A review of causal inference for biomedical informatics

Opportunities for incorporating intersectionality into biomedical informatics

Many approaches in biomedical informatics (BMI) rely on the ability to define, gather, and manipulate biomedical data to support health through a cyclical research-practice lifecycle. Researchers within this field are often fortunate to work closely with healthcare and public health systems to influence data generation and capture and have access to a vast amount of biomedical data. Many informaticists also have the expertise to engage with stakeholders, develop new methods and applications, and influence policy. However, research and policy that explicitly seeks to address the systemic drivers of health would more effectively support health. Intersectionality is a theoretical framework that can facilitate such research. It holds that individual human experiences reflect larger socio-structural level systems of privilege and oppression, and cannot be truly understood if these systems are examined in isolation. Intersectionality explicitly accounts for the interrelated nature of systems of privilege and oppression, providing a lens through which to examine and challenge inequities. In this paper, we propose intersectionality as an intervention into how we conduct BMI research. We begin by discussing intersectionality's history and core principles as they apply to BMI. We then elaborate on the potential for intersectionality to stimulate BMI research. Specifically, we posit that our efforts in BMI to improve health should address intersectionality's five key considerations: (1) systems of privilege and oppression that shape health; (2) the interrelated nature of upstream health drivers; (3) the nuances of health outcomes within groups; (4) the problematic and power-laden nature of categories that we assign to people in research and in society; and (5) research to inform and support social change.

Developing a novel causal inference algorithm for personalized biomedical causal graph learning using meta machine learning

BACKGROUND

Modeling causality through graphs, referred to as causal graph learning, offers an appropriate description of the dynamics of causality. The majority of current machine learning models in clinical decision support systems only predict associations between variables, whereas causal graph learning models causality dynamics through graphs. However, building personalized causal graphs for each individual is challenging due to the limited amount of data available for each patient.

METHOD

In this study, we present a new algorithmic framework using meta-learning for learning personalized causal graphs in biomedicine. Our framework extracts common patterns from multiple patient graphs and applies this information to develop individualized graphs. In multi-task causal graph learning, the proposed optimized initial guess of shared commonality enables the rapid adoption of knowledge to new tasks for efficient causal graph learning.

RESULTS

Experiments on one real-world biomedical causal graph learning benchmark data and four synthetic benchmarks show that our algorithm outperformed the baseline methods. Our algorithm can better understand the underlying patterns in the data, leading to more accurate predictions of the causal graph. Specifically, we reduce the structural hamming distance by 50-75%, indicating an improvement in graph prediction accuracy. Additionally, the false discovery rate is decreased by 20-30%, demonstrating that our algorithm made fewer incorrect predictions compared to the baseline algorithms.

CONCLUSION

To the best of our knowledge, this is the first study to demonstrate the effectiveness of meta-learning in personalized causal graph learning and cause inference modeling for biomedicine. In addition, the proposed algorithm can also be generalized to transnational research areas where integrated analysis is necessary for various distributions of datasets, including different clinical institutions.

Evaluating Large Language Models in Extracting Cognitive Exam Dates and Scores

Importance

Large language models (LLMs) are crucial for medical tasks. Ensuring their reliability is vital to avoid false results. Our study assesses two state-of-the-art LLMs (ChatGPT and LlaMA-2) for extracting clinical information, focusing on cognitive tests like MMSE and CDR.

Objective

Evaluate ChatGPT and LlaMA-2 performance in extracting MMSE and CDR scores, including their associated dates.

Methods

Our data consisted of 135,307 clinical notes (Jan 12th, 2010 to May 24th, 2023) mentioning MMSE, CDR, or MoCA. After applying inclusion criteria 34,465 notes remained, of which 765 underwent ChatGPT (GPT-4) and LlaMA-2, and 22 experts reviewed the responses. ChatGPT successfully extracted MMSE and CDR instances with dates from 742 notes. We used 20 notes for fine-tuning and training the reviewers. The remaining 722 were assigned to reviewers, with 309 each assigned to two reviewers simultaneously. Inter-rater-agreement (Fleiss' Kappa), precision, recall, true/false negative rates, and accuracy were calculated. Our study follows TRIPOD reporting guidelines for model validation.

Results

For MMSE information extraction, ChatGPT (vs. LlaMA-2) achieved accuracy of 83% (vs. 66.4%), sensitivity of 89.7% (vs. 69.9%), true-negative rates of 96% (vs 60.0%), and precision of 82.7% (vs 62.2%). For CDR the results were lower overall, with accuracy of 87.1% (vs. 74.5%), sensitivity of 84.3% (vs. 39.7%), true-negative rates of 99.8% (98.4%), and precision of 48.3% (vs. 16.1%). We qualitatively evaluated the MMSE errors of ChatGPT and LlaMA-2 on double-reviewed notes. LlaMA-2 errors included 27 cases of total hallucination, 19 cases of reporting other scores instead of MMSE, 25 missed scores, and 23 cases of reporting only the wrong date. In comparison, ChatGPT's errors included only 3 cases of total hallucination, 17 cases of wrong test reported instead of MMSE, and 19 cases of reporting a wrong date.

Conclusions

In this diagnostic/prognostic study of ChatGPT and LlaMA-2 for extracting cognitive exam dates and scores from clinical notes, ChatGPT exhibited high accuracy, with better performance compared to LlaMA-2. The use of LLMs could benefit dementia research and clinical care, by identifying eligible patients for treatments initialization or clinical trial enrollments. Rigorous evaluation of LLMs is crucial to understanding their capabilities and limitations.

A Comprehensive Framework for Measuring the Immediate Impact of TV Advertisements: TV-Impact

Measuring the immediate impact of television advertisements (TV ads) on online traffic poses significant challenges in many aspects. Nonetheless, a comprehensive consideration is essential to fully grasp consumer reactions to TV ads. So far, the measurement of this effect has not been studied to a large extent. Existing studies have either determined how a specific focus group, i.e., toddlers, people of a certain age group, etc., react to ads via simple statistical tests using a case study approach or have examined the effects of advertising with simple regression models. This study introduces a comprehensive framework called TV-Impact. The framework uses a Bayesian structural time-series model called CausalImpact. There are additional novel approaches developed within the framework. One of the novelties of TV-Impact lies in its dynamic algorithm for selecting control variables which are supporting data sources and presumed to be unaffected by TV ads. In addition, we proposed the concept of Group Ads to combine overlapping ads into a single ad structure. Then, Random Forest Regressor, which is a commonly preferred supervised learning method, is used to decompose the impact into single ads. The TV-Impact framework was applied to the data of iLab, a venture company in Turkey, and manages its companies' advertising strategies. The findings reveal that the TV-Impact model positively influenced the companies' strategies for allocating their TV advertisement budgets and increased the amount of traffic driven to company websites, serving as an effective decision support system.

Automated detection of causal relationships among diseases and imaging findings in textual radiology reports

OBJECTIVE

Textual radiology reports contain a wealth of information that may help understand associations among diseases and imaging observations. This study evaluated the ability to detect causal associations among diseases and imaging findings from their co-occurrence in radiology reports.

MATERIALS AND METHODS

This IRB-approved and HIPAA-compliant study analyzed 1 702 462 consecutive reports of 1 396 293 patients; patient consent was waived. Reports were analyzed for positive mention of 16 839 entities (disorders and imaging findings) of the Radiology Gamuts Ontology (RGO). Entities that occurred in fewer than 25 patients were excluded. A Bayesian network structure-learning algorithm was applied at P < 0.05 threshold: edges were evaluated as possible causal relationships. RGO and/or physician consensus served as ground truth.

RESULTS

2742 of 16 839 RGO entities were included, 53 849 patients (3.9%) had at least one included entity. The algorithm identified 725 pairs of entities as causally related; 634 were confirmed by reference to RGO or physician review (87% precision). As shown by its positive likelihood ratio, the algorithm increased detection of causally associated entities 6876-fold.

DISCUSSION

Causal relationships among diseases and imaging findings can be detected with high precision from textual radiology reports.

CONCLUSION

This approach finds causal relationships among diseases and imaging findings with high precision from textual radiology reports, despite the fact that causally related entities represent only 0.039% of all pairs of entities. Applying this approach to larger report text corpora may help detect unspecified or heretofore unrecognized associations.

Causal knowledge graph construction and evaluation for clinical decision support of diabetic nephropathy

BACKGROUND

Many important clinical decisions require causal knowledge (CK) to take action. Although many causal knowledge bases for medicine have been constructed, a comprehensive evaluation based on real-world data and methods for handling potential knowledge noise are still lacking.

OBJECTIVE

The objectives of our study are threefold: (1) propose a framework for the construction of a large-scale and high-quality causal knowledge graph (CKG); (2) design the methods for knowledge noise reduction to improve the quality of the CKG; (3) evaluate the knowledge completeness and accuracy of the CKG using real-world data.

MATERIAL AND METHODS

We extracted causal triples from three knowledge sources (SemMedDB, UpToDate and Churchill's Pocketbook of Differential Diagnosis) based on rule methods and language models, performed ontological encoding, and then designed semantic modeling between electronic health record (EHR) data and the CKG to complete knowledge instantiation. We proposed two graph pruning strategies (co-occurrence ratio and causality ratio) to reduce the potential noise introduced by SemMedDB. Finally, the evaluation was carried out by taking the diagnostic decision support (DDS) of diabetic nephropathy (DN) as a real-world case. The data originated from a Chinese hospital EHR system from October 2010 to October 2020. The knowledge completeness and accuracy of the CKG were evaluated based on three state-of-the-art embedding methods (R-GCN, MHGRN and MedPath), the annotated clinical text and the expert review, respectively.

RESULTS

This graph included 153,289 concepts and 1,719,968 causal triples. A total of 1427 inpatient data were used for evaluation. Better results were achieved by combining three knowledge sources than using only SemMedDB (three models: area under the receiver operating characteristic curve (AUC): p < 0.01, F1: p < 0.01), and the graph covered 93.9 % of the causal relations between diseases and diagnostic evidence recorded in clinical text. Causal relations played a vital role in all relations related to disease progression for DDS of DN (three models: AUC: p > 0.05, F1: p > 0.05), and after pruning, the knowledge accuracy of the CKG was significantly improved (three models: AUC: p < 0.01, F1: p < 0.01; expert review: average accuracy: + 5.5 %).

CONCLUSIONS

The results demonstrated that our proposed CKG could completely and accurately capture the abstract CK under the concrete EHR data, and the pruning strategies could improve the knowledge accuracy of our CKG. The CKG has the potential to be applied to the DDS of diseases.

Causal Criteria in Medical and Biological Disciplines: History, Essence, and Radiation Aspects. Report 4, Part 1: The Post-Hill Criteria and Ecolgoical Criteria

Part 1 of Report 4 is focused on the development and modifications of causal criteria after A.B. Hill (1965). Criteria from B. MacMahon et al. (1970-1996), regarded as the first textbook for modern epidemiology, were considered, and it was found that the named researchers did not offer anything new despite the frequent mention of this source in relation to the theme. A similar situation emerged with the criteria of M. Susser: the three obligatory points of this author, "Association" (or "Probability" of causality), "Time order," and "Direction of effect," are trivial, and two more special criteria, which are the development of "Popperian Epidemiology," i.e., "Surviability" of the hypothesis when it is tested by different methods (included in the refinement in Hill's criterion "Consistency of association") and "Predictive performance" of the hypothesis are more theoretical and hardly applicable for the practice of epidemiology and public health. The same restrictions apply to the similar "Popperian" criteria of D.L. Weed, "Predictability" and "Testability" of the causal hypothesis. Although the universal postulates of A.S. Evans for infectious and noninfectious pathologies can be considered exhaustive, they are not used either in epidemiology or in any other discipline practice, except for the field of infectious pathologies, which is probably explained by the complication of the ten-point complex. The little-known criteria of P. Cole (1997) for medical and forensic practice are the most important. The three parts of Hill's criterion-based approaches are important in that they go from a single epidemiological study through a cycle of studies (coupled with the integration of data from other biomedical disciplines) to re-base Hill's criteria for assessing the individual causality of an effect. These constructs complement the earlier guidance from R.E. Gots (1986) on establishing probabilistic personal causation. The collection of causal criteria and the guidelines for environmental disciplines (ecology of biota, human ecoepidemiology, and human ecotoxicology) were considered. The total dominance of inductive causal criteria, both initial and in modifications and with additions, was revealed for an apparently complete base of sources (1979-2020). Adaptations of all known causal schemes based on guidelines have been found, from Henle-Koch postulates to Hill and Susser, including in the international programs and practice of the U.S. Environmental Protection Agency. The Hill Criteria are used by the WHO and other organizations on chemical safety (IPCS) to assess causality in animal experiments for subsequent extrapolation to humans. Data on the assessment of the causality of effects in ecology, ecoepidemiology, and ecotoxicology, together with the use of Hill's criteria for animal experiments, are of significant relevance not only for radiation ecology, but also for radiobiology.

Overtriage, Undertriage, and Value of Care after Major Surgery: An Automated, Explainable Deep Learning-Enabled Classification System

BACKGROUND

In single-institution studies, overtriaging low-risk postoperative patients to ICUs has been associated with a low value of care; undertriaging high-risk postoperative patients to general wards has been associated with increased mortality and morbidity. This study tested the reproducibility of an automated postoperative triage classification system to generating an actionable, explainable decision support system.

STUDY DESIGN

This longitudinal cohort study included adults undergoing inpatient surgery at two university hospitals. Triage classifications were generated by an explainable deep learning model using preoperative and intraoperative electronic health record features. Nearest neighbor algorithms identified risk-matched controls. Primary outcomes were mortality, morbidity, and value of care (inverted risk-adjusted mortality/total direct costs).

RESULTS

Among 4,669 ICU admissions, 237 (5.1%) were overtriaged. Compared with 1,021 control ward admissions, overtriaged admissions had similar outcomes but higher costs ($15.9K [interquartile range $9.8K to $22.3K] vs $10.7K [$7.0K to $17.6K], p < 0.001) and lower value of care (0.2 [0.1 to 0.3] vs 1.5 [0.9 to 2.2], p < 0.001). Among 8,594 ward admissions, 1,029 (12.0%) were undertriaged. Compared with 2,498 control ICU admissions, undertriaged admissions had longer hospital length-of-stays (6.4 [3.4 to 12.4] vs 5.4 [2.6 to 10.4] days, p < 0.001); greater incidence of hospital mortality (1.7% vs 0.7%, p = 0.03), cardiac arrest (1.4% vs 0.5%, p = 0.04), and persistent acute kidney injury without renal recovery (5.2% vs 2.8%, p = 0.002); similar costs ($21.8K [$13.3K to $34.9K] vs $21.9K [$13.1K to $36.3K]); and lower value of care (0.8 [0.5 to 1.3] vs 1.2 [0.7 to 2.0], p < 0.001).

CONCLUSIONS

Overtriage was associated with low value of care; undertriage was associated with both low value of care and increased mortality and morbidity. The proposed framework for generating automated postoperative triage classifications is reproducible.

Understanding small-scale COVID-19 transmission dynamics with the Granger causality test

Mobility patterns have been broadly studied and deeply altered due to the coronavirus disease (COVID-19). In this paper, we study small-scale COVID-19 transmission dynamics in the city of Valencia and the potential role of subway stations and healthcare facilities in this transmission. A total of 2,398 adult patients were included in the analysis. We study the temporal evolution of the pandemic during the first six months at a small-area level. Two Voronoi segmentations of the city (based on the location of subway stations and healthcare facilities) have been considered, and we have applied the Granger causality test at the Voronoi cell level, considering both divisions of the study area. Considering the output of this approach, the so-called 'donor stations' are subway stations that have sent more connections than they have received and are mainly located in interchanger stations. The transmission in primary healthcare facilities showed a heterogeneous pattern. Given that subway interchange stations receive many cases from other regions of the city, implementing isolation measures in these areas might be beneficial for the reduction of transmission.

Assessing the effect of Aedes (Stegomyia) aegypti (Linnaeus, 1762) control based on machine learning for predicting the spatiotemporal distribution of eggs in ovitraps

Background

Aedes aegypti is the dominant vector of several arboviruses that threaten urban populations in tropical and subtropical countries. Because of the climate changes and the spread of the disease worldwide, the population at risk of acquiring the disease is increasing.

Methods

This study investigated the impact of the larval habitats control (CC), nebulization (NEB), and both methods (CC + NEB) using the distribution of Ae. aegypti eggs collected in urban area of Santa Bárbara d'Oeste, São Paulo State, Brazil. A total of 142,469 eggs were collected from 2014 to 2017. To verify the effects of control interventions, a spatial trend, and a predictive machine learning modeling analytical approaches were adopted.

Results

The spatial analysis revealed sites with the highest probability of Ae. aegypti occurrence and the machine learning generated an asymmetric histogram for predicting the presence of the mosquito. Results of analyses showed that CC, NEB, and CC + NEB control methods had a negative impact on the number of eggs collected in ovitraps, with effects on the distribution of eggs in the three weeks following the treatments, according to the predictive machine learning modeling.

Conclusions

The vector control interventions are essential to decrease both occurrence of the mosquito vectors and urban arboviruses. The inference processes proposed in this study revealed the relative causal impact of distinct mosquito control interventions. The spatio-temporal and the machine learning analysis are relevant and Powered by Editorial Manager® and ProduXion Manager® from Aries Systems Corporation robust analytical approach to be employed in surveillance and monitoring the results of public health programs focused on combating urban arboviruses.

Leveraging electronic health records for data science: common pitfalls and how to avoid them

Analysis of electronic health records (EHRs) is an increasingly common approach for studying real-world patient data. Use of routinely collected data offers several advantages compared with other study designs, including reduced administrative costs, the ability to update analysis as practice patterns evolve, and larger sample sizes. Methodologically, EHR analysis is subject to distinct challenges because data are not collected for research purposes. In this Viewpoint, we elaborate on the importance of in-depth knowledge of clinical workflows and describe six potential pitfalls to be avoided when working with EHR data, drawing on examples from the literature and our experience. We propose solutions for prevention or mitigation of factors associated with each of these six pitfalls-sample selection bias, imprecise variable definitions, limitations to deployment, variable measurement frequency, subjective treatment allocation, and model overfitting. Ultimately, we hope that this Viewpoint will guide researchers to further improve the methodological robustness of EHR analysis.

Still Searching for Understanding: The Importance of Diverse Research Designs, Methods, and Perspectives

BACKGROUND

Evidence-based medicine and evidence hierarchies have been widely adopted and have strongly influenced decision making across many fields, including clinical aphasiology. However, questions remain about the creation, usefulness, and validity of current evidence hierarchies.

AIMS

This article builds on ideas about scientific approaches and evidence originally shared by Elman (1995, 1998, 2006). This article reviews the history of evidence hierarchies and argues that improving the diversity of research designs, methods, and perspectives will improve understanding of the numerous and complex variables associated with aphasia intervention. Researchers and clinicians are encouraged to synthesize diverse types of scientific evidence. It is hoped that this article will stimulate thought and foster discussion in order to encourage high-caliber research of all types.

MAIN CONTRIBUTION

Concepts from a wide variety of fields including philosophy of science, research design and methodology, and precision medicine are brought together in an attempt to focus research on the scientific understanding of aphasia treatment effects.

CONCLUSION

It is hoped that by incorporating diverse research designs, methods, and perspectives, clinical aphasiologists will become better able to provide effective, personalized treatments, ensuring that each person with aphasia is able to improve their communication ability and quality of life.

Impossibility of Superluminal Signaling in Minkowski Spacetime Does Not Rule Out Causal Loops

Causality is fundamental to science, but it appears in several different forms. One is relativistic causality, which is tied to a spacetime structure and forbids signaling outside the future. A second is an operational notion of causation that considers the flow of information between physical systems and interventions on them. In [V. Vilasini and R. Colbeck, General framework for cyclic and fine-tuned causal models and their compatibility with space-time, Phys. Rev. A 106, 032204 (2022).PLRAAN2469-992610.1103/PhysRevA.106.032204], we propose a framework for characterizing when a causal model can coexist with relativistic principles such as no superluminal signaling, while allowing for cyclic and nonclassical causal influences and the possibility of causation without signaling. In a theory without superluminal causation, both superluminal signaling and causal loops are not possible in Minkowski spacetime. Here we demonstrate that if we only forbid superluminal signaling, superluminal causation remains possible and show the mathematical possibility of causal loops that can be embedded in a Minkowski spacetime without leading to superluminal signaling. The existence of such loops in the given spacetime could in principle be operationally verified using interventions. This establishes that the physical principle of no superluminal signaling is not by itself sufficient to rule out causal loops between Minkowski spacetime events. Interestingly, the conditions required to rule out causal loops in a spacetime depend on the dimension. Whether such loops are possible in three spatial dimensions remains an important open question.

Factors influencing public support for banning gasoline vehicles in newly industrialized countries for the sake of environmental improvement: a case study of China

In recent years, various countries have put forward Banning Gasoline Vehicle Sales Policy (BGVSP), and the degree of public support for BGVSP is crucial to its design and implementation. Taking China as an example, this study built a policy support index using network crawler technology and natural language processing technology. Then, multi-spatial convergence cross-mapping technology was used to study the interaction between public support and air pollution, electric vehicle (EV) infrastructure, EV technology, and use cost. The results showed that air pollution has a significant impact on public support; public support has a significant impact on the construction of the EV infrastructure and the level of EV technological research, and the use cost of traditional gasoline vehicles has a significant impact on public support. This study investigated the correlations between public support and the factors influencing public support, and the results can be used as a reference for the design and implementation of BGVSP in newly industrialized countries.

Causal associations of genetic factors with clinical progression in amyotrophic lateral sclerosis

BACKGROUND AND OBJECTIVE

Recent advances in the genetic causes of ALS reveals that about 10% of ALS patients have a genetic origin and that more than 30 genes are likely to contribute to this disease. However, four genes are more frequently associated with ALS: C9ORF72, TARDBP, SOD1, and FUS. The relationship between genetic factors and ALS progression rate is not clear. In this study, we carried out a causal analysis of ALS disease with a genetics perspective in order to assess the contribution of the four mentioned genes to the progression rate of ALS.

METHODS

In this work, we applied a novel causal learning model to the CRESLA dataset which is a longitudinal clinical dataset of ALS patients including genetic information of such patients. This study aims to discover the relationship between four mentioned genes and ALS progression rate from a causation perspective using machine learning and probabilistic methods.

RESULTS

The results indicate a meaningful association between genetic factors and ALS progression rate with causality viewpoint. Our findings revealed that causal relationships between ALSFRS-R items associated with bulbar regions have the strongest association with genetic factors, especially C9ORF72; and other three genes have the greatest contribution to the respiratory ALSFRS-R items with a causation point of view.

CONCLUSIONS

The findings revealed that genetic factors have a significant causal effect on the rate of ALS progression. Since C9ORF72 patients have higher proportion compared to those carrying other three gene mutations in the CRESLA cohort, we need a large multi-centric study to better analyze SOD1, TARDBP and FUS contribution to the ALS clinical progression. We conclude that causal associations between ALSFRS-R clinical factors is a suitable predictor for designing a prognostic model of ALS.

Causal Discovery in Manufacturing: A Structured Literature Review

Industry 4.0 radically alters manufacturing organization and management, fostering collection and analysis of increasing amounts of data. Advanced data analytics, such as machine learning (ML), are essential for implementing Industry 4.0 and obtaining insights regarding production, better decision support, and enhanced manufacturing quality and sustainability. ML outperforms traditional approaches in many cases, but its complexity leads to unclear bases for decisions. Thus, acceptance of ML and, concomitantly, Industry 4.0, is hindered due to increasing requirements of fairness, accountability, and transparency, especially in sensitive-use cases. ML does not augment organizational knowledge, which is highly desired by manufacturing experts. Causal discovery promises a solution by providing insights on causal relationships that go beyond traditional ML’s statistical dependency. Causal discovery has a theoretical background and been successfully applied in medicine, genetics, and ecology. However, in manufacturing, only experimental and scattered applications are known; no comprehensive overview about how causal discovery can be applied in manufacturing is available. This paper investigates the state and development of research on causal discovery in manufacturing by focusing on motivations for application, common application scenarios and approaches, impacts, and implementation challenges. Based on the structured literature review, four core areas are identified, and a research agenda is proposed.

Long-term exposure to ambient temperature and mortality risk in China: A nationwide study using the difference-in-differences design

The short-term effects of ambient temperature on mortality have been widely investigated. However, the epidemiological evidence on the long-term effects of temperature on mortality is rare. In present study, we conducted a nationwide quasi-experimental design, which based on a variant of difference-in-differences (DID) approach, to examine the association between long-term exposure to ambient temperature and mortality risk in China, and to analyze the effect modification of population characteristics and socioeconomic status. Data on mortality were collected from 364 communities across China during 2006-2017, and environmental data were obtained for the same period. We estimated a 2.93 % (95 % CI: 2.68 %, 3.18 %) increase in mortality risk per 1 °C decreases in annual temperature, the greater effects were observed on respiratory diseases (5.16 %, 95 % CI: 4.53 %, 5.79 %) than cardiovascular diseases (3.43 %, 95 % CI: 3.06 %, 3.80 %), and on younger people (4.21 %, 95 % CI: 3.73 %, 4.68 %) than the elderly (2.36 %, 95 % CI: 2.06 %, 2.65 %). In seasonal analysis, per 1 °C decreases in average temperature was associated with 1.55 % (95 % CI: 1.23 %, 1.87 %), -0.53 % (95 % CI: -0.89 %, -0.16 %), 2.88 % (95 % CI: 2.45 %, 3.31 %) and 4.21 % (95 % CI: 3.98 %, 4.43 %) mortality change in spring, summer, autumn and winter, respectively. The effects of long-term temperature on total mortality were more pronounced among the communities with low urbanization, low education attainment, and low GDP per capita. In total, the decrease of average temperature in summer decreased mortality risk, while increased mortality risk in other seasons, and the associations were modified by demographic characteristics and socioeconomic status. Our findings suggest that populations with disadvantaged characteristics and socioeconomic status are vulnerable to long-term exposure of temperature, and targeted policies should be formulated to strengthen the response to the health threats of temperature exposure.

Big Data to Knowledge: Application of Machine Learning to Predictive Modeling of Therapeutic Response in Cancer

Background

In recent years, the availability of high throughput technologies, establishment of large molecular patient data repositories, and advancement in computing power and storage have allowed elucidation of complex mechanisms implicated in therapeutic response in cancer patients. The breadth and depth of such data, alongside experimental noise and missing values, requires a sophisticated human-machine interaction that would allow effective learning from complex data and accurate forecasting of future outcomes, ideally embedded in the core of machine learning design.

Objective

In this review, we will discuss machine learning techniques utilized for modeling of treatment response in cancer, including Random Forests, support vector machines, neural networks, and linear and logistic regression. We will overview their mathematical foundations and discuss their limitations and alternative approaches in light of their application to therapeutic response modeling in cancer.

Conclusion

We hypothesize that the increase in the number of patient profiles and potential temporal monitoring of patient data will define even more complex techniques, such as deep learning and causal analysis, as central players in therapeutic response modeling.

Dominant factors of the phosphorus regulatory network differ under various dietary phosphate loads in healthy individuals

BACKGROUND

The purpose of this study was to explore the contribution of each factor of the phosphorus metabolism network following phosphorus diet intervention via Granger causality analysis.

METHODS

In this study, a total of six healthy male volunteers were enrolled. All participants sequentially received regular, low-, and high-phosphorus diets. Consumption of each diet lasted for five days, with a 5-day washout period between different diets. Blood and urinary samples were collected on the fifth day of consumption of each diet at 9 time points (00:00, 04:00, 08:00, 10:00, 12:00, 14:00, 16:00, 20:00, 24:00) for measurements of serum levels of phosphate, calcium, PTH, FGF23, BALP, α-Klotho, and 1,25 D and urinary phosphorus excretion. Granger causality and the centrality of the above variables in the phosphorus network were analyzed by pairwise panel Granger causality analysis using the time-series data.

RESULTS

The mean age of the participants was 28.5 ± 2.1 years. By using Granger causality analysis, we found that the α-Klotho level had the strongest connection with and played a key role in influencing the other variables. In addition, urinary phosphorus excretion was frequently regulated by other variables in the network of phosphorus metabolism following a regular phosphorus diet. After low-phosphorus diet intervention, serum phosphate affected the other factors the most, and the 1,25 D level was the main outcome factor, while urinary phosphorus excretion was the most strongly associated variable in the network of phosphorus metabolism. After high-phosphorus diet intervention, FGF23 and 1,25 D played a more critical role in active regulation and passive regulation in the Granger causality analysis.

CONCLUSIONS

Variations in dietary phosphorus intake led to changes in the central factors involved in phosphorus metabolism.

Simplifying functional network representation and interpretation through causality clustering

Functional networks, i.e. networks representing the interactions between the elements of a complex system and reconstructed from the observed elements’ dynamics, are becoming a fundamental tool to unravel the structures created by the movement of information in systems like the human brain. They also present drawbacks, one of the most important being the inherent difficulty in representing and interpreting the resulting structures for large number of nodes and links. I here propose a causality clustering approach, based on grouping nodes into clusters according to their similarity in the overall information dynamics, the latter one being measured by a causality metric. The whole system can then arbitrarily be simplified, with nodes being grouped in e.g. sources, brokers and sinks of information. The advantages and limitations of the proposed approach are discussed using a set of synthetic and real-world data sets, the latter ones representing two neuroscience and technological problems.

Causal Datasheet for Datasets: An Evaluation Guide for Real-World Data Analysis and Data Collection Design Using Bayesian Networks

Developing data-driven solutions that address real-world problems requires understanding of these problems' causes and how their interaction affects the outcome-often with only observational data. Causal Bayesian Networks (BN) have been proposed as a powerful method for discovering and representing the causal relationships from observational data as a Directed Acyclic Graph (DAG). BNs could be especially useful for research in global health in Lower and Middle Income Countries, where there is an increasing abundance of observational data that could be harnessed for policy making, program evaluation, and intervention design. However, BNs have not been widely adopted by global health professionals, and in real-world applications, confidence in the results of BNs generally remains inadequate. This is partially due to the inability to validate against some ground truth, as the true DAG is not available. This is especially problematic if a learned DAG conflicts with pre-existing domain doctrine. Here we conceptualize and demonstrate an idea of a "Causal Datasheet" that could approximate and document BN performance expectations for a given dataset, aiming to provide confidence and sample size requirements to practitioners. To generate results for such a Causal Datasheet, a tool was developed which can generate synthetic Bayesian networks and their associated synthetic datasets to mimic real-world datasets. The results given by well-known structure learning algorithms and a novel implementation of the OrderMCMC method using the Quotient Normalized Maximum Likelihood score were recorded. These results were used to populate the Causal Datasheet, and recommendations could be made dependent on whether expected performance met user-defined thresholds. We present our experience in the creation of Causal Datasheets to aid analysis decisions at different stages of the research process. First, one was deployed to help determine the appropriate sample size of a planned study of sexual and reproductive health in Madhya Pradesh, India. Second, a datasheet was created to estimate the performance of an existing maternal health survey we conducted in Uttar Pradesh, India. Third, we validated generated performance estimates and investigated current limitations on the well-known ALARM dataset. Our experience demonstrates the utility of the Causal Datasheet, which can help global health practitioners gain more confidence when applying BNs.

Non-genetic risk and protective factors and biomarkers for neurological disorders: a meta-umbrella systematic review of umbrella reviews

BACKGROUND

The etiologies of chronic neurological diseases, which heavily contribute to global disease burden, remain far from elucidated. Despite available umbrella reviews on single contributing factors or diseases, no study has systematically captured non-purely genetic risk and/or protective factors for chronic neurological diseases.

METHODS

We performed a systematic analysis of umbrella reviews (meta-umbrella) published until September 20th, 2018, using broad search terms in MEDLINE, SCOPUS, Web of Science, Cochrane Database of Systematic Reviews, Cumulative Index to Nursing and Allied Health Literature, ProQuest Dissertations & Theses, JBI Database of Systematic Reviews and Implementation Reports, DARE, and PROSPERO. The PRISMA guidelines were followed for this study. Reference lists of the identified umbrella reviews were also screened, and the methodological details were assessed using the AMSTAR tool. For each non-purely genetic factor association, random effects summary effect size, 95% confidence and prediction intervals, and significance and heterogeneity levels facilitated the assessment of the credibility of the epidemiological evidence identified.

RESULTS

We identified 2797 potentially relevant reviews, and 14 umbrella reviews (203 unique meta-analyses) were eligible. The median number of primary studies per meta-analysis was 7 (interquartile range (IQR) 7) and that of participants was 8873 (IQR 36,394). The search yielded 115 distinctly named non-genetic risk and protective factors with a significant association, with various strengths of evidence. Mediterranean diet was associated with lower risk of dementia, Alzheimer disease (AD), cognitive impairment, stroke, and neurodegenerative diseases in general. In Parkinson disease (PD) and AD/dementia, coffee consumption, and physical activity were protective factors. Low serum uric acid levels were associated with increased risk of PD. Smoking was associated with elevated risk of multiple sclerosis and dementia but lower risk of PD, while hypertension was associated with lower risk of PD but higher risk of dementia. Chronic occupational exposure to lead was associated with higher risk of amyotrophic lateral sclerosis. Late-life depression was associated with higher risk of AD and any form of dementia.

CONCLUSIONS

We identified several non-genetic risk and protective factors for various neurological diseases relevant to preventive clinical neurology, health policy, and lifestyle counseling. Our findings could offer new perspectives in secondary research (meta-research).

Semidefinite Tests for Quantum Network Topologies

Quantum networks play a major role in long-distance communication, quantum cryptography, clock synchronization, and distributed quantum computing. Generally, these protocols involve many independent sources sharing entanglement among distant parties that, upon measuring their systems, generate correlations across the network. The question of which correlations a given quantum network can give rise to remains almost uncharted. Here we show that constraints on the observable covariances, previously derived for the classical case, also hold for quantum networks. The network topology yields tests that can be cast as semidefinite programs, thus allowing for the efficient characterization of the correlations in a wide class of quantum networks, as well as systematic derivations of device-independent and experimentally testable witnesses. We obtain such semidefinite tests for fixed measurement settings, as well as parties that independently choose among collections of measurement settings. The applicability of the method is demonstrated for various networks, and compared with previous approaches.

Effect of Prehospital Epinephrine on Outcomes of Out-of-Hospital Cardiac Arrest: A Bayesian Network Approach

BACKGROUND

The benefit of prehospital epinephrine in out-of-hospital cardiac arrest (OHCA) was shown in a recent large placebo-controlled trial. However, placebo-controlled studies cannot identify the nonpharmacologic influences on concurrent or downstream events that might modify the main effect positively or negatively. We sought to identify the real-world effect of epinephrine from a clinical registry using Bayesian network with time-sequence constraints.

METHODS

We analyzed a prospective regional registry of OHCA where a prehospital advanced life support (ALS) protocol named "Smart ALS (SALS)" was gradually implemented from July 2015 to December 2016. Using Bayesian network, a causal structure was estimated. The effect of epinephrine and SALS program was modelled based on the structure using extended Cox-regression and logistic regression, respectively.

RESULTS

Among 4324 patients, SALS was applied to 2351 (54.4%) and epinephrine was administered in 1644 (38.0%). Epinephrine was associated with faster ROSC rate in nonshockable rhythm (HR: 2.02, 6.94, and 7.43; 95% CI: 1.08-3.78, 4.15-11.61, and 2.92-18.91, respectively, for 1-10, 11-20, and >20 minutes) while it was associated with slower rate up to 20 minutes in shockable rhythm (HR: 0.40, 0.50, and 2.20; 95% CI: 0.21-0.76, 0.32-0.77, and 0.76-6.33). SALS was associated with increased prehospital ROSC and neurologic recovery in noncardiac etiology (HR: 5.36 and 2.05; 95% CI: 3.48-8.24 and 1.40-3.01, respectively, for nonshockable and shockable rhythm).

CONCLUSIONS

Epinephrine was associated with faster ROSC rate in nonshockable rhythm but slower rate in shockable rhythm up to 20 minutes. SALS was associated with improved prehospital ROSC and neurologic recovery in noncardiac etiology.

The emerging landscape of health research based on biobanks linked to electronic health records: Existing resources, statistical challenges, and potential opportunities

Biobanks linked to electronic health records provide rich resources for health-related research. With improvements in administrative and informatics infrastructure, the availability and utility of data from biobanks have dramatically increased. In this paper, we first aim to characterize the current landscape of available biobanks and to describe specific biobanks, including their place of origin, size, and data types. The development and accessibility of large-scale biorepositories provide the opportunity to accelerate agnostic searches, expedite discoveries, and conduct hypothesis-generating studies of disease-treatment, disease-exposure, and disease-gene associations. Rather than designing and implementing a single study focused on a few targeted hypotheses, researchers can potentially use biobanks' existing resources to answer an expanded selection of exploratory questions as quickly as they can analyze them. However, there are many obvious and subtle challenges with the design and analysis of biobank-based studies. Our second aim is to discuss statistical issues related to biobank research such as study design, sampling strategy, phenotype identification, and missing data. We focus our discussion on biobanks that are linked to electronic health records. Some of the analytic issues are illustrated using data from the Michigan Genomics Initiative and UK Biobank, two biobanks with two different recruitment mechanisms. We summarize the current body of literature for addressing these challenges and discuss some standing open problems. This work complements and extends recent reviews about biobank-based research and serves as a resource catalog with analytical and practical guidance for statisticians, epidemiologists, and other medical researchers pursuing research using biobanks.

Frequent Causal Pattern Mining: A Computationally Efficient Framework For Estimating Bias-Corrected Effects

Our aging population increasingly suffers from multiple chronic diseases simultaneously, necessitating the comprehensive treatment of these conditions. Finding the optimal set of drugs for a combinatorial set of diseases is a combinatorial pattern exploration problem. Association rule mining is a popular tool for such problems, but the requirement of health care for finding causal, rather than associative, patterns renders association rule mining unsuitable. To address this issue, we propose a novel framework based on the Rubin-Neyman causal model for extracting causal rules from observational data, correcting for a number of common biases. Specifically, given a set of interventions and a set of items that define subpopulations (e.g., diseases), we wish to find all subpopulations in which effective intervention combinations exist and in each such subpopulation, we wish to find all intervention combinations such that dropping any intervention from this combination will reduce the efficacy of the treatment. A key aspect of our framework is the concept of closed intervention sets which extend the concept of quantifying the effect of a single intervention to a set of concurrent interventions. Closed intervention sets also allow for a pruning strategy that is strictly more efficient than the traditional pruning strategy used by the Apriori algorithm. To implement our ideas, we introduce and compare five methods of estimating causal effect from observational data and rigorously evaluate them on synthetic data to mathematically prove (when possible) why they work. We also evaluated our causal rule mining framework on the Electronic Health Records (EHR) data of a large cohort of 152000 patients from Mayo Clinic and showed that the patterns we extracted are sufficiently rich to explain the controversial findings in the medical literature regarding the effect of a class of cholesterol drugs on Type-II Diabetes Mellitus (T2DM).

Discovering Cross-Reactivity in Urine Drug Screening Immunoassays through Large-Scale Analysis of Electronic Health Records

BACKGROUND

Exposure to drugs of abuse is frequently assessed using urine drug screening (UDS) immunoassays. Although fast and relatively inexpensive, UDS assays often cross-react with unrelated compounds, which can lead to false-positive results and impair patient care. The current process of identifying cross-reactivity relies largely on case reports, making it sporadic and inefficient, and rendering knowledge of cross-reactivity incomplete. Here, we present a systematic approach to discover cross-reactive substances using data from electronic health records (EHRs).

METHODS

Using our institution's EHR data, we assembled a data set of 698651 UDS results across 10 assays and linked each UDS result to the corresponding individual's previous medication exposures. We hypothesized that exposure to a cross-reactive ingredient would increase the odds of a false-positive screen. For 2201 assay-ingredient pairs, we quantified potential cross-reactivity as an odds ratio from logistic regression. We then evaluated cross-reactivity experimentally by spiking the ingredient or its metabolite into drug-free urine and testing the spiked samples on each assay.

RESULTS

Our approach recovered multiple known cross-reactivities. After accounting for concurrent exposures to multiple ingredients, we selected 18 compounds (13 parent drugs and 5 metabolites) to evaluate experimentally. We validated 12 of 13 tested assay-ingredient pairs expected to show cross-reactivity by our analysis, discovering previously unknown cross-reactivities affecting assays for amphetamines, buprenorphine, cannabinoids, and methadone.

CONCLUSIONS

Our findings can help laboratorians and providers interpret presumptive positive UDS results. Our data-driven approach can serve as a model for high-throughput discovery of substances that interfere with laboratory tests.

Metabolome-wide association study of anti-epileptic drug treatment during pregnancy

Pregnant women with epilepsy (PWWE) require continuous anti-epileptic drug (AED) treatment to avoid risk to themselves and fetal risks secondary to maternal seizures, resulting in prolonged AED exposure to the developing embryo and fetus. The objectives of this study were to determine whether high-resolution metabolomics is able to link the metabolite profile of PWWE receiving lamotrigine or levetiracetam for seizure control to associated pharmacodynamic (PD) biological responses. Untargeted metabolomic analysis of plasma obtained from 82 PWWE was completed using high-resolution mass spectrometry. Biological alterations due to lamotrigine or levetiracetam monotherapy were determined by a metabolome-wide association study that compared patients taking either drug to those who did not require AED treatment. Metabolic changes associated with AED use were then evaluated by testing for drug-dose associated metabolic variations and pathway enrichment. AED therapy resulted in drug-associated metabolic profiles recognizable within maternal plasma. Both the parent compounds and major metabolites were detected, and each AED was correlated with other metabolic features and pathways. Changes in metabolites and metabolic pathways important to maternal health and linked to fetal neurodevelopment were detected for both drugs, including changes in one‑carbon metabolism, neurotransmitter biosynthesis and steroid metabolism. In addition, decreased levels of 5-methyltetrahydrofolate and tetrahydrofolate were detected in women taking lamotrigine, which is consistent with recent findings showing increased risk of autism spectrum disorder traits in PWWE using AED. These results represent a first step in development of pharmacometabolomic framework with potential to detect adverse AED-related metabolic changes during pregnancy.

Causal Queries from Observational Data in Biological Systems via Bayesian Networks: An Empirical Study in Small Networks

Biological networks are a very convenient modeling and visualization tool to discover knowledge from modern high-throughput genomics and post-genomics data sets. Indeed, biological entities are not isolated but are components of complex multilevel systems. We go one step further and advocate for the consideration of causal representations of the interactions in living systems. We present the causal formalism and bring it out in the context of biological networks, when the data is observational. We also discuss its ability to decipher the causal information flow as observed in gene expression. We also illustrate our exploration by experiments on small simulated networks as well as on a real biological data set.

Learning to Personalize from Practice: A Real World Evidence Approach of Care Plan Personalization based on Differential Patient Behavioral Responses in Care Management Records

Recent studies documented the importance of individuality and heterogeneity in care planning. In practice, varying behavioral responses are revealed in patients' care management (CM) records. However, today's care programs are structured around population-level evidence. What if care managers can take advantage of the revealed behavioral response for personalization? The goal of this study is thus to quantify behavioral response from CM records for informing individual-level intervention decisions. We present a Behavioral Response Inference Framework (BRIeF) for understanding differential behavioral responses that are key to effective care planning. We analyze CM records from a healthcare network over a 14-month period and obtain a set of 2,416 intervention-goal attainment records. Promising results demonstrate that the individual-level care planning strategies that are learned from practice by BRIeF, outperform population-level strategies, yielding significantly more accurate intervention recommendations for goal attainment. To our knowledge, this is the first study of learning practice-based evidence from CM records for care planning, suggesting that increased patient behavioral understanding could potentially benefit augmented intelligence for care management decision support.

Modernizing the Bradford Hill criteria for assessing causal relationships in observational data

Perhaps no other topic in risk analysis is more difficult, more controversial, or more important to risk management policy analysts and decision-makers than how to draw valid, correctly qualified causal conclusions from observational data. Statistical methods can readily quantify associations between observed variables using measures such as relative risk (RR) ratios, odds ratios (OR), slope coefficients for exposure or treatment variables in regression models, and quantities derived from these measures. Textbooks of epidemiology explain how to calculate population attributable fractions, attributable risks, burden-of-disease estimates, and probabilities of causation from relative risk (RR) ratios. Despite their suggestive names, these association-based measures have no necessary connection to causation if the associations on which they are based arise from bias, confounding, p-hacking, coincident historical trends, or other noncausal sources. But policy analysts and decision makers need something more: trustworthy predictions - and, later, evaluations - of the changes in outcomes caused by changes in policy variables. This concept of manipulative causation differs from the more familiar concepts of associational and attributive causation most widely used in epidemiology. Drawing on modern literature on causal discovery and inference principles and algorithms for drawing limited but useful causal conclusions from observational data, we propose seven criteria for assessing consistency of data with a manipulative causal exposure-response relationship - mutual information, directed dependence, internal and external consistency, coherent causal explanation of biological plausibility, causal mediation confirmation, and refutation of non-causal explanations - and discuss to what extent it is now possible to automate discovery of manipulative causal dependencies and quantification of causal effects from observational data. We compare our proposed principles for causal discovery and inference to the traditional Bradford Hill considerations from 1965. Understanding how old and new principles are related can clarify and enrich both.

Association networks in a matched case-control design - Co-occurrence patterns of preexisting chronic medical conditions in patients with major depression versus their matched controls

OBJECTIVE

We present a method for comparing association networks in a matched case-control design, which provides a high-level comparison of co-occurrence patterns of features after adjusting for confounding factors. We demonstrate this approach by examining the differential distribution of chronic medical conditions in patients with major depressive disorder (MDD) compared to the distribution of these conditions in their matched controls.

MATERIALS AND METHODS

Newly diagnosed MDD patients were matched to controls based on their demographic characteristics, socioeconomic status, place of residence, and healthcare service utilization in the Korean National Health Insurance Service's National Sample Cohort. Differences in the networks of chronic medical conditions in newly diagnosed MDD cases treated with antidepressants, and their matched controls, were prioritized with a permutation test accounting for the false discovery rate. Sensitivity analyses for the associations between prioritized pairs of chronic medical conditions and new MDD diagnosis were performed with regression modeling.

RESULTS

By comparing the association networks of chronic medical conditions in newly diagnosed depression patients and their matched controls, five pairs of such conditions were prioritized among 105 possible pairs after controlling the false discovery rate at 5%. In sensitivity analyses using regression modeling, four out of the five prioritized pairs were statistically significant for the interaction terms.

CONCLUSION

Association networks in a matched case-control design can provide a high-level comparison of comorbid features after adjusting for confounding factors, thereby supplementing traditional clinical study approaches. We demonstrate the differential co-occurrence pattern of chronic medical conditions in patients with MDD and prioritize the chronic conditions that have statistically significant interactions in regression models for depression.

Hierarchical Algorithms for Causality Retrieval in Atrial Fibrillation Intracavitary Electrograms

Multichannel intracavitary electrograms (EGMs) are acquired at the electrophysiology laboratory to guide radio frequency catheter ablation of patients suffering from atrial fibrillation. These EGMs are used by cardiologists to determine candidate areas for ablation (e.g., areas corresponding to high dominant frequencies or complex fractionated electrograms). In this paper, we introduce two hierarchical algorithms to retrieve the causal interactions among these multiple EGMs. Both algorithms are based on Granger causality, but other causality measures can be easily incorporated. In both cases, they start by selecting a root node, but they differ on the way in which they explore the set of signals to determine their cause-effect relationships: either testing the full set of unexplored signals (GS-CaRe) or performing a local search only among the set of neighbor EGMs (LS-CaRe). The ensuing causal model provides important information about the propagation of the electrical signals inside the atria, uncovering wavefronts and activation patterns that can guide cardiologists towards candidate areas for catheter ablation. Numerical experiments, on both synthetic signals and annotated real-world signals, show the good performance of the two proposed approaches.

Time, frequency, and time-varying Granger-causality measures in neuroscience

This article proposes a systematic methodological review and an objective criticism of existing methods enabling the derivation of time, frequency, and time-varying Granger-causality statistics in neuroscience. The capacity to describe the causal links between signals recorded at different brain locations during a neuroscience experiment is indeed of primary interest for neuroscientists, who often have very precise prior hypotheses about the relationships between recorded brain signals. The increasing interest and the huge number of publications related to this topic calls for this systematic review, which describes the very complex methodological aspects underlying the derivation of these statistics. In this article, we first present a general framework that allows us to review and compare Granger-causality statistics in the time domain, and the link with transfer entropy. Then, the spectral and the time-varying extensions are exposed and discussed together with their estimation and distributional properties. Although not the focus of this article, partial and conditional Granger causality, dynamical causal modelling, directed transfer function, directed coherence, partial directed coherence, and their variant are also mentioned.

Estimating the effects of second-line therapy for type 2 diabetes mellitus: retrospective cohort study

OBJECTIVE

Metformin is the recommended initial drug treatment in type 2 diabetes mellitus, but there is no clearly preferred choice for an additional drug when indicated. We compare the counterfactual drug effectiveness in lowering glycated hemoglobin (HbA1c) levels and effect on body mass index (BMI) of four diabetes second-line drug classes using electronic health records.

STUDY DESIGN AND SETTING

Retrospective analysis of electronic health records of US-based patients in the Explorys database using causal inference methodology to adjust for patient censoring and confounders.

PARTICIPANTS AND EXPOSURES

Our cohort consisted of more than 40 000 patients with type 2 diabetes, prescribed metformin along with a drug out of four second-line drug classes-sulfonylureas, thiazolidinediones, dipeptidyl peptidase 4 (DPP-4) inhibitors and glucagon-like peptide-1 agonists-during the years 2000-2015. Roughly, 17 000 of these patients were followed for 12 months after being prescribed a second-line drug.

MAIN OUTCOME MEASURES

HbA1c and BMI of these patients after 6 and 12 months following treatment.

RESULTS

We demonstrate that all four drug classes reduce HbA1c levels, but the effect of sulfonylureas after 6 and 12 months of treatment is less pronounced compared with other classes. We also estimate that DPP-4 inhibitors decrease body weight significantly more than sulfonylureas and thiazolidinediones.

CONCLUSION

Our results are in line with current knowledge on second-line drug effectiveness and effect on BMI. They demonstrate that causal inference from electronic health records is an effective way for conducting multitreatment causal inference studies.

Infer Cause of Death for Population Health Using Convolutional Neural Network

In biomedical data analysis, inferring the cause of death is a challenging and important task, which is useful for both public health reporting purposes, as well as improving patients' quality of care by identifying severer conditions. Causal inference, however, is notoriously difficult. Traditional causal inference mainly relies on analyzing data collected from experiment of specific design, which is expensive, and limited to a certain disease cohort, making the approach less generalizable. In our paper, we adopt a novel data-driven perspective to analyze and improve the death reporting process, to assist physicians identify the single underlying cause of death. To achieve this, we build state-of-the-art deep learning models, convolution neural network (CNN), and achieve around 75% accuracy in predicting the single underlying cause of death from a list of relevant medical conditions. We also provide interpretations for the black-box neural network models, so that death reporting physicians can apply the model with better understanding of the model.

Systems Medicine-Complexity Within, Simplicity Without

This paper presents a brief history of Systems Theory, progresses to Systems Biology, and its relation to the more traditional investigative method of reductionism. The emergence of Systems Medicine represents the application of Systems Biology to disease and clinical issues. The challenges faced by this transition from Systems Biology to Systems Medicine are explained; the requirements of physicians at the bedside, caring for patients, as well as the place of human-human interaction and the needs of the patients are addressed. An organ-focused transition to Systems Medicine, rather than a genomic-, molecular-, or cell-based effort is emphasized. Organ focus represents a middle-out approach to ease this transition and to maximize the benefits of scientific discovery and clinical application. This method manages the perceptions of time and space, the massive amounts of human- and patient-related data, and the ensuing complexity of information.

Open source platform for collaborative construction of wearable sensor datasets for human motion analysis and an application for gait analysis

Nearly every practical improvement in modeling human motion is well founded in a properly designed collection of data or datasets. These datasets must be made publicly available for the community could validate and accept them. It is reasonable to concede that a collective, guided enterprise could serve to devise solid and substantial datasets, as a result of a collaborative effort, in the same sense as the open software community does. In this way datasets could be complemented, extended and expanded in size with, for example, more individuals, samples and human actions. For this to be possible some commitments must be made by the collaborators, being one of them sharing the same data acquisition platform. In this paper, we offer an affordable open source hardware and software platform based on inertial wearable sensors in a way that several groups could cooperate in the construction of datasets through common software suitable for collaboration. Some experimental results about the throughput of the overall system are reported showing the feasibility of acquiring data from up to 6 sensors with a sampling frequency no less than 118Hz. Also, a proof-of-concept dataset is provided comprising sampled data from 12 subjects suitable for gait analysis.

Causal Relationship Detection in Archival Collections of Product Reviews for Understanding Technology Evolution

Technology progress is one of the key reasons behind today's rapid changes in lifestyles. Knowing how products and objects evolve can not only help with understanding the evolutionary patterns in our society but can also provide clues on effective product design and can offer support for predicting the future. We propose a general framework for analyzing technology's impact on our lives through detecting cause--effect relationships, where causes represent changes in technology while effects are changes in social life, such as new activities or new ways of using products. We address the challenge of viewing technology evolution through the “social impact lens” by mining causal relationships from the long-term collections of product reviews. In particular, we first propose dividing vocabulary into two groups: terms describing product features (called physical terms ) and terms representing product usage (called conceptual terms ). We then search for two kinds of changes related to the appearance of terms: frequency-based and context-based changes. The former indicate periods when a word was significantly more frequently used, whereas the latter indicate periods of high change in the word's context. Based on the detected changes, we then search for causal term pairs such that the change in the physical term triggers the change in the conceptual term. We next extend our approach to finding causal relationships between word groups such as a group of words representing the same technology and causing a given conceptual change or group of words representing two different technologies that simultaneously “co-cause” a conceptual change. We conduct experiments on different product types using the Amazon Product Review Dataset, which spans 1995 to 2013, and we demonstrate that our approaches outperform state-of-the-art baselines.

Causal Inference Based on the Analysis of Events of Relations for Non-stationary Variables

The main concept behind causality involves both statistical conditions and temporal relations. However, current approaches to causal inference, focusing on the probability vs. conditional probability contrast, are based on model functions or parametric estimation. These approaches are not appropriate when addressing non-stationary variables. In this work, we propose a causal inference approach based on the analysis of Events of Relations (CER). CER focuses on the temporal delay relation between cause and effect, and a binomial test is established to determine whether an "event of relation" with a non-zero delay is significantly different from one with zero delay. Because CER avoids parameter estimation of non-stationary variables per se, the method can be applied to both stationary and non-stationary signals.

Characterizing treatment pathways at scale using the OHDSI network

Observational research promises to complement experimental research by providing large, diverse populations that would be infeasible for an experiment. Observational research can test its own clinical hypotheses, and observational studies also can contribute to the design of experiments and inform the generalizability of experimental research. Understanding the diversity of populations and the variance in care is one component. In this study, the Observational Health Data Sciences and Informatics (OHDSI) collaboration created an international data network with 11 data sources from four countries, including electronic health records and administrative claims data on 250 million patients. All data were mapped to common data standards, patient privacy was maintained by using a distributed model, and results were aggregated centrally. Treatment pathways were elucidated for type 2 diabetes mellitus, hypertension, and depression. The pathways revealed that the world is moving toward more consistent therapy over time across diseases and across locations, but significant heterogeneity remains among sources, pointing to challenges in generalizing clinical trial results. Diabetes favored a single first-line medication, metformin, to a much greater extent than hypertension or depression. About 10% of diabetes and depression patients and almost 25% of hypertension patients followed a treatment pathway that was unique within the cohort. Aside from factors such as sample size and underlying population (academic medical center versus general population), electronic health records data and administrative claims data revealed similar results. Large-scale international observational research is feasible.

An Evaluation of Active Learning Causal Discovery Methods for Reverse-Engineering Local Causal Pathways of Gene Regulation

Reverse-engineering of causal pathways that implicate diseases and vital cellular functions is a fundamental problem in biomedicine. Discovery of the local causal pathway of a target variable (that consists of its direct causes and direct effects) is essential for effective intervention and can facilitate accurate diagnosis and prognosis. Recent research has provided several active learning methods that can leverage passively observed high-throughput data to draft causal pathways and then refine the inferred relations with a limited number of experiments. The current study provides a comprehensive evaluation of the performance of active learning methods for local causal pathway discovery in real biological data. Specifically, 54 active learning methods/variants from 3 families of algorithms were applied for local causal pathways reconstruction of gene regulation for 5 transcription factors in S. cerevisiae. Four aspects of the methods' performance were assessed, including adjacency discovery quality, edge orientation accuracy, complete pathway discovery quality, and experimental cost. The results of this study show that some methods provide significant performance benefits over others and therefore should be routinely used for local causal pathway discovery tasks. This study also demonstrates the feasibility of local causal pathway reconstruction in real biological systems with significant quality and low experimental cost.