A case study on the relationship between risk assessment of scientific research projects and related factors under the Naive Bayesian algorithm

This paper delves into the nuanced dynamics influencing the outcomes of risk assessment (RA) in scientific research projects (SRPs), employing the Naive Bayes algorithm. The methodology involves the selection of diverse SRPs cases, gathering data encompassing project scale, budget investment, team experience, and other pertinent factors. The paper advances the application of the Naive Bayes algorithm by introducing enhancements, specifically integrating the Tree-augmented Naive Bayes (TANB) model. This augmentation serves to estimate risk probabilities for different research projects, shedding light on the intricate interplay and contributions of various factors to the RA process. The findings underscore the efficacy of the TANB algorithm, demonstrating commendable accuracy (average accuracy 89.2%) in RA for SRPs. Notably, budget investment (regression coefficient: 0.68, P < 0.05) and team experience (regression coefficient: 0.51, P < 0.05) emerge as significant determinants obviously influencing RA outcomes. Conversely, the impact of project size (regression coefficient: 0.31, P < 0.05) is relatively modest. This paper furnishes a concrete reference framework for project managers, facilitating informed decision-making in SRPs. By comprehensively analyzing the influence of various factors on RA, the paper not only contributes empirical insights to project decision-making but also elucidates the intricate relationships between different factors. The research advocates for heightened attention to budget investment and team experience when formulating risk management strategies. This strategic focus is posited to enhance the precision of RAs and the scientific foundation of decision-making processes.

Interest in Educational Data and Barriers to Data Use Among Massive Open Online Course Instructors

Higher education instructors constantly rely on educational data to assess and evaluate the behavior of their students and to make informed decisions such as which content to focus on and how to best engage the students with it. Massive open online course (MOOC) platforms may assist in the data-driven instructional process, as they enable access to a wide range of educational data that is gathered automatically and continuously. Successful implementation of a data-driven instruction initiative depends highly on the support and acceptance of the instructors. Yet, our understanding of instructors' perspectives regarding the process of data-driven instruction, especially with reference to MOOC teaching, is still limited. Hence, this study was set to characterize MOOC instructors' interest in educational data and their perceived barriers to data use for decision-making. Taking a qualitative approach, data were collected via semi-structured interviews with higher education MOOC instructors from four public universities in Israel. Findings indicated that the instructors showed great interest mostly in data about social interactions between learners and about problems with the MOOC educational resources. The main reported barriers for using educational data for decision-making were lack of customized data, real-time access, data literacy, and institutional support. The results highlight the need to provide MOOC instructors with professional development opportunities for the proper use of educational data for skilled decision-making.

Data-driven decision-making in emergency remote teaching

Decision-making is key for teaching, with informed decisions promoting students and teachers most effectively. In this study, we explored data-driven decision-making processes of K-12 teachers (N = 302) at times of emergency remote teaching, as experienced during the COVID-19 pandemic outbreak in Israel. Using both quantitative and qualitative methodologies, and a within-subject design, we studied how teachers' data use had changed during COVID-19 days, and which data they would like to receive for improving their decision-making. We based our analysis of the data on the Universal Design of Learning (UDL) model that characterizes the diverse ways of adapting teaching and learning to different learners as a means of understanding teachers' use of data. Overall, we found a decline in data use, regardless of age or teaching experience. Interestingly, we found an increase in data use for optimizing students' access to technology and for enabling them to manage their own learning, two aspects that are strongly connected to remote learning in times of emergency. Notably, teachers wished to receive a host of data about their students' academic progress, social-emotional state, and familial situations.

Machine Learning: Algorithms, Real-World Applications and Research Directions

In the current age of the Fourth Industrial Revolution (4IR or Industry 4.0), the digital world has a wealth of data, such as Internet of Things (IoT) data, cybersecurity data, mobile data, business data, social media data, health data, etc. To intelligently analyze these data and develop the corresponding smart and automated applications, the knowledge of artificial intelligence (AI), particularly, machine learning (ML) is the key. Various types of machine learning algorithms such as supervised, unsupervised, semi-supervised, and reinforcement learning exist in the area. Besides, the deep learning, which is part of a broader family of machine learning methods, can intelligently analyze the data on a large scale. In this paper, we present a comprehensive view on these machine learning algorithms that can be applied to enhance the intelligence and the capabilities of an application. Thus, this study’s key contribution is explaining the principles of different machine learning techniques and their applicability in various real-world application domains, such as cybersecurity systems, smart cities, healthcare, e-commerce, agriculture, and many more. We also highlight the challenges and potential research directions based on our study. Overall, this paper aims to serve as a reference point for both academia and industry professionals as well as for decision-makers in various real-world situations and application areas, particularly from the technical point of view.

Data synthesis for crop variety evaluation. A review

Crop varieties should fulfill multiple requirements, including agronomic performance and product quality. Variety evaluations depend on data generated from field trials and sensory analyses, performed with different levels of participation from farmers and consumers. Such multi-faceted variety evaluation is expensive and time-consuming; hence, any use of these data should be optimized. Data synthesis can help to take advantage of existing and new data, combining data from different sources and combining it with expert knowledge to produce new information and understanding that supports decision-making. Data synthesis for crop variety evaluation can partly build on extant experiences and methods, but it also requires methodological innovation. We review the elements required to achieve data synthesis for crop variety evaluation, including (1) data types required for crop variety evaluation, (2) main challenges in data management and integration, (3) main global initiatives aiming to solve those challenges, (4) current statistical approaches to combine data for crop variety evaluation and (5) existing data synthesis methods used in evaluation of varieties to combine different datasets from multiple data sources. We conclude that currently available methods have the potential to overcome existing barriers to data synthesis and could set in motion a virtuous cycle that will encourage researchers to share data and collaborate on data-driven research.

To screen or not to screen: an interactive framework for comparing costs of mass malaria treatment interventions

BACKGROUND

Mass drug administration and mass-screen-and-treat interventions have been used to interrupt malaria transmission and reduce burden in sub-Saharan Africa. Determining which strategy will reduce costs is an important challenge for implementers; however, model-based simulations and field studies have yet to develop consensus guidelines. Moreover, there is often no way for decision-makers to directly interact with these data and/or models, incorporate local knowledge and expertise, and re-fit parameters to guide their specific goals.

METHODS

We propose a general framework for comparing costs associated with mass drug administrations and mass screen and treat based on the possible outcomes of each intervention and the costs associated with each outcome. We then used publicly available data from six countries in western Africa to develop spatial-explicit probabilistic models to estimate intervention costs based on baseline malaria prevalence, diagnostic performance, and sociodemographic factors (age and urbanicity). In addition to comparing specific scenarios, we also develop interactive web applications which allow managers to select data sources and model parameters, and directly input their own cost values.

RESULTS

The regional-level models revealed substantial spatial heterogeneity in malaria prevalence and diagnostic test sensitivity and specificity, indicating that a "one-size-fits-all" approach is unlikely to maximize resource allocation. For instance, urban communities in Burkina Faso typically had lower prevalence rates compared to rural communities (0.151 versus 0.383, respectively) as well as lower diagnostic sensitivity (0.699 versus 0.862, respectively); however, there was still substantial regional variation. Adjusting the cost associated with false negative diagnostic results to included additional costs, such as delayed treated and potential lost wages, undermined the overall costs associated with MSAT.

CONCLUSIONS

The observed spatial variability and dependence on specified cost values support not only the need for location-specific intervention approaches but also the need to move beyond standard modeling approaches and towards interactive tools which allow implementers to engage directly with data and models. We believe that the framework demonstrated in this article will help connect modeling efforts and stakeholders in order to promote data-driven decision-making for the effective management of malaria, as well as other diseases.

Juvenile Justice-Translational Research on Interventions for Adolescents in the Legal System (JJ-TRIALS): a cluster randomized trial targeting system-wide improvement in substance use services

Background

The purpose of this paper is to describe the Juvenile Justice—Translational Research on Interventions for Adolescents in the Legal System (JJ-TRIALS) study, a cooperative implementation science initiative involving the National Institute on Drug Abuse, six research centers, a coordinating center, and Juvenile Justice Partners representing seven US states. While the pooling of resources across centers enables a robust implementation study design involving 36 juvenile justice agencies and their behavioral health partner agencies, co-producing a study protocol that has potential to advance implementation science, meets the needs of all constituencies (funding agency, researchers, partners, study sites), and can be implemented with fidelity across the cooperative can be challenging. This paper describes (a) the study background and rationale, including the juvenile justice context and best practices for substance use disorders, (b) the selection and use of an implementation science framework to guide study design and inform selection of implementation components, and (c) the specific study design elements, including research questions, implementation interventions, measurement, and analytic plan.

Methods/design

The JJ-TRIALS primary study uses a head-to-head cluster randomized trial with a phased rollout to evaluate the differential effectiveness of two conditions (Core and Enhanced) in 36 sites located in seven states. A Core strategy for promoting change is compared to an Enhanced strategy that incorporates all core strategies plus active facilitation. Target outcomes include improvements in evidence-based screening, assessment, and linkage to substance use treatment.

Discussion

Contributions to implementation science are discussed as well as challenges associated with designing and deploying a complex, collaborative project.

Trial registration

NCT02672150.