Graphical Framework Research Articles

Finding Decomposable Models for Efficient Distributed Inference over Sensor Networks

Graphical models have been widely applied in distributed network computation problems such as inference in large-scale sensor networks. While belief propagation (BP) based on message passing is a powerful approach to solving such distributed inference problems, one major challenge, in the context of wireless sensor networks, is how to systematically address the trade-off between energy efficiency and inference performance. In this paper, we consider a distributed structure optimization problem and investigate the impacts of graphical model structure on energy consumption and inference performance. We first formulate the problem as a multi-objective constrained combinatorial optimization problem and prove its NP-hardness. Then, we propose an efficient distributed heuristic to solve the problem in polynomial time. Through extensive simulations, using both real-world sensor network data and synthetic data, we empirically evaluate our proposed graphical model structure optimization framework. The simulation results demonstrate that the graphical model constructed by the proposed framework can efficiently trades off the performance of the inference algorithm (measured by the mean squared error) with the energy consumed by the inference algorithm (measured by the energy used in communication). In addition, our proposed framework provides valuable insights for network designers on designing efficient model selection algorithms for distributed inference problems.

Bayesian Nonparametric Graphical Models for Time-Varying Parameters VAR

Over the last decade, big data have poured into econometrics, demanding new statistical methods for analysing high-dimensional data and complex non-linear relationships. A common approach for addressing dimensionality issues relies on the use of static graphical structures for extracting the most significant dependence interrelationships between the variables of interest. Recently, Bayesian nonparametric techniques have become popular for modelling complex phenomena in a flexible and efficient manner, but only few attempts have been made in econometrics. In this paper, we provide an innovative Bayesian nonparametric (BNP) time-varying graphical framework for making inference in high-dimensional time series. We include a Bayesian nonparametric dependent prior specification on the matrix of coefficients and the covariance matrix by mean of a Time-Series DPP as in Nieto-Barajas et al. (2012). Following Billio et al. (2019), our hierarchical prior overcomes over-parametrization and over-fitting issues by clustering the vector autoregressive (VAR) coefficients into groups and by shrinking the coefficients of each group toward a common location. Our BNP timevarying VAR model is based on a spike-and-slab construction coupled with dependent Dirichlet Process prior (DPP) and allows to: (i) infer time-varying Granger causality networks from time series; (ii) flexibly model and cluster non-zero time-varying coefficients; (iii) accommodate for potential non-linearities. In order to assess the performance of the model, we study the merits of our approach by considering a well-known macroeconomic dataset. Moreover, we check the robustness of the method by comparing two alternative specifications, with Dirac and diffuse spike prior distributions.

Bayesian inference of networks across multiple sample groups and data types.

In this article, we develop a graphical modeling framework for the inference of networks across multiple sample groups and data types. In medical studies, this setting arises whenever a set of subjects, which may be heterogeneous due to differing disease stage or subtype, is profiled across multiple platforms, such as metabolomics, proteomics, or transcriptomics data. Our proposed Bayesian hierarchical model first links the network structures within each platform using a Markov random field prior to relate edge selection across sample groups, and then links the network similarity parameters across platforms. This enables joint estimation in a flexible manner, as we make no assumptions on the directionality of influence across the data types or the extent of network similarity across the sample groups and platforms. In addition, our model formulation allows the number of variables and number of subjects to differ across the data types, and only requires that we have data for the same set of groups. We illustrate the proposed approach through both simulation studies and an application to gene expression levels and metabolite abundances on subjects with varying severity levels of chronic obstructive pulmonary disease. Bayesian inference; Chronic obstructive pulmonary disease (COPD); Data integration; Gaussian graphical model; Markov random field prior; Spike and slab prior.

A fast and agnostic method for bacterial genome-wide association studies: Bridging the gap between k-mers and genetic events.

Genome-wide association study (GWAS) methods applied to bacterial genomes have shown promising results for genetic marker discovery or detailed assessment of marker effect. Recently, alignment-free methods based on k-mer composition have proven their ability to explore the accessory genome. However, they lead to redundant descriptions and results which are sometimes hard to interpret. Here we introduce DBGWAS, an extended k-mer-based GWAS method producing interpretable genetic variants associated with distinct phenotypes. Relying on compacted De Bruijn graphs (cDBG), our method gathers cDBG nodes, identified by the association model, into subgraphs defined from their neighbourhood in the initial cDBG. DBGWAS is alignment-free and only requires a set of contigs and phenotypes. In particular, it does not require prior annotation or reference genomes. It produces subgraphs representing phenotype-associated genetic variants such as local polymorphisms and mobile genetic elements (MGE). It offers a graphical framework which helps interpret GWAS results. Importantly it is also computationally efficient—experiments took one hour and a half on average. We validated our method using antibiotic resistance phenotypes for three bacterial species. DBGWAS recovered known resistance determinants such as mutations in core genes in Mycobacterium tuberculosis, and genes acquired by horizontal transfer in Staphylococcus aureus and Pseudomonas aeruginosa—along with their MGE context. It also enabled us to formulate new hypotheses involving genetic variants not yet described in the antibiotic resistance literature. An open-source tool implementing DBGWAS is available at https://gitlab.com/leoisl/dbgwas.

FSK-Lab – An open source food safety model integration tool

In the last decades a large number of models have been developed in the quantitative microbial risk assessment (QMRA) and predictive microbiology (PM) domains. These models were generated with different scripting languages (e.g. R, MATLAB), commercial tools (e.g. @Risk) or even proprietary software tools (e.g. FSSP, FDA-iRISK). The heterogeneity in software tools used to generate models together with the lack of a harmonized model exchange format has made the (re)-use of existing models in different software tools or simulation environments very difficult. The adoption of a harmonized information exchange format called Food Safety Knowledge Markup Language (FSK-ML) would be a solution to this challenge. FSK-ML defines a framework for encoding all relevant data, metadata and model scripts in a machine-readable format. A specific feature of FSK-ML is that it allows the user to provide model scripts in different scripting languages (e.g. R, Perl, Python or MATLAB). Model metadata can be provided in accordance with the metadata schema and controlled vocabularies proposed from the Risk Assessment Knowledge Integration Platform (RAKIP) community.In order to achieve a broad adoption of FSK-ML by the scientific community it is however of extraordinary importance to provide support in terms of easy to use software solutions. In fact, it has to be as simple as possible for the end-user to create, export, import or modify standard-compliant files. Food Safety Knowledge Lab (FSK-Lab) represents such a user-friendly software tool that can create, read (import), write (export), execute and combine FSK-ML compliant objects. All metadata needed to annotate a model can also be entered and edited through FSK-Lab. It also allows generating (export) files that comply with FSK-ML and that carry the file extension “.fskx”. This ensures that all information on a model is contained in this information exchange file and that the user does not have to write and compile FSK-ML files “by hand”.FSK-Lab extends the open source Konstanz Information Miner (KNIME) data analytics platform (URL: www.knime.org), which is a graphical programming framework allowing users to create data analysis workflows from building blocks (so called nodes). Within FSK-Lab, each node has a specific task e.g. model creation can be performed with the “FSK Creator” node. As a KNIME extension, FSK-Lab allows the user to execute and integrate code from several programming languages, like Java, R, Python. All FSK-Lab software code is freely available under the GNU public license version 3.

Quickest Localization of Anomalies in Power Grids: A Stochastic Graphical Framework

Agile localization of anomalous events plays a pivotal role in enhancing the overall reliability of the grid and avoiding cascading failures. This is especially of paramount significance in the large-scale grids due to their geographical expansions and the large volume of data generated. This paper proposes a stochastic graphical framework, by leveraging which it aims to localize the anomalies with the minimum amount of data. This framework capitalizes on the strong correlation structures observed among the measurements collected from different buses. The proposed approach, at its core, collects the measurements sequentially and progressively updates its decision about the location of the anomaly. The process resumes until the location of the anomaly can be identified with desired reliability. We provide a general theory for the quickest anomaly localization and also investigate its application for quickest line outage localization. Simulations in the IEEE 118-bus model are provided to establish the gains of the proposed approach.

Linking humans to food webs: a framework for the classification of global fisheries

There is a widely acknowledged need to explicitly include humans in our conceptual and mathematical models of food webs. However, a simple and generalized method for incorporating humans into fisheries food webs has yet to be established. We developed a simple graphical framework for defining whole‐system inland fishery food webs that includes a continuum of fishery behaviors. This range of behaviors mimics those of generalist to specialist predators, which differentially influence ecosystem diversity, sustainability, and functioning. Fishery behaviors in this food‐web context are predicted to produce a range of “fishery types” – from targeted (ie specialist) to multispecies (ie generalist) inland fisheries – and relate to the socioeconomic status of fishery participants. Fishery participants in countries with low Human Development Index (HDI) values are highly connected through fisheries food webs relative to humans in more developed countries. Our framework shows that fisheries can occupy a variety of roles within a food‐web model and may thereby affect food‐web stability in different ways. This realization could help to improve sustainable fisheries management at a global scale.

Polarities in structural analysis and design: n-dimensional graphic statics and structural transformations

This paper proposes a unified and entirely geometrical methodology for generating 2D and 3D force diagrams for given planar and spatial trusses in static equilibrium within the context of graphic statics. The trusses, regarded as form diagrams, are projections of higher dimensional simply-connected stress functions, can be either self—stressed or loaded with external forces, and need not be tension-only/ compression-only. First, we provide an in-depth overview of fundamental notions of graphic statics and projective geometry related to the construction of reciprocal form and force diagrams. Specifically, we describe a series of polar transformations and discuss them from a geometric and an algebraic standpoint. Moreover, we provide an exegesis and visualization of Maxwell's reciprocal methods while discussing them within the scientific framework of his time. We then develop a contemporary graphic statics framework grounded on projective geometry and higher-dimensional reciprocal stress functions. Within this framework, we provide a general methodology for deriving any type of reciprocal diagrams for the planar and the spatial case. Advantages of this method include: direct control on any of the four reciprocal objects (form diagram, force diagram, corresponding stress functions) and no need for iterative/ procedural reconstruction of any of the diagrams since it is based on direct geometrical transformations. Finally, we highlight how duality, and in particular polarity, can be used for a wide range of applications in structural analysis and design.

Statistical Analysis of the Sixth AIAA Drag Prediction Workshop Solutions

A graphical framework is used for the statistical analysis of the results from an extensive N-version test of a collection of Reynolds-averaged Navier–Stokes computational fluid dynamics codes for the Sixth AIAA Computational Fluid Dynamics Drag Prediction Workshop in June 2016. The solutions were obtained by code developers and users from North America, Europe, Asia, and South America using both common and custom grid sequences, as well as multiple turbulence models. The aerodynamic configuration for the workshop was the Common Research Model, which is a subsonic transport wing–body previously used for both the Fourth and Fifth Drag Prediction Workshops. This work continues the statistical analysis begun in the earlier workshops and compares the results from the grid-convergence study of the most recent workshop with previous workshops. Most notably, the results demonstrate that predicted drag increments show less scatter between codes than the predicted absolute values of drag for a given configuration, and also serve to reinforce a lesson learned from the Fifth Drag Prediction Workshop regarding the importance of a common grid sequence in decreasing the solution variation regardless of the computed output quantity.

Verification of requirements for the simulation model of a production enterprise

Tatiana K. Kravchenko - Professor, Head of Department of Business Analytics, National Research University Higher School of EconomicsAddress: 20, Myasnitskaya Street, Moscow, 101000, Russian FederationE-mail: tkravchenko@hse.ruNikolay I. Golov - Senior Lecturer, Department of Business Analytics, National Research University Higher School of EconomicsAddress: 20, Myasnitskaya Street, Moscow, 101000, Russian FederationE-mail: ngolov@hse.ruAleksey V. Fomin - Senior Lecturer, Department of Business Analytics, National Research University Higher School of EconomicsAddress: 20, Myasnitskaya Street, Moscow, 101000, Russian FederationE-mail: afomin@hse.ruAleksey Y. Lipatnikov - Graduate of MSc Program, National Research University Higher School of EconomicsAddress: 20, Myasnitskaya Street, Moscow, 101000, Russian FederationE-mail: lipatnikov94@gmail.com Developing variants of scenarios for a production enterprise’s achieving a desirable financial position using simulation modeling tools requires a specification and verification of requirements for the simulation model. Availability of such variants of scenarios allows stakeholders to select the most efficient solution. The verification is performed by business analysts and key stakeholders; the aim is to assess readiness of the requirements for final approval and to check that the requirements provide all material information for future work. Verification includes evaluating the requirements regarding their compliance with the company’s business analysis standards, as well as assessment of the model’s completeness and common terminology used for description of the requirements. Understanding the desired solution, which meets all the stakeholders’ requirements, is the most important element in requirements verification. For developing a simulation model, which is essential for determining variants of development scenarios and covers financial flows of a typical production company, a list of verified requirements is determined. Criteria of requirements verification include not only acceptance criteria, but also the Graphical Requirements Analysis framework (GRA framework), that is used for verification of functional requirements. In contrast with other notations, representation of requirements for using the GRA framework allows one to understand their structure and internal logic, as well as to detect emergent effects. The result of determining the verification criteria is the Verification Cross Reference Matrix (VCRM) that includes all the requirements, methods and criteria. In the final stage, we present an example of a diagram for one of the functional requirements. The verified requirements should be used at different stages of constructing the simulation model, which is focused on development of scenarios for achieving the production enterprise’s desired future financial position. Modeling scenarios of future development of the types ”what will happen, if…?” and “what to do to achieve the goal?”, using simulation modeling systems allows one to dramatically increase the quality of decision making.

Knowledge Management Via AUTomated Organizational CARTography (AUTOCART)

The post-globalization epoch has placed businesses everywhere in new and different competitive situations where knowledgeable, effective, and efficient behavior has come to provide the competitive and comparative edge. In this paper, we propose a model to automatically acquire, visually represent, and collectively reason on organizational textual content. The model enables an organization to visualize its knowledge and knowledge flows and present them in a graphical and visual framework, referred to as AUTomated Organizational CARTography (AUTOCART). Applying this model in the area of satellite engineering, we conduct an empirical study to explore the process of knowledge acquisition and diffusion in organizations. We find that text-based knowledge diffusion may be the solution to alleviating knowledge bottlenecks and there exists cohesion between scientific and commercial research based on the practice adopted within an organization. Our research provides great insights for practitioners to effectively manage knowledge assets in organizations.

A Sparse Non-Negative Matrix Factorization Framework for Identifying Functional Units of Tongue Behavior From MRI.

Muscle coordination patterns of lingual behaviors are synergies generated by deforming local muscle groups in a variety of ways. Functional units are functional muscle groups of local structural elements within the tongue that compress, expand, and move in a cohesive and consistent manner. Identifying the functional units using tagged-magnetic resonance imaging (MRI) sheds light on the mechanisms of normal and pathological muscle coordination patterns, yielding improvement in surgical planning, treatment, or rehabilitation procedures. In this paper, to mine this information, we propose a matrix factorization and probabilistic graphical model framework to produce building blocks and their associated weighting map using motion quantities extracted from tagged-MRI. Our tagged-MRI imaging and accurate voxel-level tracking provide previously unavailable internal tongue motion patterns, thus revealing the inner workings of the tongue during speech or other lingual behaviors. We then employ spectral clustering on the weighting map to identify the cohesive regions defined by the tongue motion that may involve multiple or undocumented regions. To evaluate our method, we perform a series of experiments. We first use two-dimensional images and synthetic data to demonstrate the accuracy of our method. We then use three-dimensional synthetic and in vivo tongue motion data using protrusion and simple speech tasks to identify subject-specific and data-driven functional units of the tongue in localized regions.

Modular design of a factor-graph-based inference engine on a System-On-Chip (SoC)

Factor graphs are probabilistic graphical frameworks for modeling complex and dynamic systems. They can be used in a broad range of application domains, from machine learning and robotics, to signal processing and digital communications. One important aspect that makes a factor graph very useful and very promising to be applied widely is its inference mechanism that is suitable for performing a complex model-based reasoning. However, its features have not fully explored and factor graphs are still used mainly as modeling tools that run on standard computers. Whereas in real applications such as robotics, one needs a practical implementation of such a framework. In this paper, we describe the development of a factor-graph-based inference engine that runs on a System-on-Chip (SoC). Running natively on a low level hardware, our factor graph engine delivers highest performance for real-time applications. We designed the embedded architecture so that it conveys important aspects such as modularity, scalability, flexibility and platform-friendly framework. The proposed architecture has customizable levels of parallelism as well as re-configurable modules that are extensible to accommodate large networks. We optimized the design to achieve high efficiency in terms of clock latency and resources consumption. We have tested our design on Xilinx Zynq-7000 SoCs and the implementation result demonstrates that the proposed framework can potentially be extended into a massively distributed probabilistic computing engine.

Beyond Markov: Accounting for independence violations in causal reasoning

Although many theories of causal cognition are based on causal graphical models, a key property of such models—the independence relations stipulated by the Markov condition—is routinely violated by human reasoners. This article presents three new accounts of those independence violations, accounts that share the assumption that people’s understanding of the correlational structure of data generated from a causal graph differs from that stipulated by causal graphical model framework. To distinguish these models, experiments assessed how people reason with causal graphs that are larger than those tested in previous studies. A traditional common cause network (Y1←X→Y2) was extended so that the effects themselves had effects (Z1←Y1←X→Y2→Z2). A traditional common effect network (Y1→X←Y2) was extended so that the causes themselves had causes (Z1→Y1→X←Y2←Z2). Subjects’ inferences were most consistent with the beta-Q model in which consistent states of the world—those in which variables are either mostly all present or mostly all absent—are viewed as more probable than stipulated by the causal graphical model framework. Substantial variability in subjects’ inferences was also observed, with the result that substantial minorities of subjects were best fit by one of the other models (the dual prototype or a leaky gate models). The discrepancy between normative and human causal cognition stipulated by these models is foundational in the sense that they locate the error not in people’s causal reasoning but rather in their causal representations. As a result, they are applicable to any cognitive theory grounded in causal graphical models, including theories of analogy, learning, explanation, categorization, decision-making, and counterfactual reasoning. Preliminary evidence that independence violations indeed generalize to other judgment types is presented.

Using Contour Plots of Bicoherence to Illustrate and Investigate Cross-Frequency Coupling of EEG Oscillations

My 12/2017 SSRN e-paper investigated possible cross-frequency phase-phase coupling of scalp-recorded EEG signals. Essentially, the quadratic-coupling metric of harmonic wavelet bicoherence was applied to 1-hr blocks of data centered at identified seizures, with results presented in graphical form. That paper was motivated in part by earlier studies of delta-theta band and theta-gamma band couplings. The former studied correlations between delta-theta couplings and depth of anesthesia during surgery, using this metric; the latter demonstrated such theta-gamma couplings in rat hippocampus. In this paper MATLAB figures of contour plots of bicoherence were chosen to better illustrate and investigate cross-frequency phase-phase coupling of EEG oscillations. The graphical framework is a frequency vs. frequency matrix, 0.5-50 Hz, with colored contour plots of bicoherence, for frequency steps of 1 Hz. To demonstrate ‘proof of concept’ in a limited amount of space, some restrictions from the previous paper were made.

Magnetic covalent triazine-based frameworks as magnetic solid-phase extraction adsorbents for sensitive determination of perfluorinated compounds in environmental water samples.

Covalent organic frameworks (COFs), which are a new type of carbonaceous polymeric material, have attracted great interest because of their large surface area and high chemical and thermal stability. However, to the best of our knowledge, no work has reported the use of magnetic COFs as adsorbents for magnetic solid-phase extraction (MSPE) to enrich and determine environmental pollutants. This work aims to investigate the feasibility of using covalent triazine-based framework (CTF)/Fe2O3 composites as MSPE adsorbents to enrich and analyze perfluorinated compounds (PFCs) at trace levels in water samples. Under the optimal conditions, the method developed exhibited low limits of detection (0.62-1.39 ng·L-1), a wide linear range (5-4000 ng L-1), good repeatability (1.12-9.71%), and good reproducibility (2.45-7.74%). The new method was successfully used to determine PFCs in actual environmental water samples. MSPE based on CTF/Fe2O3 composites exhibits potential for analysis of PFCs at trace levels in environmental water samples. Graphical abstract Magnetic covalent triazine-based frameworks (CTFs) were used as magnetic solid-phase extraction adsorbents for the sensitive determination of perfluorinated compounds in environmental water samples. PFBA perfluorobutyric acid, PFBS perfluorobutane sulfonate, PFDA perfluorodecanoic acid, PFDoA perfluorododecanoic acid, PFHpA perfluoroheptanoic acid, PFHxA perfluorohexanoic acid, PFHxS perfluorohexane sulfonate, PFNA perfluorononanoic acid, PFOA perfluorooctanoic acid, PFPeA perfluoropentanoic acid, PFUdA Perfluoroundecanoic acid.

Informatics applied to health evaluation and promotion: online platform for filling in questionnaires

Objective: This study was conducted with the objective of developing and evaluating a computerized platform for health promotion for workers of the Instituto Federal Goiano Campus Ceres. Method: The system was developed using markup languages (HTML, CSS) for presentation and styling of the interface and programming languages (PHP, JavaScript) for forms data management, connecting to the database, and dynamic user-system interaction. The graphic framework Bootstrap was also used to increase the visual aspect. The main tools employed were the folowing: Atom (for code editing); FileZilla Client (for FTP files maintenance); and phpMyAdmin (for database management). The system was evaluated by means of a questionnaire created for this purpose, which was completed by 41 workers. Results and final considerations: The results indicate that the platform is useful, innovative, and applicable to various worker populations. Health informatics is a continuously expanding area. Thus, efficient and effective information collection and maintainance systems are essential.

Data Librarian, the Steward

Background. By the 2020 mark, The European Union should have a functional Digital Single Market. One of the policies sustaining the efforts in such endeavour is building a European Data Economy (European Commission 2017a). The aim is to build a common European data space a transformative space even for the information science specialists. Objectives. The study is investigative in nature aiming to extract the traits out of the trends leading to a possible specialisation having a broad scope in searching possible career paths for librarians in data science. Results. A graphical explanatory framework indicating requirements, skills and competencies needed by the librarians to achieve new cross-disciplinary engagements with patrons and the research environment. Methods. Because this study is put in the context of Open Science, and particularly addressing the European Union space, the late developments reflected in the policies and initiatives were taken under scrutiny coupled with relevant European Commission project deliverables. Other studies concentrating on the new roles of the librarians pertaining to data librarian were consulted, and also the body of information gathered around the Open Science Cloud. To couple existing studies’ conclusions with the demand in the librarianship, a body of job listings were investigated to find common traits data librarian job descriptions are exposing. To complete a picture, some training facilities were taken into the mix. Debate. Out of many possible roles envisaged for the librarians, there are a few which trigger some focus on the future skills needed to be acquired. These possible scenarios involve data management planning guidance, data stewardship and curation, and data visualisation. Some or all of them might lead to a deep transformation of the librarianship as a craft we were used to up to the Open Science rising tide. The article invites all the information specialists to look into what are the needs to shape up or even to rehash the careers of library and information science specialists.

Design and Construction of A Laser-Based Respiratory Gating System For Implementation of Deep Inspiration Breathe Hold Technique in Radiotherapy Clinics.

Background:Deep inspiration breath-hold (DIBH) is known as a radiotherapy method for the treatment of patients with left-sided breast cancer. In this method, patient is under exposure only while he/she is at the end of a deep inspiration cycle and holds his/her breath. In this situation, the volume of the lung tissue is enhanced and the heart tissue is pushed away from the treating breast. Therefore, heart dose of these patients, using DIBH, experiences a considerable decline compared to free breathing treatment. There are a few commercialized systems for implementation of DIBH in invasive or noninvasive manners.Methods:We present a novel constructed noninvasive DIBH device relied on a manufacturing near-field laser distance meter. This in-house constructed system is composed of a CD22-100AM122 laser sensor combined with a data acquisition system for monitoring the breathing curve. Qt Creator (a cross-platform JavaScript, QML, and C++-integrated development environment that is part of the SDK for development of the Qt Graphical User Interface application framework) and Keil MDK-ARM (a programming software where users can write in C and C++ and assemble for ARM-based microcontrollers) are used for composing computer and microcontroller programs, respectively.Results:This system could be mounted in treatment or computed tomography (CT) room at suitable cost; it is also easy to use and needs a little training for personnel and patients. The system can assess the location of chest wall or abdomen in real time with high precision and frequency. The performance of CD22-100AM122 demonstrates promise for respiratory monitoring for its fast sampling rate as well as high precision. It can also deliver reasonable spatial and temporal accuracy. The patient observes his/her breathing waveform through a 7” 1024 × 600 liquid crystal display and gets some instructions during treatment and CT sessions by an exploited algorithm called “interaction scenario” in this study. The system is also noninvasive and well sustainable for patients.Conclusions:The constructed system has true real-time operation and is rapid enough for delivering clear contiguous monitoring. In addition, in this system, we have provided an interaction scenario option between patient and CT or Linac operator. In addition, the constructed system has the capability of sending triggers for turning on and off CT or Linac facilities. In this concern, the system has the superiority of combining a plenty of characteristics.

Classifying clinical notes with pain assessment using machine learning.

Pain is a significant public health problem, affecting millions of people in the USA. Evidence has highlighted that patients with chronic pain often suffer from deficits in pain care quality (PCQ) including pain assessment, treatment, and reassessment. Currently, there is no intelligent and reliable approach to identify PCQ indicators inelectronic health records (EHR). Hereby, we used unstructured text narratives in the EHR to derive pain assessment in clinical notes for patients with chronic pain. Our dataset includes patients with documented pain intensity rating ratings > = 4 and initial musculoskeletal diagnoses (MSD) captured by (ICD-9-CM codes) in fiscal year 2011 and a minimal 1year of follow-up (follow-up period is 3-yr maximum); with complete data on key demographic variables. A total of 92 patients with 1058 notes was used. First, we manually annotated qualifiers and descriptors of pain assessment using the annotation schema that we previously developed. Second, we developed a reliable classifier for indicators of pain assessment in clinical note. Based on our annotation schema, we found variations in documenting the subclasses of pain assessment. In positive notes, providers mostly documented assessment of pain site (67%) and intensity of pain (57%), followed by persistence (32%). In only 27% of positive notes, did providers document a presumed etiology for the pain complaint or diagnosis. Documentation of patients' reports of factors that aggravate pain was only present in 11% of positive notes. Random forest classifier achieved the best performance labeling clinical notes with pain assessment information, compared to other classifiers; 94, 95, 94, and 94% was observed in terms of accuracy, PPV, F1-score, and AUC, respectively. Despite the wide spectrum of research that utilizes machine learning in many clinical applications, none explored using these methods for pain assessment research. In addition, previous studies using large datasets to detect and analyze characteristics of patients with various types of pain have relied exclusively on billing and coded data as the main source of information. This study, in contrast, harnessed unstructured narrative text data from the EHR to detect pain assessment clinical notes. We developed a Random forest classifier to identify clinical notes with pain assessment information. Compared to other classifiers, ours achieved the best results in most of the reported metrics. Graphical abstract Framework for detecting pain assessment in clinical notes.