What is your definition of Big Data? Researchers' understanding of the phenomenon of the decade

Imputation methods for mixed datasets in bioarchaeology

Missing data is a prevalent problem in bioarchaeological research and imputation could provide a promising solution. This work simulated missingness on a control dataset (481 samples × 41 variables) in order to explore imputation methods for mixed data (qualitative and quantitative data). The tested methods included Random Forest (RF), PCA/MCA, factorial analysis for mixed data (FAMD), hotdeck, predictive mean matching (PMM), random samples from observed values (RSOV), and a multi-method (MM) approach for the three missingness mechanisms (MCAR, MAR, and MNAR) at levels of 5%, 10%, 20%, 30%, and 40% missingness. This study also compared single imputation with an adapted multiple imputation method derived from the R package "mice". The results showed that the adapted multiple imputation technique always outperformed single imputation for the same method. The best performing methods were most often RF and MM, and other commonly successful methods were PCA/MCA and PMM multiple imputation. Across all criteria, the amount of missingness was the most important parameter for imputation accuracy. While this study found that some imputation methods performed better than others for the control dataset, each imputation method has advantages and disadvantages. Imputation remains a promising solution for datasets containing missingness; however when making a decision it is essential to consider dataset structure and research goals.

Supplementary Information

The online version contains supplementary material available at 10.1007/s12520-024-02078-2.

Electrical neuromodulation for the treatment of chronic pain: derivation of the intrinsic barriers, outcomes and considerations of the sustainability of implantable spinal cord stimulation therapies

INTRODUCTION

For over 60 years, spinal cord stimulation has endured as a therapy through innovation and novel developments. Current practice of neuromodulation requires proper patient selection, risk mitigation and use of innovation. However, there are tangible and intangible challenges in physiology, clinical science and within society.

AREAS COVERED

We provide a narrative discussion regarding novel topics in the field especially over the last decade. We highlight the challenges in the patient care setting including selection, as well as economic and socioeconomic challenges. Physician training challenges in neuromodulation is explored as well as other factors related to the use of neuromodulation such as novel indications and economics. We also discuss the concepts of technology and healthcare data.

EXPERT OPINION

Patient safety and durable outcomes are the mainstay goal for neuromodulation. Substantial work is needed to assimilate data for larger and more relevant studies reflecting a population. Big data and global interconnectivity efforts provide substantial opportunity to reinvent our scientific approach, data analysis and its management to maximize outcomes and minimize risk. As improvements in data analysis become the standard of innovation and physician training meets demand, we expect to see an expansion of novel indications and its use in broader cohorts.

Liquid biopsy, big data and artificial intelligence as a new global clinical trial model in targeted therapy

To this day, the phase III trial continues to be, as it was more than 60 years ago, the standard for the incorporation of new treatments in oncology. We currently have new tools such as NGS, Liquid Biopsy (LB), Big Data (BD) and Artificial Intelligence (AI) that will allow us to move towards faster and more universal research. This article analyzes the important weaknesses of phase III trials, the importance and current status of targeted therapy, and the contributions to LB decision-making and the knowledge of what happens in real life (RWD) that we facilitates BD and AI. Finally, what could be a clinical trial model that would take advantage of all these tools is proposed.

Tweeting for Health Using Real-time Mining and Artificial Intelligence-Based Analytics: Design and Development of a Big Data Ecosystem for Detecting and Analyzing Misinformation on Twitter

BACKGROUND

Digital misinformation, primarily on social media, has led to harmful and costly beliefs in the general population. Notably, these beliefs have resulted in public health crises to the detriment of governments worldwide and their citizens. However, public health officials need access to a comprehensive system capable of mining and analyzing large volumes of social media data in real time.

OBJECTIVE

This study aimed to design and develop a big data pipeline and ecosystem (UbiLab Misinformation Analysis System [U-MAS]) to identify and analyze false or misleading information disseminated via social media on a certain topic or set of related topics.

METHODS

U-MAS is a platform-independent ecosystem developed in Python that leverages the Twitter V2 application programming interface and the Elastic Stack. The U-MAS expert system has 5 major components: data extraction framework, latent Dirichlet allocation (LDA) topic model, sentiment analyzer, misinformation classification model, and Elastic Cloud deployment (indexing of data and visualizations). The data extraction framework queries the data through the Twitter V2 application programming interface, with queries identified by public health experts. The LDA topic model, sentiment analyzer, and misinformation classification model are independently trained using a small, expert-validated subset of the extracted data. These models are then incorporated into U-MAS to analyze and classify the remaining data. Finally, the analyzed data are loaded into an index in the Elastic Cloud deployment and can then be presented on dashboards with advanced visualizations and analytics pertinent to infodemiology and infoveillance analysis.

RESULTS

U-MAS performed efficiently and accurately. Independent investigators have successfully used the system to extract significant insights into a fluoride-related health misinformation use case (2016 to 2021). The system is currently used for a vaccine hesitancy use case (2007 to 2022) and a heat wave-related illnesses use case (2011 to 2022). Each component in the system for the fluoride misinformation use case performed as expected. The data extraction framework handles large amounts of data within short periods. The LDA topic models achieved relatively high coherence values (0.54), and the predicted topics were accurate and befitting to the data. The sentiment analyzer performed at a correlation coefficient of 0.72 but could be improved in further iterations. The misinformation classifier attained a satisfactory correlation coefficient of 0.82 against expert-validated data. Moreover, the output dashboard and analytics hosted on the Elastic Cloud deployment are intuitive for researchers without a technical background and comprehensive in their visualization and analytics capabilities. In fact, the investigators of the fluoride misinformation use case have successfully used the system to extract interesting and important insights into public health, which have been published separately.

CONCLUSIONS

The novel U-MAS pipeline has the potential to detect and analyze misleading information related to a particular topic or set of related topics.

Navigating the bridge between wet and dry lab toxicology research to address current challenges with high-dimensional data

Toxicology research has rapidly evolved, leveraging increasingly advanced technologies in high-throughput approaches to yield important information on toxicological mechanisms and health outcomes. Data produced through toxicology studies are consequently becoming larger, often producing high-dimensional data. These types of data hold promise for imparting new knowledge, yet inherently have complexities causing them to be a rate-limiting element for researchers, particularly those that are housed in "wet lab" settings (i.e., researchers that use liquids to analyze various chemicals and biomarkers as opposed to more computationally focused, "dry lab" researchers). These types of challenges represent topics of ongoing conversation amongst our team and researchers in the field. The aim of this perspective is to i) summarize hurdles in analyzing high-dimensional data in toxicology that require improved training and translation for wet lab researchers, ii) highlight example methods that have aided in translating data analysis techniques to wet lab researchers; and iii) describe challenges that remain to be effectively addressed, to date, in toxicology research. Specific aspects include methodologies that could be introduced to wet lab researchers, including data pre-processing, machine learning, and data reduction. Current challenges discussed include model interpretability, study biases, and data analysis training. Example efforts implemented to translate these data analysis techniques are also mentioned, including online data analysis resources and hands-on workshops. Questions are also posed to continue conversation in the toxicology community. Contents of this perspective represent timely issues broadly occurring in the fields of bioinformatics and toxicology that require ongoing dialogue between wet and dry lab researchers.

The Application of Systems Thinking to the Prevention and Control of Sexually Transmissible Infections among Adolescents and Adults: A Scoping Review

Systems thinking is a mechanism for making sense of complex systems that challenge linear explanations of cause-and-effect. While the prevention and control of sexually transmissible infections (STIs) has been identified as an area that may benefit from systems-level analyses, no review on the subject currently exists. The aim of this study is to conduct a scoping review to identify literature in which systems thinking has been applied to the prevention and control of STIs among adolescent and adult populations. Joanna Briggs Institute guidelines for the conduct of scoping reviews were followed. Five databases were searched for English-language studies published after 2011. A total of n = 6102 studies were screened against inclusion criteria and n = 70 were included in the review. The majority of studies (n = 34) were conducted in African nations. Few studies focused on priority sub-populations, and 93% were focused on HIV (n = 65). The most commonly applied systems thinking method was system dynamics modelling (n = 28). The review highlights areas for future research, including the need for more STI systems thinking studies focused on: (1) migrant and Indigenous populations; (2) conditions such as syphilis; and (3) innovations such as pre-exposure prophylaxis and at-home testing for HIV. The need for conceptual clarity around 'systems thinking' is also highlighted.

Current status of real-world big data research in the cardiovascular field in Japan

Real-world data (RWD) are observational data obtained by collecting, structuring, and accumulating patient information among the medical big data. RWD are derived from a variety of patient medical care and health information outside of conventional research data, and include electronic health records, claims data, registry data of disease, drug and device, health check-up data, and more recently, patient information data from wearable devices. They are currently being utilized in various forms for optimal medical care and real-world evidence (RWE) is constructed through a process of hypothesis generation and verification based on the RWD research. Together with classic clinical research and pragmatic trials, RWE shapes the learning healthcare system and contributes to the improvement of medical care. In the cardiovascular medical care of the current super-aged society, the need for a variety of RWE and the research is increasing, since the guidelines established over time and the medical care based on it cannot necessarily be the best in accordance with the current medical situation. In this review, we focus on the RWD and RWE studies in the cardiovascular medical field and outlines their current status in Japan. Furthermore, we discuss the potential for extending the studies and issues related to the use of medical big data and RWD.

United in Big Data? Exploring scholars' opinions on academic-industry partnership and the use of corporate data in digital behavioral research

The growing amount of data produced through digital technologies holds great promise for advancing behavioral research. Scholars worldwide now have the chance to access an incredible amount of personal information, thanks to the digital trace users continuously leave behind them. Private corporations play a crucial role in this scenario as the leading collectors of data on users, thus creating new incentives for partnerships between academic institutions and private companies. Due to the concerns that academic-company partnerships might raise and the ethical issues connected with Big Data research, our study explores the challenges and opportunities associated with the academic use of corporate data. We conducted 39 semi-structured interviews with academic scholars (professors, senior researchers, and postdocs) involved in Big Data research in Switzerland and the United States. We also investigated their opinions on using corporate data for scholarly research. Researchers generally showed an interest in using corporate data; however, they coincidentally shared ethical reservations towards this practice, such as threats to research integrity and concerns about a lack of transparency of companies' practices. Furthermore, participants mentioned issues of scholarly access to corporate data that might both disadvantage the academic research community and create issues of scientific validity. Academic-company partnerships could be a positive development for the advancement of scholarly behavioral research. However, strategies should be implemented to appropriately guide collaborations and appropriate use of corporate data, like implementing updated protocols and tools to govern conflicts of interest and the institution of transparent regulatory bodies to ensure adequate oversight of academic-corporate research collaborations.

Co-designing, measuring, and optimizing innovations and solutions within complex adaptive health systems

Objective

To introduce, describe, and demonstrate the emergence and testing of an evaluation method that combines different logics for co-designing, measuring, and optimizing innovations and solutions within complex adaptive health systems.

Method

We describe the development and preliminary testing of a framework to evaluate new ways of using and implementing knowledge (innovations) and technological solutions to solve problems via co-design methods and measurable approaches such as data science. The framework is called PROLIFERATE; it is initially located within the ecological logic: complexity science, by investigating the evolving and emergent properties of systems, but also embraces the mechanistic logic of implementation science (IS) (i.e., getting evidence-based interventions into practice); and the social logic, as the study of individuals, groups, and organizations. Integral to this logic mixture is measuring person-centered parameters (i.e., comprehension, emotional responses, barriers, motivations, and optimization strategies) concerning any evaluated matter across the micro, meso, and macro levels of systems. We embrace the principles of Nilsen's taxonomy to demonstrate its adaptability by comparing and encompassing the normalization process theory, the 2 × 2 conceptual map of influence on behaviors, and PROLIFERATE.

Results

Snapshots of ongoing research in different healthcare settings within Australia are offered to demonstrate how PROLIFERATE can be used for co-designing innovations, tracking their optimization process, and evaluating their impacts. The exemplification involves the evaluation of Health2Go (the design and implementation of an innovative procedure: interdisciplinary learning within an allied health service-community-based) and RAPIDx_AI (an artificial intelligence randomized clinical trial being tested to improve the cardiac care of patients within emergency departments-tertiary care).

Conclusion

PROLIFERATE is one of the first frameworks to combine ecological, mechanistic, and social logic models to co-design, track, and evaluate complex interventions while operationalizing an innovative complexity science approach: the knowledge translation complexity network model (KT-cnm). It adds a novel perspective to the importance of stakeholders' agency in the system by considering their sociodemographic characteristics and experiences within different healthcare settings (e.g., procedural innovations such as "interdisciplinary learning" for Health2Go, and tech-enabled solutions such as RAPIDx_AI). Its structured facilitation processes engage stakeholders in dynamic and productive ways while measuring and optimizing innovation within the complexities of health systems.

Informatics and data science perspective on Future of Nursing 2020-2030: Charting a pathway to health equity

The Future of Nursing 2020 to 2030 report explicitly addresses the need for integration of nursing expertise in designing, generating, analyzing, and applying data to support initiatives focused on social determinants of health (SDOH) and health equity. The metrics necessary to enable and evaluate progress on all recommendations require harnessing existing data sources and developing new ones, as well as transforming and integrating data into information systems to facilitate communication, information sharing, and decision making among the key stakeholders. We examine the recommendations of the 2021 report through an interdisciplinary lens that integrates nursing, biomedical informatics, and data science by addressing three critical questions: (a) what data are needed?, (b) what infrastructure and processes are needed to transform data into information?, and (c) what information systems are needed to "level up" nurse-led interventions from the micro-level to the meso- and macro-levels to address social determinants of health and advance health equity?

Artificial intelligence and machine-learning approaches in structure and ligand-based discovery of drugs affecting central nervous system

CNS disorders are indications with a very high unmet medical needs, relatively smaller number of available drugs, and a subpar satisfaction level among patients and caregiver. Discovery of CNS drugs is extremely expensive affair with its own unique challenges leading to extremely high attrition rates and low efficiency. With explosion of data in information age, there is hardly any aspect of life that has not been touched by data driven technologies such as artificial intelligence (AI) and machine learning (ML). Drug discovery is no exception, emergence of big data via genomic, proteomic, biological, and chemical technologies has driven pharmaceutical giants to collaborate with AI oriented companies to revolutionise drug discovery, with the goal of increasing the efficiency of the process. In recent years many examples of innovative applications of AI and ML techniques in CNS drug discovery has been reported. Research on therapeutics for diseases such as schizophrenia, Alzheimer's and Parkinsonism has been provided with a new direction and thrust from these developments. AI and ML has been applied to both ligand-based and structure-based drug discovery and design of CNS therapeutics. In this review, we have summarised the general aspects of AI and ML from the perspective of drug discovery followed by a comprehensive coverage of the recent developments in the applications of AI/ML techniques in CNS drug discovery.

"Beyond MELD" - Emerging strategies and technologies for improving mortality prediction, organ allocation and outcomes in liver transplantation

In this review article, we discuss the model for end-stage liver disease (MELD) score and its dual purpose in general and transplant hepatology. As the landscape of liver disease and transplantation has evolved considerably since the advent of the MELD score, we summarise emerging concepts, methodologies, and technologies that may improve mortality prognostication in the future. Finally, we explore how these novel concepts and technologies may be incorporated into clinical practice.

Big data analysis for decision-making processes: challenges and opportunities for the management of health-care organizations

Purpose

This study aims to provide a picture of the current state of art in the use of big data for decision-making processes for the management of health-care organizations.

Design/methodology/approach

A systematic literature review was carried out. The research uses two analyses: descriptive analysis, describing the evolution of citations; keywords; and the ten most influential papers, and bibliometric analysis, for content evaluation, for which a cluster analysis was performed.

Findings

A total of 48 articles were selected for bibliographic coupling out of an initial sample of more than 5,000 papers. Of the 48 articles, 29 are linked on the basis of their bibliography. Clustering the 29 articles on the basis of actual content, four research areas emerged: quality of care, quality of service, crisis management and data management.

Originality/value

Health-care organizations believe strongly that big data can become the most effective tool for correctly influencing the decision-making processes. Thus, more and more organizations continue to invest in big data analytics, and the literature on this topic has expanded rapidly. This study seeks to provide a comprehensive picture of the different streams of literature existing, together with gaps in research and future perspectives. The literature is mature enough for an analysis to be made and provide managers with useful insights on opportunities, criticisms and perspectives on the use of big data for health-care organizations. However, to date, there is no comprehensive literature review on the big data analysis in health care. Furthermore, as big data is a “sexy catchphrase,” more clarity on its usage may be needed. It represents an important tool to be investigated and its great potential is often yet to be discovered. This study thus sheds light on emerging issues and suggests further research that may be needed.

(How) do advanced data and analyses enable HR analytics success? A neo-configurational analysis

Purpose

Enabled by increased (“big”) data stocks and advanced (“machine learning”) analyses, the concept of human resource analytics (HRA) is expected to systematically improve decisions in human resource management (HRM). Since so far empirical evidence on this is, however, lacking, the authors' study examines which combinations of data and analyses are employed and which combinations deliver on the promise of improved decision quality.

Design/methodology/approach

Theoretically, the paper employs a neo-configurational approach for founding and conceptualizing HRA. Methodically, based on a sample of German organizations, two varieties (crisp set and multi-value) of qualitative comparative analysis (QCA) are employed to identify combinations of data and analyses sufficient and necessary for HRA success.

Findings

The authors' study identifies existing configurations of data and analyses in HRM and uncovers which of these configurations cause improved decision quality. By evidencing that and which combinations of data and analyses conjuncturally cause decision quality, the authors' study provides a first confirmation of HRA success.

Research limitations/implications

Major limitations refer to the cross-sectional and national sample and the usage of subjective measures. Major implications are the suitability of neo-configurational approaches for future research on HRA, while deeper conceptualizing and researching both the characteristics and outcomes of HRA constitutes a core future task.

Originality/value

The authors' paper employs an innovative theoretical-methodical approach to explain and analyze conditions that conjuncturally cause decision quality therewith offering much needed empirical evidence on HRA success.

The Challenges of Big Data for Research Ethics Committees: A Qualitative Swiss Study

Big data trends in health research challenge the oversight mechanism of the Research Ethics Committees (RECs). The traditional standards of research quality and the mandate of RECs illuminate deficits in facing the computational complexity, methodological novelty, and limited auditability of these approaches. To better understand the challenges facing RECs, we explored the perspectives and attitudes of the members of the seven Swiss Cantonal RECs via semi-structured qualitative interviews. Our interviews reveal limited experience among REC members with the review of big data research, insufficient expertise in data science, and uncertainty about how to mitigate big data research risks. Nonetheless, RECs could strengthen their oversight by training in data science and big data ethics, complementing their role with external experts and ad hoc boards, and introducing precise shared practices.

The NanoInformatics Knowledge Commons: Capturing spatial and temporal nanomaterial transformations in diverse systems

The empirical necessity for integrating informatics throughout the experimental process has become a focal point of the nano-community as we work in parallel to converge efforts for making nano-data reproducible and accessible. The NanoInformatics Knowledge Commons (NIKC) Database was designed to capture the complex relationship between nanomaterials and their environments over time in the concept of an 'Instance'. Our Instance Organizational Structure (IOS) was built to record metadata on nanomaterial transformations in an organizational structure permitting readily accessible data for broader scientific inquiry. By transforming published and on-going data into the IOS we are able to tell the full transformational journey of a nanomaterial within its experimental life cycle. The IOS structure has prepared curated data to be fully analyzed to uncover relationships between observable phenomenon and medium or nanomaterial characteristics. Essential to building the NIKC database and associated applications was incorporating the researcher's needs into every level of development. We started by centering the research question, the query, and the necessary data needed to support the question and query. The process used to create nanoinformatic tools informs usability and analytical capability. In this paper we present the NIKC database, our developmental process, and its curated contents. We also present the Collaboration Tool which was built to foster building new collaboration teams. Through these efforts we aim to: 1) elucidate the general principles that determine nanomaterial behavior in the environment; 2) identify metadata necessary to predict exposure potential and bio-uptake; and 3) identify key characterization assays that predict outcomes of interest.

Systemic Fairness for Sharing Health Data: Perspectives From Swiss Stakeholders

Introduction: Health research is gradually embracing a more collectivist approach, fueled by a new movement of open science, data sharing and collaborative partnerships. However, the existence of systemic contradictions hinders the sharing of health data and such collectivist endeavor. Therefore, this qualitative study explores these systemic barriers to a fair sharing of health data from the perspectives of Swiss stakeholders.

Methods: Purposive and snowball sampling were used to recruit 48 experts active in the Swiss healthcare domain, from the research/policy-making field and those having a high position in a health data enterprise (e.g., health register, hospital IT data infrastructure or a national health data initiative). Semi-structured interviews were then conducted, audio-recorded, verbatim transcribed with identifying information removed to guarantee the anonymity of participants. A theoretical thematic analysis was then carried out to identify themes and subthemes related to the topic of systemic fairness for sharing health data.

Results: Two themes related to the topic of systemic fairness for sharing health data were identified, namely (i) the hypercompetitive environment and (ii) the legal uncertainty blocking data sharing. The theme, hypercompetitive environment was further divided into two subthemes, (i) systemic contradictions to fair data sharing and the (ii) need of fair systemic attribution mechanisms.

Discussion: From the perspectives of Swiss stakeholders, hypercompetition in the Swiss academic system is hindering the sharing of health data for secondary research purposes, with the downside effect of influencing researchers to embrace individualism for career opportunities, thereby opposing the data sharing movement. In addition, there was a perceived sense of legal uncertainty from legislations governing the sharing of health data, which adds unreasonable burdens on individual researchers, who are often unequipped to deal with such facets of their data sharing activities.

The Safe pilot study: A prospective naturalistic study with repeated measures design to test the psychosis - violence link in and after discharge from forensic facilities

The research evidence is very strong for high recidivism rates of violence after discharge from forensic facilities. Big data research has found that a substantial proportion of the forensic population with relapse into violence has a psychosis diagnosis and a criminal record. However, more research on the association between psychotic symptoms and violence may inform and enhance risk assessment, prevention, and treatment. We conducted a prospective naturalistic study with a repeated measures design in a sample of 22 psychotic patients during follow-up after discharge from forensic mental health facilities. We had three aims: to test the predictive validity of three psychotic symptom scales for violence, to analyze main and interaction effects between psychotic symptoms and previous criminal conviction, and to explore the feasibility and potential benefit of the repeated measures design for prospective follow-up research. Interpreted within the limitation of the small sample size, the results were promising for all scales, particularly for adjusted effects without interaction. Two scales remained significant when their interaction with criminal conviction was adjusted. This indicates that risk judgment of psychotic patients with criminal conviction can be improved by adding measurement of fluctuations in psychotic symptoms. The repeated measures design was instrumental in this research.

Use of artificial intelligence to enhance phenotypic drug discovery

Research and development (R&D) productivity across the pharmaceutical industry has received close scrutiny over the past two decades, especially taking into consideration reports of attrition rates and the colossal cost for drug development. The respective merits of the two main drug discovery approaches, phenotypic and target based, have divided opinion across the research community, because each hold different advantages for identifying novel molecular entities with a successful path to the market. Nevertheless, both have low translatability in the clinic. Artificial intelligence (AI) and adoption of machine learning (ML) tools offer the promise of revolutionising drug development, and overcoming obstacles in the drug discovery pipeline. Here, we assess the potential of target-driven and phenotypic-based approaches and offer a holistic description of the current state of the field, from both a scientific and industry perspective. With the emerging partnerships between AI/ML and pharma still in their relative infancy, we investigate the potential and current limitations with a particular focus on phenotypic drug discovery. Finally, we emphasise the value of public-private partnerships (PPPs) and cross-disciplinary collaborations to foster innovation and facilitate efficient drug discovery programmes.

Data-driven business model development – insights from the facility management industry

Purpose

One of the leading factors that shape product and service delivery are data collected in databases and other repositories maintained by companies. The transformation of such data into knowledge and wisdom may constitute a new source of income. This paper aims to explore how small/medium-sized enterprises (SMEs) advance their business models (BMs) around data to handle data-driven products and how this contributes to their innovativeness and performance.

Design/methodology/approach

To investigate the phenomenon, the as-is BM of a multinational SME was mapped and its limitations were revealed through a qualitative study. The BM canvas was used. Then the data-driven approach was innovated within the facility management (FM) industry, where a high volume of operational and sensor-based data being collected creates added value in terms of new data-based products.

Findings

A data-driven business model (DDBM) blueprint for the FM industry that supports the need to complement service-driven operations with the data-driven approach is delivered. Enhanced BM equips a facility manager with additional managerial tools that enable decreasing property utilization costs and opens up new opportunities for generating revenue. This paper drafts the way to evolve from service to data-driven business and point out the attitudes that managers should adopt to promote and implement DDBM.

Practical implications

The DDBM constitutes a guideline that supports FM organizations in focusing their activities and resources on generating business value from data and monetizing data-driven products.

Originality/value

The research expands knowledge regarding BMs and their evolution. The gap regarding the DDBM innovation within the FM industry is filled.

First do no harm: An exploration of researchers' ethics of conduct in Big Data behavioral studies

Research ethics has traditionally been guided by well-established documents such as the Belmont Report and the Declaration of Helsinki. At the same time, the introduction of Big Data methods, that is having a great impact in behavioral research, is raising complex ethical issues that make protection of research participants an increasingly difficult challenge. By conducting 39 semi-structured interviews with academic scholars in both Switzerland and United States, our research aims at exploring the code of ethics and research practices of academic scholars involved in Big Data studies in the fields of psychology and sociology to understand if the principles set by the Belmont Report are still considered relevant in Big Data research. Our study shows how scholars generally find traditional principles to be a suitable guide to perform ethical data research but, at the same time, they recognized and elaborated on the challenges embedded in their practical application. In addition, due to the growing introduction of new actors in scholarly research, such as data holders and owners, it was also questioned whether responsibility to protect research participants should fall solely on investigators. In order to appropriately address ethics issues in Big Data research projects, education in ethics, exchange and dialogue between research teams and scholars from different disciplines should be enhanced. In addition, models of consultancy and shared responsibility between investigators, data owners and review boards should be implemented in order to ensure better protection of research participants.

Big Data and the Little Big Bang: An Epistemological (R)evolution

Starting from an analysis of frequently employed definitions of big data, it will be argued that, to overcome the intrinsic weaknesses of big data, it is more appropriate to define the object in relational terms. The excessive emphasis on volume and technological aspects of big data, derived from their current definitions, combined with neglected epistemological issues gave birth to an objectivistic rhetoric surrounding big data as implicitly neutral, omni-comprehensive, and theory-free. This rhetoric contradicts the empirical reality that embraces big data: (1) data collection is not neutral nor objective; (2) exhaustivity is a mathematical limit; and (3) interpretation and knowledge production remain both theoretically informed and subjective. Addressing these issues, big data will be interpreted as a methodological revolution carried over by evolutionary processes in technology and epistemology. By distinguishing between forms of nominal and actual access, we claim that big data promoted a new digital divide changing stakeholders, gatekeepers, and the basic rules of knowledge discovery by radically shaping the power dynamics involved in the processes of production and analysis of data.

Working Through Ethics Review of Big Data Research Projects: An Investigation into the Experiences of Swiss and American Researchers

The employment of Big Data as an increasingly used research method has introduced novel challenges to ethical research practices and to ethics committees (ECs) globally. The aim of this study is to explore the experiences of scholars with ECs in the ethical evaluation of Big Data projects. Thirty-five interviews were performed with Swiss and American researchers involved in Big Data research in psychology and sociology. The interviews were analyzed using thematic coding. Our respondents reported lack of support from ECs, absence of appropriate expertise among members of the boards, and lack of harmonized evaluation criteria between committees. To implement ECs practices we argue for updating the expertise of board members and the institution of a consultancy model between researchers and ECs.

The use of artificial intelligence, machine learning and deep learning in oncologic histopathology

BACKGROUND

Recently, there has been a momentous drive to apply advanced artificial intelligence (AI) technologies to diagnostic medicine. The introduction of AI has provided vast new opportunities to improve health care and has introduced a new wave of heightened precision in oncologic pathology. The impact of AI on oncologic pathology has now become apparent, and its use with respect to oral oncology is still in the nascent stage.

DISCUSSION

A foundational overview of AI classification systems used in medicine and a review of common terminology used in machine learning and computational pathology will be presented. This paper provides a focused review on the recent advances in AI and deep learning in oncologic histopathology and oral oncology. In addition, specific emphasis on recent studies that have applied these technologies to oral cancer prognostication will also be discussed.

CONCLUSION

Machine and deep learning methods designed to enhance prognostication of oral cancer have been proposed with much of the work focused on prediction models on patient survival and locoregional recurrences in patients with oral squamous cell carcinomas (OSCC). Few studies have explored machine learning methods on OSCC digital histopathologic images. It is evident that further research at the whole slide image level is needed and future collaborations with computer scientists may progress the field of oral oncology.