Randallmouritsen3984

BACKGROUND Drug label, or packaging insert play a significant role in all the operations from production through drug distribution channels to the end consumer. Image of the label also called Display Panel or label could be used to identify illegal, illicit, unapproved and potentially dangerous drugs. Due to the time-consuming process and high labor cost of investigation, an artificial intelligence-based deep learning model is necessary for fast and accurate identification of the drugs. METHODS In addition to image-based identification technology, we take advantages of rich text information on the pharmaceutical package insert of drug label images. In this study, we developed the Drug Label Identification through Image and Text embedding model (DLI-IT) to model text-based patterns of historical data for detection of suspicious drugs. In DLI-IT, we first trained a Connectionist Text Proposal Network (CTPN) to crop the raw image into sub-images based on the text. The texts from the cropped sub-images are recognized independently through the Tesseract OCR Engine and combined as one document for each raw image. https://www.selleckchem.com/products/PD-0332991.html Finally, we applied universal sentence embedding to transform these documents into vectors and find the most similar reference images to the test image through the cosine similarity. RESULTS We trained the DLI-IT model on 1749 opioid and 2365 non-opioid drug label images. The model was then tested on 300 external opioid drug label images, the result demonstrated our model achieves up-to 88% of the precision in drug label identification, which outperforms previous image-based or text-based identification method by up-to 35% improvement. CONCLUSION To conclude, by combining Image and Text embedding analysis under deep learning framework, our DLI-IT approach achieved a competitive performance in advancing drug label identification.BACKGROUND Community-based care services refers to the professional services provided at home to the elderly with formally assessed demands. The growth of the elderly population has increased the demand for these services, and this issue is even worse in the affordable housing community (AHC) of China. Understanding of elderly's demands for different types of community-based care services and its determinations would enable the implementation of appropriate incentive schemes to promote utilization of community-based care services in the AHCs of China. METHODS Guided by previous studies, a conceptual framework was developed. Then, a questionnaire was designed and a community based survey was conducted from May 10-20, 2018 in Daishan AHC of Nanjing City, China. Four hundred eight participants from 25,650 elderly people were selected by systematic random sampling technique. Binary logistic regression was applied to the data about the elderly' primary demands for community-based care services in the AHC, to quantify the elderly's demands and explore related individual-level factors. RESULTS The finding indicates that more than 50% of respondents had the demand for an elderly care hotline, building health archives, on-call nursing and doctor visits, medical lectures, regular medical examinations and sporting fitness. The binary logistic regression models revealed that the primary demands of the elderly for community-based care services were influenced by distinct factors. CONCLUSIONS Our findings help clarify different types of community-based care services and provide fresh information about the demand for community-based care among the elderly in AHCs. Several policy implications are discussed to enhance the efficiency of community-based care service provision.BACKGROUND Issuing of correct prescriptions is a foundation of patient safety. Medication errors represent one of the most important problems in health care, with 'look-alike and sound-alike' (LASA) being the lead error. Existing solutions to prevent LASA still have their limitations. Deep learning techniques have revolutionized identification classifiers in many fields. In search of better image-based solutions for blister package identification problem, this study using a baseline deep learning drug identification (DLDI) aims to understand how identification confusion of look-alike images by human occurs through the cognitive counterpart of deep learning solutions and thereof to suggest further solutions to approach them. METHODS We collected images of 250 types of blister-packaged drug from the Out-Patient Department (OPD) of a medical center for identification. The deep learning framework of You Only Look Once (YOLO) was adopted for implementation of the proposed deep learning. The commonly-used F1 score,to achieve automated prescription and dispensing.BACKGROUND A reasonable allocation of health resources is often characterized by equity and high efficiency. This study aims to evaluate the equity and efficiency of maternal and child health (MCH) resources allocation in Hunan Province, China. METHODS Data related to MCH resources and services was obtained from the Hunan maternal and child health information reporting and management system. The Gini coefficient and data envelopment analysis (DEA) were employed to evaluate the equity and efficiency of MCH resources allocation, respectively. RESULTS The MCH resources allocation in terms of demographic dimension were in a preferred equity status with the Gini values all less than 0.3, and the Gini values for each MCH resources' allocation in terms of the geographical dimension ranged from 0.1298 to 0.4256, with the highest values in the number of midwives and medical equipment (≥ CNY 10,000), which exceeds 0.4, indicating an alert of inequity. More than 40% regions in Hunan were found to be relatively inefficient with decreased return to scale in the allocation of MCH resources, indicating those inefficient regions were using more inputs than needed to obtain the current output levels. CONCLUSIONS The equity of MCH resources by population size is superior by geographic area and the disproportionate distribution of the number of medical equipment (≥ CNY 10,000) and midwives between different regions was the main source of inequity. Policy-makers need to consider the geographical accessibility of health resources among different regions to ensure people in different regions could get access to available health services. More than 40% of regions in Hunan were found to be inefficient, with using more health resources than needed to produce the current amount of health services. Further investigations on factors affecting the efficiency of MCH resources allocation is still needed to guide regional health plans-making and resource allocation.BACKGROUND The National Health Service diabetes prevention programme in England, (NHS DPP) aims to identify people at high risk of type 2 diabetes (T2D) and offer them a face-to-face, group-based, behaviour change intervention for at least 9 months. The NHS DPP was rolled out in phases. We aimed to elicit stakeholders' perceptions and experiences of the factors influencing implementation of, and participation in, the programme during the development phase. METHODS Individual, semi-structured telephone interviews were conducted with 50 purposively sampled stakeholders service users (n = 20); programme commissioners (n = 7); referrers (n = 8); and intervention deliverers (n = 15). Topic guides were structured using a pragmatic, theory-informed approach. Analysis employed the framework method. RESULTS We identified factors that influenced participation Risk communication at referral - stakeholders identified point of referral as a window of opportunity to offer brief advice, to provide an understanding of T2D rind Fidelity - stakeholders described procedures involved in monitoring service users' satisfaction, outcome data collection and quality assurance assessments. CONCLUSIONS The NHS DPP offers an evidence-informed behavioural intervention for T2D prevention. Better risk communication specification could ensure consistency at the referral stage and improve participation in the NHS DPP intervention. Cultural adaptations and outreach strategies could ensure the NHS DPP contributes to reducing health inequalities.BACKGROUND The International Classification of Diseases, 10th Revision (ICD-10) has been widely used to describe the diagnosis information of patients. link2 Automatic ICD-10 coding is important because manually assigning codes is expensive, time consuming and error prone. Although numerous approaches have been developed to explore automatic coding, few of them have been applied in practice. Our aim is to construct a practical, automatic ICD-10 coding machine to improve coding efficiency and quality in daily work. METHODS In this study, we propose the use of regular expressions (regexps) to establish a correspondence between diagnosis codes and diagnosis descriptions in outpatient settings and at admission and discharge. The description models of the regexps were embedded in our upgraded coding system, which queries a diagnosis description and assigns a unique diagnosis code. Like most studies, the precision (P), recall (R), F-measure (F) and overall accuracy (A) were used to evaluate the system performance. Our study had two stages. The datasets were obtained from the diagnosis information on the homepage of the discharge medical record. The testing sets were from October 1, 2017 to April 30, 2018 and from July 1, 2018 to January 31, 2019. RESULTS The values of P were 89.27 and 88.38% in the first testing phase and the second testing phase, respectively, which demonstrate high precision. The automatic ICD-10 coding system completed more than 160,000 codes in 16 months, which reduced the workload of the coders. In addition, a comparison between the amount of time needed for manual coding and automatic coding indicated the effectiveness of the system-the time needed for automatic coding takes nearly 100 times less than manual coding. CONCLUSIONS Our automatic coding system is well suited for the coding task. Further studies are warranted to perfect the description models of the regexps and to develop synthetic approaches to improve system performance.BACKGROUND Good quality midwifery care saves the lives of women and babies. Continuity of midwife carer (CMC), a key component of good quality midwifery care, results in better clinical outcomes, higher care satisfaction and enhanced caregiver experience. However, CMC uptake has tended to be small scale or transient. link3 We used realist evaluation in one Scottish health board to explore implementation of CMC as part of the Scottish Government 2017 maternity plan. METHODS Participatory research, quality improvement and iterative data collection methods were used to collect data from a range of sources including facilitated team meetings, local and national meetings, quality improvement and service evaluation surveys, audits, interviews and published literature. Data analysis developed context-mechanism-outcome configurations to explore and inform three initial programme theories, which were refined into an overarching theory of what works for whom and in what context. RESULTS Trusting relationships across all orgaional boundaries develops the context for successful implementation of CMC. These relationships then become the context that enables CMC to grow and flourish. Trusting relationships, working to full skill set and across women's care journey trigger changes in midwifery practice. Implementing and sustaining CMC within NHS organisational settings requires significant reconfiguration of services at all levels, which requires effective leadership and cannot rely solely on ground-up change.