Child sexual abuse in Indonesia: A systematic review of literature, law and policy
سوء استفاده جنسی از کودکان در اندونزی: مرور نظاممند ادبیات، حقوق و سیاست-2019
Background: Like many middle-income countries, knowledge about child sexual abuse (CSA) is limited in Indonesia. The national government has stated a commitment to protect children from the worst forms of abuse, yet the sensitivity of CSA along with the complexity of culture and law, present substantial challenges. Objective: This article reviews current knowledge about CSA in Indonesia, in the context of existing laws and policies that influence CSA prevention and intervention. Method: A systematic review of this research was conducted in the following manner: a review of scholarly literature and grey literature in English (19 papers) and in Bahasa Indonesian (11 papers), and a review of CSA-related Indonesian laws (4 documents) and policies (5 documents). Results: This review finds that knowledge about CSA in Indonesia is still limited. The taboos on discussing sexual matters were identified as factors that impede reporting of CSA. Poverty also leads to increasing children’s risk of sexual abuse. There was less attention to CSA occurring within family contexts and focus was more upon its occurrence outside of the family. The study identified that contradictory definitions of children within the law add to children’s vulnerability to CSA; this is especially the case for girls. Current child protection strategies in prevention and intervention lack specific focus on CSA. Conclusion: Further research is needed to enable the development of evidence-based approaches to better harmonize the development of law and policy with contemporary knowledge about CSA.
Keywords: Child sexual abuse | Child abuse | Child protection | Indonesia
A review of machine learning algorithms for identification and classification of non-functional requirements
مروری بر الگوریتم های یادگیری ماشین برای شناسایی و طبقه بندی نیازمندی های کاربردی-2019
Context: Recent developments in requirements engineering (RE) methods have seen a surge in using machine-learning (ML) algorithms to solve some difficult RE problems. One such problem is identifi- cation and classification of non-functional requirements (NFRs) in requirements documents. ML-based approaches to this problem have shown to produce promising results, better than those produced by traditional natural language processing (NLP) approaches. Yet, a systematic understanding of these ML approaches is still lacking. Method: This article reports on a systematic review of 24 ML-based approaches for identifying and clas- sifying NFRs. Directed by three research questions, this article aims to understand what ML algorithms are used in these approaches, how these algorithms work and how they are evaluated. Results: (1) 16 different ML algorithms are found in these approaches; of which supervised learning algorithms are most popular. (2) All 24 approaches have followed a standard process in identifying and classifying NFRs. (3) Precision and recall are the most used matrices to measure the performance of these approaches. Finding: The review finds that while ML-based approaches have the potential in the classification and identification of NFRs, they face some open challenges that will affect their performance and practical application. Impact: The review calls for the close collaboration between RE and ML researchers, to address open challenges facing the development of real-world ML systems. Significance: The use of ML in RE opens up exciting opportunities to develop novel expert and intelligent systems to support RE tasks and processes. This implies that RE is being transformed into an application of modern expert systems.
Keywords: Requirements engineering | Non-functional requirements | Requirements documents | Requirements identification Requirements | classification | Machine learning
Deep learning in medical image analysis: A third eye for doctors
یادگیری عمیق در تجزیه و تحلیل تصویر پزشکی: چشم سوم برای پزشکان-2019
Aim and scope: Artificial intelligence (AI) in medicine is a fast-growing field. The rise of deep learning algorithms, such as convolutional neural networks (CNNs), offers fascinating perspectives for the automation of medical image analysis. In this systematic review article, we screened the current literature and investigated the following question: ‘‘Can deep learning algorithms for image recognition improve visual diagnosis in medicine?’’ Materials and methods: We provide a systematic review of the articles using CNNs for medical image analysis, published in the medical literature before May 2019. Articles were screened based on the following items: type of image analysis approach (detection or classification), algorithm architecture, dataset used, training phase, test, comparison method (with specialists or other), results (accuracy, sensibility and specificity) and conclusion. Results: We identified 352 articles in the PubMed database and excluded 327 items for which performance was not assessed (review articles) or for which tasks other than detection or classification, such as segmentation, were assessed. The 25 included papers were published from 2013 to 2019 and were related to a vast array of medical specialties. Authors were mostly from North America and Asia. Large amounts of qualitative medical images were necessary to train the CNNs, often resulting from international collaboration. The most common CNNs such as AlexNet and GoogleNet, designed for the analysis of natural images, proved their applicability to medical images. Conclusion: CNNs are not replacement solutions for medical doctors, but will contribute to optimize routine tasks and thus have a potential positive impact on our practice. Specialties with a strong visual component such as radiology and pathology will be deeply transformed. Medical practitioners, including surgeons, have a key role to play in the development and implementation of such devices.
Keywords: Deep learning | Artificial intelligence | Neural network | Image analysis | Systematic review | Computer vision
The effectiveness of DNA databases in relation to their purpose and content: A systematic review
اثربخشی پایگاه داده های DNA در ارتباط با هدف و محتوای آنها: یک مرور سیستماتیک-2019
Different stakeholders use forensic DNA databases for different purposes; for example, law enforcement agencies use them as an investigative tool to identify suspects, and criminologists use them to study the offending patterns of unidentified suspects. A number of researchers have already studied their effectiveness, but none has performed an overview of the relevant literature. Such an overview could help future researchers and policymakers by evaluating their creation, use and expansion. Using a systematic review, this article synthesizes the most relevant research into the effectiveness of forensic DNA databases published between January 1985 and March 2018. We report the results of the selected studies and look deeper into the evidence by evaluating the relationship between the purpose, content, and effectiveness of DNA databases, three inseparable elements in this type of research. We classify the studies by purposes: (i) detection and clearance; (ii) deterrence; and (iii) criminological scientific knowledge. Each category uses different measurements to evaluate effectiveness. The majority of these studies report positive results, supporting the assumption that DNA databases are an effective tool for the police, society, and criminologists.
Keywords: DNA database | Systematic review | Effectiveness | Police investigation | Criminological research
A comparison of deep learning performance against health-care professionals in detecting diseases from medical imaging: a systematic review and meta-analysis
مقایسه عملکرد یادگیری عمیق در برابر متخصصان مراقبت های بهداشتی در تشخیص بیماری ها از تصویربرداری پزشکی: یک مرور منظم و متاآنالیز-2019
Background Deep learning offers considerable promise for medical diagnostics. We aimed to evaluate the diagnostic accuracy of deep learning algorithms versus health-care professionals in classifying diseases using medical imaging. Methods In this systematic review and meta-analysis, we searched Ovid-MEDLINE, Embase, Science Citation Index, and Conference Proceedings Citation Index for studies published from Jan 1, 2012, to June 6, 2019. Studies comparing the diagnostic performance of deep learning models and health-care professionals based on medical imaging, for any disease, were included. We excluded studies that used medical waveform data graphics material or investigated the accuracy of image segmentation rather than disease classification. We extracted binary diagnostic accuracy data and constructed contingency tables to derive the outcomes of interest: sensitivity and specificity. Studies undertaking an out-of-sample external validation were included in a meta-analysis, using a unified hierarchical model. This study is registered with PROSPERO, CRD42018091176. Findings Our search identified 31 587 studies, of which 82 (describing 147 patient cohorts) were included. 69 studies provided enough data to construct contingency tables, enabling calculation of test accuracy, with sensitivity ranging from 9·7% to 100·0% (mean 79·1%, SD 0·2) and specificity ranging from 38·9% to 100·0% (mean 88·3%, SD 0·1). An out-of-sample external validation was done in 25 studies, of which 14 made the comparison between deep learning models and health-care professionals in the same sample. Comparison of the performance between health-care professionals in these 14 studies, when restricting the analysis to the contingency table for each study reporting the highest accuracy, found a pooled sensitivity of 87·0% (95% CI 83·0–90·2) for deep learning models and 86·4% (79·9–91·0) for health-care professionals, and a pooled specificity of 92·5% (95% CI 85·1–96·4) for deep learning models and 90·5% (80·6–95·7) for health-care professionals. Interpretation Our review found the diagnostic performance of deep learning models to be equivalent to that of health-care professionals. However, a major finding of the review is that few studies presented externally validated results or compared the performance of deep learning models and health-care professionals using the same sample. Additionally, poor reporting is prevalent in deep learning studies, which limits reliable interpretation of the reported diagnostic accuracy. New reporting standards that address specific challenges of deep learning could improve future studies, enabling greater confidence in the results of future evaluations of this promising technology.
Applications of machine learning in addiction studies: A systematic review
کاربردهای یادگیری ماشین در مطالعات اعتیاد: یک مرور سیستماتیک-2019
This study aims to provide a systematic review of the applications of machine learning methods in addiction research. In this study, multiple searches on MEDLINE, Embase and the Cochrane Database of Systematic Reviews were performed. 23 full-text articles were assessed and 17 articles met the inclusion criteria for the final review. The selected studies covered mainly substance addiction (N=14, 82.4%), including smoking (N=4), alcohol drinking (N=3), as well as uses of cocaine (N=4), opioids (N=1), and multiple substances (N=2). Other studies were non-substance addiction (N=3, 17.6%), including gambling (N=2) and internet gaming (N=1). There were eight cross-sectional, seven cohort, one non-randomized controlled, and one crossover trial studies. Majority of the studies employed supervised learning (N=13), and others employed unsupervised learning (N=2) and reinforcement learning (N=2). Among the supervised learning studies, five studies used ensemble learning methods or multiple algorithm comparisons, six used regression, and two used classification. The two included reinforcement learning studies used the direct methods. These results suggest that machine learning methods, particularly supervised learning are increasingly used in addiction psychiatry for informing medical decisions.
Keywords: Machine learning | Supervised learning | Unsupervised learning | Reinforcement learning | Addiction
Cyberhate: A review and content analysis of intervention strategies
Cyberhate: مرور و تحلیل محتوای استراتژی های مداخله-2019
This paper presents a review of intervention programmes against cyberhate. Over the last decade, the preoccupation over the use of electronic means of communication as a tool to convey hate, racist and xenophobic contents rose tremendously. NGOs, legal professionals, private companies, and civil society have developed interventions but little is known about their impact. For this review we followed the method and protocol from the guidelines from the Cochrane Collaboration Handbook for Systematic Reviews and the Campbell Collaboration Crime and Justice guidelines. The review identified three key intervention areas: law, technology and education through the empowerment of the individuals under the form of counter-speech. No specific intervention towards aggressors was found and most projects focus on prevention or victims through confidence building and skills learning to speak out, report and potentially react in an appropriate way. We did not find any rigorously assessed interventions, which highlights a gap in research and stresses the need for this type of studies. The evaluation of effectiveness of interventions needs to be included in the near future research agenda. Up to now, although intentions are good, we have no evidence that the steps that are undertaken are effective in preventing and reducing cyberhate.
Keywords: Cyberhate | Youth | Intervention | Review | Literature review
Parental supervision and later offending: A systematic review of longitudinal studies
نظارت والدین و بعداً توهین آمیز: مرور نظاممند مطالعات طولی-2019
Parental supervision has been identified as an important influence on offending. This systematic review focuses specifically on parental supervision, compared to existing systematic reviews which tend to concentrate on a wider range of family factors. The main aim of this article is to assess the precise nature of the association between parental supervision and offending. Overall, 19 prospective longitudinal studies were identified (published since 1996) which met the inclusion criteria. The results show a weighted mean effect size (ES) of Cohens d=0.37 between parental supervision and later offending. This review discovered that studies use different types of behavior to define parental supervision. Interestingly, a larger weighted mean effect size (d=0.45) was found for studies measuring ‘level of parental knowledge’ compared to studies measuring ‘child disclosure to parents’ (d=0.33) or ‘parental rule setting’ (d=0.14). The results suggest that the strength of social bonds is important for enabling parents to maintain high levels of knowledge. Prevention programs should aim to develop robust channels of communication that increase parental knowledge regarding the activities of their children. Future research should also clarify the definition of parental supervision, in order to make it possible to compare different studies of parenting.
Keywords: Parental supervision | Offending | Delinquency | Prospective longitudinal studies
Prediction of sepsis patients using machine learning approach: A meta-analysis
پیش بینی بیماران مبتلا به سپسیس با استفاده از روش یادگیری ماشین: متاآنالیز-2019
Study objective: Sepsis is a common and major health crisis in hospitals globally. An innovative and fea- sible tool for predicting sepsis remains elusive. However, early and accurate prediction of sepsis could help physicians with proper treatments and minimize the diagnostic uncertainty. Machine learning mod- els could help to identify potential clinical variables and provide higher performance than existing tra- ditional low-performance models. We therefore performed a meta-analysis of observational studies to quantify the performance of a machine learning model to predict sepsis. Methods: A comprehensive literature search was conducted through the electronic database (e.g. PubMed, Scopus, Google Scholar, EMBASE, etc.) between January 1, 20 0 0, and March 1, 2018. All the studies pub- lished in English and reporting the sepsis prediction using machine learning algorithms were considered in this study. Two authors independently extracted valuable information from the included studies. In- clusion and exclusion of studies were based on the Preferred Reporting Items for Systematic Reviews and Meta-analysis (PRISMA) guidelines. Results: A total of 7 out of 135 studies met all of our inclusion criteria. For machine learning models, the pooled area under receiving operating curve (SAUROC) for predicting sepsis onset 3 to 4 h before, was 0.89 (95%CI: 0.86–0.92); sensitivity 0.81 (95%CI:0.80–0.81), and specificity 0.72 (95%CI:0.72–0.72) whereas the pooled SAUROC for SIRS, MEWS, and SOFA was 0.70, 0.50, and 0.78. Additionally, diagnostic odd ratio for machine learning, SIRS, MEWS, and SOFA was 15.17 (95%CI: 9.51–24.20), 3.23 (95%CI: 1.52–6.87), 31.99 (95% CI: 1.54–666.74), and 3.75(95%CI: 2.06–6.83). Conclusion: Our study findings suggest that the machine learning approach had a better performance than the existing sepsis scoring systems in predicting sepsis.
Keywords: Area under receiver operating curve | Sepsis | Machine learning | Diagnostic odd ratio
Early sexual initiation in Europe and its relationship with legislative change: A systematic review
برانگیختگی جنسی زودهنگام در اروپا و ارتباط آن با تغییرات قانونی: یک مرور سیستماتیک-2019
Early sexual initiation is often considered risky behaviour as it is related with adverse consequences such as sexually transmitted diseases or unwanted pregnancy. Multiple academic studies have demonstrated that in the second half of the 20th century, the age of young peoples first sexual initiation was on the decline in developed countries. However, little research has been conducted on the situation in the 21st century. By systematically reviewing recent studies on the timing of persons first sexual initiation in European countries, this article revealed the latest trends in the age of first sexual initiation in Europe: 1) the continuing decline of age of first sexual initiation, and 2) the difference in timing of first sexual initiation between males and females. These two findings were then compared with the latest trends in age of consent legislation in Europe to see the relationship between the trends of age of sexual initiation in law and in practice.
Keywords: Europe | First sexual initiation | Timing | Adolescents | Age of consent | Legislation