Automation of literature screening using machine learning in medical evidence synthesis: a diagnostic test accuracy systematic review protocol

Background Systematic review is an indispensable tool for optimal evidence collection and evaluation in evidence-based medicine. However, the explosive increase of the original literatures makes it difficult to accomplish critical appraisal and regular update. Artificial intelligence (AI) algorithms have been applied to automate the literature screening procedure in medical systematic reviews. In these studies, different algorithms were used and results with great variance were reported. It is therefore imperative to systematically review and analyse the developed automatic methods for literature screening and their effectiveness reported in current studies. Methods An electronic search will be conducted using PubMed, Embase, ACM Digital Library, and IEEE Xplore Digital Library databases, as well as literatures found through supplementary search in Google scholar, on automatic methods for literature screening in systematic reviews. Two reviewers will independently conduct the primary screening of the articles and data extraction, in which nonconformities will be solved by discussion with a methodologist. Data will be extracted from eligible studies, including the basic characteristics of study, the information of training set and validation set, and the function and performance of AI algorithms, and summarised in a table. The risk of bias and applicability of the eligible studies will be assessed by the two reviewers independently based on Quality Assessment of Diagnostic Accuracy Studies (QUADAS-2). Quantitative analyses, if appropriate, will also be performed. Discussion Automating systematic review process is of great help in reducing workload in evidence-based practice. Results from this systematic review will provide essential summary of the current development of AI algorithms for automatic literature screening in medical evidence synthesis and help to inspire further studies in this field. Systematic review registration PROSPERO CRD42020170815 (28 April 2020).

A Reconstruction Method for Cross-Cut Shredded Documents Based on the Extreme Learning Machine Algorithm

Reconstruction of cross-cut shredded text documents (RCCSTD) has important applications for information security and judicial evidence collection. The traditional method of manual construction is a very time-consuming task, so the use of computer-assisted efficient reconstruction is a crucial research topic. Fragment consensus information extraction and fragment pair compatibility measurement are two fundamental processes in RCCSTD. Due to the limitations of the existing classical methods of these two steps, only documents with specific structures or characteristics can be spliced, and pairing error is larger when the cutting is more fine-grained. In order to reconstruct the fragments more effectively, this paper improves the extraction method for consensus information and constructs a new global pairwise compatibility measurement model based on the extreme learning machine algorithm. The purpose of the algorithm's design is to exploit all available information and computationally suggest matches to increase the algorithm's ability to discriminate between data in various complex situations, then find the best neighbor of each fragment for splicing according to pairwise compatibility. The overall performance of our approach in several practical experiments is illustrated. The results indicate that the matching accuracy of the proposed algorithm is better than that of the previously published classical algorithms and still ensures a higher matching accuracy in the noisy datasets, which can provide a feasible method for RCCSTD intelligent systems in real scenarios.

Prevalence and Recovery of Microorganisms from Containers used for the Collection of Forensic Biological Samples

Background: Microbes play a significant role in the degradation of biological evidence collected for forensic analysis. The present study is aimed to isolate and identify the microbes present inside the empty container used for the biological evidence collection. Methods: Bacterial isolation from the selected containers was done by cotton swab over the inner surface of the containers. Streaking was done on the surface of the three different culture plates as a Blood agar plate, Nutrient plate and MacConkey plate. The plates were placed in an incubator shaker at 37ºC for 48 hours. The colonies grown on the surface of the media were counted on and used for further study. Various biochemical assays were performed to characterize isolated bacteria. Results: Staining results suggested that the presence of Gram-positive stain (Staphylococcus, Bacillus, Corynebacterium, Clostridium) and Gram negative stain (E. coli, Enterobacteriaceae, Pseudomonas, Salmonella, Shigella, Stenotrophomonas, Bdellovibrio, Acetic acid bacteria). The Catalase and Coagulase test suggested the presence of Staphylococcus aureus, S. epidermis and S. sapropyticus. Moreover, the indole test suggested the presence of Citrobacter koseri, Kebsiella oxytoca, Proteus vulgaris etc. Some of the bacteria were urea metabolizing, including Proteus spp, Helicobacter pylori, Cryptococcus spp, Corynebacterium spp. Conclusion: This study recommends that there should be proper maintenance of the chain of custody from the collection to analysis so that evidence properly prevents degradation or contamination in the biological evidence. Extra care is needed for the collection and packing of biological evidence from the crime scene. Moreover, the collection containers, if left wide open, lead to contamination and degradation of biological evidence.

Collecting Digital Evidence from Online Sources: Deficiencies in Current Polish Criminal Law

The importance of digital evidence, especially online content, is continuously increasing due to the proliferation of digital technologies in socio-economic life. However, the legal means of criminal evidence gathering in Polish legislation remain unchanged and do not take into account some contemporary challenges. In various countries, traditional rules of evidence gathering were created in the context of a physical world. These rules may be insufficient to safeguard the forensic soundness of evidence gathering methods. Inadequacies of current procedures may be especially visible in the context of transborder digital evidence gathering from online open sources. This article describes the practical shortcomings of Polish criminal evidence law in the context of digital evidence with particular attention to online open-source materials. Empirical data indicate that existing legal limitations are bypassed in practice to enable evidence collection. This unfortunately often happens at the expense of the forensic soundness of digital evidence.

Medico-legal evidence collection in child sexual assault cases: a forensic significance

Background Every year, millions of children face sexual exploitation worldwide. In India, 109 children (National Crime Records Bureau2018) were sexually abused everyday (22% jump from the previous year). Even with advanced DNA techniques, the conviction rate remains low. The methods used for forensic DNA evidence analysis vary around the world, but the primary step of biological evidence collection plays the most vital role. Proper and timely evidence collection from the victim by a trained medical professional is important. Main body Dynamics of child sexual assault being massively different from an adult rape demands altogether different approach of evidence collection. A standard sexual kit employed for evidence collection needs urgent modifications considering genital development of pre- and post-pubertal victims. In the present study, parameters including systemic collection and evaluation of forensic evidences, medico-legal examination, and developmental consequences of sexual assault on pre-pubertal victims were assessed. Further suggestions for separate evidence collection kit during medico-legal examination were given for pre-pubertal victims and alleged accused in sexual assault cases in order to streamline and for better evaluation of DNA analysis in forensic laboratories. Conclusion The importance of expert medical practitioners plays a significant role in collection of appropriate information and evidences from the victim of sexual assault. General guidelines for evidence collection in sexual assault cases are not well suited for pre-pubertal victims. Appropriate reforms pertaining to the age and genital development of victims are required. Securing clothing as forensic evidence is essential in most cases as it turned out to be the exclusive evidence bearing material. The purpose of this article is to bring awareness about the thorough medical examination and modified sexual assault kit for pre-pubertal victims and alleged accused for a better approach in evidence collection and conviction rate.

Flexible Mechanisms for Remote Attestation

Remote attestation consists of generating evidence of a system’s integrity via measurements and reporting the evidence to a remote party for appraisal in a form that can be trusted. The parties that exchange information must agree on formats and protocols. We assert there is a large variety of patterns of interactions among appraisers and attesters of interest. Therefore, it is important to standardize on flexible mechanisms for remote attestation. We make our case by describing scenarios that require the exchange of evidence among multiple parties using a variety of message passing patterns. We show cases in which changes in the order of evidence collection result in important differences to what can be inferred by an appraiser. We argue that adding the ability to negotiate the appropriate kind of attestation allows for remote attestations that better adapt to a dynamically changing environment. Finally, we suggest a language-based solution to taming the complexity of specifying and negotiating attestation procedures.

Appropriate subject of obtaining evidence of a criminal offense in the opinion of the court

The article considers the collection of evidence by the prosecution, because it is in this order that the evidence base of criminal proceedings is most often formed. Thus, the prosecutor, investigator (investigator) acting under Articles 36, 40, 401 of the Criminal Procedure Code of Ukraine, as well as an employee of the operational unit pursuant to Article 41 of the Criminal Procedure Code of Ukraine on behalf of the investigator or prosecutor have the right to collect evidence. The purpose of the article is to study the affiliation of the subjects of evidence collection as part of the procedural form of the criminal process of Ukraine, taking into account the analysis of court decisions, namely the assessment of the evidence base as a basis for deciding on the merits of criminal proceedings. Cases of involvement of an improper subject in the pre-trial investigation, which are common and typical, are systematized. There are two types of improper subjects within the investigative (search) or procedural actions, namely the subject: 1) is not appointed in the manner prescribed by law, although according to current legislation according to the list of its powers may be appropriate; 2) does not have the authority under the law to make a specific decision or to conduct investigative (search) or procedural actions. An analysis of court decisions according to which courts provide an assessment of the procedural activities of the subjects of evidence collection in criminal proceedings at the stage of pre-trial investigation, including their relevance and admissibility. Thus, attention is paid to the assessment of courts on the legality of the presence of persons during investigative (investigative) or procedural actions; the correctness of fixing such a presence. In addition, the situations of appointment of relevant subjects in criminal proceedings to fulfill their powers are considered. It is proposed to supplement the first part of Article 236 of the Criminal Procedure Code of Ukraine with a provision that clarifies the grounds for the stay and authority of the employee of the operational and investigative service during the search.

Spherically Stratified Point Projection: Feature Image Generation for Object Classification Using 3D LiDAR Data

Three-dimensional point clouds have been utilized and studied for the classification of objects at the environmental level. While most existing studies, such as those in the field of computer vision, have detected object type from the perspective of sensors, this study developed a specialized strategy for object classification using LiDAR data points on the surface of the object. We propose a method for generating a spherically stratified point projection (sP2) feature image that can be applied to existing image-classification networks by performing pointwise classification based on a 3D point cloud using only LiDAR sensors data. The sP2’s main engine performs image generation through spherical stratification, evidence collection, and channel integration. Spherical stratification categorizes neighboring points into three layers according to distance ranges. Evidence collection calculates the occupancy probability based on Bayes’ rule to project 3D points onto a two-dimensional surface corresponding to each stratified layer. Channel integration generates sP2 RGB images with three evidence values representing short, medium, and long distances. Finally, the sP2 images are used as a trainable source for classifying the points into predefined semantic labels. Experimental results indicated the effectiveness of the proposed sP2 in classifying feature images generated using the LeNet architecture.