ViPAR: a software platform for the Virtual Pooling and Analysis of Research Data

Big data in autism research: Methodological challenges and solutions

While the concept of big data has emerged over the past decade as a hot topic in nearly all areas of scientific inquiry, it has rarely been discussed in the context of autism research. In this commentary we describe aspects of big data that are relevant to autism research and methodological issues such as confounding and data error that can hamper scientific investigation. Although big data studies can have transformative impact, bigger is not always better, and big data require the same methodological considerations and interdisciplinary collaboration as "small data" to extract useful scientific insight.

Life course of retrospective harmonization initiatives: key elements to consider

Optimizing research on the developmental origins of health and disease (DOHaD) involves implementing initiatives maximizing the use of the available cohort study data; achieving sufficient statistical power to support subgroup analysis; and using participant data presenting adequate follow-up and exposure heterogeneity. It also involves being able to undertake comparison, cross-validation, or replication across data sets. To answer these requirements, cohort study data need to be findable, accessible, interoperable, and reusable (FAIR), and more particularly, it often needs to be harmonized. Harmonization is required to achieve or improve comparability of the putatively equivalent measures collected by different studies on different individuals. Although the characteristics of the research initiatives generating and using harmonized data vary extensively, all are confronted by similar issues. Having to collate, understand, process, host, and co-analyze data from individual cohort studies is particularly challenging. The scientific success and timely management of projects can be facilitated by an ensemble of factors. The current document provides an overview of the 'life course' of research projects requiring harmonization of existing data and highlights key elements to be considered from the inception to the end of the project.

Annual Research Review: Translational machine learning for child and adolescent psychiatry

Children and adolescents could benefit from the use of predictive tools that facilitate personalized diagnoses, prognoses, and treatment selection. Such tools have not yet been deployed using traditional statistical methods, potentially due to the limitations of the paradigm and the need to leverage large amounts of digital data. This review will suggest that a machine learning approach could address these challenges and is designed to introduce new readers to the background, methods, and results in the field. A rationale is first introduced followed by an outline of fundamental elements of machine learning approaches. To provide an overview of the use of the techniques in child and adolescent literature, a scoping review of broad trends is then presented. Selected studies are also highlighted in order to draw attention to research areas that are closest to translation and studies that exhibit a high degree of experimental innovation. Limitations to the research, and machine learning approaches generally, are outlined in the penultimate section highlighting issues related to sample sizes, validation, clinical utility, and ethical challenges. Finally, future directions are discussed that could enhance the possibility of clinical implementation and address specific questions relevant to the child and adolescent psychiatry. The review gives a broad overview of the machine learning paradigm in order to highlight the benefits of a shift in perspective towards practically oriented statistical solutions that aim to improve clinical care of children and adolescents.

Privacy-preserving quality control of neuroimaging datasets in federated environments

Privacy concerns for rare disease data, institutional or IRB policies, access to local computational or storage resources or download capabilities are among the reasons that may preclude analyses that pool data to a single site. A growing number of multisite projects and consortia were formed to function in the federated environment to conduct productive research under constraints of this kind. In this scenario, a quality control tool that visualizes decentralized data in its entirety via global aggregation of local computations is especially important, as it would allow the screening of samples that cannot be jointly evaluated otherwise. To solve this issue, we present two algorithms: decentralized data stochastic neighbor embedding, dSNE, and its differentially private counterpart, DP‐dSNE. We leverage publicly available datasets to simultaneously map data samples located at different sites according to their similarities. Even though the data never leaves the individual sites, dSNE does not provide any formal privacy guarantees. To overcome that, we rely on differential privacy: a formal mathematical guarantee that protects individuals from being identified as contributors to a dataset. We implement DP‐dSNE with AdaCliP, a method recently proposed to add less noise to the gradients per iteration. We introduce metrics for measuring the embedding quality and validate our algorithms on these metrics against their centralized counterpart on two toy datasets. Our validation on six multisite neuroimaging datasets shows promising results for the quality control tasks of visualization and outlier detection, highlighting the potential of our private, decentralized visualization approach.

A deterministic approach for protecting privacy in sensitive personal data

BACKGROUND

Data privacy is one of the biggest challenges for any organisation which processes personal data, especially in the area of medical research where data include sensitive information about patients and study participants. Sharing of data is therefore problematic, which is at odds with the principle of open data that is so important to the advancement of society and science. Several statistical methods and computational tools have been developed to help data custodians and analysts overcome this challenge.

METHODS

In this paper, we propose a new deterministic approach for anonymising personal data. The method stratifies the underlying data by the categorical variables and re-distributes the continuous variables through a k nearest neighbours based algorithm.

RESULTS

We demonstrate the use of the deterministic anonymisation on real data, including data from a sample of Titanic passengers, and data from participants in the 1958 Birth Cohort.

CONCLUSIONS

The proposed procedure makes data re-identification difficult while minimising the loss of utility (by preserving the spatial properties of the underlying data); the latter means that informative statistical analysis can still be conducted.

NeuroCrypt: Machine Learning Over Encrypted Distributed Neuroimaging Data

The field of neuroimaging can greatly benefit from building machine learning models to detect and predict diseases, and discover novel biomarkers, but much of the data collected at various organizations and research centers is unable to be shared due to privacy or regulatory concerns (especially for clinical data or rare disorders). In addition, aggregating data across multiple large studies results in a huge amount of duplicated technical debt and the resources required can be challenging or impossible for an individual site to build. Training on the data distributed across organizations can result in models that generalize much better than models trained on data from any of organizations alone. While there are approaches for decentralized sharing, these often do not provide the highest possible guarantees of sample privacy that only cryptography can provide. In addition, such approaches are often focused on probabilistic solutions. In this paper, we propose an approach that leverages the potential of datasets spread among a number of data collecting organizations by performing joint analyses in a secure and deterministic manner when only encrypted data is shared and manipulated. The approach is based on secure multiparty computation which refers to cryptographic protocols that enable distributed computation of a function over distributed inputs without revealing additional information about the inputs. It enables multiple organizations to train machine learning models on their joint data and apply the trained models to encrypted data without revealing their sensitive data to the other parties. In our proposed approach, organizations (or sites) securely collaborate to build a machine learning model as it would have been trained on the aggregated data of all the organizations combined. Importantly, the approach does not require a trusted party (i.e. aggregator), each contributing site plays an equal role in the process, and no site can learn individual data of any other site. We demonstrate effectiveness of the proposed approach, in a range of empirical evaluations using different machine learning algorithms including logistic regression and convolutional neural network models on human structural and functional magnetic resonance imaging datasets.

Data sharing and privacy issues in neuroimaging research: Opportunities, obstacles, challenges, and monsters under the bed

Collaborative networks and data sharing initiatives are broadening the opportunities for the advancement of science. These initiatives offer greater transparency in science, with the opportunity for external research groups to reproduce, replicate, and extend research findings. Further, larger datasets offer the opportunity to identify homogeneous patterns within subgroups of individuals, where these patterns may be obscured by the heterogeneity of the neurobiological measure in smaller samples. However, data sharing and data pooling initiatives are not without their challenges, especially with new laws that may at first glance appear quite restrictive for open science initiatives. Interestingly, what is key to some of these new laws (i.e, the European Union's general data protection regulation) is that they provide greater control of data to those who "give" their data for research purposes. Thus, the most important element in data sharing is allowing the participants to make informed decisions about how they want their data to be used, and, within the law of the specific country, to follow the participants' wishes. This framework encompasses obtaining thorough informed consent and allowing the participant to determine the extent that they want their data shared, many of the ethical and legal obstacles are reduced to just monsters under the bed. In this manuscript we discuss the many options and obstacles for data sharing, from fully open, to federated learning, to fully closed. Importantly, we highlight the intersection of data sharing, privacy, and data ownership and highlight specific examples that we believe are informative to the neuroimaging community.

A Correlated Noise-assisted Decentralized Differentially Private Estimation Protocol, and its application to fMRI Source Separation

Blind source separation algorithms such as independent component analysis (ICA) are widely used in the analysis of neuroimaging data. To leverage larger sample sizes, different data holders/sites may wish to collaboratively learn feature representations. However, such datasets are often privacy-sensitive, precluding centralized analyses that pool the data at one site. In this work, we propose a differentially private algorithm for performing ICA in a decentralized data setting. Due to the high dimension and small sample size, conventional approaches to decentralized differentially private algorithms suffer in terms of utility. When centralizing the data is not possible, we investigate the benefit of enabling limited collaboration in the form of generating jointly distributed random noise. We show that such (anti) correlated noise improves the privacy-utility trade-off, and can reach the same level of utility as the corresponding non-private algorithm for certain parameter choices. We validate this benefit using synthetic and real neuroimaging datasets. We conclude that it is possible to achieve meaningful utility while preserving privacy, even in complex signal processing systems.

Toward Generalizable and Transdiagnostic Tools for Psychosis Prediction: An Independent Validation and Improvement of the NAPLS-2 Risk Calculator in the Multisite PRONIA Cohort

BACKGROUND

Transition to psychosis is among the most adverse outcomes of clinical high-risk (CHR) syndromes encompassing ultra-high risk (UHR) and basic symptom states. Clinical risk calculators may facilitate an early and individualized interception of psychosis, but their real-world implementation requires thorough validation across diverse risk populations, including young patients with depressive syndromes.

METHODS

We validated the previously described NAPLS-2 (North American Prodrome Longitudinal Study 2) calculator in 334 patients (26 with transition to psychosis) with CHR or recent-onset depression (ROD) drawn from the multisite European PRONIA (Personalised Prognostic Tools for Early Psychosis Management) study. Patients were categorized into three risk enrichment levels, ranging from UHR, over CHR, to a broad-risk population comprising patients with CHR or ROD (CHR|ROD). We assessed how risk enrichment and different predictive algorithms influenced prognostic performance using reciprocal external validation.

RESULTS

After calibration, the NAPLS-2 model predicted psychosis with a balanced accuracy (BAC) (sensitivity, specificity) of 68% (73%, 63%) in the PRONIA-UHR cohort, 67% (74%, 60%) in the CHR cohort, and 70% (73%, 66%) in patients with CHR|ROD. Multiple model derivation in PRONIA-CHR|ROD and validation in NAPLS-2-UHR patients confirmed that broader risk definitions produced more accurate risk calculators (CHR|ROD-based vs. UHR-based performance: 67% [68%, 66%] vs. 58% [61%, 56%]). Support vector machines were superior in CHR|ROD (BAC = 71%), while ridge logistic regression and support vector machines performed similarly in CHR (BAC = 67%) and UHR cohorts (BAC = 65%). Attenuated psychotic symptoms predicted psychosis across risk levels, while younger age and reduced processing speed became increasingly relevant for broader risk cohorts.

CONCLUSIONS

Clinical-neurocognitive machine learning models operating in young patients with affective and CHR syndromes facilitate a more precise and generalizable prediction of psychosis. Future studies should investigate their therapeutic utility in large-scale clinical trials.

Official ERS technical standard: Global Lung Function Initiative reference values for static lung volumes in individuals of European ancestry

BACKGROUND

Measurement of lung volumes across the life course is critical to the diagnosis and management of lung disease. The aim of the study was to use the Global Lung Function Initiative methodology to develop all-age multi-ethnic reference equations for lung volume indices determined using body plethysmography and gas dilution techniques.

METHODS

Static lung volume data from body plethysmography and gas dilution techniques from individual, healthy participants were collated. Reference equations were derived using the LMS (lambda-mu-sigma) method and the generalised additive models of location shape and scale programme in R. The impact of measurement technique, equipment type and being overweight or obese on the derived lung volume reference ranges was assessed.

RESULTS

Data from 17 centres were submitted and reference equations were derived from 7190 observations from participants of European ancestry between the ages of 5 and 80 years. Data from non-European ancestry populations were insufficient to develop multi-ethnic equations. Measurements of functional residual capacity (FRC) collected using plethysmography and dilution techniques showed physiologically insignificant differences and were combined. Sex-specific reference equations including height and age were developed for total lung capacity (TLC), FRC, residual volume (RV), inspiratory capacity, vital capacity, expiratory reserve volume and RV/TLC. The derived equations were similar to previously published equations for FRC and TLC, with closer agreement during childhood and adolescence than in adulthood.

CONCLUSIONS

Global Lung Function Initiative reference equations for lung volumes provide a generalisable standard for reporting and interpretation of lung volumes measurements in individuals of European ancestry.

Cardioinformatics: the nexus of bioinformatics and precision cardiology

Cardiovascular disease (CVD) is the leading cause of death worldwide, causing over 17 million deaths per year, which outpaces global cancer mortality rates. Despite these sobering statistics, most bioinformatics and computational biology research and funding to date has been concentrated predominantly on cancer research, with a relatively modest footprint in CVD. In this paper, we review the existing literary landscape and critically assess the unmet need to further develop an emerging field at the multidisciplinary interface of bioinformatics and precision cardiovascular medicine, which we refer to as 'cardioinformatics'.

Pooling individual participant data from randomized controlled trials: Exploring potential loss of information

Background

Pooling individual participant data to enable pooled analyses is often complicated by diversity in variables across available datasets. Therefore, recoding original variables is often necessary to build a pooled dataset. We aimed to quantify how much information is lost in this process and to what extent this jeopardizes validity of analyses results.

Methods

Data were derived from a platform that was developed to pool data from three randomized controlled trials on the effect of treatment of cardiovascular risk factors on cognitive decline or dementia. We quantified loss of information using the R-squared of linear regression models with pooled variables as a function of their original variable(s). In case the R-squared was below 0.8, we additionally explored the potential impact of loss of information for future analyses. We did this second step by comparing whether the Beta coefficient of the predictor differed more than 10% when adding original or recoded variables as a confounder in a linear regression model. In a simulation we randomly sampled numbers, recoded those < = 1000 to 0 and those >1000 to 1 and varied the range of the continuous variable, the ratio of recoded zeroes to recoded ones, or both, and again extracted the R-squared from linear models to quantify information loss.

Results

The R-squared was below 0.8 for 8 out of 91 recoded variables. In 4 cases this had a substantial impact on the regression models, particularly when a continuous variable was recoded into a discrete variable. Our simulation showed that the least information is lost when the ratio of recoded zeroes to ones is 1:1.

Conclusions

Large, pooled datasets provide great opportunities, justifying the efforts for data harmonization. Still, caution is warranted when using recoded variables which variance is explained limitedly by their original variables as this may jeopardize the validity of study results.

European mental health research resources: Picture and recommendations of the ROAMER project

As part of the Roamer project, we sought to have a picture of the available mental health research (MHR) funding, capacity-building and infrastructures resources and to establish consensus-based recommendations that would allow an increase of European MHR resources and enable better use and accessibility to them. The methods fell into three sections (i) a review of the literature, (ii) a mental health-related keywords search within the Cordis^®, On-Course^® and Meril^® databases which contain information on European research funding, training and infrastructures. These reviews provided an overview that was presented to (iii) two experts workshops with 28 participants drawn from academic which identified gaps and produced recommendations. The literature review illustrates the debates in the scientific community on funding, training and infrastructures. The database searches estimated the fraction of health research resources available for mental health. Eight overarching goals for MHR resources were identified by the workshops; each of them was carried out with several practical recommendations. Resources for MHR are scarce considering the burden of mental disorders, the high rate of return of MHR and the under-investment of the field. The recommendations are urgently warranted to increase resources and their optimal access and use.

Decentralized distribution-sampled classification models with application to brain imaging

BACKGROUND

In this age of big data, certain models require very large data stores in order to be informative and accurate. In many cases however, the data are stored in separate locations requiring data transfer between local sites which can cause various practical hurdles, such as privacy concerns or heavy network load. This is especially true for medical imaging data, which can be constrained due to the health insurance portability and accountability act (HIPAA) which provides security protocols for medical data. Medical imaging datasets can also contain many thousands or millions of features, requiring heavy network load.

NEW METHOD

Our research expands upon current decentralized classification research by implementing a new singleshot method for both neural networks and support vector machines. Our approach is to estimate the statistical distribution of the data at each local site and pass this information to the other local sites where each site resamples from the individual distributions and trains a model on both locally available data and the resampled data. The model for each local site produces its own accuracy value which are then averaged together to produce the global average accuracy.

RESULTS

We show applications of our approach to handwritten digit classification as well as to multi-subject classification of brain imaging data collected from patients with schizophrenia and healthy controls. Overall, the results showed comparable classification accuracy to the centralized model with lower network load than multishot methods.

COMPARISON WITH EXISTING METHODS

Many decentralized classifiers are multishot, requiring heavy network traffic. Our model attempts to alleviate this load while preserving prediction accuracy.

CONCLUSIONS

We show that our proposed approach performs comparably to a centralized approach while minimizing network traffic compared to multishot methods.

Association of Genetic and Environmental Factors With Autism in a 5-Country Cohort

IMPORTANCE

The origins and development of autism spectrum disorder (ASD) remain unresolved. No individual-level study has provided estimates of additive genetic, maternal, and environmental effects in ASD across several countries.

OBJECTIVE

To estimate the additive genetic, maternal, and environmental effects in ASD.

DESIGN, SETTING, AND PARTICIPANTS

Population-based, multinational cohort study including full birth cohorts of children from Denmark, Finland, Sweden, Israel, and Western Australia born between January 1, 1998, and December 31, 2011, and followed up to age 16 years. Data were analyzed from September 23, 2016 through February 4, 2018.

MAIN OUTCOMES AND MEASURES

Across 5 countries, models were fitted to estimate variance components describing the total variance in risk for ASD occurrence owing to additive genetics, maternal, and shared and nonshared environmental effects.

RESULTS

The analytic sample included 2 001 631 individuals, of whom 1 027 546 (51.3%) were male. Among the entire sample, 22 156 were diagnosed with ASD. The median (95% CI) ASD heritability was 80.8% (73.2%-85.5%) for country-specific point estimates, ranging from 50.9% (25.1%-75.6%) (Finland) to 86.8% (69.8%-100.0%) (Israel). For the Nordic countries combined, heritability estimates ranged from 81.2% (73.9%-85.3%) to 82.7% (79.1%-86.0%). Maternal effect was estimated to range from 0.4% to 1.6%. Estimates of genetic, maternal, and environmental effects for autistic disorder were similar with ASD.

CONCLUSIONS AND RELEVANCE

Based on population data from 5 countries, the heritability of ASD was estimated to be approximately 80%, indicating that the variation in ASD occurrence in the population is mostly owing to inherited genetic influences, with no support for contribution from maternal effects. The results suggest possible modest differences in the sources of ASD risk between countries.

Recurrence Risk of Autism in Siblings and Cousins: A Multinational, Population-Based Study

OBJECTIVE

Familial recurrence risk is an important population-level measure of the combined genetic and shared familial liability of autism spectrum disorder (ASD). Objectives were to estimate ASD recurrence risk among siblings and cousins by varying degree of relatedness and by sex.

METHOD

This is a population-based cohort study of livebirths from 1998 to 2007 in California, Denmark, Finland, Israel, Sweden and Western Australia followed through 2011 to 2015. Subjects were monitored for an ASD diagnosis in their older siblings or cousins (exposure) and for their ASD diagnosis (outcome). The relative recurrence risk was estimated for different sibling and cousin pairs, for each site separately and combined, and by sex.

RESULTS

During follow-up, 29,998 cases of ASD were observed among the 2,551,918 births used to estimate recurrence in ASD and 33,769 cases of childhood autism (CA) were observed among the 6,110,942 births used to estimate CA recurrence. Compared with the risk in unaffected families, there was an 8.4-fold increase in the risk of ASD following an older sibling with ASD and a 17.4-fold increase in the risk of CA following an older sibling with CA. A 2-fold increase in the risk for cousin recurrence was observed for the 2 disorders. There also was a significant difference in sibling ASD recurrence risk by sex.

CONCLUSION

The present estimates of relative recurrence risks for ASD and CA will assist clinicians and families in understanding autism risk in the context of other families in their population. The observed variation by sex underlines the need to deepen the understanding of factors influencing ASD familial risk.

Development and use of a flexible data harmonization platform to facilitate the harmonization of individual patient data for meta-analyses

Objective

Harmonizing individual patient data (IPD) for meta-analysis has clinical and statistical advantages. Harmonizing IPD from multiple studies may benefit from a flexible data harmonization platform (DHP) that allows harmonization of IPD already during data collection. This paper describes the development and use of a flexible DHP that was initially developed for the Predicting OptimaL cAncer RehabIlitation and Supportive care (POLARIS) study.

Results

The DHP that we developed (I) allows IPD harmonization with a flexible approach, (II) has the ability to store data in a centralized and secured database server with large capacity, (III) is transparent and easy in use, and (IV) has the ability to export harmonized IPD and corresponding data dictionary to a statistical program. The DHP uses Microsoft Access as front-end application and requires a relational database management system such as Microsoft Structured Query Language (SQL) Server or MySQL as back-end application. The DHP consists of five user friendly interfaces which support the user to import original study data, to harmonize the data with a master data dictionary, and to export the harmonized data into a statistical software program of choice for further analyses. The DHP is now also adopted in two other studies.

Electronic supplementary material

The online version of this article (10.1186/s13104-019-4210-7) contains supplementary material, which is available to authorized users.

Observational health research in Europe: understanding the General Data Protection Regulation and underlying debate

Insights into the incidence and survival of cancer, the influence of lifestyle and environmental factors and the interaction of treatment regimens with outcomes are hugely dependent on observational research, patient data derived from the healthcare system and from volunteers participating in cohort studies, often non-selective. Since 25th May 2018, the European General Data Protection Regulation (GDPR) applies to such data. The GDPR focusses on more individual control for data subjects of 'their' data. Yet, the GDPR was preceded by a long debate. The research community participated actively in that debate, and as a result, the GDPR has research exemptions as well. Some of those apply directly; other exemptions need to be implemented into national law. Those exemptions will be discussed together with a general outline of the GDPR. I propose a substantive definition of research-absent in the GDPR-which can warrant its special status in the GDPR. The debate is not over yet. Most legal texts exhibit ambiguity and are interpreted against a background of values. In this case, those could be subsumed under informational self-determination versus solidarity and the deeper meaning of autonomy. Values will also guide national implementation and their interpretation. The value of individual control or informational self-determination should be balanced by nuanced visions about our mutual dependency in healthcare, as an ever-learning system, especially in the European solidarity-based healthcare systems. Good research governance might be a way forward to escape the consent or anonymise dichotomy.

Decentralized Analysis of Brain Imaging Data: Voxel-Based Morphometry and Dynamic Functional Network Connectivity

In the field of neuroimaging, there is a growing interest in developing collaborative frameworks that enable researchers to address challenging questions about the human brain by leveraging data across multiple sites all over the world. Additionally, efforts are also being directed at developing algorithms that enable collaborative analysis and feature learning from multiple sites without requiring the often large data to be centrally located. In this paper, we propose two new decentralized algorithms: (1) A decentralized regression algorithm for performing a voxel-based morphometry analysis on structural magnetic resonance imaging (MRI) data and, (2) A decentralized dynamic functional network connectivity algorithm which includes decentralized group ICA and sliding-window analysis of functional MRI data. We compare results against those obtained from their pooled (or centralized) counterparts on the same data i.e., as if they are at one site. Results produced by the decentralized algorithms are similar to the pooled-case and showcase the potential of performing multi-voxel and multivariate analyses of data located at multiple sites. Such approaches enable many more collaborative and comparative analysis in the context of large-scale neuroimaging studies.

Comparison of privacy-protecting analytic and data-sharing methods: A simulation study

PURPOSE

Privacy-protecting analytic and data-sharing methods that minimize the disclosure risk of sensitive information are increasingly important due to the growing interest in utilizing data across multiple sources. We conducted a simulation study to examine how avoiding sharing individual-level data in a distributed data network can affect analytic results.

METHODS

The base scenario had four sites of varying sizes with 5% outcome incidence, 50% treatment prevalence, and seven confounders. We varied treatment prevalence, outcome incidence, treatment effect, site size, number of sites, and covariate distribution. Confounding adjustment was conducted using propensity score or disease risk score. We compared analyses of three types of aggregate-level data requested from sites: risk-set, summary-table, or effect-estimate data (meta-analysis) with benchmark results of analysis of pooled individual-level data. We assessed bias and precision of hazard ratio estimates as well as the accuracy of standard error estimates.

RESULTS

All the aggregate-level data-sharing approaches, regardless of confounding adjustment methods, successfully approximated pooled individual-level data analysis in most simulation scenarios. Meta-analysis showed minor bias when using inverse probability of treatment weights (IPTW) in infrequent exposure (5%), rare outcome (0.01%), and small site (5,000 patients) settings. SE estimates became less accurate for IPTW risk-set approach with less frequent exposure and for propensity score-matching meta-analysis approach with rare outcomes.

CONCLUSIONS

Overall, we found that we can avoid sharing individual-level data and obtain valid results in many settings, although care must be taken with meta-analysis approach in infrequent exposure and rare outcome scenarios, particularly when confounding adjustment is performed with IPTW.

Caesarean section and risk of autism across gestational age: a multi-national cohort study of 5 million births

Background

The positive association between caesarean section (CS) and autism spectrum disorder (ASD) may be attributed to preterm delivery. However, due to lack of statistical power, no previous study thoroughly examined this association across gestational age. Moreover, most studies did not differentiate between emergency and planned CS.

Methods

Using population-based registries of four Nordic countries and Western Australia, our study population included 4 987 390 singletons surviving their first year of life, which included 671 646 CS deliveries and 31 073 ASD children. We used logistic regression to estimate odds ratios (OR) and their 95% confidence intervals (CI) for CS, adjusted for gestational age, site, maternal age and birth year. Stratified analyses were conducted by both gestational age subgroups and by week of gestation. We compared emergency versus planned CS to investigate their potential difference in the risk of ASD.

Results

Compared with vaginal delivery, the overall adjusted OR for ASD in CS delivery was 1.26 (95% CI 1.22-1.30). Stratified ORs were 1.25 (1.15-1.37), 1.16 (1.09-1.23), 1.34 (1.28-1.40) and 1.17 (1.04-1.30) for subgroups of gestational weeks 26-36, 37-38, 39-41 and 42-44, respectively. CS was significantly associated with risk of ASD for each week of gestation, from week 36 to 42, consistently across study sites (OR ranged 1.16-1.38). There was no statistically significant difference between emergency and planned CS in the risk of ASD.

Conclusion

Across the five countries, emergency or planned CS is consistently associated with a modest increased risk of ASD from gestational weeks 36 to 42 when compared with vaginal delivery.

Opportunities and obstacles for deep learning in biology and medicine

Deep learning describes a class of machine learning algorithms that are capable of combining raw inputs into layers of intermediate features. These algorithms have recently shown impressive results across a variety of domains. Biology and medicine are data-rich disciplines, but the data are complex and often ill-understood. Hence, deep learning techniques may be particularly well suited to solve problems of these fields. We examine applications of deep learning to a variety of biomedical problems-patient classification, fundamental biological processes and treatment of patients-and discuss whether deep learning will be able to transform these tasks or if the biomedical sphere poses unique challenges. Following from an extensive literature review, we find that deep learning has yet to revolutionize biomedicine or definitively resolve any of the most pressing challenges in the field, but promising advances have been made on the prior state of the art. Even though improvements over previous baselines have been modest in general, the recent progress indicates that deep learning methods will provide valuable means for speeding up or aiding human investigation. Though progress has been made linking a specific neural network's prediction to input features, understanding how users should interpret these models to make testable hypotheses about the system under study remains an open challenge. Furthermore, the limited amount of labelled data for training presents problems in some domains, as do legal and privacy constraints on work with sensitive health records. Nonetheless, we foresee deep learning enabling changes at both bench and bedside with the potential to transform several areas of biology and medicine.

Machine Learning Approaches for Clinical Psychology and Psychiatry

Machine learning approaches for clinical psychology and psychiatry explicitly focus on learning statistical functions from multidimensional data sets to make generalizable predictions about individuals. The goal of this review is to provide an accessible understanding of why this approach is important for future practice given its potential to augment decisions associated with the diagnosis, prognosis, and treatment of people suffering from mental illness using clinical and biological data. To this end, the limitations of current statistical paradigms in mental health research are critiqued, and an introduction is provided to critical machine learning methods used in clinical studies. A selective literature review is then presented aiming to reinforce the usefulness of machine learning methods and provide evidence of their potential. In the context of promising initial results, the current limitations of machine learning approaches are addressed, and considerations for future clinical translation are outlined.

The Global Lung Function Initiative (GLI) Network: bringing the world's respiratory reference values together

The Global Lung Function Initiative (GLI) Network has become the largest resource for reference values for routine lung function testing ever assembled. This article addresses how the GLI Network came about, why it is important, and its current challenges and future directions. It is an extension of an article published in Breathe in 2013 [1], and summarises recent developments and the future of the GLI Network.

Learn about the GLI Network, the largest resource reference for routine lung function testinghttp://ow.ly/ZZor30epWgi

Privacy, security, and the public health researcher in the era of electronic health record research

Health data derived from electronic health records are increasingly utilized in large-scale population health analyses. Going hand in hand with this increase in data is an increasing number of data breaches. Ensuring privacy and security of these data is a shared responsibility between the public health researcher, collaborators, and their institutions. In this article, we review the requirements of data privacy and security and discuss epidemiologic implications of emerging technologies from the computer science community that can be used for health data. In order to ensure that our needs as researchers are captured in these technologies, we must engage in the dialogue surrounding the development of these tools.

Beyond Our Borders? Public Resistance to Global Genomic Data Sharing

Prospects have never seemed better for a truly global approach to science to improve human health, with leaders of national initiatives laying out their vision of a worldwide network of related projects. An extensive literature addresses obstacles to global genomic data sharing, yet a series of public polls suggests that the scientific community may be overlooking a significant barrier: potential public resistance to data sharing across national borders. In several large United States surveys, university researchers in other countries were deemed the least acceptable group of data users, and a just-completed US survey found a marked increase in privacy and security concerns related to data access by non-US researchers. Furthermore, diminished support for sharing beyond national borders is not unique to the US, although the limited data from outside the US suggest variation across countries as well as demographic groups. Possible sources of resistance include apprehension about privacy and security protections. Strategies for building public support include making the affirmative case for global data sharing, addressing privacy, security, and other legitimate concerns, and investigating public concerns in greater depth.

COINSTAC: A Privacy Enabled Model and Prototype for Leveraging and Processing Decentralized Brain Imaging Data

The field of neuroimaging has embraced the need for sharing and collaboration. Data sharing mandates from public funding agencies and major journal publishers have spurred the development of data repositories and neuroinformatics consortia. However, efficient and effective data sharing still faces several hurdles. For example, open data sharing is on the rise but is not suitable for sensitive data that are not easily shared, such as genetics. Current approaches can be cumbersome (such as negotiating multiple data sharing agreements). There are also significant data transfer, organization and computational challenges. Centralized repositories only partially address the issues. We propose a dynamic, decentralized platform for large scale analyses called the Collaborative Informatics and Neuroimaging Suite Toolkit for Anonymous Computation (COINSTAC). The COINSTAC solution can include data missing from central repositories, allows pooling of both open and "closed" repositories by developing privacy-preserving versions of widely-used algorithms, and incorporates the tools within an easy-to-use platform enabling distributed computation. We present an initial prototype system which we demonstrate on two multi-site data sets, without aggregating the data. In addition, by iterating across sites, the COINSTAC model enables meta-analytic solutions to converge to "pooled-data" solutions (i.e., as if the entire data were in hand). More advanced approaches such as feature generation, matrix factorization models, and preprocessing can be incorporated into such a model. In sum, COINSTAC enables access to the many currently unavailable data sets, a user friendly privacy enabled interface for decentralized analysis, and a powerful solution that complements existing data sharing solutions.

Individual-based versus aggregate meta-analysis in multi-database studies of pregnancy outcomes: the Nordic example of selective serotonin reuptake inhibitors and venlafaxine in pregnancy

PURPOSE

Compare analyses of a pooled data set on the individual level with aggregate meta-analysis in a multi-database study.

METHODS

We reanalysed data on 2.3 million births in a Nordic register based cohort study. We compared estimated odds ratios (OR) for the effect of selective serotonin reuptake inhibitors (SSRI) and venlafaxine use in pregnancy on any cardiovascular birth defect and the rare outcome right ventricular outflow tract obstructions (RVOTO). Common covariates included maternal age, calendar year, birth order, maternal diabetes, and co-medication. Additional covariates were added in analyses with country-optimized adjustment.

RESULTS

Country adjusted OR (95%CI) for any cardiovascular birth defect in the individual-based pooled analysis was 1.27 (1.17-1.39), 1.17 (1.07-1.27) adjusted for common covariates and 1.15 (1.05-1.26) adjusted for all covariates. In fixed effects meta-analyses pooled OR was 1.29 (1.19-1.41) based on crude country specific ORs, 1.19 (1.09-1.29) adjusted for common covariates, and 1.16 (1.06-1.27) for country-optimized adjustment. In a random effects model the adjusted OR was 1.07 (0.87-1.32). For RVOTO, OR was 1.48 (1.15-1.89) adjusted for all covariates in the pooled data set, and 1.53 (1.19-1.96) after country-optimized adjustment. Country-specific adjusted analyses at the substance level were not possible for RVOTO.

CONCLUSION

Results of fixed effects meta-analysis and individual-based analyses of a pooled dataset were similar in this study on the association of SSRI/venlafaxine and cardiovascular birth defects. Country-optimized adjustment attenuated the estimates more than adjustment for common covariates only. When data are sparse pooled data on the individual level are needed for adjusted analyses. Copyright © 2016 John Wiley & Sons, Ltd.

A Tool for Interactive Data Visualization: Application to Over 10,000 Brain Imaging and Phantom MRI Data Sets

In this paper we propose a web-based approach for quick visualization of big data from brain magnetic resonance imaging (MRI) scans using a combination of an automated image capture and processing system, nonlinear embedding, and interactive data visualization tools. We draw upon thousands of MRI scans captured via the COllaborative Imaging and Neuroinformatics Suite (COINS). We then interface the output of several analysis pipelines based on structural and functional data to a t-distributed stochastic neighbor embedding (t-SNE) algorithm which reduces the number of dimensions for each scan in the input data set to two dimensions while preserving the local structure of data sets. Finally, we interactively display the output of this approach via a web-page, based on data driven documents (D3) JavaScript library. Two distinct approaches were used to visualize the data. In the first approach, we computed multiple quality control (QC) values from pre-processed data, which were used as inputs to the t-SNE algorithm. This approach helps in assessing the quality of each data set relative to others. In the second case, computed variables of interest (e.g., brain volume or voxel values from segmented gray matter images) were used as inputs to the t-SNE algorithm. This approach helps in identifying interesting patterns in the data sets. We demonstrate these approaches using multiple examples from over 10,000 data sets including (1) quality control measures calculated from phantom data over time, (2) quality control data from human functional MRI data across various studies, scanners, sites, (3) volumetric and density measures from human structural MRI data across various studies, scanners and sites. Results from (1) and (2) show the potential of our approach to combine t-SNE data reduction with interactive color coding of variables of interest to quickly identify visually unique clusters of data (i.e., data sets with poor QC, clustering of data by site) quickly. Results from (3) demonstrate interesting patterns of gray matter and volume, and evaluate how they map onto variables including scanners, age, and gender. In sum, the proposed approach allows researchers to rapidly identify and extract meaningful information from big data sets. Such tools are becoming increasingly important as datasets grow larger.