Learning the progression patterns of treatments using a probabilistic generative model.

Modeling a disease or the treatment of a patient has drawn much attention in recent years due to the vast amount of information that Electronic Health Records contain. This paper presents a probabilistic generative model of treatments that are described in terms of sequences of medical activities of variable length. The main objective is to identify distinct subtypes of treatments for a given disease, and discover their development and progression. To this end, the model considers that a sequence of actions has an associated hierarchical structure of latent variables that both classifies the sequences based on their evolution over time, and segments the sequences into different progression stages. The learning procedure of the model is performed with the Expectation-Maximization algorithm which considers the exponential number of configurations of the latent variables and is efficiently solved with a method based on dynamic programming. The evaluation of the model is twofold: first, we use synthetic data to demonstrate that the learning procedure allows the generative model underlying the data to be recovered; we then further assess the potential of our model to provide treatment classification and staging information in real-world data. Our model can be seen as a tool for classification, simulation, data augmentation and missing data imputation.

Characterizing Permutation-Based Combinatorial Optimization Problems in Fourier Space.

Comparing combinatorial optimization problems is a difficult task. They are defined using different criteria and terms: weights, flows, distances, etc. In spite of this apparent discrepancy, on many occasions, they tend to produce problem instances with similar properties. One avenue to compare different problems is to project them onto the same space, in order to have homogeneous representations. Expressing the problems in a unified framework could also lead to the discovery of theoretical properties or the design of new algorithms. This article proposes the use of the Fourier transform over the symmetric group as the tool to project different permutation-based combinatorial optimization problems onto the same space. Based on a previous study (Kondor, 2010), which characterized the Fourier coefficients of the quadratic assignment problem, we describe the Fourier coefficients of three other well-known problems: the symmetric and nonsymmetric traveling salesperson problem and the linear ordering problem. This transformation allows us to gain a better understanding of the intersection between the problems, as well as to bound their intrinsic dimension.

Optical method to characterize and assess setting evolution of cement pastes: publisher's note.

This publisher's note amends the author affiliations in Appl. Opt.59, D1 (2020)APOPAI0003-693510.1364/AO.59.0000D1.

Optical method to characterize and assess setting evolution of cement pastes.

In this work, a nondestructive and noninvasive technique, based on laser technology and the use of the Kubelka-Munk model to calculate the dynamic behavior of the cement paste from the diffuse reflection properties of both cement components and hydration products, is proposed. Also, the Powers-Brunauer model is used to explain this behavior during the first 9 h of the hydration process. This method allows us to obtain the initial and final cement setting times from the diffuse reflection measurements.

Anatomy of the Attraction Basins: Breaking with the Intuition.

Solving combinatorial optimization problems efficiently requires the development of algorithms that consider the specific properties of the problems. In this sense, local search algorithms are designed over a neighborhood structure that partially accounts for these properties. Considering a neighborhood, the space is usually interpreted as a natural landscape, with valleys and mountains. Under this perception, it is commonly believed that, if maximizing, the solutions located in the slopes of the same mountain belong to the same attraction basin, with the peaks of the mountains being the local optima. Unfortunately, this is a widespread erroneous visualization of a combinatorial landscape. Thus, our aim is to clarify this aspect, providing a detailed analysis of, first, the existence of plateaus where the local optima are involved, and second, the properties that define the topology of the attraction basins, picturing a reliable visualization of the landscapes. Some of the features explored in this article have never been examined before. Hence, new findings about the structure of the attraction basins are shown. The study is focused on instances of permutation-based combinatorial optimization problems considering the 2-exchange and the insert neighborhoods. As a consequence of this work, we break away from the extended belief about the anatomy of attraction basins.

Multi-Objectivising Combinatorial Optimisation Problems by Means of Elementary Landscape Decompositions.

In the last decade, many works in combinatorial optimisation have shown that, due to the advances in multi-objective optimisation, the algorithms from this field could be used for solving single-objective problems as well. In this sense, a number of papers have proposed multi-objectivising single-objective problems in order to use multi-objective algorithms in their optimisation. In this article, we follow up this idea by presenting a methodology for multi-objectivising combinatorial optimisation problems based on elementary landscape decompositions of their objective function. Under this framework, each of the elementary landscapes obtained from the decomposition is considered as an independent objective function to optimise. In order to illustrate this general methodology, we consider four problems from different domains: the quadratic assignment problem and the linear ordering problem (permutation domain), the 0-1 unconstrained quadratic optimisation problem (binary domain), and the frequency assignment problem (integer domain). We implemented two widely known multi-objective algorithms, NSGA-II and SPEA2, and compared their performance with that of a single-objective GA. The experiments conducted on a large benchmark of instances of the four problems show that the multi-objective algorithms clearly outperform the single-objective approaches. Furthermore, a discussion on the results suggests that the multi-objective space generated by this decomposition enhances the exploration ability, thus permitting NSGA-II and SPEA2 to obtain better results in the majority of the tested instances.

On the taxonomy of optimization problems under estimation of distribution algorithms.

Understanding the relationship between a search algorithm and the space of problems is a fundamental issue in the optimization field. In this paper, we lay the foundations to elaborate taxonomies of problems under estimation of distribution algorithms (EDAs). By using an infinite population model and assuming that the selection operator is based on the rank of the solutions, we group optimization problems according to the behavior of the EDA. Throughout the definition of an equivalence relation between functions it is possible to partition the space of problems in equivalence classes in which the algorithm has the same behavior. We show that only the probabilistic model is able to generate different partitions of the set of possible problems and hence, it predetermines the number of different behaviors that the algorithm can exhibit. As a natural consequence of our definitions, all the objective functions are in the same equivalence class when the algorithm does not impose restrictions to the probabilistic model. The taxonomy of problems, which is also valid for finite populations, is studied in depth for a simple EDA that considers independence among the variables of the problem. We provide the sufficient and necessary condition to decide the equivalence between functions and then we develop the operators to describe and count the members of a class. In addition, we show the intrinsic relation between univariate EDAs and the neighborhood system induced by the Hamming distance by proving that all the functions in the same class have the same number of local optima and that they are in the same ranking positions. Finally, we carry out numerical simulations in order to analyze the different behaviors that the algorithm can exhibit for the functions defined over the search space [Formula: see text].

An evaluation of methods for estimating the number of local optima in combinatorial optimization problems.

The solution of many combinatorial optimization problems is carried out by metaheuristics, which generally make use of local search algorithms. These algorithms use some kind of neighborhood structure over the search space. The performance of the algorithms strongly depends on the properties that the neighborhood imposes on the search space. One of these properties is the number of local optima. Given an instance of a combinatorial optimization problem and a neighborhood, the estimation of the number of local optima can help not only to measure the complexity of the instance, but also to choose the most convenient neighborhood to solve it. In this paper we review and evaluate several methods to estimate the number of local optima in combinatorial optimization problems. The methods reviewed not only come from the combinatorial optimization literature, but also from the statistical literature. A thorough evaluation in synthetic as well as real problems is given. We conclude by providing recommendations of methods for several scenarios.

Methodological procedure based on quantitizing/liquefying: a case study to assess work climate in an emergency department.

Introduction: In the assessment of health organizations, results-based indicators are mainly used, with no consideration of internal work dynamics. This type of assessment forfeits much of the rich, useful information needed to make decisions on improving the organization. In order to address this, a rigorous procedure based on mixed methods is laid out here on gathering, analyzing, and interpreting data associated with the implementation process. Methods: A 55-year-old doctor was selected at random from among the staff who volunteered to be interviewed at the emergency department at a public hospital located in southern Spain for an interview. Qualitative data obtained from the in-depth interview (indirect observation) were progressively systematized (liquefied and quantitized) based on a theoretical framework until a code matrix was obtained, without losing or distorting any information. Afterwards, data quality was controlled using Cohen's kappa (κ) coefficient. A quantitative polar coordinate analysis was then carried out using the free software HOISAN (v. 1.6.3.3) to obtain robust results, vectorizing the relationships between codes and specifying whenever such relationships were statistically significant (and if they resulted in behavior activation or inhibition). Finally, a supplementary quantitative and qualitative assessment was carried out. Results and discussion: The proposed method was applied to the needs assessment of teams in order to evaluate that work climate in the hospital's emergency department Health Services of a hospital. Data quality control yielded an adequate result (κ = 0.82). Significant activation and inhibition of behaviors occurred, both prospectively and retrospectively. For instance, We seek to understand the needs of our clients and We readily adapt to new circumstances showed a significant activation (vector length = 3.43, p < 0.01) both prospectively (Zsum = 0.48) and retrospectively (Zsum = 3.4).An adequate method to obtain detailed information about group dynamics in a work environment is presented, based on an in-depth interview. Practical applications for implementations to improve the functioning of organizations are presented.

A Cheap Feature Selection Approach for the K-Means Algorithm.

The increase in the number of features that need to be analyzed in a wide variety of areas, such as genome sequencing, computer vision, or sensor networks, represents a challenge for the K -means algorithm. In this regard, different dimensionality reduction approaches for the K -means algorithm have been designed recently, leading to algorithms that have proved to generate competitive clusterings. Unfortunately, most of these techniques tend to have fairly high computational costs and/or might not be easy to parallelize. In this article, we propose a fully parallelizable feature selection technique intended for the K -means algorithm. The proposal is based on a novel feature relevance measure that is closely related to the K -means error of a given clustering. Given a disjoint partition of the features, the technique consists of obtaining a clustering for each subset of features and selecting the m features with the highest relevance measure. The computational cost of this approach is just O(m·max{n·K,logm}) per subset of features. We additionally provide a theoretical analysis on the quality of the obtained solution via our proposal and empirically analyze its performance with respect to well-known feature selection and feature extraction techniques. Such an analysis shows that our proposal consistently obtains the results with lower K -means error than all the considered feature selection techniques: Laplacian scores, maximum variance, multicluster feature selection, and random selection while also requiring similar or lower computational times than these approaches. Moreover, when compared with feature extraction techniques, such as random projections, the proposed approach also shows a noticeable improvement in both error and computational time.

Merge Nondominated Sorting Algorithm for Many-Objective Optimization.

Many Pareto-based multiobjective evolutionary algorithms require ranking the solutions of the population in each iteration according to the dominance principle, which can become a costly operation particularly in the case of dealing with many-objective optimization problems. In this article, we present a new efficient algorithm for computing the nondominated sorting procedure, called merge nondominated sorting (MNDS), which has a best computational complexity of O(NlogN) and a worst computational complexity of O(MN2) , with N being the population size and M being the number of objectives. Our approach is based on the computation of the dominance set, that is, for each solution, the set of solutions that dominate it, by taking advantage of the characteristics of the merge sort algorithm. We compare MNDS against six well-known techniques that can be considered as the state-of-the-art. The results indicate that the MNDS algorithm outperforms the other techniques in terms of the number of comparisons as well as the total running time.

A machine learning approach to predict healthcare cost of breast cancer patients.

This paper presents a novel machine learning approach to perform an early prediction of the healthcare cost of breast cancer patients. The learning phase of our prediction method considers the following two steps: (1) in the first step, the patients are clustered taking into account the sequences of actions undergoing similar clinical activities and ensuring similar healthcare costs, and (2) a Markov chain is then learned for each group to describe the action-sequences of the patients in the cluster. A two step procedure is undertaken in the prediction phase: (1) first, the healthcare cost of a new patient's treatment is estimated based on the average healthcare cost of its k-nearest neighbors in each group, and (2) finally, an aggregate measure of the healthcare cost estimated by each group is used as the final predicted cost. Experiments undertaken reveal a mean absolute percentage error as small as 6%, even when half of the clinical records of a patient is available, substantiating the early prediction capability of the proposed method. Comparative analysis substantiates the superiority of the proposed algorithm over the state-of-the-art techniques.

Prioritization of candidate cancer genes--an aid to oncogenomic studies.

The development of techniques for oncogenomic analyses such as array comparative genomic hybridization, messenger RNA expression arrays and mutational screens have come to the fore in modern cancer research. Studies utilizing these techniques are able to highlight panels of genes that are altered in cancer. However, these candidate cancer genes must then be scrutinized to reveal whether they contribute to oncogenesis or are coincidental and non-causative. We present a computational method for the prioritization of candidate (i) proto-oncogenes and (ii) tumour suppressor genes from oncogenomic experiments. We constructed computational classifiers using different combinations of sequence and functional data including sequence conservation, protein domains and interactions, and regulatory data. We found that these classifiers are able to distinguish between known cancer genes and other human genes. Furthermore, the classifiers also discriminate candidate cancer genes from a recent mutational screen from other human genes. We provide a web-based facility through which cancer biologists may access our results and we propose computational cancer gene classification as a useful method of prioritizing candidate cancer genes identified in oncogenomic studies.

Learning factorizations in estimation of distribution algorithms using affinity propagation.

Estimation of distribution algorithms (EDAs) that use marginal product model factorizations have been widely applied to a broad range of mainly binary optimization problems. In this paper, we introduce the affinity propagation EDA (AffEDA) which learns a marginal product model by clustering a matrix of mutual information learned from the data using a very efficient message-passing algorithm known as affinity propagation. The introduced algorithm is tested on a set of binary and nonbinary decomposable functions and using a hard combinatorial class of problem known as the HP protein model. The results show that the algorithm is a very efficient alternative to other EDAs that use marginal product model factorizations such as the extended compact genetic algorithm (ECGA) and improves the quality of the results achieved by ECGA when the cardinality of the variables is increased.

Robust image classification against adversarial attacks using elastic similarity measures between edge count sequences.

Due to their unprecedented capacity to learn patterns from raw data, deep neural networks have become the de facto modeling choice to address complex machine learning tasks. However, recent works have emphasized the vulnerability of deep neural networks when being fed with intelligently manipulated adversarial data instances tailored to confuse the model. In order to overcome this issue, a major effort has been made to find methods capable of making deep learning models robust against adversarial inputs. This work presents a new perspective for improving the robustness of deep neural networks in image classification. In computer vision scenarios, adversarial images are crafted by manipulating legitimate inputs so that the target classifier is eventually fooled, but the manipulation is not visually distinguishable by an external observer. The reason for the imperceptibility of the attack is that the human visual system fails to detect minor variations in color space, but excels at detecting anomalies in geometric shapes. We capitalize on this fact by extracting color gradient features from input images at multiple sensitivity levels to detect possible manipulations. We resort to a deep neural classifier to predict the category of unseen images, whereas a discrimination model analyzes the extracted color gradient features with time series techniques to determine the legitimacy of input images. The performance of our method is assessed over experiments comprising state-of-the-art techniques for crafting adversarial attacks. Results corroborate the increased robustness of the classifier when using our discrimination module, yielding drastically reduced success rates of adversarial attacks that operate on the whole image rather than on localized regions or around the existing shapes of the image. Future research is outlined towards improving the detection accuracy of the proposed method for more general attack strategies.

Identifying common treatments from Electronic Health Records with missing information. An application to breast cancer.

The aim of this paper is to analyze the sequence of actions in the health system associated with a particular disease. In order to do that, using Electronic Health Records, we define a general methodology that allows us to: (i) identify the actions in the health system associated with a disease; (ii) identify those patients with a complete treatment for the disease; (iii) and discover common treatment pathways followed by the patients with a specific diagnosis. The methodology takes into account the characteristics of the EHRs, such as record heterogeneity and missing information. As an example, we use the proposed methodology to analyze breast cancer disease. For this diagnosis, 5 groups of treatments, which fit in with medical practice guidelines and expert knowledge, were obtained.

A case of hyperkeratotic crusted scabies.

Patients who are immunocompromised or have cognitive or physical disabilities are at a higher risk of being affected with infections such as crusted scabies. This is a rare skin hyperinfestation by Sarcoptes scabiei var. hominis. The main characteristic of this dermatosis is a thick crust due to the high concentration of mites; in addition, other manifestations such as papules, excoriations, and burrows may be absent. In severe cases, thick yellow-brown crusts and plaques with deep fissures are present. Diagnosis can be made by observing mites, ova, or feces from skin scrapings. Multiple therapies can be used in patients with this condition. Management with patient isolation is important to prevent institutional outbreaks. This disease can have high mortality, primarily due to sepsis. Awareness of this condition and its serious consequences is important to reduce its mortality and morbidity.

Diffuse ultraviolet erythemal irradiance on inclined planes: a comparison of experimental and modeled data.

Values of measured and modeled diffuse UV erythemal irradiance (UVER) for all sky conditions are compared on planes inclined at 40 degrees and oriented north, south, east and west. The models used for simulating diffuse UVER are of the geometric-type, mainly the Isotropic, Klucher, Hay, Muneer, Reindl and Schauberger models. To analyze the precision of the models, some statistical estimators were used such as root mean square deviation, mean absolute deviation and mean bias deviation. It was seen that all the analyzed models reproduce adequately the diffuse UVER on the south-facing plane, with greater discrepancies for the other inclined planes. When the models are applied to cloud-free conditions, the errors obtained are higher because the anisotropy of the sky dome acquires more importance and the models do not provide the estimation of diffuse UVER accurately.

Eruptive palmoplantar lesions induced by capecitabine: report of a case evaluated with dermoscopy.

Capecitabine is a prodrug used primarily as a chemotherapeutic agent. Despite its good tolerance, it has several adverse effects, including the appearance of eruptive nevi. We present the case of a patient, with a history of EC IV breast adenocarcinoma and superficial extension melanoma, which developed 2 weeks after the start of therapy with capecitabine multiple eruptive palmoplantar pigmented lesions, with diverse benign dermatoscopic patterns. With the increasing incidence of solid tumors, these agents are being more used. It is important that the treating physician knows its adverse effects and apply non-invasive diagnostic tools like dermoscopy to avoid unnecessary biopsies.

La capecitabina es un profármaco utilizado sobre todo como medicamento quimioterapéutico. A pesar de su buena tolerancia, produce diversos efectos adversos como la aparición de nevos eruptivos. Se presenta el caso de una paciente, con antecedentes de adenocarcinoma de mama (EC IV) y melanoma de extensión superficial, que desarrolló dos semanas posteriores al inicio del tratamiento con capecitabina múltiples lesiones eruptivas pigmentadas palmoplantares, con patrones variados benignos a la dermatoscopia. Con el incremento de las neoplasias sólidas, estos agentes se utilizan cada vez más. Es importante que el médico tratante conozca sus efectos adversos y aplique herramientas diagnósticas no invasivas como la dermatoscopia para evitar biopsias innecesarias.

Methodological quality checklist for studies based on observational methodology (MQCOM).

BACKGROUND: No existing instrument addresses the minimum number of items that guarantee methodological quality in studies based on observational methodology. Consequently, professionals who are not experts in observational methodology do not have a basic framework to guide their practice in this type of study. This study developed a checklist to measure the minimum number of items for methodological quality that studies based on observational methodology should consider and provided evidence of their validity based on test content and intercoder reliability. METHOD: Fifty-four judges with at least 1 year of experience in observational methodology and research based on this methodology evaluated the items of the developed checklist in terms of relevance, usefulness, and feasibility. Items were selected if they obtained at least .5 in the Osterlind indexes of the three aspects evaluated. Two coders applied the selected items to a random selection of articles that used observational methodology to investigate soccer, and intercoder reliability was examined using Cohen's kappa (k) coefficients. RESULTS: The final checklist included 16 items grouped into 11 criteria/dimensions, with adequate reliability coefficients. CONCLUSIONS: This study developed a useful instrument for non-expert professionals to enhance the methodological quality of studies based on observational methodology.