Quantitative research approaches

Hybrid machine learning approach for landslide prediction, Uttarakhand, India

Natural disasters always have a damaging effect on our way of life. Landslides  cause serious damage to both human and natural resources around the world. In this paper, the prediction accuracy of five hybrid models for landslide occurrence in the Uttarkashi, Uttarakhand (India) was evaluated and compared. In this approach, the Rough Set theory coupled with five different models namely Bayesian Network (HBNRS), Backpropagation Neural Network (HBPNNRS), Bagging (HBRS), XGBoost (HXGBRS), and Random Forest (HRFRS) were taken into account. The database for the models development was prepared using fifteen conditioning factors that had 373 landslide and 181 non-landslide locations that were then randomly divided into training and testing locations with a ratio of 75%:25%. The appropriateness and predictability of these conditioning factors were assessed using the multi-collinearity test and the least absolute shrinkage and selection operator approach. The accuracy, sensitivity, specificity, precision, and F-Measures, and the area under the curve (AUC)-receiver operating characteristics curve, were used to evaluate and compare the performance of the individual and hybrid created models. The findings indicate that the constructed hybrid model HXGBRS (AUC = 0.937, Precision = 0.946, F1-score = 0.926 and Accuracy = 89.92%) is the most accurate model for predicting landslides when compared to other models (HBPNNRS, HBNRS, HBRS, and HRFRS). Importantly, when the fusion is performed with the rough set method, the prediction capability of each model is improved. Simultaneously, the HXGBRS model proposed shows superior stability and can effectively avoid overfitting. After the core modules were developed, the user-friendly platform was designed as an integrated GIS environment using dynamic maps for effective landslide prediction in large prone areas. Users can predict the probability of landslide occurrence for selected region by changing the values of a conditioning factors. The created approach could be beneficial for predicting the impact of landslides on slopes and tracking landslides along national routes.

Systematic Review: Pain and Emotional Functioning in Pediatric Sickle Cell Disease

The objective of this systematic review was to assess the relationship between pain (frequency/intensity/duration, impairment, coping) and emotional functioning in pediatric Sickle Cell Disease, and evaluate the state of the literature. Studies were included if they met each of the following criteria: (a) primarily pediatric sample of youth or young adults up to age 21 years with SCD, (b) examined emotional functioning including anxiety and/or depressive and/or internalizing symptoms, and/or affect, (c) examined pain intensity/frequency/duration and/or pain-related impairment and/or pain coping as it relates to emotional functioning, as defined above. Using the established guidelines for systematic reviews, we searched PsycINFO, PubMED, and CINAHL databases for studies published through June 2018. Screening resulted in 33 studies meeting inclusion criteria. Study data were extracted and evaluated for scientific merit, resulting in four studies being removed. 29 studies were included in the final synthesis. Studies provide strongest evidence of a relationship between increased pain frequency and higher depressive and anxiety symptoms. There are moderate-to-strong associations between pain-related impairment and depressive symptoms, and small-to-strong associations between pain-related impairment and anxiety. When examining pain-coping strategies, maladaptive cognitive strategies show the strongest association with emotional functioning. There is a need for more adequately powered, prospective studies based on theoretical frameworks in order to advance our understanding of the relationship between pain and emotional functioning in pediatric SCD.

Family resilience and adaptive coping in children with juvenile idiopathic arthritis: protocol for a systematic review

BACKGROUND

This systematic review is the first step in a study investigating the resilience methods and processes in families of children with juvenile idiopathic arthritis. In particular, this review will focus on chronic or persistent pain, as a common symptom of juvenile idiopathic arthritis, which is the most common rheumatic disease in childhood. The experience of persistent pain can add to the functional disability associated with juvenile idiopathic arthritis. Resilience has relevance to all areas of paediatric psychology, and targeted attention to child, sibling, and parent strengths within the context of paediatric chronic pain and juvenile idiopathic arthritis in particular will augment the field on numerous levels. The objective is to determine which resilience processes are associated with a favourable quality of life in terms of academic, communication, emotional, interpersonal, physical, psychological, and social well-being in families of children with chronic pain associated with JIA.

METHODS/DESIGN

This systematic review will be conducted and reported in accordance with the Preferred Reporting Items for Systematic Reviews and Meta-Analyses statement and the PRESS (Peer Review of Electronic Search Strategies) guideline. Longitudinal, cross-sectional, and treatment studies written in English will be included, as will grey literature (i.e. conference abstracts and dissertations). Studies involving participants who are 6-18 years of age, have been diagnosed with juvenile idiopathic arthritis, are experiencing chronic pain, and are currently undergoing treatment will be included regardless of sex, arthritis type, and type of treatment. Studies including siblings who are 6-18 years of age and the patient's parents will be included.

DISCUSSION

Research exploring resilience within the adult population is accruing. Shifting our focus to protective factors of resilience in the context of paediatric chronic pain, specifically juvenile idiopathic arthritis, is a novel and promising pursuit that has the potential to optimize and inform future clinical practice and interventions. A better understanding of the role of reliance in family adaptation will facilitate the development of more effective treatment approaches and lay the foundation for more effective self-management in paediatric chronic pain.

SYSTEMATIC REVIEW REGISTRATION

This protocol is registered with the International Prospective Register of Systematic Reviews (PROSPERO) database (registration: CRD42016047226).

Psychosocial adjustment of siblings of children with cancer: a systematic review

OBJECTIVES

To promote a broader understanding of the psychosocial impact of childhood cancer on siblings, a systematic review was undertaken. Directions for future research are proposed and clinical strategies are suggested for addressing the needs of these children.

METHODS

Searches of Medline, PsycINFO and CINAHL revealed 65 relevant qualitative, quantitative, or mixed methods' papers published between 1997 and 2008. These papers were rated for scientific merit and findings were extracted for summary.

RESULTS

Siblings of children with cancer do not experience elevated mean rates of psychiatric disorders, but a significant subset experiences post-traumatic stress symptoms, negative emotional reactions (e.g. shock, fear, worry, sadness, helplessness, anger, and guilt), and poor quality of life in emotional, family, and social domains. In general, distress is greater closer to time of diagnosis. School difficulties are also evident within 2 years of diagnosis. Qualitative studies reveal family-level themes such as loss of attention and status as well as positive outcomes including increased sibling maturity and empathy.

CONCLUSIONS

Research regarding siblings of children with cancer continues to be methodologically limited. The conclusions of qualitative and quantitative studies differ considerably. We propose a research agenda to propel this field forward including greater attention to alterations in normative development (as opposed to psychiatric conditions), development of more appropriate quantitative measures, examination of potential moderators of adaptation, and use of prospective longitudinal designs. Siblings of children with cancer are a psychosocially at-risk group and should be provided with appropriate supportive services.

General design classifications

This column described the general design classifications of between-groups, within-subjects, and mixed designs. Remember that in between-groups designs, each participant is in only one group or condition. In within-subjects or repeated-measures designs, on the other hand, each participant receives all the conditions or levels of the independent variable. In mixed designs, there is at least one between-groups independent variable and at least one within-subjects independent variable. In classifying the design, do not consider the dependent variable(s). The classifications and descriptions presented in this column are for difference questions, using the randomized experimental, quasi-experimental, and comparative approaches to research. Appropriate classification and description of the design are crucial for choosing the appropriate inferential statistic, which is the topic of the next column and several to follow.