How do economic and public finance statuses affect policy responses during a pandemic? - learning from the COVID-19 first wave.

BACKGROUND: In the time of a pandemic, it is typical for public health bodies to collaborate with epidemiologists to design health policies both at national and international levels for controlling the spread. A point largely overlooked in literature is the extent economic capability and public finance status can influence the policy responses of countries during a pandemic situation. This article fills this gap by considering 12 public health and 7 economic measures (i.e., policies) in 200 countries during the COVID-19 first wave, with countries grouped across income categories. METHODS: We apply statistical analysis, inclusive of regression models, to assess the impact of economic capability and public finance status on policy responses. Multiple open-access datasets are used in this research, and information from the hybrid sources are cumulated as samples. In our analysis, we consider variables including population characteristics (population size, density) and economic and public finance status (GDR, current account balance, government surplus/deficit) further to policy responses across public health and economic measures. Additionally, we consider infection rates across countries and the institution of the measures relative to infection rate. RESULTS: Results suggest that countries from all income groups have favoured public health measures like school closures and travel bans, and economic measures like influencing interest rates. However, strong economy countries have more adopted technological monitoring than low-income countries. Contrarily, low-income countries have preferred traditional measures like curfew and obligatory mask-wearing. GDP per capita was a statistically significant factor influencing the institution of both public health and economic measures. Government finance statuses like current account balance and surplus/deficit were also significant factors influencing economic measures. CONCLUSIONS: Overall, the research reveals that, further to biological characteristics, policymakers and epidemiologists can consider the economic and public finance contexts when suggesting health responses to a pandemic. This, in turn, calls for more international cooperation on economic terms further to public health terms.

Fast COVID-19 versus H1N1 screening using Optimized Parallel Inception.

COVID-19 and swine-origin influenza A (H1N1) are both pandemics that sparked significant concern worldwide. Since these two diseases have common symptoms, a fast COVID-19 versus H1N1 screening helps better manage patients at healthcare facilities. We present a novel deep model, called Optimized Parallel Inception, for fast screening of COVID-19 and H1N1 patients. We also present a Semi-supervised Generative Adversarial Network (SGAN) to address the problem related to the smaller size of the COVID-19 and H1N1 research data. To evaluate the proposed models, we have merged two separate COVID-19 and H1N1 data from different sources to build a new dataset. The created dataset includes 4,383 positive COVID-19 cases, 989 positive H1N1 cases, and 1,059 negative cases. We applied SGAN on this dataset to remove issues related to unequal class densities. The experimental results show that the proposed model's screening accuracy is 99.2% and 99.6% for COVID-19 and H1N1, respectively. According to our analysis, the most significant symptoms and underlying chronic diseases for COVID-19 versus H1N1 screening are dry cough, breathing problems, diabetes, and gastrointestinal.

How did socio-demographic status and personal attributes influence compliance to COVID-19 preventive behaviours during the early outbreak in Japan? Lessons for pandemic management.

This study focuses on how socio-demographic status and personal attributes influence self-protective behaviours during a pandemic, with protection behaviours being assessed through three perspectives - social distancing, personal protection behaviour and social responsibility awareness. The research considers a publicly available and recently collected dataset on Japanese citizens during the COVID-19 early outbreak and utilises a data analysis framework combining Classification and Regression Tree (CART), a data mining approach, and regression analysis to gain deep insights. The analysis reveals Socio-demographic attributes - sex, marital family status and having children - as having played an influential role in Japanese citizens' abiding by the COVID-19 protection behaviours. Especially women with children are noted as more conscious than their male counterparts. Work status also appears to have some impact concerning social distancing. Trust in government also appears as a significant factor. The analysis further identifies smoking behaviour as a factor characterising subjective prevention actions with non-smokers or less-frequent smokers being more compliant to the protection behaviours. Overall, the findings imply the need of public policy campaigning to account for variations in protection behaviour due to socio-demographic and personal attributes during pandemics and national emergencies.

TClustVID: A novel machine learning classification model to investigate topics and sentiment in COVID-19 tweets.

COVID-19, caused by SARS-CoV2 infection, varies greatly in its severity but presents with serious respiratory symptoms with vascular and other complications, particularly in older adults. The disease can be spread by both symptomatic and asymptomatic infected individuals. Uncertainty remains over key aspects of the virus infectiousness (particularly the newly emerging variants) and the disease has had severe economic impacts globally. For these reasons, COVID-19 is the subject of intense and widespread discussion on social media platforms including Facebook and Twitter. These public forums substantially influence public opinions and in some cases can exacerbate the widespread panic and misinformation spread during the crisis. Thus, this work aimed to design an intelligent clustering-based classification and topic extracting model named TClustVID that analyzes COVID-19-related public tweets to extract significant sentiments with high accuracy. We gathered COVID-19 Twitter datasets from the IEEE Dataport repository and employed a range of data preprocessing methods to clean the raw data, then applied tokenization and produced a word-to-index dictionary. Thereafter, different classifications were employed on these datasets which enabled the exploration of the performance of traditional classification and TClustVID. Our analysis found that TClustVID showed higher performance compared to traditional methodologies that are determined by clustering criteria. Finally, we extracted significant topics from the clusters, split them into positive, neutral and negative sentiments, and identified the most frequent topics using the proposed model. This approach is able to rapidly identify commonly prevailing aspects of public opinions and attitudes related to COVID-19 and infection prevention strategies spreading among different populations.

Spatiotemporal association patterns in a supergroup of Rwenzori black-and-white colobus (Colobus angolensis ruwenzorii) are consistent with a multilevel society.

Primates display broad diversity in their social organization. The social groups of a few primate species are organized in a multilevel fashion, with large groups composed of multiple, core one-male units (OMUs). A characteristic of multilevel societies is that the higher levels can include hundreds of individuals. The Rwenzori black-and-white colobus (Colobus angolensis ruwenzorii) in the montane forests of Rwanda form supergroups and have been suspected to exhibit multilevel social organization. Here we present the first data on the "anatomy" of a supergroup numbering 500+ individuals. We identified subgroups within the supergroup based on progression data, extracting the social network structure from the time-stamped spatiotemporal distribution of passing individuals identified to age-sex class, and selecting an optimal time window for each network using the two-step approach developed by Uddin, Choudhury, Farhad, and Rahman (2017). We detail the existence of core units-multi-male units (MMUs) with a mean of 1.7 adult males and 3.1 adult females, as well as OMUs, all-female units and bachelor units composed of adult and sub-adult males. More than two-thirds of units are MMUs. These grouping patterns conform to a multilevel society with predominantly multi-male core units, a social system that has recently also been described for a population of the same taxon in Uganda. Individual identification will be required to corroborate these interpretations.

A machine learning model to identify early stage symptoms of SARS-Cov-2 infected patients.

The recent outbreak of the respiratory ailment COVID-19 caused by novel coronavirus SARS-Cov2 is a severe and urgent global concern. In the absence of effective treatments, the main containment strategy is to reduce the contagion by the isolation of infected individuals; however, isolation of unaffected individuals is highly undesirable. To help make rapid decisions on treatment and isolation needs, it would be useful to determine which features presented by suspected infection cases are the best predictors of a positive diagnosis. This can be done by analyzing patient characteristics, case trajectory, comorbidities, symptoms, diagnosis, and outcomes. We developed a model that employed supervised machine learning algorithms to identify the presentation features predicting COVID-19 disease diagnoses with high accuracy. Features examined included details of the individuals concerned, e.g., age, gender, observation of fever, history of travel, and clinical details such as the severity of cough and incidence of lung infection. We implemented and applied several machine learning algorithms to our collected data and found that the XGBoost algorithm performed with the highest accuracy (>85%) to predict and select features that correctly indicate COVID-19 status for all age groups. Statistical analyses revealed that the most frequent and significant predictive symptoms are fever (41.1%), cough (30.3%), lung infection (13.1%) and runny nose (8.43%). While 54.4% of people examined did not develop any symptoms that could be used for diagnosis, our work indicates that for the remainder, our predictive model could significantly improve the prediction of COVID-19 status, including at early stages of infection.

Comparing different supervised machine learning algorithms for disease prediction.

BACKGROUND: Supervised machine learning algorithms have been a dominant method in the data mining field. Disease prediction using health data has recently shown a potential application area for these methods. This study ai7ms to identify the key trends among different types of supervised machine learning algorithms, and their performance and usage for disease risk prediction. METHODS: In this study, extensive research efforts were made to identify those studies that applied more than one supervised machine learning algorithm on single disease prediction. Two databases (i.e., Scopus and PubMed) were searched for different types of search items. Thus, we selected 48 articles in total for the comparison among variants supervised machine learning algorithms for disease prediction. RESULTS: We found that the Support Vector Machine (SVM) algorithm is applied most frequently (in 29 studies) followed by the Naïve Bayes algorithm (in 23 studies). However, the Random Forest (RF) algorithm showed superior accuracy comparatively. Of the 17 studies where it was applied, RF showed the highest accuracy in 9 of them, i.e., 53%. This was followed by SVM which topped in 41% of the studies it was considered. CONCLUSION: This study provides a wide overview of the relative performance of different variants of supervised machine learning algorithms for disease prediction. This important information of relative performance can be used to aid researchers in the selection of an appropriate supervised machine learning algorithm for their studies.

Policy content and stakeholder network analysis for infant and young child feeding in Nepal.

BACKGROUND: Despite concerted effort from government and partners, Nepal continues to have a high burden of under nutrition among children. Identifying opportunities to strengthen policy support for infant and young child feeding (IYCF) is a key component to improve child survival, growth and development. This study aims to explore policy support for IYCF and to identify the influential stakeholders for IYCF for effective future policy development and programmatic action. METHODS: Policies relevant to IYCF were identified through web searches and direct approaches to relevant government ministries. Policy content was analysed based on four key domains focussed on mothers, using a qualitative synthesis approach. Three group interviews were conducted using the participatory tool "Net-Map", to identify the influential stakeholders in IYCF policy and programming processes. RESULTS: Twenty-six relevant policy documents were analysed for content relating to IYCF. General support for IYCF was found in most of the development plans and high-level health sector policies. Most implementation level documents included support for provision of correct information to mothers. Capacity building of frontline workers for IYCN and system strengthening were well supported through sectoral plans and policies. However, gaps were identified regarding maternity protection, support for monitoring and evaluation, and translation of high-level policy directives into implementation level guidelines, resulting in a lack of clarity over roles and responsibilities. Both government and non-governmental stakeholders, particularly donors, emerged as influential drivers of IYCF policy decisions in Nepal, through technical assistance and funding. The Nutrition Technical Committee under the Ministry of Health, UNICEF, Suaahara, USAID and WHO were identified as key actors providing technical assistance. Key funding agencies were identified as UNICEF and USAID. CONCLUSIONS: This study reveals strong policy support for key dimensions of IYCF, supported by a highly networked stakeholder environment. Opportunities to further strengthen IYCF policy in Nepal include: further support for training of frontline workers and complementary feeding interventions; extending maternity leave provisions; and clarifying roles and responsibilities of actors, particularly non-governmental actors. Engaging technical and funding agencies and developing partnerships with other relevant actors will be crucial for ensuring effective policy translates into effective practice.

Analysis of stakeholders networks of infant and young child nutrition programmes in Sri Lanka, India, Nepal, Bangladesh and Pakistan.

BACKGROUND: Effective public policies are needed to support appropriate infant and young child feeding (IYCF) to ensure adequate child growth and development, especially in low and middle income countries. The aim of this study was to: (i) capture stakeholder networks in relation to funding and technical support for IYCF policy across five countries in South Asia (i.e. Sri Lanka, India, Nepal, Bangladesh and Pakistan); and (ii) understand how stakeholder networks differed between countries, and identify common actors and their patterns in network engagement across the region. METHODS: The Net-Map method, which is an interview-based mapping technique to visualise and capture connections among different stakeholders that collaborate towards achieving a focused goal, has been used to map funding and technical support networks in all study sites. Our study was conducted at the national level in Bangladesh, India, Nepal, and Sri Lanka, as well as in selected states or provinces in India and Pakistan during 2013-2014. We analysed the network data using a social network analysis software (NodeXL). RESULTS: The number of stakeholders identified as providing technical support was higher than the number of stakeholders providing funding support, across all study sites. India (New Delhi site - national level) site had the highest number of influential stakeholders for both funding (43) and technical support (86) activities. Among all nine study sites, India (New Delhi - national level) and Sri Lanka had the highest number of participating government stakeholders (22) in their respective funding networks. Sri Lanka also had the highest number of participating government stakeholders for technical support (34) among all the study sites. Government stakeholders are more engaged in technical support activities compared with their involvement in funding activities. The United Nations Children's Emergency Fund (UNICEF) and the World Health Organization (WHO) were highly engaged stakeholders for both funding and technical support activities across all study sites. CONCLUSION: International stakeholders were highly involved in both the funding and technical support activities related to IYCF practices across these nine study sites. Government stakeholders received more support for funding and technical support activities from other stakeholders compared with the support that they offered. Stakeholders were, in general, more engaged for technical support activities compared with the funding activities.

Overview of the infant and young child feeding policy environment in Pakistan: Federal, Sindh and Punjab context.

BACKGROUND: Appropriate infant and young child feeding (IYCF) practices have been identified as important for appropriate child growth and development. (Ministry of Planning and Development, Ministry of National Health Services, Regulations and Coordination (2012)) Children in Pakistan still experience high rates of malnutrition, indicating a likely need for stronger IYCF policy. The purpose of this study was to identify major stakeholders who shape the IYCF policy environment and analyze which policies protect, promote and support IYCF practices, either directly or indirectly. METHODS: This study was conducted at the federal level, and in the provinces of Sindh and Punjab. We identified policies relevant to IYCF using a matrix developed by the South Asian Infant Feeding Research Network (SAIFRN), designed to capture policies at a range of levels (strategic policy documents through to implementation guidelines) in sectors relevant to IYCF. We analyzed the content using predetermined themes focused on support for mothers, and used narrative synthesis to present our findings. For the stakeholder analysis, we conducted four Net-Map activities with 49 interviewees using the Net-Map methodology. We analyzed the quantitative data using Organizational Risk Analyzer ORA and used the qualitative data to elucidate further information regarding relationships between stakeholders. RESULTS: We identified 19 policy documents for analysis. Eleven of these were nutrition and/or IYCF focused and eight were broader policies with IYCF as a component. The majority lacked detail relevant to implementation, particularly in terms of: ownership of the policies by a specific government body; sustainability of programs/strategies (most are donor funded), multi-sectoral collaboration; and effective advocacy and behavior change communication. Data collected through four Net-Map activities showed that after devolution of health ministry, provincial health departments were the key actors in the government whereas UNICEF and WHO were the key donors who were also highly influential and supportive of the objective. CONCLUSION: This analysis identified opportunities to strengthen IYCF policy in Pakistan through increased clarity on roles and responsibilities, improved multisectoral collaboration, and strong and consistent training guidelines and schedules for community health workers. The current policy environment presents opportunities, despite limitations. Our Net-Map analysis indicated several key government and international stakeholders, who differed across Federal and Provincial study sites. The detailed information regarding stakeholder influence can be used to strengthen advocacy.

Policy content and stakeholder network analysis for infant and young child feeding in India.

BACKGROUND: Over the last decade, infant and young child feeding (IYCF) indicators in India have improved. However, poor IYCF practices are still apparent, associated with pervasive high rates of child under-nutrition. Interventions to improve IYCF need augmentation by appropriate policy support to consolidate gains. The aim of this study was to identify opportunities to strengthen and support IYCF policies through a policy content and stakeholder network analysis. METHODS: IYCF policies and guidelines were systematically mapped and coded using predetermined themes. Six 'net-map' group interviews were conducted for stakeholder analysis with data analyzed using ORA (organizational risk analyzer, copyright Carley, Carnegie Mellon University) software. The study was carried out at a national level and in the states of Maharashtra and unified Andhra Pradesh. RESULTS: Thirty relevant policy documents were identified. Support for IYCF was clearly apparent and was actioned within sectoral policies and strategic plans. We identified support for provision of information to mothers and caregivers in both sectoral and high-level/strategic policy documents. At a sectoral level, there was support for training health care workers and for enabling mothers to access IYCF. Opportunities to strengthen policy included expanding coverage and translating policy goals into implementation level documents. At the national level, Ministry of Women and Child Development [MoWCD], Ministry of Health and Family Welfare [MoHFW] and the Prime Minister's Nutrition Council [PMNC] were the most influential actors in providing technical support while MoHFW, MoWCD, and Bill Melinda Gates Foundation were the most influential actors in providing funding and were therefore influential stakeholders in shaping IYCF policies and programs. CONCLUSION: We identified a wide range of strengths in the IYCF policy environment in India and also opportunities for improvement. One key strength is the integration of IYCF policies into a range of agendas and guidelines related to health and child development service delivery at the national and state level. However, the lack of a specific national policy on IYCF means that there is no formal mechanism for review and monitoring implementation across sectors and jurisdictions. Another opportunity identified is the development of IYCF policy guidelines in emergencies and for tribal populations.

Policy content and stakeholder network analysis for infant and young child feeding in Bangladesh.

BACKGROUND: Appropriate infant and young child feeding (IYCF) practices are essential for nutrition of infants and young children. Bangladesh has one of the highest levels of malnutrition globally along with sub-optimal IYCF practices. A supportive policy environment is essential to ensure that effective IYCF interventions are scaled up. The objectives of our study were to assess the support for IYCF in the national policy environment through policy analysis and stakeholder analysis and in so doing identify opportunities to strengthen the policy environment. METHODS: We used a matrix developed by SAIFRN (the South Asian Infant Feeding Research Network) to systematically identify supportive national policies, plans and guidelines for IYCF. We adapted narrative synthesis and descriptive approaches to analyze policy content, based on four themes with a focus on support for mothers. We conducted three Net-Map interviews to identify stakeholders who influenced the policies and programs related to IYCF. RESULTS: We identified 19 national policy documents relevant to IYCF. Overall, there was good level of support for IYCF practices at policy level - particularly regarding general support for IYCF and provision of information to mothers - but these were not consistently supported at implementation level, particularly regarding specificity and population coverage. We identified gaps regarding the training of health workers, capacity building, the monitoring and targeting of vulnerable mothers and providing an enabling environment to mothers, specifically with respect to maternity leave for working women. Urban populations and providers outside the public sector remained uncovered by policy. Our stakeholder analysis identified government entities such as the National Nutrition Service, as the most influential in terms of both technical and funding support as they had the mandate for formulation and implementation of policies and national programs. Stakeholders from different sectors played important roles, demonstrating the salience of IYCF. CONCLUSIONS: Although there is strong supportive policy environment for IYCF, it is important that policies cover all populations. Our analysis indicated that opportunities to strengthen the policy environment include: expanding population coverage, increasing inter-sector coordination, improving translation of policy objectives to implementation-level documents, and the engagement of non-public sectors. In addition, we recommend explicit strategies to engage diverse stakeholders in the formulation and implementation of IYCF policies.

Policy and stakeholder analysis of infant and young child feeding programmes in Sri Lanka.

BACKGROUND: Infant and young child feeding practices (IYCF) play a critical role in growth and development of children. A favourable environment supported by appropriate policies and positive contributions from all stakeholders are prerequisites for achieving optimal IYCF practices. This study aimed to assess the IYCF-related policy environment and role of stakeholders in policy making in Sri Lanka, in order to identify opportunities to strengthen the policy environment to better support appropriate IYCF and reduce childhood malnutrition. METHODS: We mapped national level policy-related documents on IYCF, and conducted a stakeholder analysis of IYCF policy making. A matrix was designed to capture data from IYCF policy-related documents using a thematic approach. A narrative synthesis of data from different documents was conducted to achieve the first objective. We then conducted an analysis of technical and funding links of stakeholders who shape IYCF policies and programmes in Sri Lanka using the Net-Map technique, to achieve the second objective. A total of 35 respondents were purposively selected based on their knowledge on the topic, and individual interviews were conducted. RESULTS: Twenty four policies were identified that contained provisions in line with global recommendations for best-practice IYCF, marketing of breast milk substitutes, strengthening health and non-health systems, maternity benefits, inter-sectoral collaboration, capacity building, health education and supplementation. However, there is no separate, written policy on IYCF in Sri Lanka. Participants identified 56 actors involved in shaping IYCF policies and programmes through technical support, and 36 through funding support. The Government Health Sector was the most connected as well as influential, followed by development partners. Almost all actors in the networks were supportive for IYCF policies and programmes. CONCLUSIONS AND RECOMMENDATIONS: All evidence-based recommendations are covered in related policies. However, advocacy should be targeted towards strategic support for IYCF in high-level policy documents. The stakeholder analysis confirmed a network led by the government health sector. Enhancing the multi-sectoral commitments stressed in policy documents is an opportunity to strengthen IYCF policy process in Sri Lanka.

A framework for administrative claim data to explore healthcare coordination and collaboration.

Previous studies have documented the application of electronic health insurance claim data for health services research purposes. In addition to administrative and billing details of healthcare services, insurance data reveal important information regarding professional interactions and/or links that emerge among healthcare service providers through, for example, informal knowledge sharing. By using details of such professional interactions and social network analysis methods, the aim of the present study was to develop a research framework to explore health care coordination and collaboration. The proposed framework was used to analyse a patient-centric care coordination network and a physician collaboration network. The usefulness of this framework and its applications in exploring collaborative efforts of different healthcare professionals and service providers is discussed.

Confirming the statistically significant superiority of tree-based machine learning algorithms over their counterparts for tabular data.

Many individual studies in the literature observed the superiority of tree-based machine learning (ML) algorithms. However, the current body of literature lacks statistical validation of this superiority. This study addresses this gap by employing five ML algorithms on 200 open-access datasets from a wide range of research contexts to statistically confirm the superiority of tree-based ML algorithms over their counterparts. Specifically, it examines two tree-based ML (Decision tree and Random forest) and three non-tree-based ML (Support vector machine, Logistic regression and k-nearest neighbour) algorithms. Results from paired-sample t-tests show that both tree-based ML algorithms reveal better performance than each non-tree-based ML algorithm for the four ML performance measures (accuracy, precision, recall and F1 score) considered in this study, each at p<0.001 significance level. This performance superiority is consistent across both the model development and test phases. This study also used paired-sample t-tests for the subsets of the research datasets from disease prediction (66) and university-ranking (50) research contexts for further validation. The observed superiority of the tree-based ML algorithms remains valid for these subsets. Tree-based ML algorithms significantly outperformed non-tree-based algorithms for these two research contexts for all four performance measures. We discuss the research implications of these findings in detail in this article.

Dataset meta-level and statistical features affect machine learning performance.

What dataset features affect machine learning (ML) performance has primarily been unknown in the current literature. This study examines the impact of tabular datasets' different meta-level and statistical features on the performance of various ML algorithms. The three meta-level features this study considered are the dataset size, the number of attributes and the ratio between the positive (class 1) and negative (class 0) class instances. It considered four statistical features for each dataset: mean, standard deviation, skewness and kurtosis. After applying the required scaling, this study averaged (uniform and weighted) each dataset's different attributes to quantify its four statistical features. We analysed 200 open-access tabular datasets from the Kaggle (147) and UCI Machine Learning Repository (53) and developed ML classification models (through classification implementation and hyperparameter tuning) for each dataset. Then, this study developed multiple regression models to explore the impact of dataset features on ML performance. We found that kurtosis has a statistically significant negative effect on the accuracy of the three non-tree-based ML algorithms of the Support vector machine (SVM), Logistic regression (LR) and K-nearest neighbour (KNN) for their classical implementation with both uniform and weighted aggregations. This study observed similar findings in most cases for ML implementations through hyperparameter tuning, except for SVM with weighted aggregation. Meta-level and statistical features barely show any statistically significant impact on the accuracy of the two tree-based ML algorithms (Decision tree and Random forest), except for implementation through hyperparameter tuning for the weighted aggregation. When we excluded some datasets based on the imbalanced statistics and a significantly higher contribution of one attribute compared to others to the classification performance, we found a significant effect of the meta-level ratio feature and statistical mean and standard deviation features on SVM, LR and KNN accuracy in many cases. Our findings open a new research direction in understanding how dataset characteristics affect ML performance and will help researchers select appropriate ML algorithms for a possible optimal accuracy outcome.

A novel approach for assessing fairness in deployed machine learning algorithms.

Fairness in machine learning (ML) emerges as a critical concern as AI systems increasingly influence diverse aspects of society, from healthcare decisions to legal judgments. Many studies show evidence of unfair ML outcomes. However, the current body of literature lacks a statistically validated approach that can evaluate the fairness of a deployed ML algorithm against a dataset. A novel evaluation approach is introduced in this research based on k-fold cross-validation and statistical t-tests to assess the fairness of ML algorithms. This approach was exercised across five benchmark datasets using six classical ML algorithms. Considering four fair ML definitions guided by the current literature, our analysis showed that the same dataset generates a fair outcome for one ML algorithm but an unfair result for another. Such an observation reveals complex, context-dependent fairness issues in ML, complicated further by the varied operational mechanisms of the underlying ML models. Our proposed approach enables researchers to check whether deploying any ML algorithms against a protected attribute within datasets is fair. We also discuss the broader implications of the proposed approach, highlighting a notable variability in its fairness outcomes. Our discussion underscores the need for adaptable fairness definitions and the exploration of methods to enhance the fairness of ensemble approaches, aiming to advance fair ML practices and ensure equitable AI deployment across societal sectors.

An NLP-based novel approach for assessing national influence in clause dissemination across bilateral investment treaties.

International investment agreements (IIAs) promote foreign investment. However, they can undermine crucial health programs, creating a dilemma for governments between corporate and public health interests. For this reason, including clauses that safeguard health has become an essential practice in IIAs. According to the current literature, some countries have played a pivotal role in leading this inclusion, while others follow the former ones. However, the existing literature needs a unique approach that can quantify the influence strength of a country in disseminating clauses that explicitly mention health provisions to others. Following an NLP (Natural Language Processing)-based text similarity analysis of Bilateral Investment Treaties (BITs), this study proposes a metric, 'Influence' (INF), which provides insights into the role of different countries or regions in the propagation of IIA texts among BITs. We demonstrate a comprehensive application of this metric using a large agreement dataset. Our findings from this application corroborate the evidence in the current literature, supporting the validity of the proposed metric. According to the INF, Germany, Canada, and Brazil emerged as the most influential players in defensive, neutral, and offensive health mentions, respectively. These countries wield substantial bargaining power in international investment law and policy, and their innovative approaches to BITs set a path for others to follow. These countries provide crucial insights into the direction and sources of influence of international investment regulations to safeguard health. The proposed metric holds substantial usage for policymakers and investors. This can help them identify vital global countries in IIA text dissemination and create new policy guidelines to safeguard health while balancing economic development and public health protection. A software tool based on the proposed INF measure can be found at https://inftool.com/.

Road networks and socio-demographic factors to explore COVID-19 infection during its different waves.

The COVID-19 pandemic triggered an unprecedented level of restrictive measures globally. Most countries resorted to lockdowns at some point to buy the much-needed time for flattening the curve and scaling up vaccination and treatment capacity. Although lockdowns, social distancing and business closures generally slowed the case growth, there is a growing concern about these restrictions' social, economic and psychological impact, especially on the disadvantaged and poorer segments of society. While we are all in this together, these segments often take the heavier toll of the pandemic and face harsher restrictions or get blamed for community transmission. This study proposes a road-network-based networked approach to model mobility patterns between localities during lockdown stages. It utilises a panel regression method to analyse the effects of mobility in transmitting COVID-19 in an Australian context, together with a close look at a suburban population's characteristics like their age, income and education. Firstly, we attempt to model how the local road networks between the neighbouring suburbs (i.e., neighbourhood measure) and current infection count affect the case growth and how they differ between delta and omicron variants. We use a geographic information system, population and infection data to measure road connections, mobility and transmission probability across the suburbs. We then looked at three socio-demographic variables: age, education and income and explored how they moderate independent and dependent variables (infection rates and neighbourhood measures). The result shows strong model performance to predict infection rate based on neighbourhood road connection. However, apart from age in the delta variant context, the other variables (income and education level) do not seem to moderate the relationship between infection rate and neighbourhood measure. The results indicate that suburbs with a more socio-economically disadvantaged population do not necessarily contribute to more community transmission. The study findings could be potentially helpful for stakeholders in tailoring any health decision for future pandemics.

Evidence-based practice in traditional persian medicine (TPM): a stakeholder and social network analysis.

BACKGROUND: The utilization of complementary and alternative medicine (CAM) is experiencing a global surge, accompanied by the adoption of national CAM policies in numerous countries. Traditional Persian medicine (TPM) is highly used as CAM in Iran, and the ongoing scientific evaluation of its interventions and the implementation of evidence-based medicine (EBM) encounters various barriers. Therefore, comprehending the characteristics and interactions of stakeholders is pivotal in advancing EBM within TPM policies. In this study, we utilized both classical stakeholder analysis and social network analysis to identify key stakeholders and potential communication patterns, thereby promoting EBM in TPM policy-making. METHODS: A cross-sectional nationwide stakeholder analysis was conducted in 2023 using snowball sampling. The interviews were carried out using a customized version of the six building blocks of health. Data were collected through semi-structured interviews. Stakeholders were assessed based on five factors (power, interest, influence, position, and competency). The connections and structure of the network were analyzed using degree, betweenness, closeness centrality, and modularity index to detect clusters of smaller networks. RESULTS: Among twenty-three identified stakeholders, the Ministry of Health and Medical Education (MOHME) and the Public were the most powerful and influential. The Iranian Academy of Medical Sciences was the most competent stakeholder. Social network analysis revealed a low density of connections among stakeholders. Pharmaceutical companies were identified as key connectors in the network, while the Public, supreme governmental bodies, and guilds acted as gatekeepers or brokers. The MOHME and Maraji were found to be high-ranking stakeholders based on four different centrality measures. CONCLUSION: This study identifies powerful stakeholders in the network and emphasizes the need to engage uninterested yet significant stakeholders. Recommendations include improving competence through education, strengthening international relations, and fostering stronger relationships. Engaging key connectors and gatekeepers is essential for bridging gaps in the network.