Accuracy in early prediction of prognosis of patients with septic shock by analysis of simple indices

Abstract Background Identifying the biological subclasses of septic shock might provide specific targeted therapies for the treatment and prognosis of septic shock. It might be possible to find biological markers for the early prediction of septic shock prognosis. Methods The data were obtained from the Gene Expression Omnibus databases (GEO) in NCBI. GO enrichment and KEGG pathway analyses were performed to investigate the functional annotation of up- and downregulated DEGs. ROC curves were drawn, and their areas under the curves (AUCs) were determined to evaluate the predictive value of the key genes. Results 117 DEGs were obtained, including 36 up- and 81 downregulated DEGs. The AUC for the MME gene was 0.879, as a key gene with the most obvious upregulation in septic shock. The AUC for the THBS1 gene was 0.889, as a key downregulated gene with the most obvious downregulation in septic shock. Conclusions The upregulation of MME via the renin-angiotensin system pathway and the downregulation of THBS1 through the PI3K–Akt signaling pathway might have implications for the early prediction of prognosis of septic shock in patients with pneumopathies.

Download Full-text

Early prediction of norepinephrine dependency and refractory septic shock with a multimodal approach of vascular failure

Journal of Critical Care ◽

10.1016/j.jcrc.2015.03.029 ◽

2015 ◽

Vol 30 (4) ◽

pp. 739-743 ◽

Cited By ~ 10

Author(s):

Marie Conrad ◽

Pierre Perez ◽

Carine Thivilier ◽

Bruno Levy

Keyword(s):

Septic Shock ◽

Early Prediction ◽

Multimodal Approach ◽

Refractory Septic Shock

Download Full-text

Temporal Belief Memory: Imputing Missing Data during RNN Training

Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence ◽

10.24963/ijcai.2018/322 ◽

2018 ◽

Cited By ~ 3

Author(s):

Yeo Jin Kim ◽

Min Chi

Keyword(s):

Septic Shock ◽

Missing Data ◽

Real Time ◽

Short Term Memory ◽

Early Prediction ◽

Short Term ◽

Time Intervals ◽

Domain Experts ◽

Long Short Term Memory ◽

Temporal Sequences

We propose a bio-inspired approach named Temporal Belief Memory (TBM) for handling missing data with recurrent neural networks (RNNs). When modeling irregularly observed temporal sequences, conventional RNNs generally ignore the real-time intervals between consecutive observations. TBM is a missing value imputation method that considers the time continuity and captures latent missing patterns based on irregular real time intervals of the inputs. We evaluate our TBM approach with real-world electronic health records (EHRs) consisting of 52,919 visits and 4,224,567 events on a task of early prediction of septic shock. We compare TBM against multiple baselines including both domain experts' rules and the state-of-the-art missing data handling approach using both RNN and long-short term memory. The experimental results show that TBM outperforms all the competitive baseline approaches for the septic shock early prediction task.

Download Full-text