Intensive Care Monitoring Research Articles

Pigeon breeder`s disease as a cause of hypersensitivity pneumonia in children.

Hypersensitivity pneumonia is a complex condition due to exposure time, intensity, different clinical presentation, and treatment practices. We aimed to evaluate the patients that were diagnosed with hypersensitivity pneumonia (HSP) due to exposure to pigeons and a review of the literature for diagnosis and treatment of Pigeon Breeder`s Disease (PBD) in children. Between the years of 2009-2018, patients who were diagnosed with HSP due to PBD were included in the study in a pediatric pulmonology department. Findings of our patients, treatments, and prognoses were compared with 17 articles in the literature about PBD in children. In a 9 year-period, 6 patients were diagnosed as HSP due to PBD. The mean age of the patients was 8.8 ± 5.4 years and the average duration of pigeon exposure was 60.1 ± 6.5 days. Precipitating antibodies were positive in 3 patients. In four cases, symptoms were resolved with only prevention of pigeon exposure. Two patients who had close contact with pigeons needed oxygen supplementation and steroid therapy. Hypersensitivity pneumonia should be considered for the differential diagnosis of patients that present with respiratory distress, cough, fever, and weight loss. Prolonged exposure and close contact may worsen the clinical symptoms. In most cases, only exposure prevention is enough, while steroid therapy, oxygen support, and intensive care monitoring may be required in severe cases.

Intelligent applications of cloud computing in enhancing health care services

In this work, a thorough evaluation of an approach to extract protocols in a series of time data has been presented based on Biological parameters in medical situations. This methodology is wholly data-enhanced with its prototypical pattern mined during every Biological timeframe dataset. The produced rules, centered on the prototypical design have been illustrated in their connection to the wide range of prototypical data arrangements. With that regard, this paper provides an analysis of an approach to effectively measure the similarity of protocol arrangements which have been introduced to verify the uniqueness of protocol arrangements. This approach is evaluated based on Biological records from the medical category in the Multi-parameter Intelligent Monitoring for Intensive Care (MIMIC) online databases such as respiratory failure, sepsis, or angina. The findings in this analysis indicate that data mining approaches can receive a distinctive framework for every medical situation and represent the produced mining rules in an understandable and contextual format.

Conditional Survival With Increasing Duration of ICU Admission: An Observational Study of Three Intensive Care Databases.

Prolonged admissions to an ICU are associated with high resource utilization and personal cost to the patient. Previous reports suggest increasing length of stay may be associated with poor outcomes. Conditional survival represents the probability of future survival after a defined period of treatment on an ICU providing a description of how prognosis evolves over time. Our objective was to describe conditional survival as length of ICU stay increased. Retrospective observational cohort study of three large intensive care databases. Three intensive care databases, two in the United States (Medical Information Mart for Intensive Care III and electronic ICU) and one in United Kingdom (Post Intensive Care Risk-Adjusted Alerting and Monitoring). Index admissions to intensive care for patients 18 years or older. None. A total of 11,648, 38,532, and 165,125 index admissions were analyzed from Post Intensive Care Risk-Adjusted Alerting and Monitoring, Medical Information Mart for Intensive Care III and electronic ICU databases respectively. In all three cohorts, conditional survival declined over the first 5-10 days after ICU admission and changed little thereafter. In patients greater than or equal to 75 years old conditional survival continued to decline with increasing length of stay. After an initial period of 5-10 days, probability of future survival does not appear to decrease with increasing length of stay in unselected patients admitted to ICUs in United Kingdom and United States [corrected]. These findings were consistent between the three populations and suggest that a prolonged admission to an ICU is not a reason for a pessimism in younger patients but may indicate a poor prognosis in the older population.

Incidence, risk factors and clinical significance of postoperative haemodynamic instability after adrenalectomy for phaeochromocytoma.

Due to risk of haemodynamic instability (HDI), it has been recommended that patients undergoing adrenalectomy for phaeochromocytoma should be monitored in an intensive care facility. The aim of this study was to evaluate the incidence, risk factors and outcomes of postoperative HDI in these patients. Retrospective cohort study of 46 consecutive patients who underwent open (OA, N=26) or laparoscopic (LA, N=20) adrenalectomy for phaeochromocytoma at a single centre [2007-2017]. HDI was defined as systolic BP >200 or <90 mmHg, heart rate >120 or <50 bpm or vasopressor therapy within 24 hours. Risk factors for intraoperative and postoperative HDI were evaluated by univariable and multivariable analyses. Intraoperative hypertension occurred in 25/42 patients (60%). Preoperative plasma normetanephrine levels ≥3,500 pmol/L were significantly associated with intraoperative hypertension on multivariable analysis [odds ratio (OR) 42; 95% CI: 4-429; P=0.002). Postoperative hypotension occurred in 21/45 patients (47%), and 13 (29%) required vasopressor therapy. Preoperative beta-blockade therapy was the only independent risk factor for postoperative hypotension on multivariable analysis (OR 4.0; 95% CI: 1.2-13.9, P=0.029). No patients (0/9) with tumours <5 cm treated by LA needed postoperative vasopressor therapy, compared to 39% (7/18) treated by OA (P=0.059). Complications developed in 9 patients (20%), and were less likely in those with intraoperative hypertension (8% vs. 41%; P=0.019). There was one postoperative death. Preoperative beta-blockade therapy is an independent risk factor for postoperative HDI after adrenalectomy for phaeochromocytoma. Patients who undergo laparoscopic adrenalectomy (LA) for phaeochromocytomas <5 cm are unlikely to need postoperative vasopressor therapy, and may not require intensive care monitoring.

Continual measurement of arterial dP/dtmax enables minimally invasive monitoring of left ventricular contractility in patients with acute heart failure

BackgroundContinuous, reliable evaluation of left ventricular (LV) contractile function in patients with advanced heart failure requiring intensive care remains challenging. Continual monitoring of dP/dtmax from the arterial line has recently become available in hemodynamic monitoring. However, the relationship between arterial dP/dtmax and LV dP/dtmax remains unclear. This study aimed to determine the relationship between arterial dP/dtmax and LV dP/dtmax assessed using echocardiography in patients with acute heart failure.MethodsForty-eight patients (mean age 70.4 years [65% male]) with acute heart failure requiring intensive care and hemodynamic monitoring were recruited. Hemodynamic variables, including arterial dP/dtmax, were continually monitored using arterial line pressure waveform analysis. LV dP/dtmax was assessed using continuous-wave Doppler analysis of mitral regurgitation flow.ResultsValues from continual arterial dP/dtmax monitoring were significantly correlated with LV dP/dtmax assessed using echocardiography (r = 0.70 [95% confidence interval (CI) 0.51–0.82]; P < 0.0001). Linear regression analysis revealed that LV dP/dtmax = 1.25 × (arterial dP/dtmax) (P < 0.0001). Arterial dP/dtmax was also significantly correlated with stroke volume (SV) (r = 0.63; P < 0.0001) and cardiac output (CO) (r = 0.42; P = 0.0289). In contrast, arterial dP/dtmax was not correlated with SV variation, dynamic arterial elastance, heart rate, systemic vascular resistance (SVR), or mean arterial pressure. Markedly stronger agreement between arterial and LV dP/dtmax was observed in subgroups with higher SVR (N = 28; r = 0.91; P < 0.0001), lower CO (N = 26; r = 0.81; P < 0.0001), and lower SV (N = 25; r = 0.60; P = 0.0014). A weak correlation was observed in the subjects with lower SVR (N = 20; r = 0.61; P = 0.0004); in the subgroups with higher CO (N = 22) and higher SV (N = 23), no significant correlation was found.ConclusionOur results suggest that in patients with acute heart failure requiring intensive care with an arterial line, continuous calculation of arterial dP/dtmax may be used for monitoring LV contractility, especially in those with higher SVR, lower CO, and lower SV, such as in patients experiencing cardiogenic shock. On the other hand, there was only a weak or no significant correlation in the subgroups with higher CO, higher SV, and lower SVR.

Multimodality monitoring in neurocritical care

Monitoring the health of an injured brain is essential to forewarn neurological worsening and to gain insight into the pathophysiology of a complex disorder.Clinical examination remains a cornerstone in monitoring patients with brain injury. The Glasgow coma score (GCS) is widely used but lacks information regarding brain stem functions like pupillary reaction and shows moderate inter-observer reliability. However, despite these shortcomings, GCS remains a robust indicator of the need for surgery and prognosis after cardiac arrest, hypoxic brain injury, and posterior circulation stroke. A new scoring system called Full Outline of Unresponsiveness has been proposed and shows excellent inter-observer reliability and includes points concerning brain stem functions.1 The most commonly used monitoring modality is intracranial pressure (ICP) monitoring. ICP shows threshold physiology where the outcome of the patients changes after a threshold of 20 to 25 mmHg. Refractory ICP is a good predictor of mortality but not of the functional outcome after traumatic brain injury.Brain injury causes varying degrees of disruption to cerebral blood flow and its autoregulation. Studying autoregulation provides a useful strategy for targeting cerebral perfusion pressure close to the autoregulatory range. Transcranial Doppler and ICMplus (Intensive Care Monitoring) are used to study autoregulation. ICMplus is a software-based tool that studies the correlation between slow changes in mean arterial pressure and ICP to evaluate the state of autoregulation throughout the duration of ICP monitoring.2 Brain tissue oxygen measures the partial pressure of oxygen in the extracellular fluid of the neural tissue. Reduction in brain tissue oxygen is a marker of cellular distress. A phase 2 trial on brain tissue oxygen monitoring demonstrated the safety and feasibility of the protocol-based management of brain tissue oxygenation and ICP, and a trend towards lower mortality and improved functional outcome in patients treated with combined oxygen and ICP protocol.3 Microdialysis is a point of care test that monitors substrate delivery and metabolism at the cellular level. The lactate-pyruvate (LP) ratio is an indicator of the redox state of cells and a high LP ratio is associated with an unfavourable outcome.4 The electroencephalogram (EEG) is used in critical care for monitoring sedation and diagnosis of seizure activity. EEG is a complex signal which requires advanced training and skills for interpretation. Novel EEG-based monitors are aimed at simplifying the signal for straightforward interpretation by bedside medical professionals. Cerebral function monitor (CFM) is a compressed single channel amplitude integrated EEG monitor mainly used for the detection of status epilepticus and burst suppression during thiopentone infusion. A novel technique that uses direct electrodes applied on the cortical surface called Electrocorticogram (ECoG) shows spreading depolarisations on the cortical surface that are caused by loss of ionic homeostasis and substrate delivery.5 These depolarisations are a sensitive indicator of impending neuronal death and may serve as a target for novel mechanistically oriented therapies.Detection, prevention, and monitoring of secondary cerebral insults that alter the prognosis from the injury, remains at the centre stage in neurocritical care. In the future, integrated informatics derived from multimodality monitoring will play a pivotal role in clinical decision algorithms.

P3531Continual measurement of arterial dP/dtmax enables mini-invasive monitoring of left ventricular contractility in acute heart failure

Abstract Introduction Continuous reliable evaluating of left ventricular (LV) contractile function in patients with advanced heart failure requiring intensive care remains challenging. Recently, continual monitoring of dP/dtmax from arterial line became available for hemodynamic monitoring. However, the relation between arterial dP/dtmax and LV dP/dtmax measurement is not fully understood. Purpose The aim of our study was to determine the relation of arterial dP/dtmax and LV dP/dtmax assessed by echocardiography in patients with acute heart failure. Methods Forty-eight patients with acute heart failure requiring intensive care and hemodynamic monitoring were recruited into the study (mean age 70.4 years, 65% were males). Hemodynamic variables including arterial dP/dtmax were continually monitored using arterial line pressure waveform analysis. LV dP/dtmax was assessed using continuous-wave Doppler analysis of mitral regurgitation flow. Results The values from continual arterial dP/dtmax monitoring significantly correlated with the LV dP/dtmax assessed by echocardiography (r=0.72, 95% confidence interval [CI] 0.54–0.83, P&lt;0.0001). Linear regression revealed that (LV dP/dtmax) = 0.87×(arterial dP/dtmax) + 291, P&lt;0.0001. Arterial dP/dtmax significantly correlated also with the stroke volume (r=0.55, P&lt;0.0001), cardiac output (r=0.32, P=0.0289), mean arterial blood pressure (r=0.43, P=0.0155) and systolic blood pressure (r=0.79, P&lt;0001). On the other hand arterial dP/dtmax did not correlate with the systemic vascular resistance (SVR), heart rate, dynamic arterial elastance, diastolic blood pressure or central venous pressure. Conclusion Our results revealed that arterial dP/dtmax values tightly and highly significantly correlate with LV dP/dtmax. Arterial dP/dtmax could be, therefore, used for continual monitoring of LV contractility. Acknowledgement/Funding Institutional grant MH CZ - DRO (Na Homolce Hospital- NNH, 00023884), IG150501

Real time continuous glucose monitoring in neonatal intensive care

Hypoglycaemia and hyperglycaemia are common in infants requiring intensive care and are associated with worse clinical outcomes. However, glucose levels are taken infrequently, and there remains controversy regarding optimal management. In adults and children continuous glucose monitoring (CGM) is now established as an important adjunct to caring for patients at risk from dysglycaemia. This technology is also increasingly providing insights into glucose regulation in the newborn, demonstrating significant periods of clinically silent hypoglycaemia and hyperglycaemia. This baseline data will be important to allow the significance of glucose dysregulation on long-term outcomes to be assessed. Small studies have also shown the potential for CGM to safely support targeting of glucose control in preterm infants, and a large multicentre trial is ongoing. Current technology is not specifically designed for use in NICU, but with rapid technological developments, CGM holds promise for the future care of babies in NICU.

Pleural Effusion Outcomes in Intensive Care: Analysis of a Large Clinical Database.

Pleural effusions are common in critically ill patients. However, the management of pleural fluid on relevant clinical outcomes is poorly studied. We evaluated the impact of pleural effusion in the intensive care unit (ICU). A large observational ICU database Multiparameter Intelligent Monitoring in Intensive Care III was utilized. Analyses used matched patients with the same admission diagnosis, age, gender, and disease severity. Of 50 765, 3897 (7.7%) of critically ill adult patients had pleural effusions. Compared to patients without effusion, patients with effusion had higher in-hospital (38.7% vs 31.3%, P < .0001), 1-month (43.1% vs 36.1%, P < .0001), 6-month (63.6% vs 55.7%, P < .0001), and 1-year mortality (73.8% vs 66.1%, P < .0001), as well as increased length of hospital stay (17.6 vs 12.7 days, P < .0001), ICU stay (7.3 vs 5.1 days, P < .0001), need for mechanical ventilation (63.1% vs 55.7%, P < .0001), and duration of mechanical ventilation (8.7 vs 6.3 days, P < .0001). A total of 1503 patients (38.6%) underwent pleural fluid drainage. Patients in the drainage group had higher in-hospital (43.9% vs 35.4%, P = .0002), 1-month (47.7% vs 39.7%, P = .0005), 6-month (67.1% vs 61.8%, P = .0161), and 1-year mortality (77.1% vs 72.1%, P = .0147), as well as increased lengths of hospital stay (22.1 vs 16.0 days, P < .0001), ICU stay (9.2d vs 6.4 days, P < .0001), and duration of mechanical ventilation (11.7 vs 7.1 days, P < .0001). The presence of a pleural effusion was associated with increased mortality in critically ill patients regardless of disease severity. Drainage of pleural effusion was associated with worse outcomes in a large, heterogeneous cohort of ICU patients.

Impact of an Intensive Care Information System on the Length of Stay of Surgical Intensive Care Unit Patients: Observational Study.

BackgroundThe implementation of computerized monitoring and prescription systems in intensive care has proven to be reliable in reducing the rate of medical error and increasing patient care time. They also showed a benefit in reducing the length of stay in the intensive care unit (ICU). However, this benefit has been poorly studied, with conflicting results.ObjectiveThis study aimed to show the impact of computerization on the length of stay in ICUs.MethodsThis was a before-after retrospective observational study. All patients admitted in the surgical ICU at the Rouen University Hospital were included, from June 1, 2015, to June 1, 2016, for the before period and from August 1, 2016, to August 1, 2017, for the after period. The data were extracted from the hospitalization report and included the following: epidemiological data (age, sex, weight, height, and body mass index), reason for ICU admission, severity score at admission, length of stay and mortality in ICU, mortality in hospital, use of life support during the stay, and ICU readmission during the same hospital stay. The consumption of antibiotics, biological analyses, and the number of chest x-rays during the stay were also analyzed.ResultsA total of 1600 patients were included: 839 in the before period and 761 in the after period. Only the severity score Simplified Acute Physiology Score II was significantly higher in the postcomputerization period (38 [SD 20] vs 40 [SD 21]; P<.05). There was no significant difference in terms of length of stay in ICU, mortality, or readmission during the stay. There was a significant increase in the volume of prescribed biological analyses (5416 [5192-5956] biological exams prescribed in the period before Intellispace Critical Care and Anesthesia [ICCA] vs 6374 [6013-6986] biological exams prescribed in the period after ICCA; P=.002), with an increase in the total cost of biological analyses, to the detriment of hematological and biochemical blood tests. There was also a trend toward reduction in the average number of chest x-rays, but this was not significant (0.55 [SD 0.39] chest x-rays per day per patient before computerization vs 0.51 [SD 0.37] chest x-rays per day per patient after computerization; P=.05). On the other hand, there was a decrease in antibiotic prescribing in terms of cost per patient after the implementation of computerization (€149.50 [$164 USD] per patient before computerization vs €105.40 [$155 USD] per patient after computerization).ConclusionsImplementation of an intensive care information system at the Rouen University Hospital in June 2016 did not have an impact on reducing the length of stay.

Effects of circadian heart rate variation on short-term and long-term mortality in intensive care unit patients: a retrospective cohort study based on MIMIC-II database

To investigate the effect of circadian heart rate variation on short-term and long-term mortality in intensive care unit (ICU) patients. A retrospective cohort study was conducted. A total of 32 536 ICU patients were recorded from 2001 to 2008 published by Multiparameter Intelligent Monitoring in Intensive Care II (MIMIC-II v2.6) in April 2011. The circadian heart rate variation was defined as the ratio of mean nighttime (23:00 to 07:00) heart rate to mean daytime (07:00 to 23:00) heart rate. The 28-day mortality and 1-year mortality were defined as outcome events. The information such as age, gender, ethnicity, first sequential organ failure assessment (SOFA) score, first simplified acute physiology score I (SAPS I), usage of sedatives and catecholamines within 24 hours admission of ICU, clinical complications [hypertension, chronic obstructive pulmonary disease (COPD), diabetes with or without complications, congestive heart failure, liver disease, renal failure, etc.], and the complete heart rate records within 24 hours after ICU admission were collected. Cox proportional risk regression models were used to investigate the association between circadian heart rate variation and 28-day mortality and 1-year mortality in ICU patients. Besides, subgroup analysis was also performed in patients with different first SOFA scores. Totally 15 382 ICU patients in MIMIC-II database were enrolled, excluding the patients without heart rate records or death records, using pacemaker with arrhythmia, without SOFA or SAPS I score records. Finally, 9 439 patients were enrolled in the study cohort. (1) Cox regression analysis of the whole patient showed that the higher circadian heart rate variation was correlated with the increased 28-day mortality [hazard ratio (HR) = 1.613, 95% confidence interval (95%CI) was 1.338-1.943, P < 0.001] and 1-year mortality (HR = 1.573, 95%CI was 1.296-1.908, P < 0.001). After adjustment for demographic factors (age, gender and ethnicity), severity of illness (SOFA and SAPS I scores), clinical complications (hypertension, COPD, diabetes with or without complications, congestive heart failure, liver disease, renal failure, etc.), and influence of medications (sedatives and catecholamines), the night-day heart rate ratio was also correlated with 28-day mortality (HR = 1.256, 95%CI was 1.018-1.549, P = 0.033) and 1-year mortality (HR = 1.249, 95%CI was 1.010-1.545, P = 0.040). (2) According to the SOFA score (median value of 5), the patients were divided into two subgroups, in which 5 478 patients with SOFA score ≤ 5 and 3 961 patients with SOFA score > 5. Cox regression subgroup analysis showed that circadian heart rate variation was related with higher 28-day mortality (HR = 1.430, 95%CI was 1.164-1.756, P = 0.001) and 1-year mortality (HR = 1.393, 95%CI was 1.123-1.729, P = 0.003) in patients with SOFA score > 5. After adjustment for covariates, the 28-day mortality (HR = 1.279, 95%CI was 1.032-1.584, P = 0.025) and 1-year mortality (HR = 1.255, 95%CI was 1.010-1.558, P = 0.040) also increased with the increasing of night-day heart rate ratio in patients with SOFA score > 5. However, the relationships did not exist in patients with SOFA score ≤ 5. In ICU patients, the 28-day mortality and 1-year mortality increase with the higher circadian heart rate variation, which indicates that the circadian heart rate variation in ICU patients is positively correlated with the short-term and long-term mortality, especially in patients with relatively severe illness.

Identification key scheme to enhance network performance in wireless body area network

Wireless Body Area Network (WBAN) refers to a group of small intelligent electronic devices placed on the human body to monitor its vital signals. the efficiency of network performance in health care applications is one of the most important prerequisites for designing an effective surveillance system. However, none of the previous studies have succeeded in proposing an effective scheme that could cover the requirements for effective network performance or the development of the WBAN system capable of sending and receiving vital patient data efficiently. The aim of this paper is to enhance the performance of the network in WBAN. In addition, to verify the transfer of patient data from sensors on the body to receivers with the least value of possible packet loss, a solution is developed that can reduce the value of packet loss, end to end delay and increase the value of throughput, relying on confirmation and matching data between the sender and receiver devices. A new scheme known as the Identification Key Scheme (IKS) is proposed based on the newly available 402–405 MHz Medical Implant Communication Service (MICS). The analysis of the network performance was implemented in real WBAN dataset and used the Multi-Parameter Intelligent Monitoring for Intensive Care (MIMIC) database. MIMIC database included the data recorded from 90 Intensive Care Unit (ICU) patients. In this study, OMNET++ was used as the network simulation tool to design and evaluate the proposed scheme. The results showed that IKS was able to reduce number of packet loss and end to end delay with increased throughput. This is an indicator of the ability of IKS in providing efficient network performance between devices in the WBAN application.

Automated Screening of Myocardial Infarction Based on Statistical Analysis of Photoplethysmographic Data

Integration of automated cardiac analysis techniques with the personal healthcare devices can aid in the timely diagnosis of myocardial infarction (MI) to reduce the risk of mortality. The use of electrocardiogram (ECG) along with advanced signal processing tools limits the application of the available techniques for such portable devices having limited processing ability. Here we propose a novel MI screening technique based on photoplethysmographic (PPG) data, which is the most widely monitored signal in everyday health monitoring. Two simple statistical features ideally reflecting the MI-induced variability in the PPG data are identified. To combat the noise sensitivity of the PPG acquisition process, the same statistical parameters are employed for eliminating the noise corrupted data segments. Classification of MI data is then performed using a simple threshold-based binary classification approach. The technique is evaluated with PPG records collected from 62 hospitalized MI patients and 65 healthy subjects. The robustness of the algorithm is cross-validated with both MI and non-MI records collected from the Multiparameter Intelligent Monitoring in Intensive Care (MIMIC) II database. The algorithm achieves an average detection accuracy of 96.25% with sensitivity and specificity of 96.36% and 96.15%, respectively. The promising results establish the utility of PPG as an alternate MI diagnosing tool. Apart from using the less obtrusive PPG signal, the proposed technique relies on simple feature extraction and classification tools, thus making it a promising alternative to the ECG based techniques for implementation on the personal healthcare devices.

Principles and pitfalls of arterial blood pressure measurement

The determination of arterial blood pressure is afundamental part of basic cardiovascular monitoring in perioperative, intensive care and emergency medicine. Blood pressure can be measured directly via an arterial catheter, which is the most accurate method. Blood pressure is most commonly monitored using noninvasive intermittent methods with an occluding upper arm cuff. Noninvasive intermittent blood pressure measurements can also be performed either manually using palpation and auscultation or automatically based on an oscillometric algorithm. Furthermore, methods such as the vascular unloading technique with a finger plethysmographic sensor are available for continuous and noninvasive blood pressure monitoring. This article explains the principles of the individual methods, the sources of errors, advantages and disadvantages and discusses the fields of application in the clinical routine.

The neutrophil-lymphocyte ratio: A promising predictor of mortality in coronary care unit patients — A cohort study

BackgroundSevere inflammation causes poor outcomes in coronary care unit (CCU) patients. The neutrophil-lymphocyte ratio (NLR), a biomarker used to monitor inflammation and the immune response, can predict a poor prognosis in various diseases. However, it remains unclear whether the NLR is associated with all-cause mortality in CCU patients. This study investigated the association between the NLR and CCU outcomes. MethodsClinical data were extracted from the Multiparameter Intelligent Monitoring in Intensive Care III (MIMIC-III) database, which contains health data for over 50,000 patients. The primary outcome was 30-day mortality and the secondary outcome was 90-day mortality. Cox proportional hazard models were used to reveal the associations between NLR and outcomes. Multivariate analyses were used to control for confounders. ResultsWe enrolled 3563 CCU patients. For 30-day mortality, the hazard ratio (HR) (95% confidence interval [CI]) for the second (NLR 4.80–10.08) and the third (NLR ≥ 10.09) tertiles were 1.57 (1.24, 1.97) and 2.76 (2.23, 3.41), respectively, compared to the first tertile (NLR < 4.80). In the model adjusted for multiple confounders, the fifth quintile (NLR ≥ 14.17) showed a slightly lower mortality risk [HR (95% CI) 1.44 (1.07, 1.94)] compared to the fourth (NLR 8.82–14.16) [HR (95% CI) 1.55 (1.15, 2.10)]. A similar trend was observed for 90-day mortality. The interactions between the acute kidney injury, respiratory failure, and pneumonia subgroups and 30-day mortality were significant. ConclusionsThe NLR was an independent predictor of 30- and 90-day mortality for CCU patients. The NLR is a promising clinical biomarker as an integrated, readily available predictor of CCU mortality.

Identifying Clinical Terms in Medical Text Using Ontology-Guided Machine Learning.

BackgroundAutomatic recognition of medical concepts in unstructured text is an important component of many clinical and research applications, and its accuracy has a large impact on electronic health record analysis. The mining of medical concepts is complicated by the broad use of synonyms and nonstandard terms in medical documents.ObjectiveWe present a machine learning model for concept recognition in large unstructured text, which optimizes the use of ontological structures and can identify previously unobserved synonyms for concepts in the ontology.MethodsWe present a neural dictionary model that can be used to predict if a phrase is synonymous to a concept in a reference ontology. Our model, called the Neural Concept Recognizer (NCR), uses a convolutional neural network to encode input phrases and then rank medical concepts based on the similarity in that space. It uses the hierarchical structure provided by the biomedical ontology as an implicit prior embedding to better learn embedding of various terms. We trained our model on two biomedical ontologies—the Human Phenotype Ontology (HPO) and Systematized Nomenclature of Medicine - Clinical Terms (SNOMED-CT).ResultsWe tested our model trained on HPO by using two different data sets: 288 annotated PubMed abstracts and 39 clinical reports. We achieved 1.7%-3% higher F1-scores than those for our strongest manually engineered rule-based baselines (P=.003). We also tested our model trained on the SNOMED-CT by using 2000 Intensive Care Unit discharge summaries from MIMIC (Multiparameter Intelligent Monitoring in Intensive Care) and achieved 0.9%-1.3% higher F1-scores than those of our baseline. The results of our experiments show high accuracy of our model as well as the value of using the taxonomy structure of the ontology in concept recognition.ConclusionMost popular medical concept recognizers rely on rule-based models, which cannot generalize well to unseen synonyms. In addition, most machine learning methods typically require large corpora of annotated text that cover all classes of concepts, which can be extremely difficult to obtain for biomedical ontologies. Without relying on large-scale labeled training data or requiring any custom training, our model can be efficiently generalized to new synonyms and performs as well or better than state-of-the-art methods custom built for specific ontologies.

MON-332 Metastatic Pancreatic Neuroendocrine Tumor: A Very Rare Cause of Ectopic ACTH Production (ACTHoma)

Introduction Ectopic ACTH syndrome (EAS)is responsible for 10% of Cushing’s syndrome. Multiple tumors, most commonly small cell carcinoma of lung are associated with EAS. Pancreatic neuroendocrine tumors (pNETs) are usually associated with secretion of pancreatic polypeptide, gastrinomas, insulinomas, glucagonomas and vasoactive intestinal peptide (VIPomas). EAS or “ACTHomas” are rarely associated with pNETs. Case 76y/o man with ah/o hairy cell leukemia, bladder cancer (both in remission), and stage M1 unresectable pNET tumor with liver metastases presented with generalized weakness. Discovery of his pNET was incidentally noted during routine surveillance with CT monitoring following successful bladder cancer treatment six years ago. Treatment of his pNET initially began with Everolimus and then switched to Lanreotide injections. No evidence of Cushing’s Syndrome at the time of diagnosis. The lesions remained stable in size and patient was doing well. Physical exam was notable for lethargy, frailty, and absence of Cushingoid features. Labs showed serum glucose 231mg/dl, sodium 141mEq/L, potassium 2.4mEq/L, AM cortisol 116 ug/dL (range 6.7-22.6ug/dl) and ACTH was 209.6pg/mL (range 7.2-63.3pg/mL). Renin-aldosterone levels were normal. Cortisol level did not suppress with low dose or high dose dexamethasone. His hospital course was significant for persistent hypokalemia despite aggressive supplementation, difficult to control blood glucose, and worsening kidney function. EAS with pNET is very refractory to management and may be rapidly progressive. They occasionally demonstrate classic manifestations of Cushingoid features. However, they often lack the traditional phenotypic features of Cushing syndrome. Treatment options for EAS in the setting of an unresectable tumor include medical management versus bilateral adrenalectomy. Metyrapone, a cortisol synthesis inhibitor, can be an effective therapy. Ketoconazole, an antifungal that inhibits cortisol production can be an alternative, but may need weeks to achieve control. Etomodate can rapidly reduce cortisol levels, but requires intensive care monitoring. Somatostatin analogs may be effective by reducing ectopic ACTH production and stabilize tumor growth. Medical versus surgical management of Cushing’s syndrome was discussed with the patient and family, but they opted for hospice care. Conclusion We present a case of pNET associated with late onset EAS without obvious signs of Cushing’s syndrome. To our knowledge this late presentation of ACTH secretion in the setting of a stable pNET has not been previously reported in the literature. EAS due to pNET is rare and metabolic abnormalities can occur rapidly without other Cushingoid manifestations which can pose significant management challenges. High index of suspicion is required for early diagnosis. Due to the aggressive nature, the 5 years survival rate is 16%.

The complexity of intracranial pressure as an indicator of cerebral autoregulation

Intracranial Pressure (ICP) is one of the main neuromonitories used today to guide the treatment of acute neurological patients in the Intensive Care Unit (ICU).Within this article the complexity of periods of intracranial hypertension is evaluated and compared with periods of stable intracranial tension. Using the multiparameter intelligent monitoring in intensive care III (MIMIC-III) database from the Beth Israel Deaconess Medical Center the complexity of periods of stable intracranial tension and high intracranial hypertension are evaluated using two quantifiers: the Permutation Entropy and their respective number of missing patterns. Both indicate a loss of complexity in hypertension signals. A physiological explanation of this loss of complexity is given using a dynamical model of the Cerebral Autoregulation and Cerebral Hemodynamics.

The association between autoimmune disease and 30-day mortality among sepsis ICU patients: a cohort study

IntroductionSepsis results from a dysregulated host response to an infection that is associated with an imbalance between pro- and anti-inflammatory cytokines. This imbalance is hypothesized to be a driver of patient mortality. Certain autoimmune diseases modulate the expression of cytokines involved in the pathophysiology of sepsis. However, the outcomes of patients with autoimmune disease who develop sepsis have not been studied in detail. The objective of this study is to determine whether patients with autoimmune diseases have different sepsis outcomes than patients without these comorbidities.MethodsUsing the Multiparameter Intelligent Monitoring in Intensive Care III database (v. 1.4) which contains retrospective clinical data for over 50,000 adult ICU stays, we compared 30-day mortality risk for sepsis patients with and without autoimmune disease. We used logistic regression models to control for known confounders, including demographics, disease severity, and immunomodulation medications. We used mediation analysis to evaluate how the chronic use of immunomodulation medications affects the relationship between autoimmune disease and 30-day mortality.ResultsOur study found a statistically significant 27.00% reduction in the 30-day mortality risk associated with autoimmune disease presence. This association was found to be the strongest (OR 0.71, 95% CI 0.54–0.93, P = 0.014) among patients with septic shock. The autoimmune disease-30-day mortality association was not mediated through the chronic use of immunomodulation medications (indirect effect OR 1.07, 95% CI 1.01–1.13, P = 0.020).ConclusionsWe demonstrated that autoimmune diseases are associated with a lower 30-day mortality risk in sepsis. Our findings suggest that autoimmune diseases affect 30-day mortality through a mechanism unrelated to the chronic use of immunomodulation medications. Since this study was conducted within a single study center, research using data from other medical centers will provide further validation.

Trust enforcement through self-adapting cloud workflow orchestration

Providing runtime intelligence of a workflow in a highly dynamic cloud execution environment is a challenging task due the continuously changing cloud resources. Guaranteeing a certain level of workflow Quality of Service (QoS) during the execution will require continuous monitoring to detect any performance violation due to resource shortage or even cloud service interruption. Most of orchestration schemes are either configuration, or deployment dependent and they do not cope with dynamically changing environment resources. In this paper, we propose a workflow orchestration, monitoring, and adaptation model that relies on trust evaluation to detect QoS performance degradation and perform an automatic reconfiguration to guarantee QoS of the workflow. The monitoring and adaptation schemes are able to detect and repair different types of real time errors and trigger different adaptation actions including workflow reconfiguration, migration, and resource scaling. We formalize the cloud resource orchestration using state machine that efficiently captures different dynamic properties of the cloud execution environment. In addition, we use validation model checker to validate our model in terms of reachability, liveness, and safety properties. Extensive experimentation is performed using a health monitoring workflow we have developed to handle dataset from Intelligent Monitoring in Intensive Care III (MIMICIII) and deployed over Docker swarm cluster. A set of scenarios were carefully chosen to evaluate workflow monitoring and the different adaptation schemes we have implemented. The results prove that our automated workflow orchestration model is self-adapting, self-configuring, react efficiently to changes and adapt accordingly while supporting high level of Workflow QoS.