Detection and Visualisation of Pneumoconiosis Using an Ensemble of Multi-Dimensional Deep Features Learned from Chest X-rays.

Pneumoconiosis is a group of occupational lung diseases induced by mineral dust inhalation and subsequent lung tissue reactions. It can eventually cause irreparable lung damage, as well as gradual and permanent physical impairments. It has affected millions of workers in hazardous industries throughout the world, and it is a leading cause of occupational death. It is difficult to diagnose early pneumoconiosis because of the low sensitivity of chest radiographs, the wide variation in interpretation between and among readers, and the scarcity of B-readers, which all add to the difficulty in diagnosing these occupational illnesses. In recent years, deep machine learning algorithms have been extremely successful at classifying and localising abnormality of medical images. In this study, we proposed an ensemble learning approach to improve pneumoconiosis detection in chest X-rays (CXRs) using nine machine learning classifiers and multi-dimensional deep features extracted using CheXNet-121 architecture. There were eight evaluation metrics utilised for each high-level feature set of the associated cross-validation datasets in order to compare the ensemble performance and state-of-the-art techniques from the literature that used the same cross-validation datasets. It is observed that integrated ensemble learning exhibits promising results (92.68% accuracy, 85.66% Matthews correlation coefficient (MCC), and 0.9302 area under the precision-recall (PR) curve), compared to individual CheXNet-121 and other state-of-the-art techniques. Finally, Grad-CAM was used to visualise the learned behaviour of individual dense blocks within CheXNet-121 and their ensembles into three-color channels of CXRs. We compared the Grad-CAM-indicated ROI to the ground-truth ROI using the intersection of the union (IOU) and average-precision (AP) values for each classifier and their ensemble. Through the visualisation of the Grad-CAM within the blue channel, the average IOU passed more than 90% of the pneumoconiosis detection in chest radiographs.

Deep Ensemble Learning for the Automatic Detection of Pneumoconiosis in Coal Worker's Chest X-ray Radiography.

Globally, coal remains one of the natural resources that provide power to the world. Thousands of people are involved in coal collection, processing, and transportation. Particulate coal dust is produced during these processes, which can crush the lung structure of workers and cause pneumoconiosis. There is no automated system for detecting and monitoring diseases in coal miners, except for specialist radiologists. This paper proposes ensemble learning techniques for detecting pneumoconiosis disease in chest X-ray radiographs (CXRs) using multiple deep learning models. Three ensemble learning techniques (simple averaging, multi-weighted averaging, and majority voting (MVOT)) were proposed to investigate performances using randomised cross-folds and leave-one-out cross-validations datasets. Five statistical measurements were used to compare the outcomes of the three investigations on the proposed integrated approach with state-of-the-art approaches from the literature for the same dataset. In the second investigation, the statistical combination was marginally enhanced in the ensemble of multi-weighted averaging on a robust model, CheXNet. However, in the third investigation, the same model elevated accuracies from 87.80 to 90.2%. The investigated results helped us identify a robust deep learning model and ensemble framework that outperformed others, achieving an accuracy of 91.50% in the automated detection of pneumoconiosis.

Computer-Aided Diagnosis of Coal Workers' Pneumoconiosis in Chest X-ray Radiographs Using Machine Learning: A Systematic Literature Review.

Computer-aided diagnostic (CAD) systems can assist radiologists in detecting coal workers' pneumoconiosis (CWP) in their chest X-rays. Early diagnosis of the CWP can significantly improve workers' survival rate. The development of the CAD systems will reduce risk in the workplace and improve the quality of chest screening for CWP diseases. This systematic literature review (SLR) amis to categorise and summarise the feature extraction and detection approaches of computer-based analysis in CWP using chest X-ray radiographs (CXR). We conducted the SLR method through 11 databases that focus on science, engineering, medicine, health, and clinical studies. The proposed SLR identified and compared 40 articles from the last 5 decades, covering three main categories of computer-based CWP detection: classical handcrafted features-based image analysis, traditional machine learning, and deep learning-based methods. Limitations of this review and future improvement of the review are also discussed.

Disjunction, tension and dissonance within nursing pain care provision for the older hospitalized person: A focused ethnographic insight.

AIMS: This study presents an ethnographic insight into the older hospitalized persons' experiences on how nurses provide pain care provision. The older persons' perceptions of culturally mediated barriers and facilitators are presented. DESIGN: Focused ethnography. METHODS: Multi-site across eight acute care units within two tertiary referral hospitals on the east coast of Australia collected over a one-year period from 2014 to 2015. Semi-structured interviews (n = 12) of older persons (11 hr). Twenty-three (23) semi-structured interviews with nine (9) registered nurses (12 hr 38 min). Participant observation (1,041 hr) during day, night and evening shifts. RESULTS: The older person experienced disjunction within pain assessment by the reliance of nurses on objective measurement gained during functional task completion. Tension emerged during pain management when the older person was not included and/or options provided were not deemed effective. For some older persons this meant they undertook a decision to exclude their nurse from involvement in pain management. A thread woven throughout was a lack of communication, continuity of care and input from the older person. CONCLUSION: This study has implications for the provision of nursing care of the older hospitalized person. Dissonance within pain care provision for the older person occurs during episodes of missed pain care. Understanding and insight is gained into aspects of missed communication opportunities between nurses and the experiences of missed pain care of the older person.

Automated detection of pneumoconiosis with multilevel deep features learned from chest X-Ray radiographs.

Early detection of pneumoconiosis in X-Rays has been a challenging task that leads to high inter- and intra-reader variability. Motivated by the success of deep learning in general and medical image classification, this paper proposes an approach to automatically detect pneumoconiosis using a deep feature based binary classifier. The features are extracted from X-rays using deep transfer learning, comprising both low and high-level feature sets. For this, a CNN model pre-trained with a transfer learning from a CheXNet model was initially used to extract deep features from the X-Ray images, then the deep features were mapped to higher-dimensional feature spaces for classification using Support Vector Machine (SVM) and CNN based feature aggregation methods. In order to cross validate the proposed method, the training and testing images were randomly split into three folds before each experiment. Nine evaluation metrics were employed to compare the performance of the proposed method and state-of-the-art methods from the literature that used the same datasets. The experimental results show that the proposed framework outperformed others, achieving an accuracy of 92.68% in the automated detection of pneumoconiosis.

Use of artificial intelligence and virtual reality within clinical simulation for nursing pain education: A scoping review.

OBJECTIVES: To explore and map the evidence for virtual reality and artificial intelligence in simulation for the provision of pain education for pre and post registration nurses. DESIGN: A scoping review of published and unpublished research from 2009 to 2019. DATA SOURCES: Nine electronic databases and hand-searching of reference lists. REVIEW METHODS: Studies were included if virtual reality or artificial intelligence interventions were used for education on pain care provision in nursing. Data were extracted and charted using an extraction tool and themes were explored using narrative analysis. RESULTS: The review process resulted in the inclusion of four published studies. All studies used mixed methods and used artificial intelligence within clinical simulations as an intervention. No studies using virtual reality for pain education met the inclusion criteria. Participants of three studies were undergraduate nursing students in universities and participants in the fourth study were registered nurses within a hospital. Outcomes measured were user acceptance of the technology and feasibility in all studies. The context was hospital located and focused on acute pain episodes, with one exception being sickle cell pain. Three studies had adult patients and the other pediatric patients. The exclusion of input from a patient perspective was notable, as was a lack of interdisciplinary involvement. CONCLUSION: Nurses are integral to the assessment and management of pain in many care settings requiring comprehensive communication and clinical skills. There is a paucity of research on the use of virtual reality or artificial intelligence in pain education for nurses. Current studies are preliminary in nature and/or pilot studies. Further empirical research, with robust design is required to inform nursing education, practice, and policy, thereby supporting the advancement of nursing pain education.

Experiences of the older hospitalised person on nursing pain care: An ethnographic insight.

AIMS AND OBJECTIVES: To present an ethnographic insight into the older hospitalised person (those aged over 65 years) perceptions and experiences of pain care provision by nurses in acute care. BACKGROUND: Pain care provision by nurses remains less than optimal for the older hospitalised person despite numerous evidence-based guidelines. There is a paucity of research providing input from the experiences of the older hospitalised person in relation to their perspectives of pain care provision by nurses in acute care. Pain care research needs more involvement from those older persons with documented diagnoses of dementia, delirium or cognitive impairment, and intellectual disabilities and those in their end stage of palliation. DESIGN: A focused ethnographic study. The consolidated criteria for reporting qualitative research (COREQ) were used to report the findings of this study. METHODS: A focused ethnographic study was conducted in 8 acute care units within 2 large tertiary referral hospitals on the east coast of Australia. Consisting of semi-structured interviews (n = 12) of cognitively intact older persons (11 hr). Twenty-three (23) semi-structured interviews with nine (9) RN participants (12 hr and 38 min). Participant observation period totalled 1,041 hr. RESULTS: The older persons' experiences of receiving pain care were based on a formulaic assessment process focusing on intensity of pain and pain management options provided often lacked their input. The older persons often did not perceive their pain care provision as being of benefit to themselves. The nurses lacked insight and understanding on the nature of pain for the older person. CONCLUSION: Understanding was gained into how the older persons' pain care was hampered due to the lack of appropriate, and meaningful pain care provision and provides insight into why the older hospitalised person continues to experience a less than optimal experience. RELEVANCE TO CLINICAL PRACTICE: Older hospitalised persons can gain continuity of pain care when nurses negotiate with them to repattern or restructure their nursing routines for pain care provision. Older people need inclusion into pain care decisions. All vulnerable older persons require nurses to use an evidence-based pain assessment tool.

Experiences of older people following the introduction of consumer-directed care to home care packages: A qualitative descriptive study.

OBJECTIVE: To explore the experiences of older people receiving home care package (HCP) support following the introduction of consumer-directed care (CDC) by the Australian government on 1 July 2015. METHODS: Thirty-one older people with existing HCP support from two service providers in regional New South Wales, Australia, participated in a face-to-face interview and/or a qualitative survey. RESULTS: Analysis revealed the theme of Choices: Preferences, constraints, balancing and choosing. Participants described choosing to live at home with HCP support; however, they were constrained by poor communication and information about service changes and options, personal budgets and access to future care. HCP services remained largely unchanged during transition to CDC. CONCLUSION: Many aspects of the initial implementation of CDC were challenging for older people. Clear, relevant and timely communication and information about CDC and its consequences for consumers appear to be needed to enhance CDC.

Home care packages: insights into the experiences of older people leading up to the introduction of consumer directed care in Australia.

This paper reports phase one, conducted from March to June 2015, of a two-phase, qualitative descriptive study designed to explore the perceptions and experiences of older people before and after the introduction of consumer directed care (CDC) to home care packages (HCP) in Australia. Eligible consumers with a local HCP provider were mailed information about the study. Data collection occurred before the introduction of CDC and included face-to-face, in-depth interviews, summaries of interviews, field notes and reflective journaling. Semi-structured questions and 'emotional touchpoints' relating to home care were used to guide the interview conversation. Line-by-line data analysis, where significant statements were highlighted and clustered to reveal emergent themes, was used. Five older people, aged 81 to 91 years, participated in the study. The four emergent themes were: seeking quality and reciprocity in carer relationships; patchworking services; the waiting game; and technology with utility. Continuity of carers was central to the development of a trusting relationship and perceptions of care quality among older consumers. Care coordinators and workers should play a key role in ensuring older people receive timely information about CDC and their rights and responsibilities. Participants' use of contemporary technologies suggests opportunities to improve engagement of HCP clients in CDC.

Efficacy of the use of evidence-based algorithmic guidelines in the acute care setting for pain assessment and management in older people: a critical review of the literature.

AIM: The aim of the literature review was to identify all examples of primary research using an algorithmic approach for the implementation of a clinical practice guideline relating to pain assessment and/or management within acute care, with a specific focus on older people. DESIGN: Critical literature review. DATA SOURCES: Inclusion criteria were; English language publications within the past 13 years; peer reviewed; research conducted within a hospital; about adult inpatients. Exclusion criteria; research located outside of a hospital context; quality improvement studies; rehabilitation studies and literature reviews. REVIEW METHODS: Critical appraisal of the literature by using a qualitative interpretation of a translational approach. The literature was thematically mapped according to the criteria of credibility, transferability, plausibility and applicability. RESULTS: No clinical practice guideline was found that directly related to both assessment and management of pain using an algorithm in acute care for older people. Five studies were found to have relevance and were critically evaluated. CONCLUSION: A critique of the literature shows that an algorithmic approach is feasible for translation into a clinical practice guideline for assessment and management of pain in older people within the acute care setting. IMPLICATIONS FOR PRACTICE: Implementation of any algorithmic approach requires consideration of the environment, culture and availability of resources.