Clustering barotrauma patients in ICU–A data mining based approach using ventilator variables

Lecture Notes in Computer Science, 9273

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.

Rotura gástrica por barotrauma

Barogenic rupture of the stomach is a rare complication following cardiopulmonary resuscitation, administration of nasal oxygen by catheter and diving accidents. We report a case of gastric barotrauma following oroesophageal intubation. In most cases, the tears occur along the lesser curvature, what have been already attributed to Laplace's formula and, more recently, to morphological features of the stomach.

Rotura gástrica por barotrauma

Barogenic rupture of the stomach is a rare complication following cardiopulmonary resuscitation, administration of nasal oxygen by catheter and diving accidents. We report a case of gastric barotrauma following oroesophageal intubation. In most cases, the tears occur along the lesser curvature, what have been already attributed to Laplace's formula and, more recently, to morphological features of the stomach.

Avaliação de alterações timpanométricas em pacientes submetidos à anestesia geral com óxido nitroso

O óxido nitroso é um gás inalatório que pode aumentar a pressão intratimpânica durante o ato anestésico, bem como causar pressão negativa após sua suspensão, principalmente em pacientes com disfunção da tuba auditiva. Estas variações pressóricas podem trazer implicações clínicas, como ruptura de membrana timpânica, desarticulação da cadeia ossicular, hemotímpano, barotrauma, deslocamento de prótese de estapedotomia e lateralização do enxerto nas timpanoplastias, além da entrada de fluido seroso na orelha média durante a fase de pressão negativa. OBJETIVO: Avaliar a influência do óxido nitroso na pressão da orelha média em uma população sem disfunção tubária, realizando timpanometria no pré e pós-operatório. FORMA DE ESTUDO: Coorte transversal. MATERIAL E MÉTODO: Foi realizado um estudo prospectivo com pacientes internados no Hospital Universitário Clementino Fraga Filho - UFRJ, submetidos à anestesia geral com o uso do óxido nitroso a 50%, durante o período de abril a julho de 2003. Avaliou-se ainda se a duração da cirurgia, anestésicos associados, presença de rinite alérgica e desvio de septo nasal poderiam influenciar no aparecimento das alterações da pressão intratimpânica. RESULTADOS: A amostra constituiu-se de 50 pacientes, encontrando-se em quase metade (48%) alterações timpanométricas no pós-operatório (curva tipo C), quando comparado às de controle do pré-operatório (curva tipo A). Sexo e idade não interferiram no aparecimento das alterações timpanométricas no pós-operatório, bem como a duração da cirurgia. O tipo de anestésico volátil associado, desvio de septo nasal e rinite alérgica não exerceram influência na pressão da orelha média no pós-operatório. CONCLUSÃO: O óxido nitroso altera a pressão na orelha média tanto na fase de indução quanto na fase de resolução anestésica.

Predicting plateau pressure in intensive medicine for ventilated patients

Barotrauma is identified as one of the leading diseases in Ventilated Patients. This type of problem is most common in the Intensive Care Units. In order to prevent this problem the use of Data Mining (DM) can be useful for predicting their occurrence. The main goal is to predict the occurence of Barotrauma in order to support the health professionals taking necessary precautions. In a first step intensivists identified the Plateau Pressure values as a possible cause of Barotrauma. Through this study DM models (classification) where induced for predicting the Plateau Pressure class (>=30 cm

Volutrauma activates the clotting cascade in the newborn but not adult rat.

Coagulopathy and alveolar fibrin deposition are common in sick neonates and attributed to the primary disease, as opposed to their ventilatory support. Hypothesizing that high tidal volume ventilation activates the extrinsic coagulation pathway, we air ventilated newborn and adult rats at low (10 ml/kg) or high (30 ml/kg) tidal volume and compared them with age-matched nonventilated controls. Blood was collected at the end of the experiment for measurement of clot time, tissue factor, and other coagulation factor content. Similar measurements were obtained from lung lavage material. The newborn clot time (44+/-1) was lower and plasma tissue factor content higher (103.4+/-0.4) than adults (88+/-4 s and 26.6+/-1.4 units; P<0.01). High, but not low, tidal volume ventilation of newborns for as little as 15 min significantly reduced clot time and increased plasma tissue factor content (P<0.01). High volume ventilation increased plasma factor Xa (0.1+/-0.1 to 1.6+/-0.4 nM; P<0.01) and thrombin (1.3+/-0.2 to 2.2+/-0.4 nM; P<0.05) and decreased antithrombin (0.12+/-0.01 to 0.05+/-0.01; P<0.01) in the newborn. Lung lavage material of high volume-ventilated newborns showed increased (P<0.01) factor Xa and thrombin. No changes in these parameters were observed in adult rats that were high volume ventilated for up to 90 min. Compared with adults, newborn rats have a greater propensity for volutrauma-activated intravascular coagulation. These data suggest that mechanical ventilation promotes neonatal thrombosis via lung tissue factor release.

Complications of different ventilation strategies in endoscopic laryngeal surgery: a 10-year review.

BACKGROUND: Spontaneous ventilation, mechanical controlled ventilation, apneic intermittent ventilation, and jet ventilation are commonly used during interventional suspension microlaryngoscopy. The aim of this study was to investigate specific complications of each technique, with special emphasis on transtracheal and transglottal jet ventilation. METHODS: The authors performed a retrospective single-institution analysis of a case series of 1,093 microlaryngoscopies performed in 661 patients between January 1994 and January 2004. Data were collected from two separate prospective databases. Feasibility and complications encountered with each technique of ventilation were analyzed as main outcome measures. RESULTS: During 1,093 suspension microlaryngoscopies, ventilation was supplied by mechanical controlled ventilation via small endotracheal tubes (n = 200), intermittent apneic ventilation (n = 159), transtracheal jet ventilation (n = 265), or transglottal jet ventilation (n = 469). Twenty-nine minor and 4 major complications occurred. Seventy-five percent of the patients with major events had an American Society of Anesthesiologists physical status classification of III. Five laryngospasms were observed with apneic intermittent ventilation. All other 24 complications (including 7 barotrauma) occurred during jet ventilation. Transtracheal jet ventilation was associated with a significantly higher complication rate than transglottal jet ventilation (P < 0.0001; odds ratio, 4.3 [95% confidence interval, 1.9-10.0]). All severe complications were related to barotraumas resulting from airway outflow obstruction during jet ventilation, most often laryngospasms. CONCLUSIONS: The use of a transtracheal cannula was the major independent risk factor for complications during jet ventilation for interventional microlaryngoscopy. The anesthetist's vigilance in clinically detecting and preventing outflow airway obstruction remains the best prevention of barotrauma during subglottic jet ventilation.

Decompression scenarios in a new underground transportation system

BACKGROUND: The risks of a public exposure to a sudden decompression, until now, have been related to civil aviation and, at a lesser extent, to diving activities. However, engineers are currently planning the use of low pressure environments for underground transportation. This method has been proposed for the future Swissmetro, a high-speed underground train designed for inter-urban linking in Switzerland. HYPOTHESIS: The use of a low pressure environment in an underground public transportation system must be considered carefully regarding the decompression risks. Indeed, due to the enclosed environment, both decompression kinetics and safety measures may differ from aviation decompression cases. METHOD: A theoretical study of decompression risks has been conducted at an early stage of the Swissmetro project. A three-compartment theoretical model, based on the physics of fluids, has been implemented with flow processing software (Ithink 5.0). Simulations have been conducted in order to analyze "decompression scenarios" for a wide range of parameters, relevant in the context of the Swissmetro main study. RESULTS: Simulation results cover a wide range from slow to explosive decompression, depending on the simulation parameters. Not surprisingly, the leaking orifice area has a tremendous impact on barotraumatic effects, while the tunnel pressure may significantly affect both hypoxic and barotraumatic effects. Calculations have also shown that reducing the free space around the vehicle may mitigate significantly an accidental decompression. CONCLUSION: Numeric simulations are relevant to assess decompression risks in the future Swissmetro system. The decompression model has proven to be useful in assisting both design choices and safety management.

Diet, ageing and genetic factors in the pathogenesis of diverticular disease

Diverticular disease (DD) is an age-related disorder of the large bowel which may affect half of the population over the age of 65 in the UK. This high prevalence ranks it as one of the most common bowel disorders in western nations. The majority of patients remain asymptomatic but there are associated life-threatening co-morbidities, which, given the large numbers of people with DD, translates into a considerable number of deaths per annum. Despite this public health burden, relatively little seems to be known about either the mechanisms of development or causality. In the 1970s, a model of DD formulated the concept that diverticula occur as a consequence of pressureinduced damage to the colon wall amongst those with a low intake of dietary fiber. In this review, we have examined the evidence regarding the influence of ageing, diet, inflammation and genetics on DD development. We argue that the evidence supporting the barotrauma hypothesis is largely anecdotal. We have also identified several gaps in the knowledge base which need to be filled before we can complete

Comparação entre ventilação mandatória intermitente e ventilação mandatória intermitente sincronizada compressão de suporte em crianças

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

How large is the lung recruitability in early acute respiratory distress syndrome: a prospective case series of patients monitored by computed tomography

Introduction: The benefits of higher positive end expiratory pressure (PEEP) in patients with acute respiratory distress syndrome (ARDS) have been modest, but few studies have fully tested the "open-lung hypothesis". This hypothesis states that most of the collapsed lung tissue observed in ARDS can be reversed at an acceptable clinical cost, potentially resulting in better lung protection, but requiring more intensive maneuvers. The short-/middle-term efficacy of a maximum recruitment strategy (MRS) was recently described in a small physiological study. The present study extends those results, describing a case-series of non-selected patients with early, severe ARDS submitted to MRS and followed until hospital discharge or death. Methods: MRS guided by thoracic computed tomography (CT) included two parts: a recruitment phase to calculate opening pressures (incremental steps under pressure-controlled ventilation up to maximum inspiratory pressures of 60 cmH(2)O, at constant driving-pressures of 15 cmH(2)O); and a PEEP titration phase (decremental PEEP steps from 25 to 10 cmH2O) used to estimate the minimum PEEP to keep lungs open. During all steps, we calculated the size of the non-aerated (-100 to +100 HU) compartment and the recruitability of the lungs (the percent mass of collapsed tissue re-aerated from baseline to maximum PEEP). Results: A total of 51 severe ARDS patients, with a mean age of 50.7 years (84% primary ARDS) was studied. The opening plateau-pressure was 59.6 (+/- 5.9 cmH(2)O), and the mean PEEP titrated after MRS was 24.6 (+/- 2.9 cmH(2)O). Mean PaO2/FiO(2) ratio increased from 125 (+/- 43) to 300 (+/- 103; P < 0.0001) after MRS and was sustained above 300 throughout seven days. Non-aerated parenchyma decreased significantly from 53.6% (interquartile range (IQR): 42.5 to 62.4) to 12.7% (IQR: 4.9 to 24.2) (P < 0.0001) after MRS. The potentially recruitable lung was estimated at 45% (IQR: 25 to 53). We did not observe major barotrauma or significant clinical complications associated with the maneuver. Conclusions: MRS could efficiently reverse hypoxemia and most of the collapsed lung tissue during the course of ARDS, compatible with a high lung recruitability in non-selected patients with early, severe ARDS. This strategy should be tested in a prospective randomized clinical trial.

Rationale, study design, and analysis plan of the Alveolar Recruitment for ARDS Trial (ART): Study protocol for a randomized controlled trial

Background: Acute respiratory distress syndrome (ARDS) is associated with high in-hospital mortality. Alveolar recruitment followed by ventilation at optimal titrated PEEP may reduce ventilator-induced lung injury and improve oxygenation in patients with ARDS, but the effects on mortality and other clinical outcomes remain unknown. This article reports the rationale, study design, and analysis plan of the Alveolar Recruitment for ARDS Trial (ART). Methods/Design: ART is a pragmatic, multicenter, randomized (concealed), controlled trial, which aims to determine if maximum stepwise alveolar recruitment associated with PEEP titration is able to increase 28-day survival in patients with ARDS compared to conventional treatment (ARDSNet strategy). We will enroll adult patients with ARDS of less than 72 h duration. The intervention group will receive an alveolar recruitment maneuver, with stepwise increases of PEEP achieving 45 cmH(2)O and peak pressure of 60 cmH2O, followed by ventilation with optimal PEEP titrated according to the static compliance of the respiratory system. In the control group, mechanical ventilation will follow a conventional protocol (ARDSNet). In both groups, we will use controlled volume mode with low tidal volumes (4 to 6 mL/kg of predicted body weight) and targeting plateau pressure <= 30 cmH2O. The primary outcome is 28-day survival, and the secondary outcomes are: length of ICU stay; length of hospital stay; pneumothorax requiring chest tube during first 7 days; barotrauma during first 7 days; mechanical ventilation-free days from days 1 to 28; ICU, in-hospital, and 6-month survival. ART is an event-guided trial planned to last until 520 events (deaths within 28 days) are observed. These events allow detection of a hazard ratio of 0.75, with 90% power and two-tailed type I error of 5%. All analysis will follow the intention-to-treat principle. Discussion: If the ART strategy with maximum recruitment and PEEP titration improves 28-day survival, this will represent a notable advance to the care of ARDS patients. Conversely, if the ART strategy is similar or inferior to the current evidence-based strategy (ARDSNet), this should also change current practice as many institutions routinely employ recruitment maneuvers and set PEEP levels according to some titration method.

Intrahepatic gas at postmortem computed tomography: forensic experience as a potential guide for in vivo trauma imaging

BACKGROUND: Until August 2004 there were 106 forensic cases examined with postmortem multislice computed tomography (MSCT) and magnetic resonance (MR) imaging before traditional autopsy within the Virtopsy project. Intrahepatic gas (IHG) was a frequent finding in postmortem MSCT examinations. The aim of this study was to investigate its cause and significance. METHODS: There were 84 virtopsy cases retrospectively investigated concerning the occurrence, location, and volume of IHG in postmortem MSCT imaging (1.25 mm collimation, 1.25 mm thickness). We assessed and noted the occurrence of intestinal distention, putrefaction, and systemic gas embolisms and the cause of death, possible open trauma, possible artificial respiration, and the postmortem interval. We investigated the relations between the findings using the contingency table (chi2 test) and the comparison of the postmortem intervals in both groups was performed using the t test in 79 nonputrefied corpses. RESULTS: IHG was found in 47 cases (59.5%). In five of the cases, the IHG was caused or influenced by putrefaction. Gas distribution within the liver of the remaining 42 cases was as follows: hepatic arteries in 21 cases, hepatic veins in 35 cases, and portal vein branches in 13 cases; among which combinations also occurred in 20 cases. The presence of IHG was strongly related to open trauma with systemic gas. Pulmonary barotrauma as occurring under artificial respiration or in drowning also caused IHG. Putrefaction did not seem to influence the occurrence of IHG until macroscopic signs of putrefaction were noticeable. CONCLUSIONS: IHG is a frequent finding in traumatic causes of death and requires a systemic gas embolism. Exceptions are putrefied or burned corpses. Common clinical causes such as necrotic bowel diseases appear rarely as a cause of IHG in our forensic case material.