Search

This paper investigates the possibility of the implementation of Genetic Programming (GP) algorithm on a publicly available COVID-19 data set, in order to obtain mathematical models which could be used for estimation of confirmed, deceased, and recovered cases and the estimation of epidemiology curve for specific countries, with a high number of cases, such as China, Italy, Spain, and USA and as well as on the global scale. The conducted investigation shows that the best mathematical models produced for estimating confirmed and deceased cases achieved R2 scores of 0.999, while the models developed for estimation of recovered cases achieved the R2 score of 0.998. The equations generated for confirmed, deceased, and recovered cases were combined in order to estimate the epidemiology curve of specific countries and on the global scale. The estimated epidemiology curve for each country obtained from these equations is almost identical to the real data contained within the data set [ABSTRACT FROM AUTHOR]

A good primary health care is the base for a better healthcare system. Taking a good decision on time by the primary health care physician could have a huge repercussion. In order to ease the diagnosis task arise the Decision Support Systems (DSS), which offer counselling instead of refresh the medical knowledge, in a profession where it is still learning every day. The implementation of these systems in diseases which are a frequent cause of visit to the doctor like ophthalmologic pathologies are, which affect directly to our quality of life, takes more importance. This paper aims to develop OphthalDSS, a totally new mobile DSS for red eye diseases diagnosis. The main utilities that OphthalDSS offers will be a study guide for medical students and a clinical decision support system for primary care professionals. Other important goal of this paper is to show the user experience results after OphthalDSS being used by medical students of the University of Valladolid. For achieving the main purpose of this research work, a decision algorithm will be developed and implemented by an Android mobile application. Moreover, the Quality of Experience (QoE) has been evaluated by the students through the questions of a short inquiry. The app developed which implements the algorithm OphthalDSS is capable of diagnose more than 30 eye's anterior segment diseases. A total of 67 medical students have evaluated the QoE. The students find the diseases' information presented very valuable, the appearance is adequate, it is always available and they have ever found what they were looking for. Furthermore, the students think that their quality of life has not been improved using the app and they can do the same without using the OphthalDSS app. OphthalDSS is easy to use, which is capable of diagnose more than 30 ocular diseases in addition to be used as a DSS tool as an educational tool at the same time. [ABSTRACT FROM AUTHOR]

Breast density is a strong risk factor for breast cancer. In this paper, we present an automated approach for breast density segmentation in mammographic images based on a supervised pixel-based classification and using textural and morphological features. The objective of the paper is not only to show the feasibility of an automatic algorithm for breast density segmentation but also to prove its potential application to the study of breast density evolution in longitudinal studies. The database used here contains three complete screening examinations, acquired 2 years apart, of 130 different patients. The approach was validated by comparing manual expert annotations with automatically obtained estimations. Transversal analysis of the breast density analysis of craniocaudal (CC) and mediolateral oblique (MLO) views of both breasts acquired in the same study showed a correlation coefficient of ρ = 0.96 between the mammographic density percentage for left and right breasts, whereas a comparison of both mammographic views showed a correlation of ρ = 0.95. A longitudinal study of breast density confirmed the trend that dense tissue percentage decreases over time, although we noticed that the decrease in the ratio depends on the initial amount of breast density. [ABSTRACT FROM AUTHOR]

Background: When patients are admitted to an intensive care unit (ICU) their risk of getting an infection will be highly depend on the length of stay at-risk in the ICU. In addition, risk of infection is likely to vary over calendar time as a result of fluctuations in the prevalence of the pathogen on the ward. Hence risk of infection is expected to depend on two time scales (time in ICU and calendar time) as well as competing events (discharge or death) and their spatial location. The purpose of this paper is to develop and apply appropriate statistical models for the risk of ICU-acquired infection accounting for multiple time scales, competing risks and the spatial clustering of the data.Methods: A multi-center data base from a Spanish surveillance network was used to study the occurrence of an infection due to Methicillin-resistant Staphylococcus aureus (MRSA). The analysis included 84,843 patient admissions between January 2006 and December 2011 from 81 ICUs. Stratified Cox models were used to study multiple time scales while accounting for spatial clustering of the data (patients within ICUs) and for death or discharge as competing events for MRSA infection.Results: Both time scales, time in ICU and calendar time, are highly associated with the MRSA hazard rate and cumulative risk. When using only one basic time scale, the interpretation and magnitude of several patient-individual risk factors differed. Risk factors concerning the severity of illness were more pronounced when using only calendar time. These differences disappeared when using both time scales simultaneously.Conclusions: The time-dependent dynamics of infections is complex and should be studied with models allowing for multiple time scales. For patient individual risk-factors we recommend stratified Cox regression models for competing events with ICU time as the basic time scale and calendar time as a covariate. The inclusion of calendar time and stratification by ICU allow to indirectly account for ICU-level effects such as local outbreaks or prevention interventions. [ABSTRACT FROM AUTHOR]

Background: Several studies have described potential microRNA (miRNA) biomarkers associated with migraine, but studies are scarcely reproducible primarily due to the heterogeneous variability of participants. Increasing evidence shows that disease-related intrinsic factors together with lifestyle (environmental factors), influence epigenetic mechanisms and in turn, diseases. Hence, the main objective of this exploratory study was to find differentially expressed miRNAs (DE miRNA) in peripheral blood mononuclear cells (PBMC) of patients with migraine compared to healthy controls in a well-controlled homogeneous cohort of non-menopausal women. Methods: Patients diagnosed with migraine according to the International Classification of Headache Disorders (ICHD-3) and healthy controls without familial history of headache disorders were recruited. All participants completed a very thorough questionnaire and structured-interview in order to control for environmental factors. RNA was extracted from PBMC and a microarray system (GeneChip miRNA 4.1 Array chip, Affymetrix) was used to determine the miRNA profiles between study groups. Principal components analysis and hierarchical clustering analysis were performed to study samples distribution and random forest (RF) algorithms were computed for the classification task. To evaluate the stability of the results and the prediction error rate, a bootstrap (.632 + rule) was run through all the procedure. Finally, a functional enrichment analysis of selected targets was computed through protein–protein interaction networks. Results: After RF classification, three DE miRNA distinguished study groups in a very homogeneous female cohort, controlled by factors such as demographics (age and BMI), life-habits (physical activity, caffeine and alcohol consumptions), comorbidities and clinical features associated to the disease: miR-342-3p, miR-532-3p and miR-758-5p. Sixty-eight target genes were predicted which were linked mainly to enriched ion channels and signaling pathways, neurotransmitter and hormone homeostasis, infectious diseases and circadian entrainment. Conclusions: A 3-miRNA (miR-342-3p, miR-532-3p and miR-758-5p) novel signature has been found differentially expressed between controls and patients with migraine. Enrichment analysis showed that these pathways are closely associated with known migraine pathophysiology, which could lead to the first reliable epigenetic biomarker set. Further studies should be performed to validate these findings in a larger and more heterogeneous sample. [ABSTRACT FROM AUTHOR]

Background: The ABCDE bundle is a set of evidence‐based practices to systematically reduce the risks of sedation, delirium, and immobility in intensive care patients. Implementing the bundle improves clinical outcome. Aims and Objectives: To investigate the association between patient outcomes and compliance with bundle components ABC (analgosedation algorithms), D (delirium protocol), and E (early mobilization protocol). Design: A Spanish multicentre cohort study of adult patients receiving invasive mechanical ventilation (IMV) for ≥48 h until extubation. Methods: The primary outcome was pain level, cooperation to permit Medical Research Council Scale administration, patient days of delirium, and mobility. The secondary outcome was cumulative drug dosing by IMV days. Tertiary outcomes (ICU days, IMV days, bed rest days, ICU mortality, ICUAW) and independent variables (analgosedation, delirium, early mobilization protocols) were also studied. Results: Data were collected from 605 patients in 80 ICUs and 5214 patient days with IMV. Two‐thirds of the ICUs studied applied no protocols. Pain was not assessed on 83.6% of patient days. Patient cooperation made scale administration feasible on 20.7% of days. Delirium and immobility were found on 4.2% and 69.9% of days, respectively. Patients had shorter stays in ICUs with bundle protocols and fewer days of IMV in ICUs with delirium and mobilization bundle components (P = 0.006 and P = 0.03, respectively). Analgosedation protocols were associated with more opioid dosing (P = 0.02), and delirium and early mobilization protocols with more propofol (P = 0.001), dexmedetomidine (P = 0.001), and lower benzodiazepine dosing (P = 0.008). Conclusions: The implementation rate of ABCDE bundle components was very low in our Spanish setting, but when implemented, patients had a shorter ICU stay, more analgesia dosing, and lighter sedation. Relevance to clinical practice: Applying some but not all the bundle components, there is increased analgesia and light sedation drug use, decreased benzodiazepines, and increased patient cooperation and mobility, resulting in a shorter ICU stay and fewer days of IMV. [ABSTRACT FROM AUTHOR]

Collaborative learning can improve the pedagogical effectiveness of MOOCs. Group formation, an essential step in the design of collaborative learning activities, can be challenging in MOOCs given the scale and the wide variety in such contexts. We discuss the need for considering the behaviours of the students in the course to form groups in MOOC contexts, and propose a grouping approach that employs homogeneity in terms of students' engagement in the course. Two grouping strategies with different degrees of homogeneity are derived from this approach, and their impact to form successful groups is examined in a real MOOC context. The grouping criteria were established using student activity logs (e.g. page-views). The role of the timing of grouping was also examined by carrying out the intervention once in the first and once in the second half of the course. The results indicate that in both interventions, the groups formed with a greater degree of homogeneity had higher rates of task-completion and peer interactions, Additionally, students from these groups reported higher levels of satisfaction with their group experiences. On the other hand, a consistent improvement of all indicators was observed in the second intervention, since student engagement becomes more stable later in the course. [ABSTRACT FROM AUTHOR]

Student dropout in Engineering Education is an important problem which has been studied from different perspectives, as well as using different techniques. This manuscript describes the methodology used in order to address this question in the context of learning analytics. Bayesian networks (BNs) have been used as they provide adequate methods for the representation, interpretation and contextualisation of data. The proposed approach is illustrated through a case study about Computer Science (CS) dropout at the University of Castilla-La Mancha (Spain), which is close to 40%. To that end, several BNs were obtained from a database which contained 383 records representing both academic and social data of the students enrolled in the CS degree during four courses. Then, these probabilistic models were interpreted and evaluated. The results obtained revealed that the best model that fits the data is provided by the K2 algorithm although the great heterogeneity of the data studied did not permit the adjustment of the dropout profile of the student too accurately. Nonetheless, the methodology described here can be taken as a reference for future works. [ABSTRACT FROM AUTHOR]

The diversity of bibliometric indices today poses the challenge of exploiting the relationships among them. Our research uncovers the best core set of relevant indices for predicting other bibliometric indices. An added difficulty is to select the role of each variable, that is, which bibliometric indices are predictive variables and which are response variables. This results in a novel multioutput regression problem where the role of each variable (predictor or response) is unknown beforehand. We use Gaussian Bayesian networks to solve the this problem and discover multivariate relationships among bibliometric indices. These networks are learnt by a genetic algorithm that looks for the optimal models that best predict bibliometric data. Results show that the optimal induced Gaussian Bayesian networks corroborate previous relationships between several indices, but also suggest new, previously unreported interactions. An extended analysis of the best model illustrates that a set of 12 bibliometric indices can be accurately predicted using only a smaller predictive core subset composed of citations, g-index, q2-index, and hr-index. This research is performed using bibliometric data on Spanish full professors associated with the computer science area. [ABSTRACT FROM AUTHOR]

Background: Factors explaining disparities in risk of substance use between immigrants and natives and between immigrant subgroups are poorly understood. We aimed to describe such disparities and identify some explanatory factors in Spain. Methods: Participants were residents aged 15-64 years from 2005 to 07 nationally representative surveys. Outcomes were prevalences of alcohol, tobacco, sedative-hypnotics, cannabis and other illegal substance use. Immigrants were recent if <5 years of Spanish stay and long term if ≥10 years. Country-of-origin income per capita and population level of substance use were taken from international databases. Adjusted prevalence ratios (aPRs) and percent change from Poisson regression with robust variance were used to estimate risk disparities and effects of immigration variables. Results: Most immigrants had lower substance use than natives, although it generally increased with increasing Spanish stay, especially for illegal substances. This lower risk could be partially explained by country-of-origin contextual factors as a lower level of income or substance use and religious or cultural factors such as Islam. By origin, recent immigrant aPRs and convergence-divergence risk patterns were, respectively, as follows: lower aPRs with upward convergence (often incomplete) toward natives' risk in immigrants from Muslim area, Eastern-Europe and Latin-America excluding South-Cone, lower/ similar aPRs with upward overtaking or divergent patterns in South-Cone Americans and similar/higher aPRs with stable or upward divergent patterns in Non-Eastern-Europeans. Conclusion: Spain is a host context that seems to facilitate increased substance use among immigrants, even those from countries with prevalences close to Spain. However, country-of-origin context is important in explaining disparities in substance use among immigrants. [ABSTRACT FROM AUTHOR]

Background We assessed the local implementation of syndromic surveillance (SyS) as part of the European project ‘System for Information on, Detection and Analysis of Risks and Threats to Health’ in Santander, Spain. Methods We applied a cumulative sum algorithm on emergency department (ED) chief complaints for influenza-like illness in the seasons 2010–11 and 2011–12. We fine tuned the algorithm using a receiver operating characteristic analysis to identify the optimal trade-off of sensitivity and specificity and defined alert criteria. We assessed the timeliness of the SyS system to detect the onset of the influenza season. Results The ED data correlated with the sentinel data. With the best algorithm settings we achieved 70/63% sensitivity and 89/95% specificity for 2010–11/2011–12. At least 2 consecutive days of signals defined an alert. In 2010–11 the SyS system alerted 1 week before the sentinel system and in 2011–12 in the same week. The data from the ED is available on a daily basis providing an advantage in timeliness compared with the weekly sentinel data. Conclusions ED-based SyS in Santander complements sentinel influenza surveillance by providing timely information. Local fine tuning and definition of alert criteria are recommended to enhance validity. [ABSTRACT FROM AUTHOR]

BackgroundPredictD is a risk algorithm that was developed to predict risk of onset of major depression over 12 months in general practice attendees in Europe and validated in a similar population in Chile. It was the first risk algorithm to be developed in the field of mental disorders. Our objective was to extend predictD as an algorithm to detect people at risk of major depression over 24 months.MethodParticipants were 4190 adult attendees to general practices in the UK, Spain, Slovenia and Portugal, who were not depressed at baseline and were followed up for 24 months. The original predictD risk algorithm for onset of DSM-IV major depression had already been developed in data arising from the first 12 months of follow-up. In this analysis we fitted predictD to the longer period of follow-up, first by examining only the second year (12–24 months) and then the whole period of follow-up (0–24 months).ResultsThe instrument performed well for prediction of major depression from 12 to 24 months [c-index 0.728, 95% confidence interval (CI) 0.675–0.781], or over the whole 24 months (c-index 0.783, 95% CI 0.757–0.809).ConclusionsThe predictD risk algorithm for major depression is accurate over 24 months, extending it current use of prediction over 12 months. This strengthens its use in prevention efforts in general medical settings. [ABSTRACT FROM AUTHOR]

BackgroundThe different incidence rates of, and risk factors for, depression in different countries argue for the need to have a specific risk algorithm for each country or a supranational risk algorithm. We aimed to develop and validate a predictD-Spain risk algorithm (PSRA) for the onset of major depression and to compare the performance of the PSRA with the predictD-Europe risk algorithm (PERA) in Spanish primary care.MethodA prospective cohort study with evaluations at baseline, 6 and 12 months. We measured 39 known risk factors and used multi-level logistic regression and inverse probability weighting to build the PSRA. In Spain (4574), Chile (2133) and another five European countries (5184), 11 891 non-depressed adult primary care attendees formed our at-risk population. The main outcome was DSM-IV major depression (CIDI).ResultsSix variables were patient characteristics or past events (sex, age, sex×age interaction, education, physical child abuse, and lifetime depression) and six were current status [Short Form 12 (SF-12) physical score, SF-12 mental score, dissatisfaction with unpaid work, number of serious problems in very close persons, dissatisfaction with living together at home, and taking medication for stress, anxiety or depression]. The C-index of the PSRA was 0.82 [95% confidence interval (CI) 0.79–0.84]. The Integrated Discrimination Improvement (IDI) was 0.0558 [standard error (s.e.)=0.0071, Zexp=7.88, p<0.0001] mainly due to the increase in sensitivity. Both the IDI and calibration plots showed that the PSRA functioned better than the PERA in Spain.ConclusionsThe PSRA included new variables and afforded an improved performance over the PERA for predicting the onset of major depression in Spain. However, the PERA is still the best option in other European countries. [ABSTRACT FROM PUBLISHER]