Search

Septic shock is a severe health condition caused by uncontrolled sepsis. Advancements in the high-throughput sequencing techniques have risen the number of potential genetic biomarkers under review. Multiple genetic markers and functional pathways play a part in the development and progression of pediatric septic shock. Fifty-four differentially expressed pediatric septic shock gene biomarkers were identified using gene expression data from 181 pediatric intensive care unit (PICU) patients within the first 24 hours of admission. The gene expression signatures discovered showed discriminatory power between pediatric septic shock survivors and nonsurvivors types. Using functional enrichment analysis of differentially expressed genes (DEGs), the known genes and pathways in septic shock were validated, and unexplored septic shock-related genes and functional groups were identified. Septic shock survivors were distinguished from septic shock non-survivors by differential expression of genes involved in the immune response, chemokine-mediated signaling, neutrophil chemotaxis, and chemokine activity. The identification of the septic shock gene biomarkers may facilitate in septic shock diagnosis, treatment, and prognosis.

BACKGROUND Sickle cell disease (SCD) is a genetic disorder of the red blood cells, resulting in multiple acute and chronic complications, including pain episodes, stroke, and kidney disease. Patients with SCD develop chronic organ dysfunction, which may progress to organ failure during disease exacerbations. Early detection of acute physiological deterioration leading to organ failure is not always attainable. Machine learning techniques that allow for prediction of organ failure may enable early identification and treatment and potentially reduce mortality. OBJECTIVE The aim of this study was to test the hypothesis that machine learning physiomarkers can predict the development of organ dysfunction in a sample of adult patients with SCD admitted to intensive care units (ICUs). METHODS We applied diverse machine learning methods, statistical methods, and data visualization techniques to develop classification models to distinguish SCD from controls. RESULTS We studied 63 sequential SCD patients admitted to ICUs with 163 patient encounters (mean age 30.7 years, SD 9.8 years). A subset of these patient encounters, 22.7% (37/163), met the sequential organ failure assessment criteria. The other 126 SCD patient encounters served as controls. A set of signal processing features (such as fast Fourier transform, energy, and continuous wavelet transform) derived from heart rate, blood pressure, and respiratory rate was identified to distinguish patients with SCD who developed acute physiological deterioration leading to organ failure from patients with SCD who did not meet the criteria. A multilayer perceptron model accurately predicted organ failure up to 6 hours before onset, with an average sensitivity and specificity of 96% and 98%, respectively. CONCLUSIONS This retrospective study demonstrated the viability of using machine learning to predict acute organ failure among hospitalized adults with SCD. The discovery of salient physiomarkers through machine learning techniques has the potential to further accelerate the development and implementation of innovative care delivery protocols and strategies for medically vulnerable patients.

Background Sickle cell disease (SCD) is a genetic disorder of the red blood cells, resulting in multiple acute and chronic complications, including pain episodes, stroke, and kidney disease. Patients with SCD develop chronic organ dysfunction, which may progress to organ failure during disease exacerbations. Early detection of acute physiological deterioration leading to organ failure is not always attainable. Machine learning techniques that allow for prediction of organ failure may enable early identification and treatment and potentially reduce mortality. Objective The aim of this study was to test the hypothesis that machine learning physiomarkers can predict the development of organ dysfunction in a sample of adult patients with SCD admitted to intensive care units (ICUs). Methods We applied diverse machine learning methods, statistical methods, and data visualization techniques to develop classification models to distinguish SCD from controls. Results We studied 63 sequential SCD patients admitted to ICUs with 163 patient encounters (mean age 30.7 years, SD 9.8 years). A subset of these patient encounters, 22.7% (37/163), met the sequential organ failure assessment criteria. The other 126 SCD patient encounters served as controls. A set of signal processing features (such as fast Fourier transform, energy, and continuous wavelet transform) derived from heart rate, blood pressure, and respiratory rate was identified to distinguish patients with SCD who developed acute physiological deterioration leading to organ failure from patients with SCD who did not meet the criteria. A multilayer perceptron model accurately predicted organ failure up to 6 hours before onset, with an average sensitivity and specificity of 96% and 98%, respectively. Conclusions This retrospective study demonstrated the viability of using machine learning to predict acute organ failure among hospitalized adults with SCD. The discovery of salient physiomarkers through machine learning techniques has the potential to further accelerate the development and implementation of innovative care delivery protocols and strategies for medically vulnerable patients.

BackgroundSickle cell disease (SCD) is a genetic disorder of the red blood cells, resulting in multiple acute and chronic complications including pain episodes, stroke, and kidney disease. Patients with SCD develop chronic organ dysfunction, which may progress to organ failure during disease exacerbations. Early detection of acute physiological deterioration leading to organ failure is not always attainable. Machine learning techniques that allow for prediction of organ failure may enable earlier identification and treatment, and potentially reduce mortality. We tested the hypothesis that machine learning physiomarkers could predict the development of organ dysfunction in an adult sample of patients with SCD admitted to intensive care units.Methods and FindingsWe studied 63 sequential SCD patients with 163 patient encounters, mean age 33.0±11.0 years, admitted to intensive care units, some of whom (6.7%) had pre-existing cardiovascular or kidney disease. A subset of these patient encounters (37; 23%) met sequential organ failure assessment (SOFA) criteria. The site of organ failure included: central nervous system (32), cardiovascular (11), renal (10), liver (7), respiratory (5) and coagulation (2) systems. Most (81.5%) of the patient encounters who experienced organ failure had single organ failure. The other 126 SCD patient encounters served as controls. A set of signal processing features (such as fast fourier transform, energy, continuous wavelet transform, etc.) derived from heart rate, blood pressure, and respiratory rate were identified to distinguish patients with SCD who developed acute physiological deterioration leading to organ failure, from SCD patients who did not meet the criteria. A random forest model accurately predicted organ failure up to six hours prior to onset, with a five-fold cross-validation accuracy of 94.57% (average sensitivity and specificity of 90.24% and 98.9% respectively).ConclusionsThis study demonstrates the viability of using machine learning to predict acute physiological deterioration heralded organ failure among hospitalized adults with SCD. The discovery of salient physiomarkers through machine learning techniques has the potential to further accelerate the development and implementation of innovative care delivery protocols and strategies for medically vulnerable patients.

Supplemental Digital Content is available in the text., Background: Acute respiratory failure occurs frequently in hospitalized patients and often begins outside the ICU, associated with increased length of stay, cost, and mortality. Delays in decompensation recognition are associated with worse outcomes. Objectives: The objective of this study is to predict acute respiratory failure requiring any advanced respiratory support (including noninvasive ventilation). With the advent of the coronavirus disease pandemic, concern regarding acute respiratory failure has increased. Derivation Cohort: All admission encounters from January 2014 to June 2017 from three hospitals in the Emory Healthcare network (82,699). Validation Cohort: External validation cohort: all admission encounters from January 2014 to June 2017 from a fourth hospital in the Emory Healthcare network (40,143). Temporal validation cohort: all admission encounters from February to April 2020 from four hospitals in the Emory Healthcare network coronavirus disease tested (2,564) and coronavirus disease positive (389). Prediction Model: All admission encounters had vital signs, laboratory, and demographic data extracted. Exclusion criteria included invasive mechanical ventilation started within the operating room or advanced respiratory support within the first 8 hours of admission. Encounters were discretized into hour intervals from 8 hours after admission to discharge or advanced respiratory support initiation and binary labeled for advanced respiratory support. Prediction of Acute Respiratory Failure requiring advanced respiratory support in Advance of Interventions and Treatment, our eXtreme Gradient Boosting-based algorithm, was compared against Modified Early Warning Score. Results: Prediction of Acute Respiratory Failure requiring advanced respiratory support in Advance of Interventions and Treatment had significantly better discrimination than Modified Early Warning Score (area under the receiver operating characteristic curve 0.85 vs 0.57 [test], 0.84 vs 0.61 [external validation]). Prediction of Acute Respiratory Failure requiring advanced respiratory support in Advance of Interventions and Treatment maintained a positive predictive value (0.31–0.21) similar to that of Modified Early Warning Score greater than 4 (0.29–0.25) while identifying 6.62 (validation) to 9.58 (test) times more true positives. Furthermore, Prediction of Acute Respiratory Failure requiring advanced respiratory support in Advance of Interventions and Treatment performed more effectively in temporal validation (area under the receiver operating characteristic curve 0.86 [coronavirus disease tested], 0.93 [coronavirus disease positive]), while achieving identifying 4.25–4.51× more true positives. Conclusions: Prediction of Acute Respiratory Failure requiring advanced respiratory support in Advance of Interventions and Treatment is more effective than Modified Early Warning Score in predicting respiratory failure requiring advanced respiratory support at external validation and in coronavirus disease 2019 patients. Silent prospective validation necessary before local deployment.

Early detection of sepsis can be life-saving. Machine learning models have shown great promise in early sepsis prediction when applied to patient physiological data in real-time. However, these existing models often under-perform in terms of positive predictive value, an important metric in clinical settings. This is especially the case when the models are applied to data with less than 50% sepsis prevalence, reflective of the incidence rate of sepsis on the floor or in the ICU. In this study, we develop HeMA, a hierarchically enriched machine learning approach for managing false alarms in real time, and conduct a case study for early sepsis prediction. Specifically, we develop a two-stage framework, where a first stage machine learning model is paired with statistical tests, particularly Kolmogorov-Smirnov tests, in the second stage, to predict whether a patient would develop sepsis. Compared with machine learning models alone, the framework results in an increase in specificity and positive predictive value, without compromising F1 score. In particular, the framework shows improved performance when applied to data with 50% and 25% sepsis prevalence, collected from a large hospital system in the US, resulting in up to 18% and 7% increase in specificity and positive predictive value, respectively. Despite the significant improvements observed, and although F1 score is not negatively affected, because of the up to 6% decrease in sensitivity, further improvements and pilot studies may be necessary before deploying the framework in a clinical setting. Finally, external validation conducted using a publicly available dataset produces similar results, validating that the proposed framework is generalizable.

INTRODUCTION: The novel coronavirus (SARS-CoV-2) has led to a large cascade of transmissions resulting in high numbers of individuals hospitalized for the coronavirus disease 2019 (COVID-19), an impact still being accounted across the globe In this study, we seek to evaluate whether novel heart rate variability (HRV) measures can predict mortality within 24 hours of admission to the ICU among critically ill COVID-19 patients METHODS: All medical, surgical, neurocritical, transplant, and cardiac ICU admissions with COVID-19 between March 1 through April 31st, 2020 within Emory Healthcare system were screened Patients were selected to be included in the analysis if they were in the ICU for greater than 24 hours, had at least one positive qRT-PCR test for SARS-CoV-2 earlier in their hospitalization EKG (250 Hz) was then analyzed for each patient over a 300 second (s) observational window, that was shifted by 30s in each iteration for the first 24 hrs after admission MATLAB® was used to analyze the continuous EKG and extract relevant HRV features We use the Kruskal-Wallis and Steel-Dwass tests (P < 0 05) for statistical analysis and interpretations of HRV multiple measures RESULTS: A total of 312 COVID-19 patients were identified in a clinical chart review for SARS-CoV-2 by use of quantitative RT-PCR (qRT-PCR), of which 85 patients were admitted to the ICU and had sufficient data quality The median HRV aggregates, including AC, DC, LFHF, VLF, SD1, SD2, SD1SD2, RMSSD, and pNN50 were all statistically significant (FDR p

In this work, we introduce a novel visualization technique, the Temporal Intensity Map, which visually integrates data values over time to reveal the frequency, duration, and timing of significant features in streaming data. We combine the Temporal Intensity Map with several coordinated visualizations of detected events in data streams to create PhysioEx, a visual dashboard for multiple heterogeneous data streams. We have applied PhysioEx in a design study in the field of neonatal medicine, to support clinical researchers exploring physiologic data streams. We evaluated our method through consultations with domain experts. Results show that our tool provides deep insight capabilities, supports hypothesis generation, and can be well integrated into the workflow of clinical researchers.

Purpose Sepsis is a life-threatening condition with high mortality rates and expensive treatment costs. To improve short- and long-term outcomes, it is critical to detect at-risk sepsis patients at an early stage. Methods A data-set consisting of high-frequency physiological data from 1161 critically ill patients was analyzed. 377 patients had developed sepsis, and had data at least 3 h prior to the onset of sepsis. A random forest classifier was trained to discriminate between sepsis and non-sepsis patients in real-time using a total of 132 features extracted from a moving time-window. The model was trained on 80% of the patients and was tested on the remaining 20% of the patients, for two observational periods of lengths 3 and 6 h prior to onset. Results The model that used continuous physiological data alone resulted in sensitivity and F1 score of up to 80% and 67% one hour before sepsis onset. On average, these models were able to predict sepsis 294.19 ± 6.50 min (5 h) before the onset. Conclusions The use of machine learning algorithms on continuous streams of physiological data can allow for early identification of at-risk patients in real-time with high accuracy.

We used artificial intelligence to develop a novel algorithm using physiomarkers to predict the onset of severe sepsis in critically ill children.Observational cohort study.PICU.Children age between 6 and 18 years old.None.Continuous minute-by-minute physiologic data were available for a total of 493 critically ill children admitted to a tertiary care PICU over an 8-month period, 20 of whom developed severe sepsis. Using an alert time stamp generated by an electronic screening algorithm as a reference point, we studied up to 24 prior hours of continuous physiologic data. We identified physiomarkers, including SD of heart rate, systolic and diastolic blood pressure, and symbolic transitions probabilities of those variables that discriminated severe sepsis patients from controls (all other patients admitted to the PICU who did not meet severe sepsis criteria). We used logistic regression, random forests, and deep Convolutional Neural Network methods to derive our models. Analysis was performed using data generated in two windows prior to the firing of the electronic screening algorithm, namely, 2-8 and 8-24 hours. When analyzing the physiomarkers present in the 2-8 hours analysis window, logistic regression performed with specificity of 87.4% and sensitivity of 55.0%, random forest performed with 79.6% specificity and 80.0% sensitivity, and the Convolutional Neural Network performed with 83.0% specificity and 75.0% sensitivity. When analyzing physiomarkers from the 8-24 hours window, logistic regression resulted in 77.1% specificity and 39.3% sensitivity, random forest performed with 82.3% specificity and 61.1% sensitivity, whereas the Convolutional Neural Network method achieved 81% specificity and 76% sensitivity.Artificial intelligence can be used to predict the onset of severe sepsis using physiomarkers in critically ill children. Further, it may detect severe sepsis as early as 8 hours prior to a real-time electronic severe sepsis screening algorithm.

Objective: Atrial fibrillation (AF) is a major cause of hospitalization and death in the United States. Moreover, as the average age of individuals increases around the world, early detection and diagnosis of AF become even more pressing. In this paper, we introduce a novel deep learning architecture for the detection of normal sinus rhythm, AF, other abnormal rhythms, and noise. Approach: We have demonstrated through a systematic approach many hyperparameters, input sets, and optimization methods that yielded influence in both training time and performance accuracy. We have focused on these properties to identify an optimal 13-layer convolutional neural network (CNN) model which was trained on 8528 short single-lead ECG recordings and evaluated on a test dataset of 3658 recordings. Main results: The proposed CNN architecture achieved a state-of-the-art performance in identifying normal, AF and other rhythms with an average F 1-score of 0.83. Significance: We have presented a robust deep learning-based architecture that can identify abnormal cardiac rhythms using short single-lead ECG recordings. The proposed architecture is computationally fast and can also be used in real-time cardiac arrhythmia detection applications.

Rationale:Sepsis is a life-threatening condition with high mortality rates and expensive treatment costs. To improve short- and long-term outcomes, it is critical to detect at-risk sepsis patients at an early stage.Objective:Our primary goal was to develop machine learning models capable of predicting sepsis using streaming physiological data in real-time.Methods:A dataset consisting of high-frequency physiological data from 1,161 critically ill patients admitted to the intensive care unit (ICU) was analyzed in this IRB-approved retrospective observational cohort study. Of that total, 634 patients were identified to have developed sepsis. In this paper, we define sepsis as meeting the Systemic Inflammatory Response Syndrome (SIRS) criteria in the presence of the suspicion of infection. In addition to the physiological data, we include white blood cell count (WBC) to develop a model that can signal the future occurrence of sepsis. A random forest classifier was trained to discriminate between sepsis and non-sepsis patients using a total of 108 features extracted from 2-hour moving time-windows. The models were trained on 80% of the patients and were tested on the remaining 20% of the patients, for two observational periods of lengths 3 and 6 hours.Results:The models, respectively, resulted in F1 scores of 75% and 69% half-hour before sepsis onset and 79% and 76% ten minutes before sepsis onset. On average, the models were able to predict sepsis 210 minutes (3.5 hours) before the onset.Conclusions:The use of robust machine learning algorithms, continuous streams of physiological data, and WBC, allows for early identification of at-risk patients in real-time with high accuracy.

In the original version of this article, the incorrect version of Fig. 3 was published. Following is the correct figure.

Sepsis is an acute, life-threatening condition that results from bacterial infections, often acquired in the hospital. Undetected, sepsis can progress to severe sepsis and septic shock, with a risk of death as high as 30% to 80%. Early detection of sepsis can improve patient outcomes. Collecting and evaluating continuous physiological variables, such as vital signs, using sophisticated classification algorithms may be highly beneficial to aid diagnosis of septic patients. However, setting up a data acquisition system that can collect (and store) high frequency/high volume data is challenging both from technology management and storage standpoints. In this paper, we build two deep learning models, a convolutional neural network and a multilayer perceptron model, to classify patients into sepsis and non-sepsis groups using data collected at various frequencies from the first 12 hours after admission. Our results indicate that the convolutional neural network model outperforms the multilayer perceptron model for all data collection frequencies. In addition, our results put into perspective the value of data collection frequency and translate its value into lives saved. Such analysis can guide future investments in data acquisition systems by hospitals.

Detection of atrial fibrillation (AF) from electrocardiogram (ECG) recordings is one of the prevailing challenges in the field of cardiac computing. The task of the PhysioNet/Computing in Cardiology 2017 challenge is to distinguish the AF rhythms from non-AF rhythms using a short single lead ECG recording. In this study, we analyzed 62 time and frequency-domain, linear, and nonlinear features to discriminate four classes, viz., normal sinus rhythm, AF, noisy, or other rhythm. The feature space dimension was reduced to 37 using a Genetic Algorithm based feature selection. We trained a random forest classifier on the given 8,528 training dataset and obtained a ten-fold cross validation classification accuracy of 82. 7%. On the test dataset, we obtained an F r score of 0.91, 0.74, and 0.70 for NSR, AF, and other rhythms, respectively. Results suggest that with the proposed model it is possible to classify cardiac abnormalities from a single lead ECG even when the recordings are of short duration.

A myriad of data is produced in intensive care units (ICU) even for short periods of time. This data is frequently used for monitoring patient’s immediate health status, not for real-time analysis because of technical challenges in real-time processing of such massive data. Data storage is also another challenge in making ICU data useful for retrospective studies. Therefore, it is important to know the minimal sampling frequency requirement to develop real-time analysis on ICU data and to develop a data storage plan. In this study, we have applied the Probabilistic Symbolic Pattern Recognition (PSPR) method in Paroxysmal Atrial Fibrillation (PAF) screening problem by analyzing electrocardiogram signals at different sampling frequencies varying from 128 Hz to 8 Hz. Our results show that using PSPR method, we can obtain a classification accuracy of 82.67% in identifying PAF subjects even when the test data is sampled at 8 Hz frequency (73.33% for 128 Hz). This classification accuracy drastically improved to 92% when other descriptive features were used along with PSPR features. The PSPR’s PAF screening ability at low sampling frequency indicates its potential for real-time analysis and wearable embedded computing applications.

© 2016 IEEE. In this paper, we introduce a novel dynamic visual analytic tool called the Cohort Relative Aligned Dashboard (CoRAD). We present the design components of CoRAD, along with alternatives that lead to the final instantiation. We also present an evaluation involving expert clinical researchers, comparing CoRAD against an existing analytics method. The results of the evaluation show CoRAD to be more usable and useful for the target user. The relative alignment of physiologic data to clinical events were found to be a highlight of the tool. Clinical experts also found the interactive selection and filter functions to be useful in reducing information overload. Moreover, CoRAD was also found to allow clinical researchers to generate alternative hypotheses and test them in vivo.

The critical care environment is a complex and critical environment, containing numerous body sensors attached to critically ill patients and producing continuous streams of physiological data. In conjunction, human-generated clinical data are produced by clinicians providing care for those patients. Currently, physiological information is displayed in a limited univariate method, inherited from conventional practices of biomedical engineering firms who design and manufacture these medical devices. However, the method in which this information is displayed was developed with limited consideration from user-centered design practices, and largely excludes influential relationship to their underlying medical knowledge and experience. Moreover, these univariate displays have limited abilities to project trends. This paper proposes a framework for displaying multi-dimensional and complex data to users in the critical care environment. We present a case study of neonatal intensive care, a form of critical care for premature and ill term infants to illustrate the framework's practical impact.

Objective: In Ontario, there are significant geographical disparities in colorectal cancer incidence. In particular, the northern region of Timiskaming has the highest incidence of colorectal cancer in Ontario while the southern region of Peel displays the lowest. We aimed to identify non-nutritional modifiable environmental factors in Timiskaming that may be associated with its diverging colorectal cancer incidence rates when compared to Peel. Methods: We performed a systematic review to identify established and proposed environmental factors associated with colorectal cancer incidence, created an assessment questionnaire tool regarding these environmental exposures, and applied this questionnaire among 114 participants from the communities of Timiskaming and Peel. Results: We found that tobacco smoking, alcohol consumption, residential use of organochlorine pesticides, and potential exposure to toxic metals were dominant factors among Timiskaming respondents. We found significant differences regarding active smoking, chronic alcohol use, reported indoor and outdoor household pesticide use, and gold and silver mining in the Timiskaming region. Conclusions: This study, the first to assess environmental factors in the Timiskaming community, identified higher reported exposures to tobacco, alcohol, pesticides, and mining in Timiskaming when compared with Peel. These significant findings highlight the need for specific public health assessments and interventions regarding community environmental exposures.

This paper presents an extension called the Complex Business Processes for Stream Processing (CBPsp) to the Solution Manager Service (SMS) framework to support the definition and enactment of complex business processes for event stream processing. The critical care of an infant involves multiple caregivers performing complex activities, thus a system that is capable of presenting complex business processes to produce context sensitive real-time support is required. The proposed system CBPsp, supports the integration of heterogeneous sequential business processes and distinct data types to produce meaningful business objective driven outputs in real-time. Two research contributions are delivered. The first contribution is the real-time integration of synchronous and asynchronous streams in a loosely coupled model based on Service-Oriented Architecture principles. The second contribution is the definition and enactment of complex business processes along with their meaningful business objectives at the point of analysis within data stream management systems.

Clinical Decision Support Systems (CDSSs) play important roles aiding in patient care; they provide accurate data analysis and timely evidence-informed recommendations. Although the availability of biomedical data continues to flourish, there have been limited translations of this type of data to information in real-time at the bedside. Existing systems have either focused on providing process-oriented or knowledge-modeled frameworks, often relying on retrospective data analysis. We have developed a framework capable of providing clinicians the ability to represent existing knowledge and processes in realtime. This framework presents a real-time environment for modeling clinical workflow processes abstracted from clinical guidelines, while applying existing knowledge to produce intelligent evidence-informed recommendations. In this paper we provide a framework to support the detection of neonatal hypoglycaemia using a design supporting the automated realtime, evidence-informed enactment of complex businessprocesses existing in clinical practice guidelines.

This paper introduces a method for interactive knowledge testing for a clinical decision support system developed as a part of the Artemis Project. Knowledge within the medical domain is vast and continuously being defined and re-defined. The volume of modern clinical decision support systems that support a flexible and intuitive environment that recognizes this principle is shocking limited. Clinical decision support systems have either been delivered as a package with Electronic Health Records or custom made and delivered along with medical monitoring devices. This has led to a large gap within support systems that are integrated with the entire continuum of care, and therefore limited in the ability to be modified. The purpose of this paper is to illustrate that an environment that is supportive of the ideal interactive can be delivered for a modern clinical decision support system within the Artemis Project. The method for delivering this is through a demonstration using Ptolemy II to simulate real-time components of InfoSphere Streams, and generate the respective Java code. This proof-of-concept paper paves the path for future work in the area of generating direct code that can be executed within Artemis directly.

As a result of advances in software technology, particularly stream computing, it is now possible to implement scalable systems capable of real-time analysis of multiple physiological data streams of multiple patients. There is a growing body of evidence showing that early onset indicators of some medical conditions can be observed as subtle changes in the physiological data streams of affected patients. These real-time healthcare analytics systems can detect the early onset indicators and thus may result in earlier detection of the medical condition which may lead to earlier intervention and improved patient outcomes. Blood draws and nasal suctioning can cause changes in the values of some physiological data stream elements. Such events, sometimes referred to as physiological stream artifacts can cause the real-time analytics systems to generate false alarms since the systems assume each data element is indicative the patient's underlying physiological condition. In order to minimize the generation of false alarms, artifact events must be captured and integrated in real time with the analytics result. We present the summary of an artifact study in a tertiary neonatal intensive care unit within a children's hospital where a real-time analytics system is being piloted as part of a clinical research study. We utilize the information gathered relating to the nature of these events and propose a framework to integrate the artifact events with the analytic results in real time

This paper proposes a framework for mobile nursing documentation enabling the integration of clinical intervention data with both electronic health record systems and real-time intelligent decision support systems for patient monitoring. A brief discussion on the networking and information security concerns is presented in order to provide context for the mobile application design decisions surround data transmission and storage. The framework is demonstrated using an initial case study in a neonatal intensive care unit.

This paper proposes a framework for the integration of physiological and clinical health data within a Service-Oriented architecture framework. This integration will subsequently be used in real-time event stream processing in intelligent patient monitoring devices. Service-oriented architecture offers a unique method of integrating health data as information is collected from multiple medical devices that lack any substantial means of standardization. Employing various services to facilitate the transmission and integration of these data will result in significant improvement in both efficacy and analytical velocity of intelligent patient monitoring systems. We demonstrate this approach within the Neonatal Intensive Care setting.

Colorectal cancer is the third most diagnosed cancer and second leading cause of cancer related deaths in Canada. As Ontario has the largest population in Canada, it also has great disparities in colorectal cancer incidence. The region of Timiskaming has the highest incidence for colorectal cancer, while the region of Peel has the lowest incidence for colorectal cancer in Ontario. There are no previously published studies regarding cancer or environmental risk factors performed in the Timiskaming region. The purpose of this study was to identify the dominant non-nutritional modifiable environmental risk factors in the region of Timiskaming compared to the reference region of Peel that may be associated with diverging colorectal cancer incidence rates. After reviewing the available published literature, a questionnaire assessment tool regarding environmental exposures was created. This questionnaire tool was created by combining standardized questionnaire tools available in the published literature that assessed environmental exposures. The questionnaire assessment tool was then utilized within a pilot study group followed by the Timiskaming and Peel participant communities. The tool assessed the exposures of tobacco smoking, alcohol use, pesticides/organochlorines, metal toxins, occupational exposures, and medical ionizing radiation. A total of 53 participants completed the questionnaire tool in Timiskaming, and a total of 61 participants completed the questionnaire tool in Peel. Findings indicate that there are dominant non-nutritional modifiable environmental risk factors in the region of Timiskaming that may be associated with colorectal cancer when compared to the region of Peel. The significant dominant environmental factors identified by Timiskaming participants were tobacco smoking, alcohol use, pesticides/organochlorines, and metal toxins. The findings also indicate that the Peel community may have important community health initiatives that can be used in the Timiskaming community to reduce the present colorectal cancer disparities. Following this study, it is imperative that recommendations are directed at a community level and relate to the assessment of potential non-nutritional modifiable environmental risk factors. While colorectal cancer disparities are evident, future research should help to understand the relationship between cancer disparities and environmental risk factors. Citation Format: Jeavana Sritharan, Rishikesan Kamaleswaran, Ken McFarlan, Manon Lemonde, Clemon George, Otto Sanchez. Assessing the environmental factors in two Ontario communities with diverging colorectal cancer incidence rates . [abstract]. In: Proceedings of the 104th Annual Meeting of the American Association for Cancer Research; 2013 Apr 6-10; Washington, DC. Philadelphia (PA): AACR; Cancer Res 2013;73(8 Suppl):Abstract nr 4819. doi:10.1158/1538-7445.AM2013-4819

This paper presents in detail the component of the Complex Business Process for Stream Processing framework that is responsible for integrating complex business processes to enable knowledge-driven Clinical Decision Support System (CDSS) recommendations. CDSSs aid the clinician in supporting the care of patients by providing accurate data analysis and evidence-based recommendations. However, the incorporation of a dynamic knowledge-management system that supports the definition and enactment of complex business processes and real-time data streams has not been researched. In this paper we discuss the process web service as an innovative method of providing contextual information to a real-time data stream processing CDSS.

This paper proposes a methodology for the event stream processing of synchronous (physiological) and asynchronous (clinical) health data streams. The purpose is to illustrate the feasibility of Artemis, our extension of IBM's InfoSphere Streams, to appropriately deliver notifications from an initial clinical hypothesis within the critical care environment. We demonstrate that an positive alert can be delivered that is indicative of an onset of instability in critically ill newborns. Artemis, is also tested for its potential to allow clinicians the ability to interact directly with the rule-based system to prove certain hypothesis. We begin this methodology with a model of the clinical case study, and then transform that model into Stream's SPADE code. Subsequently, it is compiled and executed within the Streams environment to deliver notifications in real-time of the newborns health state.

We present a method for transmission and processing of real-time trans-continental medical data streams. We apply fundamentals of existing network technologies to create a secure tunnel from a remote hospital through an open-network to the Artemis Cloud. We capture and store incoming 1Hz data stream in our real-time event stream processor to allow for online real-time monitoring of the patient status. The contributions of this paper extend the Critical Care as a Service paradigm by incorporating remote monitoring centers. The results establish feasibility of the system to support real-time monitoring. However, existing protocols were required significant optimization to account for variability in throughput and availability of the network.