RESUMEN
Data science is playing an increasingly important role in the design and analysis of engineered biology. This has been fueled by the development of high-throughput methods like massively parallel reporter assays, data-rich microscopy techniques, computational protein structure prediction and design, and the development of whole-cell models able to generate huge volumes of data. Although the ability to apply data-centric analyses in these contexts is appealing and increasingly simple to do, it comes with potential risks. For example, how might biases in the underlying data affect the validity of a result and what might the environmental impact of large-scale data analyses be? Here, we present a community-developed framework for assessing data hazards to help address these concerns and demonstrate its application to two synthetic biology case studies. We show the diversity of considerations that arise in common types of bioengineering projects and provide some guidelines and mitigating steps. Understanding potential issues and dangers when working with data and proactively addressing them will be essential for ensuring the appropriate use of emerging data-intensive AI methods and help increase the trustworthiness of their applications in synthetic biology.
RESUMEN
BACKGROUND: The use of social media data to predict mental health outcomes has the potential to allow for the continuous monitoring of mental health and well-being and provide timely information that can supplement traditional clinical assessments. However, it is crucial that the methodologies used to create models for this purpose are of high quality from both a mental health and machine learning perspective. Twitter has been a popular choice of social media because of the accessibility of its data, but access to big data sets is not a guarantee of robust results. OBJECTIVE: This study aims to review the current methodologies used in the literature for predicting mental health outcomes from Twitter data, with a focus on the quality of the underlying mental health data and the machine learning methods used. METHODS: A systematic search was performed across 6 databases, using keywords related to mental health disorders, algorithms, and social media. In total, 2759 records were screened, of which 164 (5.94%) papers were analyzed. Information about methodologies for data acquisition, preprocessing, model creation, and validation was collected, as well as information about replicability and ethical considerations. RESULTS: The 164 studies reviewed used 119 primary data sets. There were an additional 8 data sets identified that were not described in enough detail to include, and 6.1% (10/164) of the papers did not describe their data sets at all. Of these 119 data sets, only 16 (13.4%) had access to ground truth data (ie, known characteristics) about the mental health disorders of social media users. The other 86.6% (103/119) of data sets collected data by searching keywords or phrases, which may not be representative of patterns of Twitter use for those with mental health disorders. The annotation of mental health disorders for classification labels was variable, and 57.1% (68/119) of the data sets had no ground truth or clinical input on this annotation. Despite being a common mental health disorder, anxiety received little attention. CONCLUSIONS: The sharing of high-quality ground truth data sets is crucial for the development of trustworthy algorithms that have clinical and research utility. Further collaboration across disciplines and contexts is encouraged to better understand what types of predictions will be useful in supporting the management and identification of mental health disorders. A series of recommendations for researchers in this field and for the wider research community are made, with the aim of enhancing the quality and utility of future outputs.
Asunto(s)
Salud Mental , Medios de Comunicación Sociales , Humanos , Algoritmos , Trastornos de Ansiedad , Aprendizaje AutomáticoRESUMEN
MOTIVATION: Social media represent an unrivalled opportunity for epidemiological cohorts to collect large amounts of high-resolution time course data on mental health. Equally, the high-quality data held by epidemiological cohorts could greatly benefit social media research as a source of ground truth for validating digital phenotyping algorithms. However, there is currently a lack of software for doing this in a secure and acceptable manner. We worked with cohort leaders and participants to co-design an open-source, robust and expandable software framework for gathering social media data in epidemiological cohorts. IMPLEMENTATION: Epicosm is implemented as a Python framework that is straightforward to deploy and run inside a cohort's data safe haven. GENERAL FEATURES: The software regularly gathers Tweets from a list of accounts and stores them in a database for linking to existing cohort data. AVAILABILITY: This open-source software is freely available at [https://dynamicgenetics.github.io/Epicosm/].
Asunto(s)
Medios de Comunicación Sociales , Humanos , Programas Informáticos , Algoritmos , Exactitud de los Datos , Bases de Datos FactualesRESUMEN
Awareness and management of ethical issues in data science are becoming crucial skills for data scientists. Discussion of contemporary issues in collaborative and interdisciplinary spaces is an engaging way to allow data-science work to be influenced by those with expertise in sociological fields and so improve the ability of data scientists to think critically about the ethics of their work. However, opportunities to do so are limited. Data Ethics Club is a fortnightly discussion group about data science and ethics whose community-generated resources are hosted publicly online. These include a collaborative list of materials around topics of interest and guides for leading an online data-ethics discussion group. Our meetings and resources are designed to reduce the barriers to learning, reflection, and critique on data science and ethics, with the broader aim of building ethics into the cultural fabric of quality data-science work.
RESUMEN
BACKGROUND: Two-sample Mendelian randomization (2SMR) is an increasingly popular epidemiological method that uses genetic variants as instruments for making causal inferences. Clear reporting of methods employed in such studies is important for evaluating their underlying quality. However, the quality of methodological reporting of 2SMR studies is currently unclear. We aimed to assess the reporting quality of studies that used MR-Base, one of the most popular platforms for implementing 2SMR analysis. METHODS: We created a bespoke reporting checklist to evaluate reporting quality of 2SMR studies. We then searched Web of Science Core Collection, PsycInfo, MEDLINE, EMBASE and Google Scholar citations of the MR-Base descriptor paper to identify published MR studies that used MR-Base for any component of the MR analysis. Study screening and data extraction were performed by at least two independent reviewers. RESULTS: In the primary analysis, 87 studies were included. Reporting quality was generally poor across studies, with a mean of 53% (SD = 14%) of items reported in each study. Many items required for evaluating the validity of key assumptions made in MR were poorly reported: only 44% of studies provided sufficient details for assessing if the genetic variant associates with the exposure ('relevance' assumption), 31% for assessing if there are any variant-outcome confounders ('independence' assumption), 89% for the assessing if the variant causes the outcome independently of the exposure ('exclusion restriction' assumption) and 32% for assumptions of falsification tests. We did not find evidence of a change in reporting quality over time or a difference in reporting quality between studies that used MR-Base and a random sample of MR studies that did not use this platform. CONCLUSIONS: The quality of reporting of two-sample Mendelian randomization studies in our sample was generally poor. Journals and researchers should consider using the STROBE-MR guidelines to improve reporting quality.
Asunto(s)
Análisis de la Aleatorización Mendeliana , Proyectos de Investigación , Humanos , Análisis de la Aleatorización Mendeliana/métodos , Causalidad , Lista de VerificaciónRESUMEN
The relationship between mental health and social media has received significant research and policy attention. However, there is little population representative data about who social media users are which limits understanding of confounding factors between mental health and social media. Here we profile users of Facebook, Twitter, Instagram, Snapchat and YouTube from the Avon Longitudinal Study of Parents and Children population cohort (N=4,083). We provide estimates of demographics and mental health and well-being outcomes by platform. We find that users of different platforms and frequencies are not homogeneous. User groups differ primarily by sex and YouTube users are the most likely to have poorer mental health outcomes. Instagram and Snapchat users tend to have higher well-being than the other social media sites considered. Relationships between use-frequency and well-being differ depending on the specific well-being construct measured. The reproducibility of future research may be improved by stratifying by sex and being specific about the well-being constructs used.
RESUMEN
BACKGROUND: Disasters such as the COVID-19 pandemic pose an overwhelming demand on resources that cannot always be met by official organisations. Limited resources and human response to crises can lead members of local communities to turn to one another to fulfil immediate needs. This spontaneous citizen-led response can be crucial to a community's ability to cope in a crisis. It is thus essential to understand the scope of such initiatives so that support can be provided where it is most needed. Nevertheless, quickly developing situations and varying definitions can make the community response challenging to measure. AIM: To create an accessible interactive map of the citizen-led community response to need during the COVID-19 pandemic in Wales, UK that combines information gathered from multiple data providers to reflect different interpretations of need and support. APPROACH: We gathered data from a combination of official data providers and community-generated sources to create 14 variables representative of need and support. These variables are derived by a reproducible data pipeline that enables flexible integration of new data. The interactive tool is available online (www.covidresponsemap.wales) and can map available data at two geographic resolutions. Users choose their variables of interest, and interpretation of the map is aided by a linked bee-swarm plot. DISCUSSION: The novel approach we developed enables people at all levels of community response to explore and analyse the distribution of need and support across Wales. While there can be limitations to the accuracy of community-generated data, we demonstrate that they can be effectively used alongside traditional data sources to maximise the understanding of community action. This adds to our overall aim to measure community response and resilience, as well as to make complex population health data accessible to a range of audiences. Future developments include the integration of other factors such as well-being.
RESUMEN
Background: Cohort studies gather huge volumes of information about a range of phenotypes but new sources of information such as social media data are yet to be integrated. Participant's long-term engagement with cohort studies, as well as the potential for their social media data to be linked to other longitudinal data, could provide novel advances but may also give participants a unique perspective on the acceptability of this growing research area. Methods: Two focus groups explored participant views towards the acceptability and best practice for the collection of social media data for research purposes. Participants were drawn from the Avon Longitudinal Study of Parents and Children cohort; individuals from the index cohort of young people (N=9) and from the parent generation (N=5) took part in two separate 90-minute focus groups. The discussions were audio recorded and subjected to qualitative analysis. Results: Participants were generally supportive of the collection of social media data to facilitate health and social research. They felt that their trust in the cohort study would encourage them to do so. Concern was expressed about the collection of data from friends or connections who had not consented. In terms of best practice for collecting the data, participants generally preferred the use of anonymous data derived from social media to be shared with researchers. Conclusion: Cohort studies have trusting relationships with their participants; for this relationship to extend to linking their social media data with longitudinal information, procedural safeguards are needed. Participants understand the goals and potential of research integrating social media data into cohort studies, but further research is required on the acquisition of their friend's data. The views gathered from participants provide important guidance for future work seeking to integrate social media in cohort studies.
RESUMEN
Introduction: Digital footprint records - the tracks and traces amassed by individuals as a result of their interactions with the internet, digital devices and services - can provide ecologically valid data on individual behaviours. These could enhance longitudinal population study databanks; but few UK longitudinal studies are attempting this. When using novel sources of data, study managers must engage with participants in order to develop ethical data processing frameworks that facilitate data sharing whilst safeguarding participant interests. Objectives: This paper aims to summarise the participant involvement approach used by the ALSPAC birth cohort study to inform the development of a framework for using linked participant digital footprint data, and provide an exemplar for other data linkage infrastructures. Methods: The paper synthesises five qualitative forms of inquiry. Thematic analysis was used to code transcripts for common themes in relation to conditions associated with the acceptability of sharing digital footprint data for longitudinal research. Results: We identified six themes: participant understanding; sensitivity of location data; concerns for third parties; clarity on data granularity; mechanisms of data sharing and consent; and trustworthiness of the organisation. For cohort members to consider the sharing of digital footprint data acceptable, they require information about the value, validity and risks; control over sharing elements of the data they consider sensitive; appropriate mechanisms to authorise or object to their records being used; and trust in the organisation. Conclusion: Realising the potential for using digital footprint records within longitudinal research will be subject to ensuring that this use of personal data is acceptable; and that rigorously controlled population data science benefiting the public good is distinguishable from the misuse and lack of personal control of similar data within other settings. Participant co-development informs the ethical-governance framework for these novel linkages in a manner which is acceptable and does not undermine the role of the trusted data custodian.