Empirical Data Research Articles

Community preparedness for earthquake disasters: A preliminary assessment of awareness and disaster infrastructure response in Cianjur, West Java-Indonesia

Background The danger of earthquakes poses a serious threat to people worldwide. One of the most significant challenges is preparing communities to cope effectively with this disaster. Therefore, understanding earthquake hazards is critically important for preparedness, mitigation, and an effective response to this threat. This report aims to observe and conduct a preliminary assessment of the degree to which community preparedness for earthquake disasters has been implemented. Methods Empirical data were obtained from survey respondents and interviews. The respondents were members of a community affected by the Cianjur earthquake, which occurred on November 21, 2022. The data were analysed using the mean range approach, based on Likert scales. Additionally, the Spearman correlation method was employed to indicate the relationship between community awareness and infrastructure readiness. Result Based on empirical evidence and preliminary analysis, it is evident that the preparedness of the community to respond effectively to earthquake catastrophes is inadequate. An apparent lack of readiness is observed in the inadequate construction of housing that fails to meet disaster standards, and the absence of disaster response facilities is notable. Conclusions Based on our initial assumption, it appears that knowledge related to disaster resilience in this area has not been adequately disseminated or socialized. However, this premise requires further investigation.

Suicidal Ideation and Behaviors Among LGBTQ+ Adolescents and Young Adults Who Have Experienced Sexual Violence: A Scoping Review of the Literature.

The relationship between sexual violence (SV) experiences and suicidal ideation (SI) is known. However, when applied to lesbian, gay, bisexual, transgender, queer, and more (LGBTQ+) populations, the impact that experiences with SV have on the severity and magnitude of SI continues to be explored. A scoping review of the literature was conducted to summarize the current literature related to SI experienced by LGBTQ+ adolescents and young adults (AYAs) who have experienced SV. Studies were found by searching electronic databases. To be included in the review, the study must have (a) been written in the English language, (b) been conducted in the United States, (c) presented empirical data, (d) been exclusively focused on LGBTQ+ AYAs, (e) focused on experiences with SV or have analyses separate from other types of violence, and (f) investigated suicidality as an outcome. All relevant studies published to date were included. Forty-one articles were retrieved for full-text review, of which five were determined to meet eligibility. LGBTQ+ AYAs were significantly associated with increased rates of SI compared with their cisgender heterosexual peers. LGBTQ+ AYAs were also associated with higher rates of SV victimization, ranging from intimate partner violence to previous child sexual abuse. Higher rates of depression were also associated with the population studied in each included article. The relationship between SV and SI in this population is not well studied, as highlighted through this completed review. Targeting this knowledge gap through future research can lead to intervention development for this population niche.

Analysis of The Use of Problem-Based Learning Model in Improving Learning Outcomes of Hindu Religious Education in Grade V Students of UPT SD Negeri 6 Arawa Sidrap

The learning process does not teach students to work together in groups, resulting in less active learning. Students also lack the critical thinking skills required to solve problems. This issue arises due to teachers' lack of knowledge and the absence of innovative learning models. Consequently, it leads to low student learning outcomes, necessitating research to examine this matter. The objective of this study is to analyze the implementation of a problem-based learning model in improving the learning outcomes of Hindu religious education in grade V students of UPT SD Negeri 6 Arawa, Sidrap Regency. The research approach employed is qualitative research with the type of library research. Data sources include books, scientific journals, magazines, newspapers, and other relevant information. The informants were selected based on their relevance to the topic under study. Research instruments comprised books, scientific journals, and other relevant documents. The data collection technique employed was documentation study, while qualitative content analysis was used for data analysis. The findings indicate that the problem-based learning model is an appropriate choice for teachers who wish to develop students' analytical abilities, enable them to apply existing knowledge in new situations, and encourage independent and responsible problem-solving skills. This model enhances students' critical, analytical, systematic, and logical thinking abilities, enabling them to find alternative solutions to problems through empirical data exploration, ultimately fostering a scientific attitude. In conclusion, the use of problem-based learning models can improve learning outcomes in Hindu religious education in grade V students of UPT SD Negeri 6 Arawa Sidrap.

Enlightening the shadow dimensions of part‐time entrepreneurship: Navigating fear of failure and enhancing social status

AbstractPart‐time entrepreneurs—individuals acting simultaneously as entrepreneurs and employees—are often considered to be in a transitional stage towards becoming full‐time entrepreneurs. However, they can also exit a venture or remain hybrid entrepreneurs. Based on this evidence, we explore the influence of social norms (social status and shame of failing), the desire to create a company, entrepreneurial motivation, the need for achievement, risk propensity, and indirect shame on the entrepreneurial intention of part‐time entrepreneurs. A questionnaire was administered to 304 part‐time entrepreneurs residing in Brazil. The results of partial least squares structural equation modeling (PLS‐SEM) have shown that social status and entrepreneurial motivation positively influence the entrepreneurial intention of hybrid entrepreneurs, while the shame of failing has a negative effect on this dimension. We also found that the desire to create a company has a positive impact on entrepreneurial intention but negatively moderates the relationship between social status and entrepreneurial intention, that is, the direct relationship becomes weaker as the desire to create a company increases. Accordingly, this study provides evidence on the main drivers of entrepreneurial intention by focusing on the specific case of part‐time entrepreneurs. The uniqueness of this study, therefore, lies in its valuable contribution to empirical knowledge about hybrid entrepreneurship, a category often underestimated in research dedicated to the field of entrepreneurship.

Artificial neural network hyperparameters optimization for predicting the thermal conductivity of MXene/graphene nanofluids

BackgroundThe critical role of thermal conductivity (TC) as a significant thermo-physical property in MXene/graphene-based nanofluids for photovoltaic/thermal systems has motivated recent research into developing precision predictive models. The multilayer perceptron neural network (MLPNN) has emerged as an eminent AI algorithm for this task. MethodsThis study employs Bayesian optimization, random search (RS), and grid search (GS) to fine-tune MLPNN hyperparameters—hidden layers, neurons, activation functions, standardization, and regularization—to elevate TC modeling efficiency. The proposed methodology unfolds in sequential phases: data analysis, data pre-processing, and introduction of MLPNN, GS, RS, Bayesian approach, and their integration algorithm. The next phase entails developing predictive models and presenting optimal cases. Lastly, the final models undergo statistical evaluation and graphical comparison for a thorough analysis. FindingsResults manifest that the GS-MLPNN model excels, achieving the lowest testing data error (MAPE = 0.5261%) and high conformity with empirical data (R = 0.99941). Meanwhile, the RS method adjusts hyperparameters with negligible precision loss (MAPE = 0.6046%, R = 0.99887). Contrarily, Bayesian optimization lags, increasing errors (MAPE = 3.1981%) and lower correlation (R = 0.98099), suggesting its relative inefficacy for this specific application. The optimized models provide efficient predictions, significantly reducing the financial/computing costs associated with experimental/numerical analysis.

LEGAL LIABILITY OF A PHYSICIAN FOR PROVIDING INADEQUATE MEDICAL CARE TO A PATIENT: ANALYSIS OF APPROACHES BASED ON THE EXAMPLES OF KAZAKHSTAN AND THE UNITED STATES

Background: This research focuses on the determination of liability for medical professionals causing harm to patients, using the criminal legislation of the Republic of Kazakhstan as a foundation. Criminal liability for medical offences is stipulated in Chapter 12 of the Criminal Code. By identifying the mandatory characteristics or elements of a medical criminal offence according to the criminal legislation of Kazakhstan, parallels are drawn with the types of culpability provided for in developed countries worldwide. The authors reviewed scholarly works examining the effectiveness of handling cases involving harm to patients and decisions regarding the satisfaction or dismissal of the patient's claims in Kazakhstan. Attention has been given to empirical data collected within the territory of the Republic of Kazakhstan. The results of sociological research conducted by the authors over a period of 3 months among healthcare professionals from different regions of the country have been utilised. Special attention has been devoted to international experiences in implementing measures to improve patient safety, reducing citizen complaints regarding the quality of healthcare services, and enhancing the legal protection of medical personnel. The research selects provisions from scholarly works that reduce the risk of harm to patients and thereby contribute to reducing medical crime levels. Methods: In this research, the authors employed a number of methods of scientific research to achieve their goals and solve their tasks, in particular legal analysis, comparative legal analysis, survey, questionnaire, and interviewing. Legal analysis of the Criminal Legislation of the Republic of Kazakhstan, including Chapter 12 of the Criminal Code, was conducted to identify the specifics of criminal liability for medical offences, exemplified by Article 317. This analysis highlighted the nuances of criminal liability for medical offences in Kazakhstan. Comparative legal analysis made it possible to compare the responsibilities of doctors in the USA and Kazakhstan. Attention was drawn to the similarity of the concepts of guilt in the form of negligence, with a specific emphasis on the American approach, which offers valuable insights for Kazakhstan. These aspects could be adapted to improve Kazakhstan's legal system. The specific cases of harm to patients considered by the courts of the Republic of Kazakhstan were studied, and court decisions concerning the satisfaction of patients' claims and their rejection were analysed, which allowed the authors to identify the main arguments and trends in judicial practice. Surveys and questionnaires were conducted among medical workers from various regions of Kazakhstan to gather empirical data on their perceptions of duties and responsibilities. Additionally, in-depth interviews were also conducted with experts in the field of medicine and law, as well as patients, and representatives of health authorities, providing high-quality data on the problems and challenges faced by medical workers. Statistical data collected during sociological research were processed and analysed. This included data on citizen complaints about the quality of medical care, cases of harm to patients and other relevant statistical indicators. The study of the problem at various levels revealed the level of patient safety and legal protection of medical personnel. Results and Conclusion: Creating conditions for medicine and ensuring effective social and professional medical insurance are some factors that provide opportunities for medical practice as a whole and the healthcare system. These facts also facilitate a proper legal assessment of a doctor's performance

Robust optimization approaches in inventory management: Part B - the comparative study

This comparative study, constituting Part B of our extensive investigation into Robust Optimization (RO) in inventory management, builds on the foundational insights from Part A’s survey. It conducts a thorough analysis of various RO formulations and algorithms, emphasizing their practical application, efficacy, and computational considerations in inventory management contexts. This study is meticulously structured to address the pivotal inquiries identified in Part A, encompassing the effective representation of uncertainty, the selection of optimal decision criteria, the influence of decision rules on inventory management performance, computational challenges, and the adaptability of these methods to evolving technological and market conditions. This research juxtaposes theoretical findings with empirical data, offering a comprehensive evaluation of the strengths, limitations, and practical implications of each robust inventory model discussed in the literature. This investigation not only complements the survey in Part A but also serves as a standalone, in-depth contribution to robust inventory management.

Impact of product market competition on the overconfidence cash holdings relationship in Chinese firms

Traditional Confucian and hierarchical cultures in China often lead managers to become overconfident and hold more cash, which negatively impacts enterprise development. Therefore, in China, the mitigation of excess cash holdings among overconfident managers is worthy of further research. This study examines the effects of manager overconfidence on corporate cash holdings using data from 922 Chinese listed companies and totals 6849 observations. This study is based on a quantitative analysis approach using the Fixed Effects Model and Generalised Method of Moments. The empirical data indicate that manager overconfidence is positively associated with cash holdings. Furthermore, product market competition mitigates the direct correlation between managerial overconfidence and cash holdings. Finally, the impact was particularly noticeable for small and non-state-owned enterprises. This study draws on China's Confucian and hierarchical cultures to explain why overconfident managers tend to hold more cash and offers a different perspective on how product market competition affects the abovementioned relationship. This research enhances the understanding of managerial overconfidence and its economic repercussions and also contributes to the effect of product market competition on the corporate governance of Chinese listed companies.

Workplace support for physicians during the COVID-19 Pandemic: Did it affect burnout?

BackgroundA concern before 2020, physician burnout worsened during the COVID-19 pandemic. Little empirical data are available on pandemic workplace support interventions or their influence on burnout. We surveyed a national sample of frontline physicians on burnout and workplace support during the pandemic.MethodsWe surveyed a stratified random sample of 12,833 US physicians most likely to care for adult COVID-19 patients from the comprehensive AMA Physician Professional Data ™ file. The sample included 6722 primary care physicians (3331 family physicians, 3391 internists), 880 hospitalists, 1783 critical care physicians (894 critical care physicians, 889 pulmonary intensivists), 2548 emergency medicine physicians, and 900 infectious disease physicians. The emailed survey elicited physicians’ perceptions of organizational interventions to provide workplace support and/or to address burnout. Burnout was assessed with the Professional Fulfillment Index Burnout Composite scale (PFI-BC). Proportional specialty representation and response bias were addressed by survey weighting. Logistic regression assessed the association of physician characteristics and workplace interventions with burnout.ResultsAfter weighting, respondents were representative of the total sample. Overall physician burnout was 45.4%, significantly higher than in our previous survey. Open-ended responses mentioned that staffing shortages (physician, nursing, and other staff) combined with the increased volume, complexity, and acuity of patients during the pandemic increased job demands. The most frequent workplace support interventions were direct pandemic control measures (increased access to personal protective equipment, 70.0%); improved telehealth functionality (43.4%); and individual resiliency tools (yoga, meditation, 30.7%). Respondents placed highest priority on workplace interventions to increase financial support and increase nursing and clinician staffing. Factors significantly associated with lower odds of burnout were practicing critical care (compared with emergency medicine) OR 0.33 (95% CI 0.12 – 0.93), improved telehealth functionality OR 0.47 (95% CI 0.23 – 0.97) and being in practice for 11 years or longer OR 0.44 (95% CI 0.19–0.99).ConclusionsBurnout across frontline specialties increased during the pandemic. Physician respondents focused on inadequate staffing in the context of caring for more and sicker patients, combined with the lack of administrative efforts to mitigate problems. Burnout mitigation requires system-level interventions beyond individual-focused stress reduction programs to improve staffing, increase compensation, and build effective teams.

Satisfaction and sustainability concerns in whale-watching tourism: A user-generated content model

This study examines the satisfaction and sustainability concerns of whale-watching tourists by analysing user-generated content (UGC) on social media. A satisfaction model was developed and estimated utilising an ordered probit analysis with UGC data from TripAdvisor over the last 13 years that includes a specific whale-watching lexicon. The model addresses most of the physical, human, environmental, experiential, and operational aspects of the activity, including consumers’ feelings and sustainability concerns. The significance of the variables in the model was proven with the available empirical data. The findings provide a comprehensive description of the underpinnings of whale watchers’ preferences and concerns. The evidence reveals compelling social trends towards higher sustainability concerns influencing satisfaction, providing valuable information for the industry and its decision-makers for understanding preferences for sustainability in whale-watching tourism.

When is lethal deceptive pollination maintained? A population dynamics approach.

Not all plant-pollinator interactions are mutualistic, and in fact, deceptive pollination systems are widespread in nature. The genus Arisaema has a pollination system known as lethal deceptive pollination, in which plants not only attract pollinating insects without providing any rewards, but also trap them until they die. Many Arisaema species are endangered from various disturbances including reduction in forest habitat, modification of the forest understory owing to increasing deer abundance, and plant theft for horticultural cultivation. We aimed to theoretically investigate how lethal deceptive pollination can be maintained from a demographic perspective and how plant and pollinator populations respond to different types of disturbance. We developed and analysed a mathematical model to describe the population dynamics of a deceptive plant species and its victim pollinator. Calibrating the model based on empirical data, we assessed the conditions under which plants and pollinators could coexist, while manipulating relevant key parameters. The model exhibited qualitatively distinct behaviours depending on certain parameters. The plant becomes extinct when it has a low capability for vegetative reproduction and slow transition from male to female, and plant-insect co-extinction occurs especially when the plant is highly attractive to male insects. Increasing deer abundance has both positive and negative effects because of removal of other competitive plants and diminishing pollinators, respectively. Theft for horticultural cultivation can readily threaten plants whether male or female plants are frequently collected. The impact of forest habitat reduction may be limited compared to that of other disturbance types. Our results have emphasised that the demographic vulnerability of lethal deceptive pollination systems would differ qualitatively from that of general mutualistic pollination systems. It is therefore important to consider the demographics of both victim pollinators and deceptive plants to estimate how endangered Arisaema populations respond to various disturbances.

Dynamic mean-variance portfolio selection under factor models

Utilizing insights from financial literature and empirical financial data, we introduce a comprehensive system of factor models designed to capture both return and risk dynamics. Our focus extends to addressing the multi-period mean-variance portfolio selection challenge within the framework of these proposed factor models. Through rigorous analysis, we formulate a semi-analytical optimal portfolio policy, characterized by a linear relationship with the current wealth level. The coefficients of this optimal policy are intricately linked to a specific stochastic process known as the future investment opportunity (FIO), reflecting the investor's anticipation of future investment prospects. Furthermore, empirical examination within the U.S. market context underscores the efficacy of our approach. By incorporating the factor models for return and risk, our optimal portfolio policy exhibits superior out-of-sample Sharpe ratio compared to benchmark policies.

Harnessing the power of AI and IoT for real-time CO2 emission monitoring

Global CO2 emissions have been an essential topic of the environmental discussion. Still, empirical data is needed to support arguments that high-quality government actions could reduce these emissions. By analyzing data from 137 nations from 2000 to 2020, we offer strong evidence that state policies focused on promoting healthy ecosystems, sustainable economic growth, and transcendent legislative changes are capable of decreasing CO2 emissions. Based on our findings, there are essentially three critical institutional factors that need to be improved for environmental policies to be efficient: the concept of law, which protects citizens' intellectual property rights; citizens' speech, which allows them to participate in elections and represent themselves freely, and the management of corruption. Policies aimed at promoting economic growth, lowering oil and gas use, enhancing the usage of green energy by the public and private sectors, and enhancing such institutional factors are all necessary components of a climate-friendly financial strategy.

A Future Beyond the Impasse? Exploring Post-Conflict Religious Heritage

ABSTRACT With the alarming rise in intercommunal conflicts worldwide, knowledge regarding post-conflict cultural heritage issues must advance to help formulate effective management systems and policies. Through an Actor-Network Theory-inspired approach, this paper explores the actors’ role in protecting religious heritage sites abandoned by displaced communities. Discourse analysis of relevant literature and empirical data from exhaustive fieldwork documenting and categorising the use-status and preservation state of church sites from Northern Cyprus has revealed multiple networks of human and non-human actors and actants. Through ANT concepts of fact-building and translation, a flat platform has been developed showing the positions and interests of the conflicting parties with a focus on the neglected or underestimated dimensions of heritage protection. This platform allows heritage conservation to be viewed from a broader perspective and, in a sense, helps dilute the conflicting parties’ positions and make their stakes less critical. It also emphasises the importance of compromise solutions, including pragmatically negotiating potential alternative uses and actively integrating the local community with the stakeholder group to protect the heritage of the displaced communities.

Empirical Data from Organizations in Chinses Green Industrial Zones on Institutional Constraints, Ecological Logistical Management, and Circular Economic Resources

Empirical Data from Organizations in Chinses Green Industrial Zones on Institutional Constraints, Ecological Logistical Management, and Circular Economic Resources

Phase-field approach for fracture prediction of brittle cracked components

The versatility of the phase-field method (PFM) in predicting elusive fracture trajectories has attracted researchers in recent years; however, limited focus has been directed toward fracture load prediction for brittle materials. This study presents a computationally low-cost and straightforward framework based on phase-field modeling to predict the fracture loads and fracture initiantion angles of brittle cracked components under in-plane loading conditions. The framework was assessed through a comprehensive comparison between numerical and experimental data for various specimens and test configurations. Despite using 1D analytical formulations for calculating phase-field parameters, great accordance between empirical data and simulation results demonstrated the effectiveness of the proposed model. A technique that restricts the computation of the phase-field variable merely around the crack tip was applied to significantly reduce the computational costs of PFM simulations. Furthermore, we examined different numerical aspects and confirmed the robustness of the proposed procedure.

Experimental evaluation of interactive Edge/Cloud Virtual Reality gaming over Wi-Fi using unity render streaming

Virtual Reality (VR) streaming enables end-users to seamlessly immerse themselves in interactive virtual environments using even low-end devices. However, the quality of the VR experience heavily relies on Wireless Fidelity (Wi-Fi) performance, since it serves as the last hop in the network chain. Our study delves into the intricate interplay between Wi-Fi and VR traffic, drawing upon empirical data and leveraging a Wi-Fi simulator. In this work, we further evaluate Wi-Fi’s suitability for VR streaming in terms of the Quality of Service (QoS) it provides. In particular, we employ Unity Render Streaming to remotely stream real-time VR gaming content over Wi-Fi 6 using Web Real-Time Communication (WebRTC), considering a server physically located at the network’s edge, near the end user. Our findings demonstrate the system’s sustained network performance, showcasing minimal round-trip time (RTT) and jitter at 60 and 90 frames per second (fps). In addition, we uncover the characteristics and patterns of the generated traffic streams, unveiling a distinctive video transmission approach inherent to WebRTC-based services: the systematic packetization of video frames (VFs) and their transmission in discrete batches at regular intervals, regardless of the targeted frame rate. This interval-based transmission strategy maintains consistent video packet delays across video frame rates but leads to increased Wi-Fi airtime consumption. Our results demonstrate that shortening the interval between batches is advantageous, as it enhances Wi-Fi efficiency and reduces delays in delivering complete frames.

Negative symptoms in treatment-resistant schizophrenia and its relationship with functioning

BackgroundRecent operational criteria for treatment-resistant schizophrenia (TRS) recognized positive and negative symptoms. TRS patients may have heterogeneity in negative symptoms, but empirical data were lacking. We aimed to characterize TRS patients based on negative symptoms using cluster analysis, and to examine between-cluster differences in social functioning. MethodsWe administered the Clinical Assessment Interview of Negative symptoms (CAINS), Brief Negative Symptom Scale (BNSS), the Positive and Negative Syndrome Scale (PANSS) and the Social and Occupational Functional Assessment (SOFAS to 126 TRS outpatients. All patients also completed the Temporal Experience of Pleasure Scale (TEPS), the Emotion Expressivity Scale (EES), and the Social Functional Scale (SFS). A two-stage hierarchical cluster analysis was performed with the CAINS, TEPS and EES as clustering variables. We validated the clusters using ANOVAs to compare group differences in the BNSS, PANSS, SOFAS and SFS. ResultsClustering indices supported a 3-cluster solution. Clusters 1 (n = 46) and 3 (n = 16) exhibited higher CAINS scores than Cluster 2 (n = 64), and were negative-symptom TRS subtypes. Cluster 1 reported lower TEPS than Cluster 3; but Cluster 3 reported lower EES than Cluster 1. Upon validation, Clusters 1 and 3 exhibited higher BNSS scores than Cluster 2, but only Cluster 1 exhibited lower SOFAS and higher PANSS general symptoms than Cluster 2. Both Clusters 1 and 3 had higher self-report functioning than Cluster 2. ConclusionWe provided evidence for heterogeneity of negative symptoms in TRS. Negative symptoms can characterize TRS patients and predict functional outcome.

Screening and Diagnostic Mammography During Pregnancy and Lactation: A Systematic Review of the Literature.

In recent years, the age of childbearing has been increasing in Western countries, and consequently the need to conduct mammography during pregnancy and lactation is also increasing. The aim of the present study was to systematically review the existing evidence regarding the overall use of mammographyduring pregnancy and lactation. A systematic review of the literature was conducted in PubMed, Epistemonikos, and clinicaltrials.gov, by using the search terms "pregnancy" AND "mammography", and "lactation" AND "mammography". The review protocol was prospectively registered in PROSPERO (CRD42024543971). Initially, 1,038 articles were identified; the titles and abstracts of 441 studies were screened; 40 studies were retrieved; after assessment of full texts, 20 studies were included for data extraction and further analysis. All 20 studies were retrospective; 14 studies included women with pregnancy-associated breast cancer, five studies included women with breast symptoms during pregnancy and/or lactation and one study included young breast cancer patients under age 40. Overall, 420 diagnostic and one incidental screening mammography examinations were performed during pregnancy and/or lactation with a 78.6% cumulative detection rate of breast cancer. The role of mammography was confounded by the use of breast ultrasound in most studies. In conclusion, the use of mammography during pregnancy and lactation is based on empirical data from retrospective studies, not directly addressing this issue. Hence, well-designed, focused, prospective clinical studies are needed in order to improve existing evidence regarding the use of diagnostic and screening mammography during pregnancy and lactation.

Inferring the extinction risk of marine fish to inform global conservation priorities.

While extinction risk categorization is fundamental for building robust conservation planning for marine fishes, empirical data on occurrence and vulnerability to disturbances are still lacking for most marine teleost fish species, preventing the assessment of their International Union for the Conservation of Nature (IUCN) status. In this article, we predicted the IUCN status of marine fishes based on two machine learning algorithms, trained with available species occurrences, biological traits, taxonomy, and human uses. We found that extinction risk for marine fish species is higher than initially estimated by the IUCN, increasing from 2.5% to 12.7%. Species predicted as Threatened were mainly characterized by a small geographic range, a relatively large body size, and a low growth rate. Hotspots of predicted Threatened species peaked mainly in the South China Sea, the Philippine Sea, the Celebes Sea, the west coast Australia and North America. We also explored the consequences of including these predicted species' IUCN status in the prioritization of marine protected areas through conservation planning. We found a marked increase in prioritization ranks for subpolar and polar regions despite their low species richness. We suggest to integrate multifactorial ensemble learning to assess species extinction risk and offer a more complete view of endangered taxonomic groups to ultimately reach global conservation targets like the extending coverage of protected areas where species are the most vulnerable.