Septic shock prediction for ICU patients via coupled HMM walking on sequential contrast patterns

Ghosh, Shameek; Li, Jinyan; Cao, Longbing; Ramamohanarao, Kotagiri

doi:10.1016/j.jbi.2016.12.010

Cited by 83 publications

(78 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Agrawal et al [36] proposed SPM. Based on this research, many achievements have been made, such as high utility mining [37], contrast SPM [38,39], and closed SPM [40,41]. Closed SPM can effectively compress the frequent patterns [42,43].…”

Section: Related Workmentioning

confidence: 99%

NetNCSP: Nonoverlapping closed sequential pattern mining

Zhu

et al. 2020

Knowledge-Based Systems

View full text Add to dashboard Cite

Section: Related Workmentioning

confidence: 99%

NetNCSP: Nonoverlapping closed sequential pattern mining

Zhu

et al. 2020

Knowledge-Based Systems

View full text Add to dashboard Cite

“…The variety of methods used, summarized in ►Table 2, added to the richness of this systematic scoping review. Common methods include linear regression (n ¼ 2), 8,9 logistic regression (n ¼ 5), 10-14 support vector machines (n ¼ 4), [15][16][17][18] Markov models (n ¼ 4), [19][20][21][22] and Bayesian networks (n ¼ 2). 23,24 Additionally, a few studies (n ¼ 6), [25][26][27][28][29][30] used an industry created tool, InSight (Dascena Inc.), to validate performance compared with the more commonly used methods.…”

Section: Variability In Machine Learning or Modeling Techniquesmentioning

confidence: 99%

“…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.…”

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

“…Septic shock is a common clinical syndrome resulting from tissue perfusion deficiency caused by severe systemic infection, leading to tissue hypoxia, vital organ damage, and even multiple organ failure (1,2). Septic shock refers to persistent low blood pressure in patients with severe sepsis that cannot be corrected after adequate fluid replacement, accompanied by tissue hypoperfusion (3).…”

Section: Introductionmentioning

confidence: 99%

Correlation Between Pulmonary Vascular Permeability Index, Shock Index, and Severity of Septic Shock and Their Evaluation Values for Prognosis

Xiao

Zhou

Guo

2020

Iran Red Crescent Med J

View full text Add to dashboard Cite

Background: The changes before and after fluid resuscitation in patients with septic shock and their relationship with prognosis have rarely been reported. Objectives: We aimed to observe the correlation between pulmonary vascular permeability index (PVPI), shock index (SI), and severity of septic shock. Methods: This case-control study retrospectively analyzed the clinical data of 154 patients with septic shock treated at our hospital (Weifang, China) from October 2016 to October 2018. They were divided into a survival group or a death group according to the 28day prognosis. Univariate analysis was performed for vital signs, the acute physiology and chronic health evaluation II (APACHE-II) score, the sequential organ failure assessment (SOFA) score at admission, SI at admission (SI1), SI at 3 h after fluid resuscitation (SI2), PVPI at admission (PVPI1), PVPI at 3 h after fluid resuscitation (PVPI2), and lactate clearance rate (LCR). The correlations of PVPI and SI with the APACHE-II score, SOFA score, and LCR were analyzed by plotting the receiver operating characteristic curves. Results: Among the 154 cases, 70 survived after 28 days and 84 died. We observed that SI1, SI2, PVPI1, PVPI2, APACHE-II score, and SOFA score were significantly lower in the survival group than in the death group, while LCR was significantly higher (P < 0.05). Also, SI1, SI2, PVPI1, and PVPI2 were positively correlated with APSCHE-II and SOFA scores of patients with septic shock, but negatively correlated with LCR (P < 0.05). Moreover, SI2 predicted the prognosis of patients with septic shock significantly better than SI1, PVPI1, and PVPI2 did. When SI2 was 1.22, the Youden index was 0.822, the sensitivity was 91.23%, the specificity was 89.47%, the positive predictive value was 0.912, and the negative predictive value was 0.924. The positive and negative likelihood ratios were 0.897 and 0.375, respectively. Conclusions: Based on the study, SI after fluid resuscitation was more valuable for evaluating the prognosis of patients with septic shock than SI at admission, as well as PVPI values at admission and after fluid resuscitation.

show abstract

Septic shock prediction for ICU patients via coupled HMM walking on sequential contrast patterns

Cited by 83 publications

References 26 publications

NetNCSP: Nonoverlapping closed sequential pattern mining

NetNCSP: Nonoverlapping closed sequential pattern mining

A Review of Predictive Analytics Solutions for Sepsis Patients

Correlation Between Pulmonary Vascular Permeability Index, Shock Index, and Severity of Septic Shock and Their Evaluation Values for Prognosis

Contact Info

Product

Resources

About