Mobile-UI-Repair: a deep learning based UI smell detection technique for mobile user interface.

The graphical user interface (GUI) in mobile applications plays a crucial role in connecting users with mobile applications. GUIs often receive many UI design smells, bugs, or feature enhancement requests. The design smells include text overlap, component occlusion, blur screens, null values, and missing images. It also provides for the behavior of mobile applications during their usage. Manual testing of mobile applications (app as short in the rest of the document) is essential to ensuring app quality, especially for identifying usability and accessibility that may be missed during automated testing. However, it is time-consuming and inefficient due to the need for testers to perform actions repeatedly and the possibility of missing some functionalities. Although several approaches have been proposed, they require significant performance improvement. In addition, the key challenges of these approaches are incorporating the design guidelines and rules necessary to follow during app development and combine the syntactical and semantic information available on the development forums. In this study, we proposed a UI bug identification and localization approach called Mobile-UI-Repair (M-UI-R). M-UI-R is capable of recognizing graphical user interfaces (GUIs) display issues and accurately identifying the specific location of the bug within the GUI. M-UI-R is trained and tested on the history data and also validated on real-time data. The evaluation shows that the average precision is 87.7% and the average recall is 86.5% achieved in the detection of UI display issues. M-UI-R also achieved an average precision of 71.5% and an average recall of 70.7% in the localization of UI design smell. Moreover, a survey involving eight developers demonstrates that the proposed approach provides valuable support for enhancing the user interface of mobile applications. This aids developers in their efforts to fix bugs.

Cognitive therapy for depression in tuberculosis treatment: protocol for multicentre pragmatic parallel arm randomised control trial with an internal pilot.

INTRODUCTION AND OBJECTIVES: There is an unmet need to develop high-quality evidence addressing tuberculosis (TB)-related mental health comorbidity, particularly in the context of lower-middle-income countries. This study aims to examine the effectiveness and cost-effectiveness of cognitive behavioural therapy (CBT) versus enhanced treatment as usual (ETAU) in improving depressive symptoms in people with TB and comorbid depression, enhancing adherence with anti-TB treatment (ATT) and its implementation in the real-world setting of Pakistan. METHODS: We will conduct a pragmatic parallel arm randomised control trial with an internal pilot. A brief psychological intervention based on CBT has been developed using a combination of qualitative and ethnographic studies. The inbuilt pilot trial will have a sample size of 80, while we plan to recruit 560 (280 per arm) participants in the definitive trial. Participants who started on ATT within 1 month of diagnosis for pulmonary and extrapulmonary TB or multidrug resistant TB (MDR-TB) and meeting the criteria for depression on Patient Health Questionnaire-9 (PHQ-9) will be randomised with 1:1 allocation to receive six sessions of CBT (delivered by TB healthcare workers) or ETAU. Data on the feasibility outcomes of the pilot will be considered to proceed with the definitive trial. Participants will be assessed (by a blinded assessor) for the following main trial primary outcomes: (1) severity of depression using PHQ-9 scale (interviewer-administered questionnaire) at baseline, weeks 8, 24 and 32 postrandomisation and (2) ATT at baseline and week 24 at the end of ATT therapy. ETHICS AND DISSEMINATION: Ethical approval has been obtained from Keele University Research Ethics Committee (ref: 2023-0599-792), Khyber Medical University Ethical Review Board (ref: DIR/KMU-EB/CT/000990) and National Bioethics Committee Pakistan (ref: No.4-87/NBC-998/23/587). The results of this study will be reported in peer-reviewed journals and academic conferences and disseminated to stakeholders and policymakers. TRIAL REGISTRATION NUMBER: ISRCTN10761003.

Role of the afferent lymph as an immunological conduit to analyze tissue antigenic and inflammatory load.

The lymphatic fluid is the conduit by which part of the tissue "omics" is transported to the draining lymph node for immunosurveillance. Following cannulation of the pre-nodal cervical and mesenteric afferent lymphatics, herein we investigate the lymph proteomic composition, uncovering that its composition varies according to the tissue of origin. Tissue specificity is also reflected in the dendritic cell-major histocompatibility complex class II-eluted immunopeptidome harvested from the cervical and mesenteric nodes. Following inflammatory disruption of the gut barrier, the lymph antigenic and inflammatory loads are analyzed in both mice and subjects with inflammatory bowel diseases. Gastrointestinal tissue damage reflects the lymph inflammatory and damage-associated molecular pattern signatures, microbiome-derived by-products, and immunomodulatory molecules, including metabolites of the gut-brain axis, mapped in the afferent mesenteric lymph. Our data point to the relevance of the lymphatic fluid to probe the tissue-specific antigenic and inflammatory load transported to the draining lymph node for immunosurveillance.

Process evaluation of a pragmatic feasibility trial on smokeless tobacco cessation intervention delivered in dental hospitals.

BACKGROUND: Article 14 of the WHO 'Framework Convention on Tobacco Control' recommends, that all oral healthcare providers provide support for tobacco cessation, to all patients. Despite evidence on the effectiveness of tobacco cessation interventions in dental settings, implementation remains low in most high-burden countries like Pakistan. A pragmatic pilot trial of a dentist-delivered behavioural support intervention for smokeless tobacco (ST) cessation, was conducted in dental hospitals in Pakistan. This paper presents the findings of the process evaluation of the trial. METHODS: A mixed-method process evaluation of a multi-centre randomised control pilot trial of dentist-delivered behavioural support intervention ST cessation was conducted. The intervention included three sessions namely: pre-quit, quit and post-quit sessions. The process evaluation involved: semi-structured interviews with trial participants (n = 26, of which dental patients were n = 13 and participating dentists were n = 13 conducted from June-August 2022); and fidelity assessment of audio recordings of the intervention sessions (n = 29). The framework approach was used to thematically analyse the interview data. RESULTS: Overall the trial procedures were well accepted, however, young patients expressed uneasiness over revealing their ST use status. The intervention was received positively by dentists and patients. Dentists identified some challenges in delivering behavioural support to their patients. Of these, some were related to the contents of the intervention whereas, others were related to the logistics of delivering the intervention in a clinical setting (such as workload and space). Acceptability of the intervention resources was overall low amongst young patients as they did not take the intervention resources home due to fear of their family members finding out about their ST use. The intervention was successful in achieving the intended impact (in those who engaged with the intervention), i.e., change in the patients' ST use behaviour. Giving up ST with the aid of behavioural support also had an unintended negative effect i.e., the use of harmful substances (cannabis, cigarettes) to give up ST use. Patients' satisfaction with their dental treatment seemed to influence the intervention outcome. CONCLUSION: While there are many variables to consider, but for the participants of this study, behavioural support for abstinence delivered through dentists during routine dental care, appears to be an acceptable and practical approach in helping patients give up ST use, in a country like Pakistan, where negligible support is offered to ST users.

Hinman Syndrome: A Rare Entity With Neurogenic Bladder-Like Symptoms.

Hinman syndrome, as is the case with many other rare conditions, is a disease very commonly under-considered or missed in the diagnosis of patients with the presenting symptoms. Clinical and radiographic manifestations of the condition are easily confused with neurogenic bladder without proper history collection and neurological examination. Patients typically present with symptoms including enuresis, urinary retention, reoccurring urinary tract infections, and encopresis. Imaging often shows hydroureteronephrosis and marked bladder wall thickening. While these signs are characteristic of neurogenic bladder, routine neurologic examinations and MRIs of patients with Hinman syndrome often show normal results, and their condition is currently thought to be an acquired behavioral and psychological disorder, often associated with abnormal family dynamics. We present the case of a 14-year-old boy, who presented to the emergency department with nausea, bilateral flank pain, and urinary retention. The patient had an over seven-year history of recurrent urinary tract infections (UTI) and intermittent encopresis and followed up with different providers. Due to the patient's extensive history and the failure of previous treatments, he was evaluated for causes of neurogenic bladder, but the MRI of the lumbar spine was normal. Fluoroscopic voiding cystourethrogram (VCUG) was ordered and demonstrated abnormal and trabeculated contour of the urinary bladder with bilateral vesicoureteral reflux consistent with the diagnosis of Hinman syndrome.

The Lifetime Health and Economic Burden of Smokeless Tobacco use in Bangladesh, India, and Pakistan: Results From ASTRAMOD.

INTRODUCTION: Under the current policy landscapes, the lifetime health and economic burden of smokeless tobacco (ST) products, consumed by over 297 million ST users in South Asia, is unknown. The aim of this study was to estimate the lifetime health effects and costs attributable to current and future ST use in Bangladesh, India, and Pakistan where the majority of ST users live. AIMS AND METHODS: We developed a Markov-based state-transition model (ASTRAMOD) to predict the lifetime costs of treatment of four diseases (oral, pharyngeal, esophageal cancers, and stroke) and disability-adjusted life years (DALYs), attributable to the current and future use of ST under existing ST policy scenario. Country-specific Global Adult Tobacco Surveys, life tables, and meta-analyses of South Asian and South East Asian studies were used to populate the model. A probabilistic sensitivity analysis evaluated the uncertainty in model predictions. RESULTS: If there were no change in the current ST policies, the lifetime ST-attributable treatment costs would be over US$19 billion in India, over US$1.5 billion in Bangladesh, and over US$3 billion in Pakistan. For all countries, the attributable costs are higher for younger cohorts with costs declining with increasing age for those over 50. The model predicted that a typical 15-year-old male adoloscent would gain 0.07-0.18 life years, avert 0.07-0.19 DALYs, and generate a cost-savings of US$7-21 on healthcare spending if ST policies were changed to eliminate ST use. CONCLUSIONS: Policy interventions aimed at decreasing the uptake of ST and increasing quitting success have the potential to substantially decrease the economic and health burden of ST. IMPLICATIONS: This study provides the most comprehensive estimates of the lifetime health and economic burden of ST by 5-year age and sex cohorts. This is also the first study that highlights the scale of health and economic burden of ST in Bangladesh, India, and Pakistan if there were no changes in the current ST policies. Policymakers and practitioners can use the reported data to justify their decisions to improve current ST policies and practices in their country. Researchers can use the ASTRAMOD methodology to estimate the impact of future ST policy changes.

Multifaceted manifestations: A case report of MRSA pneumonia with sepsis, pyelonephritis, and ileus muscle abscess.

Methicillin-resistant staph aureus (MRSA) infections are challenging to treat, and with the emergence of community-associated MRSA (CA-MRSA) strains, early consideration of this pathogen in populations without typical risk factors is critical. Here we present a case of CA-MRSA pneumonia that resulted in Community-acquired pneumonia (CAP) with septic shock, pyelonephritis, and muscle abscess.

A systematic investigation of tobacco industry sourced data relating to illicit tobacco trade featured in Pakistan's media coverage (2015-2020).

INTRODUCTION: Previous evidence suggests the tobacco industry uses media to disseminate misleading narratives relating to illicit tobacco trade (ITT) as part of efforts to influence policy outcomes. Such evidence is largely High-Income Countries (HIC) focussed, resulting in a literature gap for Low- and Middle-Income Countries (LMICs). Pakistan and its annual budget cycle is used as a case study for addressing this gap. METHODS: Electronic English-language articles from newspapers in Pakistan (328) were sourced from LexisNexis and a sub-sample of Urdu-language electronic articles (12) were identified through internet searches.The articles were published between 2015- 2020and included claims/estimates relating to ITT, which were coded to identify cited data sources. Changes in media coverage before and after Pakistan's annual budget announcements were explored via Wilcoxon signed rank and Poisson regression tests. RESULTS: Of the 357 claims/estimates analysed, 66 (20%) were industry funded. The most prevalent sources were national government bodies (36.6%) and tobacco companies or their representatives (15.1%). Wilcoxon signed-rank and Poisson regression tests on the frequency of English-language articles both created a p-value of < 0.05 for the frequency of relevant articles between the months of April and May, compared to the other months, indicating statistical significance. CONCLUSIONS: There was a statistically significant increase in the number of English-language articles featuring claims/estimates relating to Pakistan's ITT in the months leading up to the annual budget each year. The government should consider measures to improve transparency standards within media coverage and promote factcheck journalism to safeguard against industry tactics to manipulate public discourses. IMPLICATIONS: This paper is, to our knowledge, the largest exploration of the use of data sourced from the tobacco industry within a country's media that has been undertaken to date, utilising a team of seven coders across the UK and Pakistan. Our findings reveal weaknesses within media coverage of ITT in Pakistan, both in English and Urdu language publications. We encourage the government to consider new standards to enhance transparency and promote factcheck journalism within media coverage in the country.

Emotion detection from handwriting and drawing samples using an attention-based transformer model.

Emotion detection (ED) involves the identification and understanding of an individual's emotional state through various cues such as facial expressions, voice tones, physiological changes, and behavioral patterns. In this context, behavioral analysis is employed to observe actions and behaviors for emotional interpretation. This work specifically employs behavioral metrics like drawing and handwriting to determine a person's emotional state, recognizing these actions as physical functions integrating motor and cognitive processes. The study proposes an attention-based transformer model as an innovative approach to identify emotions from handwriting and drawing samples, thereby advancing the capabilities of ED into the domains of fine motor skills and artistic expression. The initial data obtained provides a set of points that correspond to the handwriting or drawing strokes. Each stroke point is subsequently delivered to the attention-based transformer model, which embeds it into a high-dimensional vector space. The model builds a prediction about the emotional state of the person who generated the sample by integrating the most important components and patterns in the input sequence using self-attentional processes. The proposed approach possesses a distinct advantage in its enhanced capacity to capture long-range correlations compared to conventional recurrent neural networks (RNN). This characteristic makes it particularly well-suited for the precise identification of emotions from samples of handwriting and drawings, signifying a notable advancement in the field of emotion detection. The proposed method produced cutting-edge outcomes of 92.64% on the benchmark dataset known as EMOTHAW (Emotion Recognition via Handwriting and Drawing).

Renal Infarction as the First Manifestation of Undiagnosed Atrial Fibrillation With Coexisting Left Atrial Thrombus: A Case Report and Review of the Literature.

Acute renal infarction, presenting with nonspecific symptoms, such as abdominal pain, nausea, vomiting, and hematuria, can lead to delayed diagnosis due to similarities with other medical conditions. Computed tomography with IV contrast is used to diagnose renal parenchymal infarction, treated through surgical, percutaneous interventions, and anticoagulation therapy. Investigation for the infarction source is crucial, particularly in the absence of prior cardiac issues, necessitating heart rhythm monitoring and an echocardiogram to evaluate paroxysmal atrial fibrillation (PAF) and intracardiac thrombus, respectively. Renal infarction may elevate blood pressure due to renin release, recommending medications like angiotensin-converting enzyme inhibitors/angiotensin receptor blockers. We present a case of renal infarction due to PAF with a concomitant intracardiac thrombus.

Right-to-Left Intra-cardiac Shunt in a COVID-19 Patient Leading to Stroke and Poor Prognosis: A Case Report and Review of the Literature.

Coronavirus disease 2019 (COVID-19) often presents with a wide range of complications, including respiratory distress, acute respiratory distress syndrome (ARDS), and hypercoagulable states with resultant cerebrovascular incidents. Intra- and extra-pulmonological shunts can further complicate patient courses, leading to persistent hypoxemia and paradoxical emboli, resulting in potentially life-threatening consequences, necessitating a comprehensive, multidisciplinary approach to patient care. Here we present the case of a 73-year-old male who experienced severe persistent hypoxemic respiratory failure, superimposed methicillin-resistant Staphylococcus aureus (MRSA) pneumonia, and stroke with a previously undiagnosed patent foramen ovale (PFO) contributing to his clinical presentation.

Smokeless Tobacco Cessation Support in Dental Hospitals in Pakistan: Dentists and Dental Patients' Perspectives on Current Practices, Support Needed, and Opportunities Available.

INTRODUCTION: Despite evidence on the effectiveness of tobacco cessation interventions in dental settings, the implementation remains low, especially for smokeless tobacco (ST). The purpose of this study was to develop an understanding of the influences governing the implementation of ST cessation support in dental hospitals. AIMS AND METHODS: A multicenter qualitative study was conducted at two tertiary-care dental hospitals, in Pakistan. Semi-structured interview guide, guided by the Capability-Opportunity-Motivation-Behavior (COM-B) model, were used to capture the views of dentists (n = 12) and dental patients (n = 12), regarding ST cessation support in dental hospitals. Framework approach was used to thematically analyze the data. RESULTS: Screening of ST users in routine dental practice was seldom practiced and the cessation support offered was brief advice. Barriers identified by dentists included: Fear of offending and stereotyping patients; lack of knowledge and skills; lack of privacy; lack of belief in the effectiveness of behavioral support; lack of time and workload pressure; ST use amongst dentists; lack of referral systems and; the absence of a mandatory requirement of offering ST cessation support. Facilitators included: Delivering support through junior dentists and the length of interaction between the dentist and the patient. Naswar was the most common ST product used by dental patients. Patients reported receiving negligible cessation support from any healthcare provider. CONCLUSIONS: A range of influences governing the implementation of ST cessation support in dental hospitals were identified. These findings can inform the implementation of behavioral interventions for ST cessation in dental and other clinical settings, in low and middle-income countries. IMPLICATIONS: Smokeless tobacco control considerably lags, in comparison to the control of combustible tobacco. This is the first study that qualitatively explores the implementation of ST cessation support in dental settings in Pakistan. Utilizing the "Capability-Opportunity-Motivation-Behavior" model, it provides an in-depth understanding of the inability of dentists in implementing effective behavioral interventions for ST cessation support in routine dental practice. Highlighting the striking discrepancy between the patient's need for and receptivity towards cessation support and the dentists' concerns over their patients' receptivity towards cessation support, it calls for the need for effective implementation strategies to optimize dentist-led tobacco cessation interventions in low-resource settings.

Smoke veil prior regularized surgical field desmoking without paired in-vivo data.

Though deep learning-based surgical smoke removal methods have shown significant improvements in effectiveness and efficiency, the lack of paired smoke and smoke-free images in real surgical scenarios limits the performance of these methods. Therefore, methods that can achieve good generalization performance without paired in-vivo data are in high demand. In this work, we propose a smoke veil prior regularized two-stage smoke removal framework based on the physical model of smoke image formation. More precisely, in the first stage, we leverage a reconstruction loss, a consistency loss and a smoke veil prior-based regularization term to perform fully supervised training on a synthetic paired image dataset. Then a self-supervised training stage is deployed on the real smoke images, where only the consistency loss and the smoke veil prior-based loss are minimized. Experiments show that the proposed method outperforms the state-of-the-art ones on synthetic dataset. The average PSNR, SSIM and RMSE values are 21.99±2.34, 0.9001±0.0252 and 0.2151±0.0643, respectively. The qualitative visual inspection on real dataset further demonstrates the effectiveness of the proposed method.

Behaviour Change Intervention for Smokeless Tobacco (ST) Cessation Delivered through Dentists in Dental Settings: A pragmatic pilot trial.

INTRODUCTION: Evidence on smokeless tobacco (ST) cessation interventions is scarce. The South Asian (SA) region which shares more than 90% of the burden of ST use, is grossly underrepresented in research on ST cessation. This study aimed to assess the feasibility of delivering and investigating a behavioural support intervention for ST cessation in dental settings in Pakistan. METHODS: A multi-centre, pilot, 2-armed parallel group, individually randomised control trial, with a 1:1 allocation ratio, was conducted at two dental hospitals. Eligibility criteria included: being a ST user; seeking dental treatment and; not currently accessing cessation support. All participants were provided written self-help, ST cessation material. The intervention group also received a dentist-delivered, bespoke behavioural support intervention for ST cessation developed for users of SA origin. Participants were followed up telephonically at three and six months. Self-reported six month abstinence was verified by salivary cotinine. Analysis was descriptive, with 95% confidence intervals presented where appropriate. RESULTS: 100 participants were successfully recruited from the selected hospitals. Of these 78% continued to engage throughout the study duration and provided primary outcome data, whereas, 63% completed all hospital visits. The outcome measures were successfully collected. Biochemically verified six-month abstinence in the intervention and control group was 10% and 4%. CONCLUSIONS: It was feasible to deliver and evaluate a dentist-delivered behavioural support intervention for ST cessation in Pakistan. The data suggested that the intervention may improve ST quit rates. The findings of this study will be useful in informing the design of future definitive studies. IMPLICATIONS: To our knowledge this is the first pragmatic pilot trial on ST cessation in dental settings in Pakistan and the first trial on dentist-delivered structured behavioural support intervention for ST cessation. It adds to the scarce, trial evidence base on ST cessation interventions. Findings suggest behavioural support intervention for ST cessation may improve quit rates. The trial was conducted in a country with poor ST control measures, where ST products are not taxed, the products are sold openly to and by minors and the users are offered negligible cessation support. The findings may therefore be generalisable to LMICs and particularly South Asian countries, with similar policy backgrounds.

A dilemma of patients: poor quality administration of tertiary care hospitals: a cross-sectional study.

Introduction: The study focuses on healthcare delivery standards in Pakistan's tertiary care hospitals. Poor accountability and a lack of financial and human resources are the main contributing factors to a hospital's substandard performance and low patient satisfaction rates. Feedback surveillance forms are the Achilles tendon in the quality improvement of a facility, and this practice is, unfortunately, not widely practiced in the hospitals of Pakistan. Through this paper and experience, the authors hope to shed light on the need for regular feedback surveys and implementing their results to improve healthcare quality. Settings and Design: A prospective, observational study of seven tertiary care hospitals in Pakistan. Materials and Methods: The data was collected using a survey form. Each survey form was filled out by a team comprising three public health professionals who observed the hospital and its functioning without interfering with its workings. The questionnaire was developed with the help of Tools for Assessing the Operationality of District Health Systems: Health Facility Questionnaire designated in the respective facilities. The analysis was then draughted as a qualitative narrative review. Finally, the review was broken down into an assessment of the hospital's outpatient clinic setting, inpatient department, emergency department and other departments. Results: The survey was conducted at seven public sector hospitals in three major cities of Pakistan. The survey focused on administrative and nonmedical parameters of healthcare facilities. Overall, the hospitals of Lahore and Islamabad lacked mass casualty apparatus and cleanliness, and staff behaviour can be improved. The hospitals in Rawalpindi have mass casualty apparatuses in place. However, they need improvement in accessibility services and hygiene and staff attitude. Conclusions: The survey showed that all the hospitals had good access and accessibility, and the directions were clearly marked for the visitors. The hospital staff is knowledgeable about the hospital, but their behaviour needs to be improved. Also, the quality of the cleanliness and waiting areas is fair but needs improvements. Finally, regular cheques via regular feedback and quality assessments can improve healthcare delivery.

Delayed Metastatic Cholangiocarcinoma to the Stomach With Imaging Characteristics Resembling Gastrointestinal Stromal Tumor: A Case Report and Review of the Literature.

Intrahepatic cholangiocarcinoma (ICC) is a relatively rare subtype of cholangiocarcinoma, and there has been an increasing incidence of ICC in Western countries in recent years. Surgical resection is the most effective treatment for ICC. However, overall outcomes are extremely poor given that most patients are diagnosed at an advanced stage, and postoperative ICC recurrence is still very high despite hepatic resection. We report a case of metastatic ICC to the stomach presenting after resection of the original tumor, with imaging characteristics highly resembling gastrointestinal stromal tumor (GIST) on imaging. Reported cases of metastatic ICC to the liver are sparse. Given that there is a significant difference in the survival rate between metastatic cholangiocarcinoma and other tumors arising from the gastrointestinal tract, including GISTs, it is important to delineate the differences via imaging features. We further discuss the imaging characteristics of intrahepatic ICC, comparing and contrasting it to other gastric tumors.

The global impact of tobacco control policies on smokeless tobacco use: a systematic review.

BACKGROUND: Smokeless tobacco, used by more than 300 million people globally, results in substantial morbidity and mortality. For smokeless tobacco control, many countries have adopted policies beyond the WHO Framework Convention on Tobacco Control, which has been instrumental in reducing smoking prevalence. The impact of these policies (within and outside the Framework Convention on Tobacco Control) on smokeless tobacco use remains unclear. We aimed to systematically review policies that are relevant to smokeless tobacco and its context and investigate their impact on smokeless tobacco use. METHODS: In this systematic review, we searched 11 electronic databases and grey literature between Jan 1, 2005, and Sept 20, 2021, in English and key south Asian languages, to summarise smokeless tobacco policies and their impact. Inclusion criteria were all types of studies on smokeless tobacco users that mentioned any smokeless tobacco relevant policies since 2005, except systematic reviews. Policies issued by organisations or private institutions were excluded as well as studies on e-cigarettes and Electronic Nicotine Delivery System except where harm reduction or switching were evaluated as a tobacco cessation strategy. Two reviewers independently screened articles, and data were extracted after standardisation. Quality of studies was appraised using the Effective Public Health Practice Project's Quality Assessment Tool. Outcomes for impact assessment included smokeless tobacco prevalence, uptake, cessation, and health effects. Due to substantial heterogeneity in the descriptions of policies and outcomes, data were descriptively and narratively synthesised. This systematic review was registered in PROSPERO (CRD42020191946). FINDINGS: 14 317 records were identified, of which 252 eligible studies were included as describing smokeless tobacco policies. 57 countries had policies targeting smokeless tobacco, of which 17 had policies outside the Framework Convention on Tobacco Control for smokeless tobacco (eg, spitting bans). 18 studies evaluated the impact, which were of variable quality (six strong, seven moderate, and five weak) and reported mainly on prevalence of smokeless tobacco use. The body of work evaluating policy initiatives based on the Framework Convention on Tobacco Control found that these initiatives were associated with reductions in smokeless tobacco prevalence of between 4·4% and 30·3% for taxation and 22·2% and 70·9% for multifaceted policies. Two studies evaluating the non-Framework policy of sales bans reported significant reductions in smokeless tobacco sale (6·4%) and use (combined sex 17·6%); one study, however, reported an increased trend in smokeless tobacco use in the youth after a total sales ban, likely due to cross-border smuggling. The one study reporting on cessation found a 13·3% increase in quit attempts in individuals exposed (47·5%) to Framework Convention on Tobacco Control policy: education, communication, training, and public awareness, compared with non-exposed (34·2%). INTERPRETATION: Many countries have implemented smokeless tobacco control policies, including those that extend beyond the Framework Convention on Tobacco Control. The available evidence suggests that taxation and multifaceted policy initiatives are associated with meaningful reductions in smokeless tobacco use. FUNDING: UK National Institute for Health Research.

A neural network based framework for effective laparoscopic video quality assessment.

Video quality assessment is a challenging problem having a critical significance in the context of medical imaging. For instance, in laparoscopic surgery, the acquired video data suffers from different kinds of distortion that not only hinder surgery performance but also affect the execution of subsequent tasks in surgical navigation and robotic surgeries. For this reason, we propose in this paper neural network-based approaches for distortion classification as well as quality prediction. More precisely, a Residual Network (ResNet) based approach is firstly developed for simultaneous ranking and classification task. Then, this architecture is extended to make it appropriate for the quality prediction task by using an additional Fully Connected Neural Network (FCNN). To train the overall architecture (ResNet and FCNN models), transfer learning and end-to-end learning approaches are investigated. Experimental results, carried out on a new laparoscopic video quality database, have shown the efficiency of the proposed methods compared to recent conventional and deep learning based approaches.

Non-compliant packaging and illicit smokeless tobacco in Bangladesh, India and Pakistan: findings of a pack analysis.

INTRODUCTION: Illicit smokeless tobacco (ST) trade has seldom been documented despite ST use in at least 127 countries across the world. Based on non-compliance with packaging regulations, we report the proportion of illicit ST products from samples on sale in Bangladesh, India and Pakistan where 85% of global ST users reside. METHODS: We purchased unique ST products from tobacco sellers in two purposively selected administrative areas (division/district) in each of the three countries. The criteria to determine illicit ST products were based on country-specific legal requirements for ST packaging and labelling. These requirements included: 'market retail price disclosure', 'sale statement disclosure', 'pictorial health warning (PHW) pertinence', 'appropriate textual health warning' and 'using misleading descriptors (MDs)'. Non-compliance with even one of the legal requirements was considered to render the ST product illicit. RESULTS: Almost all ST products bought in Bangladesh and India were non-compliant with the local packaging requirements and hence potentially illicit, all products in Pakistan lacked desirable features. The most common feature missing was health warnings: 84% packs in Bangladesh, 93% in India, and 100% in Pakistan either did not have PHW or their sizes were too small. In Bangladesh, 61% packs carried MDs. In India and Pakistan, the proportions of such packs were 32% and 42%, respectively. CONCLUSIONS: Weak and poorly enforced ST control policies may be slowing the progress of tobacco control in South Asia. Standardised regulations are required for packaging and labelling ST. Improving compliance and reducing sale of cheap illicit products may require business licensing and market surveillance.