Early sepsis detection in critical care patients using multiscale blood pressure and heart rate dynamics

Shashikumar, Supreeth P.; Stanley, Matthew D.; Sadiq, Ismail; Li, Qiao; Holder, Andre; Clifford, Gari D.; Nemati, Shamim

doi:10.1016/j.jelectrocard.2017.08.013

Cited by 122 publications

(84 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Sepsis outcomes improve significantly with earlier detection and treatment. ML applied to heart rate and BP dynamics can independently predict sepsis 4 h prior to clinical onset . Similarly, InSight is an accurate ML based sepsis prediction algorithm that is robust to missing data and uses the change in vital signs over time to also accurately predict sepsis and severe sepsis hours prior to onset .…”

Section: Clinical Monitoringmentioning

confidence: 99%

Artificial intelligence and machine learning in emergency medicine

Stewart

Sprivulis

Dwivedi

2018

Emerg Medicine Australasia

113

View full text Add to dashboard Cite

Interest in artificial intelligence (AI) research has grown rapidly over the past few years, in part thanks to the numerous successes of modern machine learning techniques such as deep learning, the availability of large datasets and improvements in computing power. AI is proving to be increasingly applicable to healthcare and there is a growing list of tasks where algorithms have matched or surpassed physician performance. Despite the successes there remain significant concerns and challenges surrounding algorithm opacity, trust and patient data security. Notwithstanding these challenges, AI technologies will likely become increasingly integrated into emergency medicine in the coming years. This perspective presents an overview of current AI research relevant to emergency medicine.

show abstract

Section: Clinical Monitoringmentioning

confidence: 99%

Artificial intelligence and machine learning in emergency medicine

Stewart

Sprivulis

Dwivedi

2018

Emerg Medicine Australasia

113

View full text Add to dashboard Cite

show abstract

“…Many studies used publicly available data sets, such as Medical Information Mart for Intensive Care (MIMIC) (n ¼ 8), 8,12,19,[25][26][27][28]32 or the less commonly used Medical Data Warehousing and Analysis (MEDAN) project 18,34 These data sets are extensive and provide researchers with real, de-identified data that can be used as testing, training, or validation sets when using predictive analytics. Additionally, many studies (n ¼ 22) used ICU data (either local 14,17,[20][21][22][23][29][30][31][35][36][37] or MIMIC), while nine studies used ED [9][10][11]13,15,16,24,38,39 data. While local data varied greatly in size, ranging from 24 to 198,833, some used MIMIC in addition to their local data sets, which created a potentially more generalizable set of data to increase statistical significance and to increase the transfer of learning.…”

Section: Variability In Data Sample Selection and Sizementioning

confidence: 99%

A Review of Predictive Analytics Solutions for Sepsis Patients

Teng

Wilcox

2020

Appl Clin Inform

View full text Add to dashboard Cite

Background Early detection and efficient management of sepsis are important for improving health care quality, effectiveness, and costs. Due to its high cost and prevalence, sepsis is a major focus area across institutions and many studies have emerged over the past years with different models or novel machine learning techniques in early detection of sepsis or potential mortality associated with sepsis. Objective To understand predictive analytics solutions for sepsis patients, either in early detection of onset or mortality. Methods and Results We performed a systematized narrative review and identified common and unique characteristics between their approaches and results in studies that used predictive analytics solutions for sepsis patients. After reviewing 148 retrieved papers, a total of 31 qualifying papers were analyzed with variances in model, including linear regression (n = 2), logistic regression (n = 5), support vector machines (n = 4), and Markov models (n = 4), as well as population (range: 24–198,833) and feature size (range: 2–285). Many of the studies used local data sets of varying sizes and locations while others used the publicly available Medical Information Mart for Intensive Care data. Additionally, vital signs or laboratory test results were commonly used as features for training and testing purposes; however, a few used more unique features including gene expression data from blood plasma and unstructured text and data from clinician notes. Conclusion Overall, we found variation in the domain of predictive analytics tools for septic patients, from feature and population size to choice of method or algorithm. There are still limitations in transferability and generalizability of the algorithms or methods used. However, it is evident that implementing predictive analytics tools are beneficial in the early detection of sepsis or death related to sepsis. Since most of these studies were retrospective, the translational value in the real-world setting in different wards should be further investigated.

show abstract

“…Early diagnosis and comprehensive treatment are important for survival in sepsis patients [2]; however, the most appropriate diagnostic criteria and treatment remain controversial [3]. The Third International Consensus Definitions for Sepsis and Septic Shock (Sepsis-3) introduced the extent of organ damage into the definition for sepsis, using the Sequential Organ Failure Assessment (SOFA) score for assessing the dysregulated immune responses to invasive infection based on mortality [4].…”

Section: Introductionmentioning

confidence: 99%

Clinical value of full-length tryptophanyl-tRNA synthetase for sepsis detection in critically ill patients-A retrospective clinical assessment

Choi

Yoon

Sin

et al. 2020

Preprint

View full text Add to dashboard Cite

Background Sepsis is associated with high mortality, and the related innate immune system activation and diagnostic factors are not fully understood. This study aimed to statistically analyse the clinical value of full-length tryptophanyl-tRNA synthetase (WRS) induced through inflammatory stimuli in the detection of sepsis and mortality prediction in critically ill patients. Method In this retrospective analysis, we prospectively collected blood samples from patients in the medical intensive care unit (ICU) at Yonsei University College of Medicine, from March 2015 to June 2018. Sepsis detection and mortality prediction using WRS levels were compared to that with procalcitonin (PCT), C-reactive protein (CRP), and interleukin-6 (IL-6) levels, and with Sequential Organ Failure Assessment (SOFA) and Acute Physiology and Chronic Health Evaluation II (APACHE II) scores, using area under the receiver operating characteristic curve (AUROC) and Cox proportional-hazards and Kaplan-Meier survival analyses.Results We enrolled 241 study patients, of whom 190 (78.8%) had been diagnosed with sepsis on ICU admission. The AUROCs for sepsis discrimination with WRS, PCT, CRP, and IL-6 levels, and SOFA and APACHE II scores were 0.864, 0.727, 0.625, 0.651, 0.840, and 0.754, respectively. The prediction of 28-day mortality in patients with sepsis using WRS levels was possible and non-inferior to that with the SOFA score (WRS vs. SOFA, AUROC 0.687 vs. 0.711; AUROC difference, 0.024; P = 0.650). Conclusions WRS secreted early in sepsis may be useful not only for early detection of sepsis but also for mortality prediction in critically ill patients.

show abstract

Early sepsis detection in critical care patients using multiscale blood pressure and heart rate dynamics

Cited by 122 publications

References 19 publications

Artificial intelligence and machine learning in emergency medicine

Artificial intelligence and machine learning in emergency medicine

A Review of Predictive Analytics Solutions for Sepsis Patients

Clinical value of full-length tryptophanyl-tRNA synthetase for sepsis detection in critically ill patients-A retrospective clinical assessment

Contact Info

Product

Resources

About