Real-Time decision support using data mining to predict blood pressure critical events in intensive medicine patients

Patient blood pressure is an important vital signal to the physicians take a decision and to better understand the patient condition. In Intensive Care Units is possible monitoring the blood pressure due the fact of the patient being in continuous monitoring through bedside monitors and the use of sensors. The intensivist only have access to vital signs values when they look to the monitor or consult the values hourly collected. Most important is the sequence of the values collected, i.e., a set of highest or lowest values can signify a critical event and bring future complications to a patient as is Hypotension or Hypertension. This complications can leverage a set of dangerous diseases and side-effects. The main goal of this work is to predict the probability of a patient has a blood pressure critical event in the next hours by combining a set of patient data collected in real-time and using Data Mining classification techniques. As output the models indicate the probability (%) of a patient has a Blood Pressure Critical Event in the next hour. The achieved results showed to be very promising, presenting sensitivity around of 95%.

Kangaroo mother care diminishes pain from heel lance in very preterm neonates: a crossover trial.

BACKGROUND: Skin-to-skin contact, or kangaroo mother care (KMC) has been shown to be efficacious in diminishing pain response to heel lance in full term and moderately preterm neonates. The purpose of this study was to determine if KMC would also be efficacious in very preterm neonates. METHODS: Preterm neonates (n = 61) between 28 0/7 and 31 6/7 weeks gestational age in three Level III NICU's in Canada comprised the sample. A single-blind randomized crossover design was employed. In the experimental condition, the infant was held in KMC for 15 minutes prior to and throughout heel lance procedure. In the control condition, the infant was in prone position swaddled in a blanket in the incubator. The primary outcome was the Premature Infant Pain Profile (PIPP), which is comprised of three facial actions, maximum heart rate, minimum oxygen saturation levels from baseline in 30-second blocks from heel lance. The secondary outcome was time to recover, defined as heart rate return to baseline. Continuous video, heart rate and oxygen saturation monitoring were recorded with event markers during the procedure and were subsequently analyzed. Repeated measures analysis-of-variance was employed to generate results. RESULTS: PIPP scores at 90 seconds post lance were significantly lower in the KMC condition (8.871 (95%CI 7.852-9.889) versus 10.677 (95%CI 9.563-11.792) p < .001) and non-significant mean differences ranging from 1.2 to1.8. favoring KMC condition at 30, 60 and 120 seconds. Time to recovery was significantly shorter, by a minute(123 seconds (95%CI 103-142) versus 193 seconds (95%CI 158-227). Facial actions were highly significantly lower across all points in time reaching a two-fold difference by 120 seconds post-lance and heart rate was significantly lower across the first 90 seconds in the KMC condition. CONCLUSION: Very preterm neonates appear to have endogenous mechanisms elicited through skin-to-skin maternal contact that decrease pain response, but not as powerfully as in older preterm neonates. The shorter recovery time in KMC is clinically important in helping maintain homeostasis. TRIAL REGISTRATION: (Current Controlled Trials) ISRCTN63551708.

Perinatal care at the limit of viability between 22 and 26 completed weeks of gestation in Switzerland.

Perinatal care of pregnant women at high risk for preterm delivery and of preterm infants born at the limit of viability (22-26 completed weeks of gestation) requires a multidisciplinary approach by an experienced perinatal team. Limited precision in the determination of both gestational age and foetal weight, as well as biological variability may significantly affect the course of action chosen in individual cases. The decisions that must be taken with the pregnant women and on behalf of the preterm infant in this context are complex and have far-reaching consequences. When counselling pregnant women and their partners, neonatologists and obstetricians should provide them with comprehensive information in a sensitive and supportive way to build a basis of trust. The decisions are developed in a continuing dialogue between all parties involved (physicians, midwives, nursing staff and parents) with the principal aim to find solutions that are in the infant's and pregnant woman's best interest. Knowledge of current gestational age-specific mortality and morbidity rates and how they are modified by prenatally known prognostic factors (estimated foetal weight, sex, exposure or nonexposure to antenatal corticosteroids, single or multiple births) as well as the application of accepted ethical principles form the basis for responsible decision-making. Communication between all parties involved plays a central role. The members of the interdisciplinary working group suggest that the care of preterm infants with a gestational age between 22 0/7 and 23 6/7 weeks should generally be limited to palliative care. Obstetric interventions for foetal indications such as Caesarean section delivery are usually not indicated. In selected cases, for example, after 23 weeks of pregnancy have been completed and several of the above mentioned prenatally known prognostic factors are favourable or well informed parents insist on the initiation of life-sustaining therapies, active obstetric interventions for foetal indications and provisional intensive care of the neonate may be reasonable. In preterm infants with a gestational age between 24 0/7 and 24 6/7 weeks, it can be difficult to determine whether the burden of obstetric interventions and neonatal intensive care is justified given the limited chances of success of such a therapy. In such cases, the individual constellation of prenatally known factors which impact on prognosis can be helpful in the decision making process with the parents. In preterm infants with a gestational age between 25 0/7 and 25 6/7 weeks, foetal surveillance, obstetric interventions for foetal indications and neonatal intensive care measures are generally indicated. However, if several prenatally known prognostic factors are unfavourable and the parents agree, primary non-intervention and neonatal palliative care can be considered. All pregnant women with threatening preterm delivery or premature rupture of membranes at the limit of viability must be transferred to a perinatal centre with a level III neonatal intensive care unit no later than 23 0/7 weeks of gestation, unless emergency delivery is indicated. An experienced neonatology team should be involved in all deliveries that take place after 23 0/7 weeks of gestation to help to decide together with the parents if the initiation of intensive care measures appears to be appropriate or if preference should be given to palliative care (i.e., primary non-intervention). In doubtful situations, it can be reasonable to initiate intensive care and to admit the preterm infant to a neonatal intensive care unit (i.e., provisional intensive care). The infant's clinical evolution and additional discussions with the parents will help to clarify whether the life-sustaining therapies should be continued or withdrawn. Life support is continued as long as there is reasonable hope for survival and the infant's burden of intensive care is acceptable. If, on the other hand, the health care team and the parents have to recognise that in the light of a very poor prognosis the burden of the currently used therapies has become disproportionate, intensive care measures are no longer justified and other aspects of care (e.g., relief of pain and suffering) are the new priorities (i.e., redirection of care). If a decision is made to withhold or withdraw life-sustaining therapies, the health care team should focus on comfort care for the dying infant and support for the parents.

Nosocomial Outbreak of Infection With Pan-Drug-Resistant Acinetobacter baumannii in a Tertiary Care University Hospital

OBJECTIVE To describe what is, to our knowledge, the first nosocomial outbreak of infection with pan-drug-resistant (including colistin-resistant) Acinetobacter baumannii, to determine the risk factors associated with these types of infections, and to determine their clinical impact. DESIGN Nested case-control cohort study and a clinical-microbiological study. SETTING A 1,521-bed tertiary care university hospital in Seville, Spain. PATIENTS Case patients were inpatients who had a pan-drug-resistant A. baumannii isolate recovered from a clinical or surveillance sample obtained at least 48 hours after admission to an intensive care unit (ICU) during the time of the epidemic outbreak. Control patients were patients who were admitted to any of the "boxes" (ie, rooms that partition off a distinct area for a patient's bed and the equipment needed to care for the patient) of an ICU for at least 48 hours during the time of the epidemic outbreak. RESULTS All the clinical isolates had similar antibiotic susceptibility patterns (ie, they were resistant to all the antibiotics tested, including colistin), and, on the basis of repetitive extragenic palindromic-polymerase chain reaction, it was determined that all of them were of the same clone. The previous use of quinolones and glycopeptides and an ICU stay were associated with the acquisition of infection or colonization with pan-drug-resistant A. baumannii. To control this outbreak, we implemented the following multicomponent intervention program: the performance of environmental decontamination of the ICUs involved, an environmental survey, a revision of cleaning protocols, active surveillance for colonization with pan-drug-resistant A. baumannii, educational programs for the staff, and the display of posters that illustrate contact isolation measures and antimicrobial use recommendations. CONCLUSIONS We were not able to identify the common source for these cases of infection, but the adopted measures have proven to be effective at controlling the outbreak.

Recommendations on the use of EEG monitoring in critically ill patients: consensus statement from the neurointensive care section of the ESICM.

OBJECTIVES: Recommendations for EEG monitoring in the ICU are lacking. The Neurointensive Care Section of the ESICM assembled a multidisciplinary group to establish consensus recommendations on the use of EEG in the ICU. METHODS: A systematic review was performed and 42 studies were included. Data were extracted using the PICO approach, including: (a) population, i.e. ICU patients with at least one of the following: traumatic brain injury, subarachnoid hemorrhage, intracerebral hemorrhage, stroke, coma after cardiac arrest, septic and metabolic encephalopathy, encephalitis, and status epilepticus; (b) intervention, i.e. EEG monitoring of at least 30 min duration; (c) control, i.e. intermittent vs. continuous EEG, as no studies compared patients with a specific clinical condition, with and without EEG monitoring; (d) outcome endpoints, i.e. seizure detection, ischemia detection, and prognostication. After selection, evidence was classified and recommendations developed using the GRADE system. RECOMMENDATIONS: The panel recommends EEG in generalized convulsive status epilepticus and to rule out nonconvulsive seizures in brain-injured patients and in comatose ICU patients without primary brain injury who have unexplained and persistent altered consciousness. We suggest EEG to detect ischemia in comatose patients with subarachnoid hemorrhage and to improve prognostication of coma after cardiac arrest. We recommend continuous over intermittent EEG for refractory status epilepticus and suggest it for patients with status epilepticus and suspected ongoing seizures and for comatose patients with unexplained and persistent altered consciousness. CONCLUSIONS: EEG monitoring is an important diagnostic tool for specific indications. Further data are necessary to understand its potential for ischemia assessment and coma prognostication.

Respiratory variability in mechanically ventilated patients. Critical Care 2011

Introduction: Increased respiratory pattern variability is associated with improved oxygenation. Pressure support (PS) is a widely used partial-assist mechanical ventilation (MV) mode, in which each breathing cycle is initiated by flow or pressure variation at the airway due to patient inspiratory effort. Neurally adjusted ventilatory assist (NAVA) is relatively new and uses the electrical activity of the diaphragm (Eadi) to deliver ventilatory support proportional to the patient's inspiratory demand. We hypothesize that respiratory variability should be greater with NAVA compared with PS.Methods: Twenty-two patients underwent 20 minutes of PS followed by 20 minutes of NAVA. Flow and Eadi curves were used to obtain tidal volume (Vt) and ∫Eadi for 300 to 400 breaths in each patient. Patient-specific cumulative distribution functions (CDF) show the percentage Vt and ∫Eadi within a clinically defined (±10%) variability band for each patient. Values are normalized to patient-specific medians for direct comparison. Variability in Vt (outcome) is thus expressed in terms of variability in ∫Eadi (demand) on the same plot.Results: Variability in Vt relative to variability in ∫Eadi is significantly greater for NAVA than PS (P = 0.00012). Hence, greater variability in outcome Vt is obtained for a given demand in ∫Eadi, under NAVA, as illustrated in Figure 1 for a typical patient. A Fisher 2 × 2 contingency analysis showed that 45% of patients under NAVA had a Vt variability in equal proportion to ∫Eadi variability, versus 0% for PS (P < 0.05).Conclusions: NAVA yields greater variability in tidal volume, relative to ∫Eadi demand, and a better match between Vt and ∫Eadi. These results indicate that NAVA could achieve improved oxygenation compared with PS when sufficient underlying variability in ∫Eadi is present, due to its ability to achieve higher tidal volume variability from a given variability in ∫Eadi.

Improving patient safety: how and why incidences occur in nursing care

The present investigation was a cross-sectional, quantitative research study analyzing incidents associated with nursing care using a root-cause methodological analysis. The study was conducted in a public hospital intensive care unit (ICU) in Santiago de Chile and investigated 18 incidents related to nursing care that occurred from January to March of 2012. The sample was composed of six cases involving medications and the self-removal of therapeutic devices. The contributing factors were related to the tasks and technology, the professional work team, the patients, and the environment. The analysis confirmed that the cases presented with similar contributing factors, thereby indicating that the vulnerable aspects of the system are primarily responsible for the incidence occurrence. We conclude that root-cause analysis facilitates the identification of these vulnerable points. Proactive management in system-error prevention is made possible by recommendations.

Nursing workload in specialized Semi-intensive Therapy unit: workforce size criteria

Abstract OBJECTIVE To assess the nursing workload (NW) in Semi-intensive Therapy Unit, specialized in the care of children with Craniofacial anomalies and associated syndromes; to compare the amount of workforce required according to the Nursing Activities Score (NAS) and the COFEN Resolution 293/04. METHOD Cross-sectional study, whose sample was composed of 72 patients. Nursing workload was assessed through retrospective application of the NAS. RESULTS the NAS mean was 49.5%. Nursing workload for the last day of hospitalization was lower in patients being discharged to home (p<0.001) and higher on the first compared to last day of hospitalization (p< 0.001). The number of professionals required according to NAS was superior to the COFEN Resolution 293/04, being 17 and 14, respectively. CONCLUSION the nursing workload corresponded to approximately 50% of the working time of nursing professional and was influenced by day and outcome of hospitalization. The amount of professionals was greater than that determined by the existing legislation.

Interactions between respiration and systemic hemodynamics. Part II: practical implications in critical care.

In Part I of this review, we have covered basic concepts regarding cardiorespiratory interactions. Here, we put this theoretical framework to practical use. We describe mechanisms underlying Kussmaul's sign and pulsus paradoxus. We review the literature on the use of respiratory variations of blood pressure to evaluate volume status. We show the possibilities of attaining the latter aim by investigating with ultrasonography how the geometry of great veins fluctuates with respiration. We provide a Guytonian analysis of the effects of PEEP on cardiac output. We terminate with some remarks on the potential of positive pressure breathing to induce acute cor pulmonale, and on the cardiovascular mechanisms that at times may underly the failure to wean a patient from the ventilator.

Le Soutien psychiatrique Intensif dans le Milieu (SIM) à Lausanne: un projet pilote [Intensive Psychiatric Support at the Setting in Lausanne: a pilot project]

While the hospital remains an important element of the psychiatric health-care system, the fact that it is always the best place to treat acute psychotic episodes is still debated. After a brief review of the literature relative to the main existing community care models, the authors describe the development in the Department Universitaire de Psychiatrie Adulte (DUPA), of an alternative to hospitalisation for patient going through a severe acute psychiatric episode. They present three clinical situations and the aims of the research project, which will follow this pilot phase.

Invasive candidiasis: comparison of management choices by infectious disease and critical care specialists.

OBJECTIVE: To compare the management of invasive candidiasis between infectious disease and critical care specialists. DESIGN AND SETTING: Clinical case scenarios of invasive candidiasis were presented during interactive sessions at national specialty meetings. Participants responded to questions using an anonymous electronic voting system. PATIENTS AND PARTICIPANTS: Sixty-five infectious disease and 51 critical care physicians in Switzerland. RESULTS: Critical care specialists were more likely to ask advice from a colleague with expertise in the field of fungal infections to treat Candida glabrata (19.5% vs. 3.5%) and C. krusei (36.4% vs. 3.3%) candidemia. Most participants reported that they would change or remove a central venous catheter in the presence of candidemia, but 77.1% of critical care specialists would start concomitant antifungal treatment, compared to only 50% of infectious disease specialists. Similarly, more critical care specialists would start antifungal prophylaxis when Candida spp. are isolated from the peritoneal fluid at time of surgery for peritonitis resulting from bowel perforation (22.2% vs. 7.2%). The two groups equally considered Candida spp. as pathogens in tertiary peritonitis, but critical care specialists would more frequently use amphotericin B than fluconazole, caspofungin, or voriconazole. In mechanically ventilated patients the isolation of 10(4) Candida spp. from a bronchoalveolar lavage was considered a colonizing organism by 94.9% of infectious disease, compared to 46.8% of critical care specialists, with a marked difference in the use of antifungal agents (5.1% vs. 51%). CONCLUSIONS: These data highlight differences between management approaches for candidiasis in two groups of specialists, particularly in the reported use of antifungals.

Diagnostic potential of neutrophil elastase inhibitor complex in the routine care of critically ill newborn infants.

It has been suggested that determination of the neutrophil elastase alpha1-proteinase inhibitor complex (E-alpha1PI) improves the diagnosis of bacterial infection in newborns. We evaluated the use of E-alpha1PI measurements in 143 newborns, consecutively admitted to a tertiary intensive care unit, employing a new random access assay and a sampling procedure that minimises post-collection artefacts. The 95% range for noninfected newborns was 20-110 microg/l up to the 5th day of life and 20-85 microg/l thereafter. The sensitivity as to the diagnosis of culture-proven bloodstream infection was 80% for E-alpha1PI, 86% for the immature to total neutrophil ratio, 64% for C-reactive protein and 37% for the total white blood cell count. The corresponding specificity amounted to 97%, 85%, 85% and 86%, respectively. E-alpha1PI increases preceded elevations of C-reactive protein by 18 h. Like C-reactive protein, E-alpha1PI levels did not distinguish between bloodstream infection and non-bacterial inflammatory responses. Results of E-alpha1PI became available within 1 h of collection and usually 2-3 h before manual leucocyte counts. CONCLUSION: Determination of neutrophil elastase alpha1-proteinase inhibitor levels yields diagnostic advantages comparable to those of manual differential counts but provide faster turnaround times.

Experience and endocrine stress responses in neonatal and pediatric critical care nurses and physicians.

OBJECTIVE: Critical care is a working environment with frequent exposure to stressful events. High levels of psychological stress have been associated with increased prevalence of burnout. Psychological distress acts as a potent trigger of cortisol secretions. We attempted to objectify endocrine stress reactivity. DESIGN: Observational cohort study during two 12-day periods in successive years. SETTING: A tertiary multidisciplinary neonatal and pediatric intensive care unit (33 beds). SUBJECTS: One hundred and twelve nurses and 27 physicians (94% accrual rate). INTERVENTIONS AND MEASUREMENTS: Cortisol determined from salivary samples collected every 2 hrs and after stressful events. Participants recorded the subjective perception of stress with every sample. Endocrine reactions were defined as transient surges in cortisol of &gt;50% and 2.5 nmol/L over the baseline. MAIN RESULTS: During 7,145 working hours, we observed 474 (12.5%) endocrine reactions from 3,781 samples. The mean cortisol increase amounted to 10.6 nmol/L (219%). The mean occurrence rate of endocrine reactions per subject and sample was 0.159 (range, 0-0.43). Although the mean raw cortisol levels were lower in experienced team members (&gt;3 yrs of intensive care vs. &lt;3 yrs, 4.1 vs. 4.95 nmol/L, p &lt; .001), professional experience failed to attenuate the frequency and magnitude of endocrine reactions, except for the subgroup of nurses and physicians with &gt;8 yrs of intensive care experience. A high proportion (71.3%) of endocrine reactions occurred without conscious perception of stress. Unawareness of stress was higher in intensive care nurses (75.1%) than in intermediate care nurses (51.8%, p &lt; .01). CONCLUSIONS: Stress-related cortisol surges occur frequently in neonatal and pediatric critical care staff. Cortisol increases are independent of subjective stress perception. Professional experience does not abate the endocrine stress reactivity.

Behavioral changes in brain-injured critical care adults with different levels of consciousness during nociceptive stimulation: an observational study.

PURPOSE: The primary objective of this study was to describe the frequency of behaviors observed during rest, a non-nociceptive procedure, and a nociceptive procedure in brain-injured intensive care unit (ICU) patients with different levels of consciousness (LOC). Second, it examined the inter-rater reliability and discriminant and concurrent validity of the behavioral checklist used. METHODS: The non-nociceptive procedure involved calling the patient and shaking his/her shoulder. The nociceptive procedure involved turning the patient. The frequency of behaviors was recorded using a behavioral checklist. RESULTS: Patients with absence of movement, or stereotyped flexion or extension responses to a nociceptive stimulus displayed more behaviors during turning (median 5.5, range 0-14) than patients with localized responses (median 4, range 0-10) or able to self-report their pain (median 4, range 0-10). Face flushing, clenched teeth, clenched fist, and tremor were more frequent in patients with absence of movement, or stereotyped responses to a nociceptive stimulus. The reliability of the checklist was supported by a high intra-class correlation coefficient (0.77-0.92), and the internal consistency was acceptable in all three groups (KR 20, 0.71-0.85). Discriminant validity was supported as significantly more behaviors were observed during nociceptive stimulation than at rest. Concurrent validity was confirmed as checklist scores were correlated to the patients' self-reports of pain (r s = 0.53; 95 % CI 0.21-0.75). CONCLUSION: Brain-injured patients reacted significantly more during a nociceptive stimulus and the number of observed behaviors was higher in patients with a stereotyped response.