Search

It is vital to develop an appropriate prediction model and link carefully to measurable events such as clinical parameters and patient outcomes to analyze the severity of the disease. Timely identifying retinal diseases is becoming more vital to prevent blindness among young and adults. Investigation of blood vessels delivers preliminary information on the existence and treatment of glaucoma, retinopathy, and so on. During the analysis of diabetic retinopathy, one of the essential steps is to extract the retinal blood vessel accurately. This study presents an improved Gabor filter through various enhancement approaches. The degraded images with the enhancement of certain features can simplify image interpretation both for a human observer and for machine recognition. Thus, in this work, few enhancement approaches such as Gamma corrected adaptively with distributed weight (GCADW), joint equalization of histogram (JEH), homomorphic filter, unsharp masking filter, adaptive unsharp masking filter, and particle swarm optimization (PSO) based unsharp masking filter are taken into consideration. In this paper, an effort has been made to improve the performance of the Gabor filter by combining it with different enhancement methods and to enhance the detection of blood vessels. The performance of all the suggested approaches is assessed on publicly available databases such as DRIVE and CHASE_DB1. The results of all the integrated enhanced techniques are analyzed, discussed, and compared. The best result is delivered by PSO unsharp masking filter combined with the Gabor filter with an accuracy of 0.9593 for the DRIVE database and 0.9685 for the CHASE_DB1 database. The results illustrate the robustness of the recommended model in automatic blood vessel segmentation that makes it possible to be a clinical support decision tool in diabetic retinopathy diagnosis.

The wearable healthcare equipment is primarily designed to alert patients of any specific health conditions or to act as a useful tool for treatment or follow-up. With the growth of technologies and connectivity, the security of these devices has become a growing concern. The lack of security awareness amongst novice users and the risk of several intermediary attacks for accessing health information severely endangers the use of IoT-enabled healthcare systems. In this paper, a blockchain-based secure data storage system is proposed along with a user authentication and health status prediction system. Firstly, this work utilizes reversed public-private keys combined Rivest-Shamir-Adleman (RP

Despite the vaccine against the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) being reported to be safe and effective, the unwillingness to vaccinate and doubts are still common. The aim of this international study was to assess the major reasons for the unwillingness to vaccinate in a group of students from Poland (n = 1202), Bangladesh (n = 1586), India (n = 484), Mexico (n = 234), Egypt (n = 566), Philippines (n = 2076), Pakistan (n = 506), Vietnam (n = 98) and China (n = 503). We conducted an online cross-sectional study that aimed to assess (1) the percentage of vaccinated and unvaccinated students and (2) the reasons associated with willingness/unwillingness to the vaccine. The study included 7255 respondents from 9 countries with a mean age of 21.85 ± 3.66 years. Only 22.11% (n = 1604) of students were vaccinated. However, the majority (69.25%, n = 5025) expressed a willingness to be vaccinated. More willing to vaccinate were students in informal relationships who worked mentally, used psychological/psychiatric services before the pandemic, and studied medicine. There are cultural differences regarding the reasons associated with the unwillingness to vaccinate, but some ‘universal’ might be distinguished that apply to the whole group.

Background: Machine learning is a promising approach to personalize atrial fibrillation management strategies for patients after catheter ablation. Prior atrial fibrillation ablation outcome prediction studies applied classical machine learning methods to hand-crafted clinical scores, and none have leveraged intracardiac electrograms or 12-lead surface electrocardiograms for outcome prediction. We hypothesized that (1) machine learning models trained on electrograms or electrocardiogram (ECG) signals can perform better at predicting patient outcomes after atrial fibrillation ablation than existing clinical scores and (2) multimodal fusion of electrogram, ECG, and clinical features can further improve the prediction of patient outcomes. Methods: Consecutive patients who underwent catheter ablation between 2015 and 2017 with panoramic left atrial electrogram before ablation and clinical follow-up for at least 1 year following ablation were included. Convolutional neural network and a novel multimodal fusion framework were developed for predicting 1-year atrial fibrillation recurrence after catheter ablation from electrogram, ECG signals, and clinical features. The models were trained and validated using 10-fold cross-validation on patient-level splits. Results: One hundred fifty-six patients (64.5±10.5 years, 74% male, 42% paroxysmal) were analyzed. Using electrogram signals alone, the convolutional neural network achieved an area under the receiver operating characteristics curve (AUROC) of 0.731, outperforming the existing APPLE scores (AUROC=0.644) and CHA2DS2-VASc scores (AUROC=0.650). Similarly using 12-lead ECG alone, the convolutional neural network achieved an AUROC of 0.767. Combining electrogram, ECG, and clinical features, the fusion model achieved an AUROC of 0.859, outperforming single and dual modality models. Conclusions: Deep neural networks trained on electrogram or ECG signals improved the prediction of catheter ablation outcome compared with existing clinical scores, and fusion of electrogram, ECG, and clinical features further improved the prediction. This suggests the promise of using machine learning to help treatment planning for patients after catheter ablation.

Background During the last six decades, extensive use of antibiotics has selected resistant strains, increasing the rate of fatal infectious diseases, and exerting an economic burden on society. This situation is widely accepted as a global problem, yet its degree is not well elucidated in many regions of the world. Up till now, no systemic analysis of Antimicrobial resistance (AMR) in Pakistan has been published. The current study aims to describe the antibiotic-resistance scenario of Pakistan from human samples of the last 10 y, to find the gaps in surveillances and methodology and recommendations for researchers and prescribers founded on these outcomes. Methods Original research articles analyzed the pattern of Antibiotic resistance of any World Health Organization (WHO) enlisted priority pathogens in Pakistan (published onward 2009 till March 2020), were collected from PubMed, Google scholar, and PakMedi Net search engines. These articles were selected based on predefined inclusion and exclusion criteria. Data about the study characteristics and antibiotic-resistance for a given bacterium were excluded from literature. Antibiotic resistance to a particular bacterium was calculated as a median resistance with 95% Confidence Interval (CI). Results Studies published in the last 10 y showed that Urinary Tract Infection (UTI) is the most reported clinical diagnosis (16.1%) in Pakistan. E. coli were reported in 28 (30.11%) studies showing high resistance to antibiotics’ first line. Methicillin-resistant Staphylococcus aureus (MRSA) was found in 49% of S. aureus’ total reported cases. Phenotypic resistance pattern has mostly been evaluated by Disk Diffusion Method (DDM) (82.8%), taken Clinical Laboratory Standards Institute (CLSI) as a breakpoint reference guideline (in 79.6% studies). Only 28 (30.11%) studies have made molecular identification of the resistance gene. blaTEM (78.94% in Shigella spp) and blaNDM-1 (32.75% in Klebsiella spp) are the prominent reported resistant genes followed by VanA (45.53% in Enterococcus spp), mcr-1 (1.61% in Acinetobacter spp), and blaKPC-2 (31.67% in E. coli). Most of the studies were from Sindh (40.86%), followed by Punjab (35.48%), while Baluchistan’s AMR data was not available. Conclusion Outcomes of our study emphasize that most of the pathogens show high resistance to commonly used antibiotics; also, we find gaps in surveillances and breaches in methodological data. Based on these findings, we recommend the regularization of surveillance practice and precise actions to combat the region’s AMR.

Carcinoma is a primary source of morbidity in women globally, with metastatic disease accounting for most deaths. Its early discovery and diagnosis may significantly increase the odds of survival. Breast cancer imaging is critical for early identification, clinical staging, management choices, and treatment planning. In the current study, the FastAI technology is used with the ResNet-32 model to precisely identify ductal carcinoma. ResNet-32 is having few layers comparted to majority of its counterparts with almost identical performance. FastAI offers a rapid approximation toward the outcome for deep learning models via GPU acceleration and a faster callback mechanism, which would result in faster execution of the model with lesser code and yield better precision in classifying the tissue slides. Residual Network (ResNet) is proven to handle the vanishing gradient and effective feature learning better. Integration of two computationally efficient technologies has yielded a precision accuracy with reasonable computational efforts. The proposed model has shown considerable efficiency in the evaluating parameters like sensitivity, specificity, accuracy, and F1 Score against the other dominantly used deep learning models. These insights have shown that the proposed approach might assist practitioners in analyzing Breast Cancer (BC) cases appropriately, perhaps saving future complications and death. Clinical and pathological analysis and predictive accuracy have been improved with digital image processing.

Biomedical images contain a huge number of sensor measurements that can provide disease characteristics. Computer-assisted analysis of such parameters aids in the early detection of disease, and as a result aids medical professionals in quickly selecting appropriate medications. Human Activity Recognition, abbreviated as ‘HAR’, is the prediction of common human measurements, which consist of movements such as walking, running, drinking, cooking, etc. It is extremely advantageous for services in the sphere of medical care, such as fitness trackers, senior care, and archiving patient information for future use. The two types of data that can be fed to the HAR system as input are, first, video sequences or images of human activities, and second, time-series data of physical movements during different activities recorded through sensors such as accelerometers, gyroscopes, etc., that are present in smart gadgets. In this paper, we have decided to work with time-series kind of data as the input. Here, we propose an ensemble of four deep learning-based classification models, namely, ‘CNN-net’, ‘CNNLSTM-net’, ‘ConvLSTM-net’, and ‘StackedLSTM-net’, which is termed as ‘Ensem-HAR’. Each of the classification models used in the ensemble is based on a typical 1D Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) network; however, they differ in terms of their architectural variations. Prediction through the proposed Ensem-HAR is carried out by stacking predictions from each of the four mentioned classification models, then training a Blender or Meta-learner on the stacked prediction, which provides the final prediction on test data. Our proposed model was evaluated over three benchmark datasets, WISDM, PAMAP2, and UCI-HAR; the proposed Ensem-HAR model for biomedical measurement achieved 98.70%, 97.45%, and 95.05% accuracy, respectively, on the mentioned datasets. The results from the experiments reveal that the suggested model performs better than the other multiple generated measurements to which it was compared.

Lymph node metastasis in breast cancer may be accurately predicted using a DenseNet-169 model. However, the current system for identifying metastases in a lymph node is manual and tedious. A pathologist well-versed with the process of detection and characterization of lymph nodes goes through hours investigating histological slides. Furthermore, because of the massive size of most whole-slide images (WSI), it is wise to divide a slide into batches of small image patches and apply methods independently on each patch. The present work introduces a novel method for the automated diagnosis and detection of metastases from whole slide images using the Fast AI framework and the 1-cycle policy. Additionally, it compares this new approach to previous methods. The proposed model has surpassed other state-of-art methods with more than 97.4% accuracy. In addition, a mobile application is developed for prompt and quick response. It collects user information and models to diagnose metastases present in the early stages of cancer. These results indicate that the suggested model may assist general practitioners in accurately analyzing breast cancer situations, hence preventing future complications and mortality. With digital image processing, histopathologic interpretation and diagnostic accuracy have improved considerably.

Uncertainty and isolation have been linked to mental health problems. Uncertainty surrounding the COVID-19 pandemic has the potential to trigger mental health problems, which include anxiety, stress, and depression. This paper evaluates the prevalence, psychological responses, and associated correlates of depression, anxiety, and stress in a global population during the Coronavirus Disease (COVID-19) pandemic. A cross-sectional study design was adopted. 678 completed forms were collected during the COVID-19 quarantine/lockdown. An online questionnaire was designed and DASS-21 was used as the screening tool. A non-probability sampling technique strategy was applied. 50.9% of participants showed traits of anxiety, 57.4% showed signs of stress, and 58.6% exhibited depression. Stress, anxiety, and depression are overwhelmingly prevalent across the globe during this COVID-19 pandemic, and multiple factors can influence the rates of these mental health conditions. Our factorial analysis showed notable associations and manifestations of stress, anxiety, and depressive symptoms. People aged 18-24, females, and people in non-marital relationships experienced stress, anxiety, and depression. Separated individuals experienced stress and anxiety. Married people experienced anxiety. Single and divorced people experienced depression. Unemployed individuals experienced stress and depression. Students experienced anxiety and depression. Canada, the UK, and Pakistan are all countries that are experiencing stress and depression as a whole. An extended number of days in quarantine was associated with increased stress, anxiety, and depression. Family presence yielded lower levels of stress, anxiety, and depression. Lastly, lack of exercise was associated with increased stress, anxiety, and depression.

Background:Lungs are the second most common reported site of distant metastasis in Breast cancer after bone. Mostly the studies were conducted in cell lines and animal model. To date, there is no blood biomarker reported that could determine the breast cancer progression in terms of lung metastasis.Objective:The aim of this study is to determine Nidogen-1 (NID1)’s mRNA and protein expressions in non-invasive blood samples of breast cancer, in early (II) and lung metastasis advanced stages (III & IV) of naive and treated groups. To determine the functional association of NID1, we employed an in silico analysis, STRING database version 11.Methods:A total of n = 175 cases of breast cancer were recruited in our study. Real time quantitative PCR and ELISA were performed to analyze the mRNA and protein expressions of NID1 respectively. An in silico method is also used to assess NID1’s interactome. Some significant patents related to this topic were also studied and discussed in this research paper.Results:The results show high levels of NID1’s mRNA in the naive group (Group A) as compared to treated group (Group B). Similar trend of increased NID1’s protein expressions was also observed among naive and treated groups, respectively. Our results also show the significant impact of treatment on NID1’s gene and protein expressions. In silico analysis has revealed the functional association of NID1 with its different interactome protein partners.Conclusions:The increased expression of NID1 in early to advanced naive as compared to the treated groups with lung metastasis makes it a promising marker which has pro-metastatic role in breast cancer.

Human Action Recognition (HAR) is a popular area of research in computer vision due to its wide range of applications such as surveillance, health care, and gaming, etc. Action recognition based on 3D skeleton data allows simplistic, cost-efficient models to be formed making it a widely used method. In this work, we propose DSwarm-Net, a framework that employs deep learning and swarm intelligence-based metaheuristic for HAR that uses 3D skeleton data for action classification. We extract four different types of features from the skeletal data namely: Distance, Distance Velocity, Angle, and Angle Velocity, which capture complementary information from the skeleton joints for encoding them into images. Encoding the skeleton data features into images is an alternative to the traditional video-processing approach and it helps in making the classification task less complex. The Distance and Distance Velocity encoded images have been stacked depth-wise and fed into a Convolutional Neural Network model which is a modified version of Inception-ResNet. Similarly, the Angle and Angle Velocity encoded images have been stacked depth-wise and fed into the same network. After training these models, deep features have been extracted from the pre-final layer of the networks, and the obtained feature representation is optimized by a nature-inspired metaheuristic, called Ant Lion Optimizer, to eliminate the non-informative or misleading features and to reduce the dimensionality of the feature set. DSwarm-Net has been evaluated on three publicly available HAR datasets, namely UTD-MHAD, HDM05, and NTU RGB+D 60 achieving competitive results, thus confirming the superiority of the proposed model compared to state-of-the-art models.

Imbalance in hyperspectral images creates a crisis in its analysis and classification operation. Resampling techniques are utilized to minimize the data imbalance. Although only a limited number of resampling methods were explored in the previous research, a small quantity of work has been done. In this study, we propose a novel illustrative study of the performance of the existing resampling techniques, viz. oversampling, undersampling, and hybrid sampling, for removing the imbalance from the minor samples of the hyperspectral dataset. The balanced dataset is classified in the next step, using the tree-based ensemble classifiers by including the spectral and spatial features. Finally, the comparative study is performed based on the statistical analysis of the outcome obtained from those classifiers that are discussed in the results section. In addition, we applied a new ensemble hybrid classifier named random rotation forest to our dataset. Three benchmark hyperspectral datasets: Indian Pines, Salinas Valley, and Pavia University, are applied for performing the experiments. We have taken precision, recall, F score, Cohen kappa, and overall accuracy as assessment metrics to evaluate our model. The obtained result shows that SMOTE, Tomek Links, and their combinations stand out to be the more optimized resampling strategies. Moreover, the ensemble classifiers such as rotation forest and random rotation ensemble provide more accuracy than others of their kind.

Pulsed-field ablation (PFA) yields a novel ablation technology for atrial fibrillation (AF). PFA lesions promise to be highly durable, however clinical data on lesion characteristics are still limited.This study sought to investigate PFA lesion creation with ultrahigh-density (UHDx) mapping.Consecutive AF patients underwent PFA-based pulmonary vein isolation (PVI) using a multispline catheter (Farwave, Farapulse Inc.). Additional ablation, including left atrial posterior wall isolation (LAPWI) and mitral isthmus ablation (MI) were performed in a subset of persistent AF patients. The extent of PFA-lesions and decrease of LA-voltage were assessed with pre- and post PFA UHDx-mapping (Orion™ catheter and Rhythmia™ 3D-mapping system, Boston Scientific).In 20 patients, acute PVI was achieved in 80/80 PVs, LAPW isolation in 9/9 patients, MI ablation in 2/2 (procedure time: 123 ± 21.6 min, fluoroscopy time: 19.2 ± 5.5 min). UHDx-mapping subsequent to PVI revealed early PV-reconnection in five case (5/80, 6.25%). Gaps were located at the anterior-superior PV ostia and were successfully targeted with additional PFA. Repeat UHDx mapping after PFA revealed a significant decrease of voltage along the PV ostia (1.67 ± 1.36 mV vs. 0.053 ± 0.038 mV, p .0001) with almost no complex electrogram-fractionation at the lesion border zones. PFA-catheter visualization within the mapping system was feasible in 17/19 (84.9%) patients and adequate in 92.9% of ablation sites.For the first time illustrated by UHDx mapping, PFA creates wide antral circumferential lesions and homogenous LAPW isolation with depression of tissue voltage to a minimum. Although with a low incidence, early PV reconnection can still occur also in the setting of PFA.

Introduction: Plasmid-mediated colistin resistance genes, especially mcr-3 combined with the fosfomycin resistance gene fosA3, are a grave health concern. Our study was designed to determine the epidemiological characteristics of the combination of mcr-3 and fosA3 in Anhui province, China. Methodology: A total of 127 multi-drug-resistant (MDR) E. coli strains were assessed for antibiotic resistance/sensitivity to detect mcr-3 and fosA3 using polymerase chain reaction (PCR) and sequencing. The genes of interest were conjugated using EC600, and replicon and sequence types (STs) were identified by PCR-based replicon typing (PBRT) and multilocus sequence typing (MLST). Cluster similarity and genomic relatedness among the positive isolates were confirmed by Xbal PFGE. Results: The processed E. coli isolates were highly resistant to the tested antibiotics; the prevalence of mcr-3 was 0.78% in the transferable IncP-type plasmid in ST131, whereas fosA3 prevalence was 38.58% among different transferable plasmids, including IncFIIK, IncFII and IncA/C, and in various STs including ST69, ST1193, ST12, ST46, ST57, ST1196, ST38, ST95, ST131, ST7584 and ST10184. Both were successfully transferred to EC600. The Xbal PFGE cluster exposed similarities among the STs. Conclusions: Our results show that to control the spread of colistin and fosfomycin resistance genes in human pathogens, the ban on colistin must be continued in animal feeding farms not only in China but around the world; additionally, awareness platforms on the use of colistin must be implemented and strict policies in poultry and pig farms must be maintained. Furthermore, fosfomycin misuse by patients and overuse by physicians must be strictly managed to stop the spread of fosfomycin resistance.

Charge density mapping of atrial fibrillation (AF) reveals dynamic localized rotational activation (LRA), irregular activation (LIA) and focal firing (FF). Their spatial stability, conduction characteristics and the optimal duration of mapping required to reveal these phenomena and has not been explored.Bi-atrial mapping of AF propagation was undertaken using AcQMap (Acutus Medical) and variability of activation patterns quantified up to a duration of 30 s. The frequency of each pattern was quantified at each unique point of the chamber over two separate 30-s recordings before ablation and RIn 21 patients, 62 paired LA and RA maps were obtained. LIA was highly spatially stable with RIrregular activation patterns characterized by changing wavefront direction are temporally and spatially stable in contrast with LRA that is transient with least spatial stability. Focal activation appears of intermediate stability. Regions of LIA show increased heterogeneity following extrastimulus pacing and may represent fixed anatomical substrate.

In machine learning and data science, feature selection is considered as a crucial step of data preprocessing. When we directly apply the raw data for classification or clustering purposes, sometimes we observe that the learning algorithms do not perform well. One possible reason for this is the presence of redundant, noisy, and non-informative features or attributes in the datasets. Hence, feature selection methods are used to identify the subset of relevant features that can maximize the model performance. Moreover, due to reduction in feature dimension, both training time and storage required by the model can be reduced as well. In this paper, we present a tri-stage wrapper-filter-based feature selection framework for the purpose of medical report-based disease detection. In the first stage, an ensemble was formed by four filter methods—Mutual Information, ReliefF, Chi Square, and Xvariance—and then each feature from the union set was assessed by three classification algorithms—support vector machine, naïve Bayes, and k-nearest neighbors—and an average accuracy was calculated. The features with higher accuracy were selected to obtain a preliminary subset of optimal features. In the second stage, Pearson correlation was used to discard highly correlated features. In these two stages, XGBoost classification algorithm was applied to obtain the most contributing features that, in turn, provide the best optimal subset. Then, in the final stage, we fed the obtained feature subset to a meta-heuristic algorithm, called whale optimization algorithm, in order to further reduce the feature set and to achieve higher accuracy. We evaluated the proposed feature selection framework on four publicly available disease datasets taken from the UCI machine learning repository, namely, arrhythmia, leukemia, DLBCL, and prostate cancer. Our obtained results confirm that the proposed method can perform better than many state-of-the-art methods and can detect important features as well. Less features ensure less medical tests for correct diagnosis, thus saving both time and cost.

Deep learning models are efficient in learning the features that assist in understanding complex patterns precisely. This study proposed a computerized process of classifying skin disease through deep learning based MobileNet V2 and Long Short Term Memory (LSTM). The MobileNet V2 model proved to be efficient with a better accuracy that can work on lightweight computational devices. The proposed model is efficient in maintaining stateful information for precise predictions. A grey-level co-occurrence matrix is used for assessing the progress of diseased growth. The performance has been compared against other state-of-the-art models such as Fine-Tuned Neural Networks (FTNN), Convolutional Neural Network (CNN), Very Deep Convolutional Networks for Large-Scale Image Recognition developed by Visual Geometry Group (VGG), and convolutional neural network architecture that expanded with few changes. The HAM10000 dataset is used and the proposed method has outperformed other methods with more than 85% accuracy. Its robustness in recognizing the affected region much faster with almost 2× lesser computations than the conventional MobileNet model results in minimal computational efforts. Furthermore, a mobile application is designed for instant and proper action. It helps the patient and dermatologists identify the type of disease from the affected region’s image at the initial stage of the skin disease. These findings suggest that the proposed system can help general practitioners efficiently and effectively diagnose skin conditions, thereby reducing further complications and morbidity.

This study aimed to test the psychometric properties of the Urdu version of the Safety Attitudes Questionnaire for inpatient settings in Pakistan.The SAQ short form (inpatient version) was translated with the back-translation technique into Urdu. The SAQ-Urdu was administered in three teaching hospitals in Pakistan to a sample of 483 front line healthcare personnel from August 2016 through December 2017. Confirmatory factor analysis was performed to test the factor structure of the responses. Cronbach's alphas and correlation coefficients were computed. Mean and percentage agreement scores for items were reported.The response rate was 75%. Goodness-of-fit indices from the confirmatory factor analysis showed a reasonable model fit (χ2=213.27, df=125, p0.001; CFI 0.94, RMSEA 0.044). Cronbach's alphas of survey factors (teamwork climate, safety climate, job satisfaction, perceptions of management, and working conditions) ranged from 0.71 to 0.87. In terms of mean percentage agreement scores, substantial variability was found at the clinical unit level.The Urdu version of the SAQ showed satisfactory internal psychometric properties. The attitudes around patient safety considerably vary and indicate a need for improvement.

Globally, cervical cancer remains as the foremost prevailing cancer in females. Hence, it is necessary to distinguish the importance of risk factors of cervical cancer to classify potential patients. The present work proposes a cervical cancer prediction model (CCPM) that offers early prediction of cervical cancer using risk factors as inputs. The CCPM first removes outliers by using outlier detection methods such as density-based spatial clustering of applications with noise (DBSCAN) and isolation forest (iForest) and by increasing the number of cases in the dataset in a balanced way, for example, through synthetic minority over-sampling technique (SMOTE) and SMOTE with Tomek link (SMOTETomek). Finally, it employs random forest (RF) as a classifier. Thus, CCPM lies on four scenarios: (1) DBSCAN + SMOTETomek + RF, (2) DBSCAN + SMOTE+ RF, (3) iForest + SMOTETomek + RF, and (4) iForest + SMOTE + RF. A dataset of 858 potential patients was used to validate the performance of the proposed method. We found that combinations of iForest with SMOTE and iForest with SMOTETomek provided better performances than those of DBSCAN with SMOTE and DBSCAN with SMOTETomek. We also observed that RF performed the best among several popular machine learning classifiers. Furthermore, the proposed CCPM showed better accuracy than previously proposed methods for forecasting cervical cancer. In addition, a mobile application that can collect cervical cancer risk factors data and provides results from CCPM is developed for instant and proper action at the initial stage of cervical cancer.

Pakistan has recently observed a significant growth in public health education programmes. Little is known about the structure of these programmes nor whether they are adequately responsive to national health system needs.We reviewed existing public health degree programmes in Pakistan along with an exploration of the national public health market and health system needs.A mixed-methods study was conducted between January 2015 and March 2016. Seventeen public health degree programmes were reviewed for programmatic and instructional attributes. Thirteen key-informant interviews were conducted to explore health system needs and challenges related to public health workforce.We found substantial variation in public health academic programmes in terms of offered courses, credit hours, number of faculty and tuition costs. About 70% of public health degree programmes were generic (i.e. with no specific concentration track) and only 18% offered practicums. Overall median tuition cost in 2016 was US$ 10 350. During key-informant interviews, emerged themes for challenges included lack of practical public health skills, limited knowledge of latest theoretical principles, poor communication skills and insufficient IT orientation. Identified themes about knowledge and skills areas to address future public health challenges of Pakistan included system thinking mind set, healthcare IT skills, and leadership and management skills.Public health education in Pakistan falls short of meeting current national challenges. Pakistan needs a national public health accreditation body for regulating education, harmonizing global standards to local context and developing relevant career pathways.تعليم الصحة العامة واحتياجات النظام الصحي بباكستان: دراسة باتباع مزيج من الطرق.محمد فضل ذيشان، عثمان رضا، سعيد أنور، دردانة خان، عامر عباس، نويد صادق، عميرقاضي.شهدت باكستان مؤخرا نموًّا كبيرًا في برامج التعليم في الصحة العامة. إن المعلومات قليلة حول بنية برامج التعليم في الصحة العامة وما إذا كانت استجابتها كافية لتلبية احتياجات النظام الصحي الوطني.استعرضنا البرامج الموجودة حاليًّا لمنح الشهادات الدراسية في الصحة العامة في باكستان إلى جانب استكشاف سوق الصحة العامة واحتياجات النظام الصحي على الصعيد الوطني.أجرينا دراسة بمزيج من الطرق في الفترة بين يناير/كانون الثاني 2015 ومارس/آذار 2016. استعرضنا المواصفات البرنامجية والتلقينية في 17 برنامجًا يمنح شهادة في الصحة العامة. أجرينا 13 مقابلة مع أشخاص ذوي أهمية رئيسية كمصادر للمعلومات لاستكشاف احتياجات النظام الصحي والتحديات ذات الصلة بالقوى العاملة في الصحة العامة.وجدنا اختلافًا كبيرًا بين البرامج الأكاديمية في مجال الصحة العامة من حيثُ الدورات التعليمية التي تقدمها والساعات المعتمدة التي تحتسبها وعدد أعضاء هيئة التدريس فيها والرسوم الدراسية التي تطلبها. واتضح لنا أن حوالي 70 % البرامج التي تمنح شهادات في الصحة العامة كانت عامة (أي أنها لا تركِّز على مسار تخصصي) ، وأن نسبة التدريب العملي الذي تقدمه لا يزيد على 18 % فقط. وكان متوسط تكلفة رسوم التعليم في عام 2016 مقدرة بالدولارات الأمريكية 10350. أثناء المقابلات مع الأشخاص ذوي الأهمية الرئيسية كمصادر للمعلومات اتضح لنا مواضيع التحديات ومنها الافتقار إلى المهارات العملية في مجال الصحة العامة، والمعرفة المحدودة النطاق بأحدث المبادئ النظرية، وتدني مستوى مهارات الاتصال، وعدم كفاية التوجه نحو تكنولوجيا المعلومات. وحددنا المواضيع التي تدور حول مجالات المعلومات والمهارات اللازمة لمواجهة التحديات المستقبلية في مجال الصحة العامة في باكستان ومنها توجيه الذهن نحو التفكير بالنظام، ومهارات تكنولوجيا المعلومات في الرعاية الصحية، ومهارات القيادة ومهارات الإدارة.لا يلبي التعليم في مجال الصحة العامة في باكستان مقتضيات التحديات الوطنية الحالية. تحتاج باكستان إلى هيئة اعتماد وطنية في الصحة العامة لتنظيم التعليم، ومواءمة المعايير العالمية مع السياق المحلي وتطوير مسارات المستقبل المهني ذات الصلة.Enseignement en santé publique et besoins du système de santé au Pakistan : étude à méthodologie mixte.Le Pakistan connaît depuis peu une forte augmentation du nombre de ses programmes d’enseignement en santé publique. La structure de ces programmes et leur adéquation aux besoins du système de santé national restent méconnues.Nous avons examiné les programmes en santé publique diplômants qui existent actuellement au Pakistan et nous avons étudié le marché national pour ce domaine ainsi que les besoins du système de santé.Une étude à méthodologie mixte a été réalisée entre janvier 2015 et mars 2016. Dix-sept programmes en santé publique diplômants ont été passés en revue afin de déterminer leurs caractéristiques programmatiques et pédagogiques. Treize entretiens avec des informateurs clés ont été menés afin d’analyser les besoins du système de santé et les problèmes des personnels dans le secteur de la santé publique.Nous avons constaté des différences considérables entre les filières académiques en santé publique, tant sur le plan des cours proposés que des heures d’étude, des effectifs du corps enseignant et des frais de scolarité. Environ 70 % des programmes diplômants en santé publique étaient génériques (c’est-à-dire sans filière spécialisée) et seuls 18 % proposaient des stages pratiques. La valeur médiane des frais de scolarité généraux (en 2016) s’élevait à 10 350 dollars US. Au cours des entretiens avec les informateurs clés, les problématiques soulevées comprenaient le manque de compétences pratiques en matière de santé publique, les connaissances limitées concernant les derniers principes théoriques, les faibles compétences en communication et l’orientation insuffisante vers les moyens informatisés. Les thématiques identifiées dans les domaines des connaissances et des compétences nécessaires afin de relever les défis futurs du Pakistan en matière de santé publique comprenaient une approche intellectuelle systémique, des compétences informatiques axées sur les soins de santé et des aptitudes en leadership et en gestion.L’enseignement en santé publique au Pakistan n’est pas à la hauteur des difficultés auxquelles le pays fait face à l’heure actuelle. Le Pakistan a besoin d’un organisme d’accréditation national en santé publique capable de réglementer l’enseignement, d’harmoniser les normes mondiales en fonction du contexte local et de développer des filières professionnelles pertinentes.

Hospital waste management (HWM) rules in Pakistan were issued in 2005. Despite a decade of enactment, adherence to HWM 2005 rules has been inconsistent and systematic assessment of adherence using a World Health Organization (WHO)-recommended questionnaire has not been done in all teaching hospitals of Peshawar District.This study assessed the adherence to HWM 2005 rules by tertiary care teaching hospitals of Peshawar District with respect to HWM personnel, policy and practices.Pretested structured questionnaires based on WHO recommendations were used to survey all teaching hospitals of Peshawar District from January to March 2015. Data were also collected on HWM infrastructure and processes from 1 randomly selected medical, surgical, paediatric, and obstetrics/gynaecology unit in each hospital. Besides descriptive statistics, public and private hospitals were compared using Fisher's exact and Wilcoxon rank-sum tests.Most surveyed hospitals lacked formal HWM plans (70%), written procedures (80%), related job descriptions (80%) or records (90%). Many hospitals neither had trained HWM supervisors (56%) nor did they organize formal HWM trainings for new staff (40%). None of the hospitals followed waste segregation and colour coding. When compared to national HWM 2005 rules, multiple gaps in appropriate transportation, storage and disposal were found with no statistically significant difference between public and private hospitals.Serious gaps in adherence to HWM 2005 rules exist in surveyed hospitals. With recent devolution of environmental function, the Government of Khyber Pakhtunkhwa should enact provincial HWM rules (and ensure their implementation) to facilitate effective HWM practice across provincial healthcare facilities.ممارسات وتنفيذ القواعد الوطنية لإدارة نفاقات المستشفيات لعام 2005 في باكستان.محمد فضل ذيشان، أحمد العباد، عبد العزيز، افتاب سبحاني، آصف شاه، طاهر خان، هداية الله، عمير قاضي.صدرت قواعد إدارة نفايات المستشفيات في باكستان في عام 2005. وعلى الرغم من مرور عقد على سن هذه القواعد، ظل الامتثال لها يفتقر إلى الاتساق، ولم يُر أي تقييم منهجي للامتثال باستخدام استبيان موصى به من منظمة الصحة العالمية في جميع المستشفيات التعليمية في منطقة بيشاور.عمدت هذه الدراسة إلى تقييم الامتثال لقواعد إدارة نفايات المستشفيات لعام 2005 في مستشفيات الرعاية الثلاثية التعليمية في منطقة بيشاور بالنسبة للمختصين بإدارة نفايات المستشفيات وسياساتها وممارساتها.استُخدمت استبيانات منظمّة ومجرّبة سلفاً استناداً إلى توصيات منظمة الصحة العالمية لمسح جميع المستشفيات التعليمية في منطقة بيشاور في الفترة من يناير إلى مارس 2015. وجمعت بيانات أيضا بشأن البنية التحتية لإدارة نفايات المستشفيات وعملياتها من وحدة واحدة من كل من أقسام الباطنة، الجراحة، طب الأطفال، النساء والولادة اختيرت عشوائياً في كل مستشفى. وبالإضافة إلى الإحصاءات الوصفية، أجريت مقارنة بين مستشفيات عامة وخاصة باستخدام اختبار فيشر الدقيق واختبار ويلكوكسون لحساب مجموع الرتب.افتقرت معظم المستشفيات الخاضعة للاستقصاء لأي خطط رسمية لإدارة نفايات المستشفيات (70 %) أو إجراءات مكتوبة (80 %) أو توصيف للوظائف ذات الصلة (80 %) أو سجلات (90 %). ولم يقدم كثير من المستشفيات أي تدريب للمشرفين (56 %) ولا تنظيم دورات تدريبية رسمية بشأن إدارة نفايات المستشفيات للموظفين الجدد (40 %). ولم تلتزم أي من المستشفيات بفصل النفايات والترميز اللوني. وعند مقارنة هذه القواعد بالقواعد الوطنية لإدارة نفايات المستشفيات لعام 2005 ، ظهرت عدة فجوات تتصل بالنقل والتخزين والتخلص الملائم مع عدم ظهور أي فرق ذي دلالة إحصائية بين المستشفيات العامة والخاصة.توجد فجوات خطيرة في الامتثال لقواعد إدارة نفايات المستشفيات لعام 2005 في المستشفيات الخاضعة للمسح. وبعد إلغاء الوظيفة البيئية مؤخراً، ينبغي لحكومة خيبر باختونخوا سن قواعد لإدارة نفايات المستشفيات على مستوى المقاطعات (وكفالة تنفيذها) لتيسير ممارسة إدارة نفايات المستشفيات بفعالية في جميع مرافق الرعاية الصحية على مستوى المقاطعات.Pratiques et application des réglementations nationales en matière de gestion des déchets hospitaliers 2005 : étude de cas au Pakistan.Les réglementations en matière de gestion des déchets hospitaliers au Pakistan ont été publiées en 2005. Dix ans après leur adoption, l’observation des réglementations de 2005 en matière de gestion des déchets hospitaliers demeure incohérente, et une évaluation systématique de la conformité à l’aide d’un questionnaire recommandé par l'Organistation mondiale de la Santé (OMS) n’a pas été effectuée dans tous les hôpitaux universitaires du district de Peshawar (Khyber Pakhtunkhwa).La présente étude a évalué l’observation des réglementations de 2005 en matière de gestion des déchets hospitaliers par les hôpitaux universitaires de soins tertiaires dans le district de Peshawar eu égard au personnel, aux politiques et aux pratiques de gestion des déchets hospitaliers.Des questionnaires structurés prétestés reposant sur les recommandations de l’OMS ont été utilisés pour enquêter dans tous les hôpitaux universitaires du district de Peshawar entre janvier et mars 2015. Des données ont également été recueillies sur les infrastructures et les processus de gestion des déchets hospitaliers auprès de départements de médecine, de chirurgie, de pédiatrie, de gynécologie/d’obstétrique sélectionnés de façon aléatoire dans chaque hôpital. Outre les statistiques descriptives, les hôpitaux publics et privés ont été comparés à l’aide du test exact de Fisher et du test des rangs signés de Wilcoxon.La plupart des hôpitaux enquêtés n'avaient pas de plans officiels (70 %), de procédures écrites (80 %), de descriptifs de postes associés (80 %) ou de dossiers (90 %) pour la gestion des déchets hospitaliers. De nombreux hôpitaux n’avaient pas formé de responsables en gestion des déchets hospitaliers (56 %), ou organisé de formations officielles dans le domaine pour les nouveaux membres du personnel (40 %). Aucun des hôpitaux ne procédait à un tri des déchets ou n’appliquait le code couleurs. Eu égard aux réglementations nationales en matière de gestion des déchets hospitaliers, des lacunes multiples en matière de transports, d’entreposage et d’élimination appropriés ont été révélées, sans différences significatives entre les hôpitaux publics et privés.Il existe de sérieuses lacunes concernant le respect des réglementations de 2005 en matière de gestion des déchets hospitaliers dans les hôpitaux ayant fait l’objet de l’enquête. Au vu de la décentralisation récente de la gestion environnementale, le gouvernement de Khyber Pakhtunkhwa devrait adopter des réglementations en matière de gestion des déchets hospitaliers à l’échelle de la province (et garantir leur application) afin de faciliter la mise en place de pratiques efficaces de gestion des déchets hospitaliers au sein des établissements de soins de santé dans la province.

Decrease in crop yield and degradation in product quality due to plant diseases such as rust and blast in pearl millet is the cause of concern for farmers and the agriculture industry. The stipulation of expert advice for disease identification is also a challenge for the farmers. The traditional techniques adopted for plant disease detection require more human intervention, are unhandy for farmers, and have a high cost of deployment, operation, and maintenance. Therefore, there is a requirement for automating plant disease detection and classification. Deep learning and IoT-based solutions are proposed in the literature for plant disease detection and classification. However, there is a huge scope to develop low-cost systems by integrating these techniques for data collection, feature visualization, and disease detection. This research aims to develop the ‘Automatic and Intelligent Data Collector and Classifier’ framework by integrating IoT and deep learning. The framework automatically collects the imagery and parametric data from the pearl millet farmland at ICAR, Mysore, India. It automatically sends the collected data to the cloud server and the Raspberry Pi. The ‘Custom-Net’ model designed as a part of this research is deployed on the cloud server. It collaborates with the Raspberry Pi to precisely predict the blast and rust diseases in pearl millet. Moreover, the Grad-CAM is employed to visualize the features extracted by the ‘Custom-Net’. Furthermore, the impact of transfer learning on the ‘Custom-Net’ and state-of-the-art models viz. Inception ResNet-V2, Inception-V3, ResNet-50, VGG-16, and VGG-19 is shown in this manuscript. Based on the experimental results, and features visualization by Grad-CAM, it is observed that the ‘Custom-Net’ extracts the relevant features and the transfer learning improves the extraction of relevant features. Additionally, the ‘Custom-Net’ model reports a classification accuracy of 98.78% that is equivalent to state-of-the-art models viz. Inception ResNet-V2, Inception-V3, ResNet-50, VGG-16, and VGG-19. Although the classification of ‘Custom-Net’ is comparable to state-of-the-art models, it is effective in reducing the training time by 86.67%. It makes the model more suitable for automating disease detection. This proves that the proposed model is effective in providing a low-cost and handy tool for farmers to improve crop yield and product quality.

Objective As supermarkets continue to expand their healthcare categories, consumers now have more choice and access to non-prescription medicines. The aim of this current research is to empirically examine the drivers and barriers of consumer purchase intentions, namely trust and perceived risk, of non-prescription medicines in both supermarkets and community pharmacy settings. Method Data were collected using an in-store intercept survey of 402 supermarket shoppers and 310 community pharmacy shoppers. Confirmatory factor analysis including a measurement and structural model tests were employed using AMOS software package to identify variances in the drivers and barriers of purchase intentions between these retail settings. Key findings This study found an association between the purchase intention of non-prescription medicines in community pharmacies with their perceived competence, benevolence and provision accurate information. Other than time risk, no other elements of risk were associated with purchase intentions within this setting. In contrast, the perceived risks associated with the purchase of non-prescription medicines within the supermarkets setting – specifically physical and social risk, were present. Results indicate respondents were more likely to intend to purchase medicines from a supermarket if they perceived that the retailer was competent in providing access to safe non-prescription medicines and had the ability to handle transactions. Conclusions This is the first study to examine the psychological drivers and barriers of purchase intentions of non-prescription medicines in supermarkets and community pharmacies, finding very different results across both retail settings. The study presents a comprehensive model of purchase intentions of non-prescription medicines and recommends directions for pharmacy practitioners and supermarkets.

To investigate personality disorders in medical students appearing for medical school entrance exam.The cross-sectional study was conducted at Peshawar Medical College from August 2015 to May 2016, and comprised all the students who undertook medical school entrance examination of the College. They were asked to fill screening questionnaire of international personality disorder examination, based on International Classification of Disease version-10. Demographic information was collected from the application form. After screening of all the medical students during the entrance exam, detailed interview was taken from the students who were invited for admission interview. The data was analyzed using SPSS 20.There were 1334 subjects with a mean age of 18.91.41 years. Of the total, 745(55.8%) were male students. The most common personality traits were anankastic 1170(88%), schizoid 932(70%) and dependent 705(53%). Of the total, 322(24%) students were called for interview. The mean age of the interview sample was 18.91.03 years and 189 (58.7%) of them were females. Definite personality disorders in order of frequency were dependent 3(0.93%), schizoid 2(0.62%) and anankastic 1(0.31%). There was a significant correlation of female gender with histrionics, anxious, dependent and borderline personality disorder (p0.05). There was a significant correlation between academic performance and dissocial, impulsive and borderline personality disorder separately (p0.05).Anankastic, schizoid and dependent personality traits and disorders were the commonest on screening and detailed interview.

OBJECTIVES To assess the surgical informed consent (SIC) practices for obstetric and gynaecological (OB-GYN) procedures at different hospitals in Pakistan. METHODS Study was conducted in five hospitals (three public and two private) of Peshawar, Pakistan. A pretested structured tablet-based questionnaire was administered from October 2016 through January 2017 among post-op OB-GYN patients. RESULTS About 27% of the patients (significantly more in private hospitals, P = 0.001) did not remember a formal consent administration. Most patients (80%) felt they had no choice about signing the consent. About 65% (mostly in public as compared with private hospitals) mentioned that they would have signed it regardless of the specifics in it (P

Current technology provides an efficient way of monitoring the personal health of individuals. Bluetooth Low Energy (BLE)-based sensors can be considered as a solution for monitoring personal vital signs data. In this study, we propose a personalized healthcare monitoring system by utilizing a BLE-based sensor device, real-time data processing, and machine learning-based algorithms to help diabetic patients to better self-manage their chronic condition. BLEs were used to gather users&rsquo, vital signs data such as blood pressure, heart rate, weight, and blood glucose (BG) from sensor nodes to smartphones, while real-time data processing was utilized to manage the large amount of continuously generated sensor data. The proposed real-time data processing utilized Apache Kafka as a streaming platform and MongoDB to store the sensor data from the patient. The results show that commercial versions of the BLE-based sensors and the proposed real-time data processing are sufficiently efficient to monitor the vital signs data of diabetic patients. Furthermore, machine learning&ndash, based classification methods were tested on a diabetes dataset and showed that a Multilayer Perceptron can provide early prediction of diabetes given the user&rsquo, s sensor data as input. The results also reveal that Long Short-Term Memory can accurately predict the future BG level based on the current sensor data. In addition, the proposed diabetes classification and BG prediction could be combined with personalized diet and physical activity suggestions in order to improve the health quality of patients and to avoid critical conditions in the future.

The importance of childhood immunization in prevention of highly fatal diseases and disability cannot be overemphasized. Pakistan has a national Expanded Program on Immunization but the compliance is far below the international benchmark for achieving a herd immunity. Monitoring the compliance to timely receipt of vaccinations is crucial to establishing and preventing disease and disability associated risk in children. There is little or no evidence that reports the timeliness of the vaccinations according to the EPI schedule in Peshawar. The primary objective of the study was to evaluate rate of Fully Immunized Children and to report compliance to the timeliness of vaccine specific schedule during the study period in the EPI center in the capital city of Peshawar, Khyber Pakhtunkhwa province of Pakistan. We collected consecutive retrospective data of the infants enrolled from June 2014 to December 2015 in one EPI center for our study. Out of the total 157 (n) children, fully immunized children (FIC) were 62 (39.5%) and only 19 (12.1%) were FIC with timely visits. Dropouts increased with successive vaccinations with highest for Measles 1 (42%). On-time vaccinations decreased over time, while the proportion of children receiving vaccination outside the ideal window period reaches as high as 46%. The study reports a low compliance to EPI schedule, and also highlights that immunization coverage is not a good indicator of age appropriate vaccinations.

Context Method mix-the percentage distribution of contraceptive users in a given country, by method-is one measure that reflects the availability of a range of contraceptive methods. A skewed method mix-one in which 50% or more of contraceptive users rely on a single method-could be cause for concern as a sign of insufficiency of alternative methods or provider bias. Shifts in method mix are important to individual countries, donors and scholars studying contraceptive dynamics. Methods To determine current patterns and recent changes in method mix, we examined 109 low- and middle-income countries. A variety of statistical methods were used to test four factors as correlates of skewed method mix: geographic region, family planning program effort index, modern contraceptive prevalence rate and human development index. An assessment of changes in reliance on female and male sterilization, the IUD, the implant and the injectable was conducted for countries with available data. Results Of the 109 countries included in this analysis, 30% had a skewed method mix-a modest decrease from 35% in a 2006 analysis. Only geographic region showed any correlation with method skew, but it was only marginally significant. The proportion of users relying on female sterilization, male sterilization or the IUD decreased in far more countries than it increased; the pattern was reversed for the injectable. Conclusion Method mix skew is not a definitive indicator of lack of contraceptive choice or provider bias; it may instead reflect cultural preferences. In countries with a skewed method mix, investigation is warranted to identify the cause.

Appalachian residents have a higher overall cancer burden than the rest of the United States because of the unique features of the region. Treatment delays vary widely within Appalachia, with colorectal cancer patients undergoing median treatment delays of 5 days in Kentucky compared to 9 days for patients in Pennsylvania, Ohio, and North Carolina combined.This study identified the source of this disparity in treatment delay using statistical decomposition techniques.This study used linked 2006 to 2008 cancer registry and Medicare claims data for the Appalachian counties of Kentucky, Pennsylvania, Ohio, and North Carolina to estimate a 2-part model of treatment delay. An Oaxaca Decomposition of the 2-part model revealed the contribution of the individual determinants to the disparity in delay between Kentucky counties and the remaining 3 states.The Oaxaca Decomposition revealed that the higher percentage of patients treated at for-profit facilities in Kentucky proved the key contributor to the observed disparity. In Kentucky, 22.3% patients began their treatment at a for-profit facility compared to 1.4% in the remaining states. Patients initiating treatment at for-profit facilities explained 79% of the observed difference in immediate treatment (2 days after diagnosis) and 72% of Kentucky's advantage in log days to treatment.The unique role of for-profit facilities led to reduced treatment delay for colorectal cancer patients in Kentucky. However, it remains unknown whether for-profit hospitals' more rapid treatment converts to better health outcomes for colorectal cancer patients.