issues, this paper proposes a novel hybrid rough set reasoning model (H2RM) that resolves problems of inaccurate prediction and management of type-1 diabetes mellitus (T1DM) and type-2 diabetes mellitus (T2DM). For verification of the proposed model, experimental data from fifty patients, acquired from a local hospital in semi-structured format, is used. First, the data is transformed into structured format and then used for mining prediction rules. Rough set theory (RST) based techniques and algorithms are used to mine the prediction rules. During the online execution phase of the model, these rules are used to predict T1DM and T2DM for new patients. Furthermore, the proposed model assists physicians to manage diabetes using knowledge extracted from online diabetes guidelines. Correlation-based trend analysis techniques are used to manage diabetic observations. Experimental results demonstrate that the proposed model outperforms the existing methods with 95.9% average and balanced accuracies.

Human facial expression recognition using stepwise linear discriminant analysis and hidden conditional random fields.

This paper introduces an accurate and robust facial expression recognition (FER) system. For feature extraction, the proposed FER system employs stepwise linear discriminant analysis (SWLDA). SWLDA focuses on selecting the localized features from the expression frames using the partial F-test values, thereby reducing the within class variance and increasing the low between variance among different expression classes. For recognition, the hidden conditional random fields (HCRFs) model is utilized. HCRF is capable of approximating a complex distribution using a mixture of Gaussian density functions. To achieve optimum results, the system employs a hierarchical recognition strategy. Under these settings, expressions are divided into three categories based on parts of the face that contribute most toward an expression. During recognition, at the first level, SWLDA and HCRF are employed to recognize the expression category; whereas, at the second level, the label for the expression within the recognized category is determined using a separate set of SWLDA and HCRF, trained just for that category. In order to validate the system, four publicly available data sets were used, and a total of four experiments were performed. The weighted average recognition rate for the proposed FER approach was 96.37% across the four different data sets, which is a significant improvement in contrast to the existing FER methods.

ATHENA: a personalized platform to promote an active lifestyle and wellbeing based on physical, mental and social health primitives.

Technology provides ample opportunities for the acquisition and processing of physical, mental and social health primitives. However, several challenges remain for researchers as how to define the relationship between reported physical activities, mood and social interaction to define an active lifestyle. We are conducting a project, ATHENA(activity-awareness for human-engaged wellness applications) to design and integrate the relationship between these basic health primitives to approximate the human lifestyle and real-time recommendations for wellbeing services. Our goal is to develop a system to promote an active lifestyle for individuals and to recommend to them valuable interventions by making comparisons to their past habits. The proposed system processes sensory data through our developed machine learning algorithms inside smart devices and utilizes cloud infrastructure to reduce the cost. We exploit big data infrastructure for massive sensory data storage and fast retrieval for recommendations. Our contributions include the development of a prototype system to promote an active lifestyle and a visual design capable of engaging users in the goal of increasing self-motivation. We believe that our study will impact the design of future ubiquitous wellness applications.

Video-based human activity recognition using multilevel wavelet decomposition and stepwise linear discriminant analysis.

Video-based human activity recognition (HAR) means the analysis of motions and behaviors of human from the low level sensors. Over the last decade, automatic HAR is an exigent research area and is considered a significant concern in the field of computer vision and pattern recognition. In this paper, we have presented a robust and an accurate activity recognition system called WS-HAR that consists of wavelet transform coupled with stepwise linear discriminant analysis (SWLDA) followed by hidden Markov model (HMM). Symlet wavelet has been employed in order to extract the features from the activity frames. The most prominent features were selected by proposing a robust technique called stepwise linear discriminant analysis (SWLDA) that focuses on selecting the localized features from the activity frames and discriminating their class based on regression values (i.e., partial F-test values). Finally, we applied a well-known sequential classifier called hidden Markov model (HMM) to give the appropriate labels to the activities. In order to validate the performance of the WS-HAR, we utilized two publicly available standard datasets under two different experimental settings, n??fold cross validation scheme based on subjects; and a set of experiments was performed in order to show the effectiveness of each approach. The weighted average recognition rate for the WS-HAR was 97% across the two different datasets that is a significant improvement in classication accuracy compared to the existing well-known statistical and state-of-the-art methods.

Effect of vascular endothelial growth factor upregulation on retinal gene expression in the Kimba mouse.

BACKGROUND: The Kimba mouse carries a human vascular endothelial growth factor transgene causing retinal neovascularisation similar to that seen in diabetic retinopathy. Here, we examine the relationship between differential gene expression induced by vascular endothelial growth factor overexpression and the architectural changes that occur in the retinae of these mice. METHODS: Retinal gene expression changes in juvenile and adult Kimba mice were assayed by microarray and compared with age-matched wild-type littermates. Transcription of selected genes was validated by quantitative real-time polymerase chain reaction. Protein translation was determined using immunohistochemistry and enzyme-linked immunosorbent assay. RESULTS: Semaphorin 3C was upregulated, and nuclear receptor subfamily 2, group 3, member 3 (Nr2e3) was downregulated in juvenile Kimba mice. Betacellulin and endothelin 2 were upregulated in adults. Semaphorin 3C colocalized with glial fibrillary acidic protein in Müller cells of Kimba retinae at greater signal intensities than in wild type. Endothelin 2 colocalised to Müller cell end feet and extended into the outer limiting membrane. Endothelin receptor type B staining was most pronounced in the inner nuclear layer, the region containing Müller cell somata. CONCLUSIONS: An early spike in vascular endothelial growth factor induced significant long-term retinal neovascularisation associated with changes to the retinal ganglion, photoreceptor and Müller cells. Overexpression of vascular endothelial growth factor led to dysregulation of photoreceptor metabolism through differential expression of Nr2e3, endothelin 2, betacellulin and semaphorin 3C. Alterations in the expression of these genes may therefore play key roles in the pathological mechanisms that result from retinal neovascularisation.

In vivo monitoring of VEGF-induced retinal damage in the Kimba mouse model of retinal neovascularization.

PURPOSE: To monitor retinal and vascular changes associated with neovascularization, which were generated through photoreceptor-specific overexpression of human vascular endothelial growth factor (hVEGF), in transgenic trVEGF029 (Kimba) mice. MATERIALS AND METHODS: The Spectralis Heidelberg Retina Angiography and Optical Coherence Tomography (HRA+OCT) imaging device was used to track changes in the retina and retinal vasculature of Kimba mouse eyes (n = 32) and control C57Bl/6J mouse eyes (n = 20) at 4, 8, 12, 16, and 20 weeks of age. RESULTS: Retinal vascular leakage, focal dilated vessel, vessel tortuosity, attenuated vessel, venous beading, capillary dropout, retinal non-perfusion, neovascularization, and focal retinal detachment were observed in Kimba mouse eyes. Through track changes, we detected edema in the peripheral part of the retina of 2/32 Kimba mouse eyes examined. The retinae of the Kimba mice were significantly thinner than control mice retinae at all ages of the mice assessed (p < 0.01). CONCLUSIONS: In vivo monitoring of retinal vascular and neural retinal changes in the Kimba mice using the Spectralis HRA+OCT imaging device allowed us to assess and track VEGF-induced damages in great detail and in real-time. Real-time monitoring of these changes can be used to study the interplay between VEGF overexpression and other molecular factors and to monitor dynamic retinal changes following therapeutic intervention.

Characterization of a mouse model of hyperglycemia and retinal neovascularization.

One of the limitations of research into diabetic retinopathy is the lack of suitable animal models. To study how the two important factors--hyperglycemia and vascular endothelial growth factor--interact in diabetic retinopathy, the Akimba mouse (Ins2AkitaVEGF+/-) was generated by crossing the Akita mouse (Ins2Akita) with the Kimba mouse (VEGF+/+). C57Bl/6 and the parental and Akimba mouse lines were characterized by biometric measurements, histology, immunohistochemistry, and Spectralis Heidelberg retinal angiography and optical coherence tomography. The Akimba line not only retained the characteristics of the parental strains, such as developing hyperglycemia and retinal neovascularization, but developed higher blood glucose levels at a younger age and had worse kidney-body weight ratios than the Akita line. With aging, the Akimba line demonstrated enhanced photoreceptor cell loss, thinning of the retina, and more severe retinal vascular pathology, including more severe capillary nonperfusion, vessel constriction, beading, neovascularization, fibroses, and edema, compared with the Kimba line. The vascular changes were associated with major histocompatibility complex class II+ cellular staining throughout the retina. Together, these observations suggest that hyperglycemia resulted in higher prevalences of edema and exacerbated the vascular endothelial growth factor-driven neovascular and retinal changes in the Akimba line. Thus, the Akimba line could become a useful model for studying the interplay between hyperglycemia and vascular endothelial growth factor and for testing treatment strategies for potentially blinding complications, such as edema.

Acute reversible lens opacity affects retinal HRA+OCT imaging in mice / 国际眼科杂志(Guoji Yanke Zazhi)

AIM: To assess the affect of ketamine and xylazine (ketamine/xylazine) to the transient lens opacity in mice.METHODS: Kimba mice (n=10) and wild-type mice (wt, n=8) were sedated with intraperitoneal injection of ketamine (60mg/kg for mice) and xylazine (10mg/kg) at 4, 8, 12 and 16 weeks old respectively. Pupils were dilated with tropicamide 25g/L alone to allow imaging lens status and retina using Spectralis HRA+OCT. RESULTS: All Kimba mice and wt presented extreme proptosis, suppression of the eye-blink reflex, corneal surface drying and lens opacities which occurred as early as 21±6 minutes after giving anesthesia and the lens opacities lasted up to 150±24 minutes.CONCLUSION: Ketamine/xylazine can cause transient lens opacity that may be related with the drugs side-effect.