Intelligent decision support to predict patient barotrauma risk in intensive care units

The occurrence of Barotrauma is identified as a major concern for health professionals, since it can be fatal for patients. In order to support the decision process and to predict the risk of occurring barotrauma Data Mining models were induced. Based on this principle, the present study addresses the Data Mining process aiming to provide hourly probability of a patient has Barotrauma. The process of discovering implicit knowledge in data collected from Intensive Care Units patientswas achieved through the standard process Cross Industry Standard Process for Data Mining. With the goal of making predictions according to the classification approach they several DM techniques were selected: Decision Trees, Naive Bayes and Support Vector Machine. The study was focused on identifying the validity and viability to predict a composite variable. To predict the Barotrauma two classes were created: “risk” and “no risk”. Such target come from combining two variables: Plateau Pressure and PCO2. The best models presented a sensitivity between 96.19% and 100%. In terms of accuracy the values varied between 87.5% and 100%. This study and the achieved results demonstrated the feasibility of predicting the risk of a patient having Barotrauma by presenting the probability associated.

Stress induced risk-aversion is reverted by D2/D3 agonist in the rat

Stress exposure triggers cognitive and behavioral impairments that influence decision-making processes. Decisions under a context of uncertainty require complex reward-prediction processes that are known to be mediated by the mesocorticolimbic dopamine (DA) system in brain areas sensitive to the deleterious effects of chronic stress, in particular the orbitofrontal cortex (OFC). Using a decision-making task, we show that chronic stress biases risk-based decision-making to safer behaviors. This decision-making pattern is associated with an increased activation of the lateral part of the OFC and with morphological changes in pyramidal neurons specifically recruited by this task. Additionally, stress exposure induces a hypodopaminergic status accompanied by increased mRNA levels of the dopamine receptor type 2 (Drd2) in the OFC; importantly, treatment with a D2/D3 agonist quinpirole reverts the shift to safer behaviors induced by stress on risky decision-making. These results suggest that the brain mechanisms related to risk-based decision-making are altered after chronic stress, but can be modulated by manipulation of dopaminergic transmission.

Masonry infill walls under blast loading using confined underwater blast wave generators (WBWG)

The vulnerability of the masonry envelop under blast loading is considered critical due to the risk of loss of lives. The behaviour of masonry infill walls subjected to dynamic out-of-plane loading was experimentally investigated in this work. Using confined underwater blast wave generators (WBWG), applying the extremely high rate conversion of the explosive detonation energy into the kinetic energy of a thick water confinement, allowed a surface area distribution avoiding also the generation of high velocity fragments and reducing atmospheric sound wave. In the present study, water plastic containers, having in its centre a detonator inside a cylindrical explosive charge, were used in unreinforced masonry infills panels with 1.7m by 3.5m. Besides the usage of pressure and displacement transducers, pictures with high-speed video cameras were recorded to enable processing of the deflections and identification of failure modes. Additional numerical studies were performed in both unreinforced and reinforced walls. Bed joint reinforcement and grid reinforcement were used to strengthen the infill walls, and the results are presented and compared, allowing to obtain pressure-impulse diagrams for design of masonry infill walls.

Decision methods applied to solve a safety problem on a waste treatment facility

To solve a health and safety problem on a waste treatment facility, different multicriteria decision methods were used, including the PROV Exponential decision method. Four alternatives and ten attributes were considered. We found a congruent solution, validated by the different methods. The AHP and the PROV Exponential decision method led us to the same options ordering, but the last method reinforced one of the options as being the best performing one, and detached the least performing option. Also, the ELECTRE I method results led to the same ordering which allowed to point the best solution with reasonable confidence. This paper demonstrates the potential of using multicriteria decision methods to support decision making on complex problems such as risk control and accidents prevention.

Defining risk acceptance criteria in occupational settings: A case study in the furniture industrial sector

The use of appropriate acceptance criteria in the risk assessment process for occupational accidents is an important issue but often overlooked in the literature, particularly when new risk assessment methods are proposed and discussed. In most cases, there is no information on how or by whom they were defined, or even how companies can adapt them to their own circumstances. Bearing this in mind, this study analysed the problem of the definition of risk acceptance criteria for occupational settings, defining the quantitative acceptance criteria for the specific case study of the Portuguese furniture industrial sector. The key steps to be considered in formulating acceptance criteria were analysed in the literature review. By applying the identified steps, the acceptance criteria for the furniture industrial sector were then defined. The Cumulative Distribution Function (CDF) for the injury statistics of the industrial sector was identified as the maximum tolerable risk level. The acceptable threshold was defined by adjusting the CDF to the Occupational, Safety & Health (OSH) practitioners’ risk acceptance judgement. Adjustments of acceptance criteria to the companies’ safety cultures were exemplified by adjusting the Burr distribution parameters. An example of a risk matrix was also used to demonstrate the integration of the defined acceptance criteria into a risk metric. This work has provided substantial contributions to the issue of acceptance criteria for occupational accidents, which may be useful in overcoming the practical difficulties faced by authorities, companies and experts.

Predicting type of delivery by identification of obstetric risk factors through data mining

In Maternity Care, a quick decision has to be made about the most suitable delivery type for the current patient. Guidelines are followed by physicians to support that decision; however, those practice recommendations are limited and underused. In the last years, caesarean delivery has been pursued in over 28% of pregnancies, and other operative techniques regarding specific problems have also been excessively employed. This study identifies obstetric and pregnancy factors that can be used to predict the most appropriate delivery technique, through the induction of data mining models using real data gathered in the perinatal and maternal care unit of Centro Hospitalar of Oporto (CHP). Predicting the type of birth envisions high-quality services, increased safety and effectiveness of specific practices to help guide maternity care decisions and facilitate optimal outcomes in mother and child. In this work was possible to acquire good results, achieving sensitivity and specificity values of 90.11% and 80.05%, respectively, providing the CHP with a model capable of correctly identify caesarean sections and vaginal deliveries.

The role of ascorbate peroxidase, guaiacol peroxidase, and polysaccharides in cassava (Manihot esculenta Crantz) roots under postharvest physiological deterioration

Abstract This study aimed to investigate the role of ascorbate peroxidase (APX), guaiacol peroxidase (GPX), polysaccharides, and protein contents associated with the early events of postharvest physiological deterioration (PPD) in cassava roots. Increases in APX and GPX activity, as well as total protein contents occurred from 3 to 5 days of storage and were correlated with the delay of PPD. Cassava samples stained with periodic acid-Schiff (PAS) highlighted the presence of starch and cellulose. Degradation of starch granules during PPD was also detected. Slight metachromatic reaction with toluidine blue is indicative of increasing of acidic polysaccharides and may play an important role in PPD delay. Principal component analysis (PCA) classified samples according to their levels of enzymatic activity based on the decision tree model which showed GPX and total protein amounts to be correlated with PPD. The Oriental (ORI) cultivar was more susceptible to PPD.

Predicting harsh discipline in at-risk mothers: the moderating effect of socioeconomic deprivation severity

Socioeconomic disadvantage is an important predictor of maternal harsh discipline, but few studies have examined risk mechanisms for harsh parenting within disadvantaged samples. In the present study, parenting stress, family conflict, and child difficult temperament are examined as predictors of maternal harsh discipline among a group of 58 mothers from socioeconomically disadvantaged backgrounds and their young children between the ages of 1- to 4-years-old. Maternal harsh discipline was measured using standardized observations, and mothers reported on parenting stress, family conflict, and child temperament. Severity of socioeconomic deprivation was included as a moderator in these associations. Results showed that parenting stress and family conflict predicted maternal harsh discipline, but only in the most severely deprived families. These findings extend prior research on the processes through which socioeconomic deprivation severity and family functioning impact maternal harsh discipline within a high-risk sample of low-income families. They suggest that the spillover of negative parental functioning into parent–child interactions is particularly likely under conditions of substantial socioeconomic deprivation. Severity of socioeconomic stress seems to undermine maternal adaptive forms of coping, resulting in harsh disciplining practices. Intervention efforts aimed at improving parenting and family relations, as well as an adaptive coping style assume especial relevance.

Logic programming and artificial neural networks in breast cancer detection

About 90% of breast cancers do not cause or are capable of producing death if detected at an early stage and treated properly. Indeed, it is still not known a specific cause for the illness. It may be not only a beginning, but also a set of associations that will determine the onset of the disease. Undeniably, there are some factors that seem to be associated with the boosted risk of the malady. Pondering the present study, different breast cancer risk assessment models where considered. It is our intention to develop a hybrid decision support system under a formal framework based on Logic Programming for knowledge representation and reasoning, complemented with an approach to computing centered on Artificial Neural Networks, to evaluate the risk of developing breast cancer and the respective Degree-of-Confidence that one has on such a happening.

The importance of risk assessment in the context of investment project management: a case study

Risk management is an important component of project management. Nevertheless, such process begins with risk assessment and evaluation. In this research project, a detailed analysis of the methodologies used to treat risks in investment projects adopted by the Banco da Amazonia S.A. was made. Investment projects submitted to the FNO (Constitutional Fund for Financing the North) during 2011 and 2012 were considered for that purpose. It was found that the evaluators of this credit institution use multiple indicators for risk assessment which assume a central role in terms of decision-making and contribute for the approval or the rejection of the submitted projects; namely, the proven ability to pay, the financial records of project promotors, several financial restrictions, level of equity, level of financial indebtedness, evidence of the existence of a consumer market, the proven experience of the partners/owners in the business, environmental aspects, etc. Furthermore, the bank has technological systems to support the risk assessment process, an internal communication system and a unique system for the management of operational risk.

Project scheduling and cost minimization with multiple availability constrained resources under stochastic conditions

The authors propose a mathematical model to minimize the project total cost where there are multiple resources constrained by maximum availability. They assume the resources as renewable and the activities can use any subset of resources requiring any quantity from a limited real interval. The stochastic nature is inferred by means of a stochastic work content defined per resource within an activity and following a known distribution and the total cost is the sum of the resource allocation cost with the tardiness cost or earliness bonus in case the project finishes after or before the due date, respectively. The model was computationally implemented relying upon an interchange of two global optimization metaheuristics – the electromagnetism-like mechanism and the evolutionary strategies. Two experiments were conducted testing the implementation to projects with single and multiple resources, and with or without maximum availability constraints. The set of collected results shows good behavior in general and provide a tool to further assist project manager decision making in the planning phase.

Autoimmune diseases and pregnancy: analysis of a series of cases

BACKGROUND: An autoimmune disease is characterized by tissue damage, caused by self-reactivity of different effector mechanisms of the immune system, namely antibodies and T cells. All autoimmune diseases, to some extent, have implications for fertility and obstetrics. Currently, due to available treatments and specialised care for pregnant women with autoimmune disease, the prognosis for both mother and child has improved significantly. However these pregnancies are always high risk. The purpose of this study is to analyse the fertility/pregnancy process of women with systemic and organ-specific autoimmune diseases and assess pathological and treatment implications. METHODS: The authors performed an analysis of the clinical records and relevant obstetric history of five patients representing five distinct autoimmune pathological scenarios, selected from Autoimmune Disease Consultation at the Hospital of Braga, and reviewed the literature. RESULTS: The five clinical cases are the following: Case 1-28 years old with systemic lupus erythematosus, and clinical remission of the disease, under medication with hydroxychloroquine, prednisolone and acetylsalicylic acid, with incomplete miscarriage at 7 weeks of gestation without signs of thrombosis. Case 2-44 years old with history of two late miscarriages, a single preterm delivery (33 weeks) and multiple thrombotic events over the years, was diagnosed with antiphospholipid syndrome after acute myocardial infarction. Case 3-31 years old with polymyositis, treated with azathioprine for 3 years with complete remission of the disease, took the informed decision to get pregnant after medical consultation and full weaning from azathioprine, and gave birth to a healthy term new-born. Case 4-38 years old pregnant woman developed Behcet's syndrome during the final 15 weeks of gestation and with disease exacerbation after delivery. Case 5-36 years old with autoimmune thyroiditis diagnosed during her first pregnancy, with difficult control over the thyroid function over the years and first trimester miscarriage, suffered a second miscarriage despite clinical stability and antibody regression. CONCLUSIONS: As described in literature, the authors found a strong association between autoimmune disease and obstetric complications, especially with systemic lupus erythematosus, antiphospholipid syndrome and autoimmune thyroiditis.

Development of a methodology to incorporate risk and uncertainty in electricity power planning

Dissertação de mestrado em Engenharia Industrial

ACL injuries identifiable for pre-participation imagiological analysis: Risk factors

Identification of pre-participation risk factors for noncontact anterior cruciate ligament (ACL) injuries has been attracting a great deal of interest in the sports medicine and traumatology communities. Appropriate methods that enable predicting which patients could benefit from pre- ventive strategies are most welcome. This would enable athlete-specific training and conditioning or tailored equipment in order to develop appropriate strategies to reduce incidence of injury. In order to accomplish these goals, the ideal system should be able to assess both anatomic and functional features. Complementarily, the screening method must be cost-effective and suited for widespread application. Anatomic study protocol requiring only standard X rays could answer some of such demands. Dynamic MRI/CT evaluation and electronically assisted pivot-shift evaluation can be powerful tools providing complementary information. These upcoming insights, when validated and properly combined, envision changing pre-participation knee examination in the near future. Herein different methods (validated or under research) aiming to improve the capacity to identify persons/athletes with higher risk for ACL injury are overviewed. 

Development of a model for occupational risk acceptance criteria definition in industrial settings

Doctoral Dissertation for PhD degree in Industrial and Systems Engineering