Error-prone Data Research Articles

A scalable and transparent data pipeline for AI-enabled health data ecosystems.

Transparency and traceability are essential for establishing trustworthy artificial intelligence (AI). The lack of transparency in the data preparation process is a significant obstacle in developing reliable AI systems which can lead to issues related to reproducibility, debugging AI models, bias and fairness, and compliance and regulation. We introduce a formal data preparation pipeline specification to improve upon the manual and error-prone data extraction processes used in AI and data analytics applications, with a focus on traceability. We propose a declarative language to define the extraction of AI-ready datasets from health data adhering to a common data model, particularly those conforming to HL7 Fast Healthcare Interoperability Resources (FHIR). We utilize the FHIR profiling to develop a common data model tailored to an AI use case to enable the explicit declaration of the needed information such as phenotype and AI feature definitions. In our pipeline model, we convert complex, high-dimensional electronic health records data represented with irregular time series sampling to a flat structure by defining a target population, feature groups and final datasets. Our design considers the requirements of various AI use cases from different projects which lead to implementation of many feature types exhibiting intricate temporal relations. We implement a scalable and high-performant feature repository to execute the data preparation pipeline definitions. This software not only ensures reliable, fault-tolerant distributed processing to produce AI-ready datasets and their metadata including many statistics alongside, but also serve as a pluggable component of a decision support application based on a trained AI model during online prediction to automatically prepare feature values of individual entities. We deployed and tested the proposed methodology and the implementation in three different research projects. We present the developed FHIR profiles as a common data model, feature group definitions and feature definitions within a data preparation pipeline while training an AI model for "predicting complications after cardiac surgeries". Through the implementation across various pilot use cases, it has been demonstrated that our framework possesses the necessary breadth and flexibility to define a diverse array of features, each tailored to specific temporal and contextual criteria.

Research on the key technologies of the whole process of digital intelligent detection system of silicate binding material

Abstract In construction engineering, silicate binding material detection is the key work to ensure the safety of building structures. Although the current detection instruments have made great progress compared with the traditional detection methods, there are still problems such as low efficiency, heavy workload, and error-prone data due to manual operation. Based on the practical problems faced by silicate binding material quality detection, this paper studies the key technologies of the whole process digital intelligent detection system of silicate binding material, including multi-machine cooperative automatic dumping and scraping technology, multi-strategy robot scheduling algorithm and full-link traceability technology, and shows the application effect through the LIMS system function platform. The research effectively improves the working efficiency of silicate binding material detection, realizes real-time monitoring of data and unique coding of the whole process, and ensures the timeliness, authenticity, accuracy, and traceability of detection data.

SIMEXBoost: An R package for Analysis of High-Dimensional Error-Prone Data Based on Boosting Method

SIMEXBoost: An R package for Analysis of High-Dimensional Error-Prone Data Based on Boosting Method

Three-phase generalized raking and multiple imputation estimators to address error-prone data.

Validation studies are often used to obtain more reliable information in settings with error-prone data. Validated data on a subsample of subjects can be used together with error-prone data on all subjects to improve estimation. In practice, more than one round of data validation may be required, and direct application of standard approaches for combining validation data into analyses may lead to inefficient estimators since the information available from intermediate validation steps is only partially considered or even completely ignored. In this paper, we present two novel extensions of multiple imputation and generalized raking estimators that make full use of all available data. We show through simulations that incorporating information from intermediate steps can lead to substantial gains in efficiency. This work is motivated by and illustrated in a study of contraceptive effectiveness among 83 671 women living with HIV, whose data were originally extracted from electronic medical records, of whom 4732 had their charts reviewed, and a subsequent 1210 also had a telephone interview to validate key study variables.

Acquisition of temporal patterns from electronic health records: an application to multimorbid patients

BackgroundThe exponential growth of digital healthcare data is fueling the development of Knowledge Discovery in Databases (KDD). Extracting temporal relationships between medical events is essential to reveal hidden patterns that can help physicians find optimal treatments, diagnose illnesses, detect drug adverse reactions, and more. This paper presents an approach for the extraction of patient evolution patterns from electronic health records written in Catalan and/or Spanish.MethodsWe propose a robust formulation for extracting Temporal Association Rules (TARs) that goes beyond simple rule extraction by considering the sequence of multiple visits. Our highly configurable algorithm leverages this formulation to extract Temporal Association Rules from sequences of medical instances. We can generate rules in the desired format, content, and temporal factors while accounting for different levels of abstraction of medical instances. To demonstrate the effectiveness of our methodology, we applied it to extract patient evolution patterns from clinical histories of multimorbid patients suffering from heart disease and stroke who visited Primary Care Centers (CAP) in Catalonia. Our main objective is to uncover complex rules with multiple temporal steps, that comprise a set of medical instances.ResultsAs we are working with real-world, error-prone data, we propose a process of validation of the results by expert practitioners in primary care. Despite our limited dataset, the high percentage of patterns deemed correct and relevant by the experts is promising. The insights gained from these patterns can inform preventive measures and help detect risk factors, ultimately leading to better treatments and outcomes for patients.ConclusionOur algorithm successfully extracted a set of meaningful and relevant temporal patterns, especially for the specific type of multimorbid patients considered. These patterns were evaluated by experts and demonstrated the ability to predict risk factors that are commonly associated with certain diseases. Moreover, the average time gap between the occurrence of medical events provided critical insight into the term of these risk factors. This information holds significant value in the context of primary healthcare and preventive medicine, highlighting the potential of our method to serve as a valuable medical tool.

Cloud Object Storage Synchronization: Design, Analysis, and Implementation

Cloud storage synchronization among different computing terminals has attracted large-scale uses among enterprise and individual users. It enables users to maintain the same copy of data in real time, which eases users the tedious yet error-prone data management burden. However, existing cloud storage synchronization systems are in a closed form. Users are fixed to a certain cloud service provider, which makes it hard to transfer from one provider to another when balancing factors such as performance, cost, security, etc. To bridge this gap, this article proposes a new synchronization system based on standard cloud <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">object</i> storage. Specifically, we first formulate the cloud object storage synchronization problem by defining some useful concepts. We then use the idea of state encoding and a push-pull paradigm to propose a cloud object storage synchronization system. The proposed system supports real-time, multiple-terminal, and cloud-independent storage synchronization. We also prototyped the proposed system. The experimental results show that the proposed system is promising for practical usages.

HarmonizR enables data harmonization across independent proteomic datasets with appropriate handling of missing values

Dataset integration is common practice to overcome limitations in statistically underpowered omics datasets. Proteome datasets display high technical variability and frequent missing values. Sophisticated strategies for batch effect reduction are lacking or rely on error-prone data imputation. Here we introduce HarmonizR, a data harmonization tool with appropriate missing value handling. The method exploits the structure of available data and matrix dissection for minimal data loss, without data imputation. This strategy implements two common batch effect reduction methods—ComBat and limma (removeBatchEffect()). The HarmonizR strategy, evaluated on four exemplarily analyzed datasets with up to 23 batches, demonstrated successful data harmonization for different tissue preservation techniques, LC-MS/MS instrumentation setups, and quantification approaches. Compared to data imputation methods, HarmonizR was more efficient and performed superior regarding the detection of significant proteins. HarmonizR is an efficient tool for missing data tolerant experimental variance reduction and is easily adjustable for individual dataset properties and user preferences.

OTHR-07. A new framework for missing value tolerant data integration

Dataset integration is common practice to overcome limitations, e.g., in statistically underpowered omics datasets. This is of particular importance when analyzing rare tumor entities. However, combining datasets leads to the introduction of biases, so called 'batch effects', which are due to differences in quantification techniques, laboratory equipment or used tissue type. A common problem is the missing quantification for features like gene transcripts or proteins within a dataset. These missing values can appear at random in a given dataset and also get introduced by combination of multiple datasets. Currently, strategies beyond common normalization for batch effect reduction are either missing entirely or are unable to handle absence of data points and therefore rely on error-prone data imputation. We introduce a framework that enables batch effect adjustments for combined datasets while avoiding data loss by appropriately handling missing values without imputation. The underlying idea is based on a matrix dissection approach, adjusting common information from the integrated dataset under guarantee of sufficient data presence. The strategy is implemented within the R environment and linked with popular software stacks that are built on top of R. Successful data adjustment is exemplarily shown for proteomic data generated by different quantification approaches and LC-MS/MS instrumentation setups.

Multi-view graph convolutional networks with attention mechanism

Recent advances in graph convolutional networks (GCNs), which mainly focus on how to exploit information from different hops of neighbors in an efficient way, have brought substantial improvement to many graph data modeling tasks. Most of the existing GCN-based models however are built on the basis of a fixed adjacency matrix, i.e., a single view topology of the underlying graph. That inherently limits the expressive power of the developed models especially when the raw graphs are often noisy or even incomplete due to the inevitably error-prone data measurement or collection. In this paper, we propose a novel framework, termed Multi-View Graph Convolutional Networks with Attention Mechanism (MAGCN), by incorporating multiple views of topology and an attention-based feature aggregation strategy into the computation of graph convolution. As an advanced variant of GCNs, MAGCN is fed with multiple “trustable” topologies, which already exist for a given task or are empirically generated by some classical graph construction methods, which has good potential to produce a better learning representation for downstream tasks. Furthermore, we present some theoretical analysis about the expressive power and flexibility of MAGCN, which provides a general explanation as to why multi-view based methods can potentially outperform those relying on a single view. Our experimental study demonstrates the state-of-the-art accuracies of MAGCN on Cora, Citeseer, and Pubmed datasets. Robustness analysis is also undertaken to show the advantage of MAGCN in handling some uncertainty issues in node classification tasks.

De-noising analysis of noisy data under mixed graphical models

Graphical models are useful to characterize the dependence structure of variables and have been commonly used for analysis of complex structured data. While various estimation methods have been developed under different graphical models, those methods are, however, inadequate to handle noisy data with measurement error. The development of most existing approaches relies on the implicit yet stringent assumption that the associated variables must be measured precisely. This assumption is unrealistic for many applications because mismeasurement in variables is usually presented in the data collection process. In this paper, we consider analysis of error-prone data under graphical models. To understand the impact of measurement error, we first study the asymptotic bias of the naive analysis which disregards the feature of measurement error in the variables. Furthermore, we develop a de-noising estimation procedure to account for measurement error effects. Theoretical results are established for the proposed method and numerical studies are reported to assess the finite sample performance of our proposed method.

Efficient odds ratio estimation under two-phase sampling using error-prone data from a multi-national HIV research cohort.

Persons living with HIV engage in routine clinical care, generating large amounts of data in observational HIV cohorts. These data are often error-prone, and directly using them in biomedical research could bias estimation and give misleading results. A cost-effective solution is the two-phase design, under which the error-prone variables are observed for all patients during Phase I, and that information is used to select patients for data auditing during Phase II. For example, the Caribbean, Central, and South America network for HIV epidemiology (CCASAnet) selected a random sample from each site for data auditing. Herein, we consider efficient odds ratio estimation with partially audited, error-prone data. We propose a semiparametric approach that uses all information from both phases and accommodates a number of error mechanisms. We allow both the outcome and covariates to be error-prone and these errors to be correlated, and selection of the Phase II sample can depend on Phase I data in an arbitrary manner. We devise a computationally efficient, numerically stable EM algorithm to obtain estimators that are consistent, asymptotically normal, and asymptotically efficient. We demonstrate the advantages of the proposed methods over existing ones through extensive simulations. Finally, we provide applications to the CCASAnetcohort.

Derivation of S-Curve from Oscillatory Hydrograph Using Digital Filter

An oscillatory S-curve causes unexpected fluctuations in a unit hydrograph (UH) of desired duration or an instantaneous UH (IUH) that may affect the constraints for hydrologic stability. On the other hand, the Savitzky–Golay smoothing and differentiation filter (SG filter) is a digital filter known to smooth data without distorting the signal tendency. The present study proposes a method based on the SG filter to cope with oscillatory S-curves. Compared to previous conventional methods, the application of the SG filter to an S-curve was shown to drastically reduce the oscillation problems on the UH and IUH. In this method, the SG filter parameters are selected to give the minimum influence on smoothing and differentiation. Based on runoff reproduction results and performance criteria, it appears that the SG filter performed both smoothing and differentiation without the remarkable variation of hydrograph properties such as peak or time-to peak. The IUH, UH, and S-curve were estimated using storm data from two watersheds. The reproduced runoffs showed high levels of model performance criteria. In addition, the analyses of two other watersheds revealed that small watershed areas may experience scale problems. The proposed method is believed to be valuable when error-prone data are involved in analyzing the linear rainfall–runoff relationship.

Two-Phase Sampling Designs for Data Validation in Settings with Covariate Measurement Error and Continuous Outcome.

Measurement errors are present in many data collection procedures and can harm analyses by biasing estimates. To correct for measurement error, researchers often validate a subsample of records and then incorporate the information learned from this validation sample into estimation. In practice, the validation sample is often selected using simple random sampling (SRS). However, SRS leads to inefficient estimates because it ignores information on the error-prone variables, which can be highly correlated to the unknown truth. Applying and extending ideas from the two-phase sampling literature, we propose optimal and nearly-optimal designs for selecting the validation sample in the classical measurement-error framework. We target designs to improve the efficiency of model-based and design-based estimators, and show how the resulting designs compare to each other. Our results suggest that sampling schemes that extract more information from the error-prone data are substantially more efficient than SRS, for both design- and model-based estimators. The optimal procedure, however, depends on the analysis method, and can differ substantially. This is supported by theory and simulations. We illustrate the various designs using data from an HIV cohort study.

A map of mass spectrometry-based in silico fragmentation prediction and compound identification in metabolomics.

Metabolomics, the comprehensive study of the metabolome, and lipidomics-the large-scale study of pathways and networks of cellular lipids-are major driving forces in enabling personalized medicine. Complicated and error-prone data analysis still remains a bottleneck, however, especially for identifying novel metabolites. Comparing experimental mass spectra to curated databases containing reference spectra has been the gold standard for identification of compounds, but constructing such databases is a costly and time-demanding task. Many software applications try to circumvent this process by utilizing cutting-edge advances in computational methods-including quantum chemistry and machine learning-and simulate mass spectra by performing theoretical, so called in silico fragmentations of compounds. Other solutions concentrate directly on experimental spectra and try to identify structural properties by investigating reoccurring patterns and the relationships between them. The considerable progress made in the field allows recent approaches to provide valuable clues to expedite annotation of experimental mass spectra. This review sheds light on individual strengths and weaknesses of these tools, and attempts to evaluate them-especially in view of lipidomics, when considering complex mixtures found in biological samples as well as mass spectrometer inter-instrument variability.

Corrected score methods for estimating Bayesian networks with error‐prone nodes

Motivated by inferring cellular signaling networks using noisy flow cytometry data, we develop procedures to draw inference for Bayesian networks based on error-prone data. Two methods for inferring causal relationships between nodes in a network are proposed based on penalized estimation methods that account for measurement error and encourage sparsity. We discuss consistency of the proposed network estimators and develop an approach for selecting the tuning parameter in the penalized estimation methods. Empirical studies are carried out to compare the proposed methods with a naive method that ignores measurement error. Finally, we apply these methods to infer signaling networks using single cell flow cytometry data.

Unsupervised content-preserving transformation for optical microscopy

The development of deep learning and open access to a substantial collection of imaging data together provide a potential solution for computational image transformation, which is gradually changing the landscape of optical imaging and biomedical research. However, current implementations of deep learning usually operate in a supervised manner, and their reliance on laborious and error-prone data annotation procedures remains a barrier to more general applicability. Here, we propose an unsupervised image transformation to facilitate the utilization of deep learning for optical microscopy, even in some cases in which supervised models cannot be applied. Through the introduction of a saliency constraint, the unsupervised model, named Unsupervised content-preserving Transformation for Optical Microscopy (UTOM), can learn the mapping between two image domains without requiring paired training data while avoiding distortions of the image content. UTOM shows promising performance in a wide range of biomedical image transformation tasks, including in silico histological staining, fluorescence image restoration, and virtual fluorescence labeling. Quantitative evaluations reveal that UTOM achieves stable and high-fidelity image transformations across different imaging conditions and modalities. We anticipate that our framework will encourage a paradigm shift in training neural networks and enable more applications of artificial intelligence in biomedical imaging.

A timed tally counter for microscopic examination of thick blood smears in malaria studies

BackgroundDespite many technological advances for malaria parasite detection (e.g. high resolution image acquisition), microscopic reading of thick blood smear (TBS) remains the gold standard. Even though available in low technology environment, the microscopy of TBS is slow and time consuming. Moreover microscopy may induce errors at many levels and has no quality control.MethodsA electronic extension of the mechanical tally counter is proposed. In addition to the counting process it includes the process of counting itself that relies on the time elapsed between two successive pressures of the counting button leading to a timed tally counter (TTC). The microscopist performs the reading with the specific instruction starting by counting, in each high power fields, leucocytes first and then parasites. The time-stamp of all pressures of counting buttons are recorded along with the nature of the count. The data are recorded internally in CSV format and are exportable. The detection of HPFs locations and leukocyte/parasite counts per HPFs is performed through a hidden semi-Markov model (with outliers) allowing both to take into account the known distribution of leukocyte per HPFs (using a negative binomial distribution) and the pauses and hesitation of the microscopist during the reading. Parameters are estimated via the expectation-maximization algorithm. Hyper-parameters are calibrated using expert annotations. Forward/backward recursions are used to obtain the HPFs locations.ResultsThis approach provides richer data at no extra cost. It has been demonstrated that the method can derive parasites per HPF, leukocytes per HPF, and parasite/leukocyte ratio with robust non-parametric confidence intervals. Moreover a direct digital data entry leads to a less expensive process and decreased time-consuming and error-prone manual data entry. Lastly the TTC allows detecting possible protocol break during reading and prevents the risk of fraud.Discussion and conclusionIntroducing a programmed digital device in the data acquisition of TBS reading gives the opportunity to develop easily new (possible adaptive) reading protocols that will be easily followed by the reader since they will be embedded directly in the device. With the TTC the reader only has to read HPFs, counting leukocytes first and parasites second, and the counter will beep when the protocol is completed.

Inferring room-level use of domestic space heating from room temperature and humidity measurements using a deep, dilated convolutional network

Time series data about when heating is on and off in homes can be useful for research on building energy use and occupant behaviours, particularly data at room level and at a granularity of minutes. Direct methods which measure the temperature of radiators and other heaters can be effective at producing such data, but are expensive. Indirect methods, which infer heating on- and off-times from ambient room temperature data, can be cheaper but produce more error-prone data. Existing indirect methods have however utilised relatively simple prediction algorithms based on changes in ambient temperature between closely adjacent time points. In the method presented here we have implemented several refinements to this approach:•An Artificial Neural Network algorithm is applied to the prediction task: a deep, dilated convolutional network.•A wider range of input features is utilised to base predictions upon: ambient room temperature and humidity, and external temperature and humidity.•Predictions for each time point are based on data from a wider, 600-minute, time window.•We evaluate model performance on a dataset with 10 min granularity and achieve mean precision and recall during the heating season of >=0.74 for individual time points, and >=0.82 for full heating events, outperforming comparator methods.

Two-phase analysis and study design for survival models with error-prone exposures.

Increasingly, medical research is dependent on data collected for non-research purposes, such as electronic health records data. Health records data and other large databases can be prone to measurement error in key exposures, and unadjusted analyses of error-prone data can bias study results. Validating a subset of records is a cost-effective way of gaining information on the error structure, which in turn can be used to adjust analyses for this error and improve inference. We extend the mean score method for the two-phase analysis of discrete-time survival models, which uses the unvalidated covariates as auxiliary variables that act as surrogates for the unobserved true exposures. This method relies on a two-phase sampling design and an estimation approach that preserves the consistency of complete case regression parameter estimates in the validated subset, with increased precision leveraged from the auxiliary data. Furthermore, we develop optimal sampling strategies which minimize the variance of the mean score estimator for a target exposure under a fixed cost constraint. We consider the setting where an internal pilot is necessary for the optimal design so that the phase two sample is split into a pilot and an adaptive optimal sample. Through simulations and data example, we evaluate efficiency gains of the mean score estimator using the derived optimal validation design compared to balanced and simple random sampling for the phase two sample. We also empirically explore efficiency gains that the proposed discrete optimal design can provide for the Cox proportional hazards model in the setting of a continuous-time survival outcome.

Setting up a maternal and newborn registry applying electronic platform: an experience from the Bangladesh site of the global network for women\u2019s and children\u2019s health

BackgroundThe Global Network for Women’s and Children’s Health Research (Global Network, GN) has established the Maternal Newborn Health Registry (MNHR) to assess MNH outcomes over time. Bangladesh is the newest country in the GN and has implemented a full electronic MNH registry system, from married women surveillance to pregnancy enrollment and subsequent follow ups.MethodLike other GN sites, the Bangladesh MNHR is a prospective, population-based observational study that tracks pregnancies and MNH outcomes. The MNHR site is in the Ghatail and Kalihati sub-districts of the Tangail district. The study area consists of 12 registry clusters each of ~ 18,000–19,000 population. All pregnant women identified through a two-monthly house-to-house surveillance are enrolled in the registry upon consenting and followed up on scheduled visits until 42 days after pregnancy outcome. A comprehensive automated registry data capture system has been developed that allows for married women surveillance, pregnancy enrollment, and data collection during follow-up visits using a web-linked tablet-PC-based system.ResultDuring March–May 2019, a total of 56,064 households located were listed in the Bangladesh MNH registry site. Of the total 221,462 population covered, 49,269 were currently married women in reproductive age (CMWRA). About 13% CMWRA were less susceptible to pregnancy. Large variability was observed in selected contraceptive usage across clusters. Overall, 5% of the listed CMWRAs were reported as currently pregnant.ConclusionIn comparison to paper-pen capturing system electronic data capturing system (EDC) has advantages of less error-prone data collection, real-time data collection progress monitoring, data quality check and sharing. But the implementation of EDC in a resource-poor setting depends on technical infrastructure, skilled staff, software development, community acceptance and a data security system. Our experience of pregnancy registration, intervention coverage, and outcome tracking provides important contextualized considerations for both design and implementation of individual-level health information capturing and sharing systems.