Varying Naïve Bayes Models With Applications to Classification of Chinese Text Documents

Document classification is an area of great importance for which many classification methods have been developed. However, most of these methods cannot generate time-dependent classification rules. Thus, they are not the best choices for problems with time-varying structures. To address this problem, we propose a varying naïve Bayes model, which is a natural extension of the naïve Bayes model that allows for time-dependent classification rule. The method of kernel smoothing is developed for parameter estimation and a BIC-type criterion is invented for feature selection. Asymptotic theory is developed and numerical studies are conducted. Finally, the proposed method is demonstrated on a real dataset, which was generated by the Mayor Public Hotline of Changchun, the capital city of Jilin Province in Northeast China.     

Costs of colorectal cancer screening provision in CDC’s Colorectal Cancer Control Program: Comparisons of colonoscopy and FOBT/FIT based screening

We assess annual costs of screening provision activities implemented by 23 of the Centers for Disease Control and Prevention’s Colorectal Cancer Control Program (CRCCP) grantees and report differences in costs between colonoscopy and FOBT/FIT-based screening programs. We analysed annual cost data for the first three years of the CRCCP (July 2009–June 2011) for each screening provision activity and categorized them into clinical and non-clinical screening provision activities. The largest cost components for both colonoscopy and FOBT/FIT-based programs were screening and diagnostic services, program management, and data collection and tracking. During the first 3 years of the CRCCP, the average annual clinical cost for screening and diagnostic services per person served was $1150 for colonoscopy programs, compared to $304 for FIT/FOBT-based programs. Overall, FOBT/FIT-based programs appear to have slightly higher non-clinical costs per person served (average $1018; median $838) than colonoscopy programs (average $980; median $686). Colonoscopy-based CRCCP programs have higher clinical costs than FOBT/FIT-based programs during the 3-year study timeframe (translating into fewer people screened). Non-clinical costs for both approaches are similar and substantial. Future studies of the cost-effectiveness of colorectal cancer screening initiatives should consider both clinical and non-clinical costs.     

Social Work in the Emergency Department—Implementation of a Domestic and Family Violence Screening Program

Abstract

Women who have experienced domestic and family violence use health services more frequently than women who have not. Early identification and intervention by the health system may reduce health problems associated with domestic and family violence and lead to savings for the health sector. This study aimed to evaluate the impact of a new domestic and family violence screening program, which was based on an ecological model and introduced by a social work team in the Emergency Department of a major metropolitan hospital. The evaluation method included an audit of social work case files to assess the effect on referral rates and a survey of Emergency Department staff to obtain perceptions of the impact of the program on the staff and clients. In the 3-month period following the introduction of the program, the rate of referral to social work increased by 213%. Staff agreed that the Emergency Department is an appropriate place to ask about domestic and family violence, under certain conditions. Findings suggest that an ecological social work model provides an approach to screening for domestic and family violence that not only contributes to increased identification and supportive client interventions but may also contribute to more sustainable systemic change.     

FDI甄别、东道国福利及引资启示——基于委托-代理理论视角

FDI的流入为东道国的经济增长和社会福利带来各种效应。通过对FDI各种效应的分析,可以将FDI划分为数量型FDI和质量型FDI。在此分类的基础之上,东道国通过委托外企公司吸引不同类型的外资流入,为本国的经济增长和社会福利增加服务。根据委托——代理模型对两种不同类型FDI的分析显示:(1)数量型FDI的极端偏好会恶化本国的福利水平,只有同时引进质量型FDI才可能使本国的福利得到改进;(2)针对外资企业引进“数量型”FDI努力的边际成本和引进“质量型”FDI努力的边际成本之间的不同关系,东道国应分别采用不同的引资激励政策以使得FDI的引进符合本国的经济增长和社会福利所需。     

Midwifery care: A perinatal mental health case scenario

The establishment of the National Perinatal Depression Initiative (NPDI, 2008–2013) has brought a focus across Australia for the need to identify women at risk of perinatal mental health disorders, suggesting that routine screening by relevant health professionals may aid earlier detection, better care and improved outcomes. Midwives are frequently the primary point of contact in the perinatal period and thus ideally placed to identify, interpret and manage complex situations, including screening for perinatal mental health disorders.This paper offers strategies that could be implemented into daily midwifery practice in order to achieve the goals consistent with the National Perinatal Depression Initiative. A case study (Jen) and discussion, guided by recommendations from the Australian Nursing and Midwifery Competency standards and beyondblue Clinical Practice Guidelines, are used to demonstrate how midwifery care can be provided.In accordance with her legal obligations, the midwife should act within her scope of practice to undertake a series of psychosocial and medical assessments in order to best determine how midwifery care and support can be of benefit to Jen, her infant and her family. Suggestions described include administration of validated screening questionnaires, clinical interview, physical assessment, discussion with partner, awareness of the mother–infant interactions and questioning around baby's sleep and feeding. Based on evaluation of the information gained from a bio-psycho-social assessment, suggestions are made as to the midwifery care options that could be applied.     

Screening alternatives graphically by an extended case-based distance approach

Screening is a helpful process of multiple criteria decision aid (MCDA) to reduce a larger set of alternatives into a smaller one containing the best alternatives; thereby, decision makers are able to concentrate on evaluating alternatives within a smaller set. Therefore, determining how to assist decision makers in screening is an important issue for MCDA. This study proposes an extended case-based distance approach incorporating the advantages of a case-based distance method, a mixed-integer programming approach of discriminant analysis, and a multidimensional scaling technique to help decision makers screen alternatives visually in MCDA. The proposed approach can screen alternatives by evaluating sets of cases selected by decision makers, providing visual aids to observe decision context, reducing the number of misclassifications, and improving multiple solution problems. An interactive screening procedure is also developed to provide flexibility so that decision makers can check and adjust screening results iteratively.