Deep learning-based clustering robustly identified two classes of sepsis with both prognostic and predictive values

Abstract

Background Sepsis is a heterogenous syndrome and individualized management strategy is the key to successful treatment. Genome wide expression profiling has been utilized for identifying subclasses of sepsis, but the clinical utility of these subclasses was limited because of the classification instability, and the lack of a robust class prediction model with extensive external validation. The study aimed to develop a parsimonious class model for the prediction of class membership and validate the model for its prognostic and predictive capability in external datasets. Methods The Gene Expression Omnibus (GEO) and ArrayExpress databases were searched from inception to April 2020. Datasets containing whole blood gene expression profiling in adult sepsis patients were included. Autoencoder was used to extract representative features for k-means clustering. Genetic algorithms (GA) were employed to derive a parsimonious 5-gene class prediction model. The class model was then applied to external datasets ( n = 780) to evaluate its prognostic and predictive performance. Findings A total of 12 datasets involving 1613 patients were included. Two classes were identified in the discovery cohort ( n = 685). Class 1 was characterized by immunosuppression with higher mortality than class 2 (21.8% [70/321] vs. 12.1% [44/364]; p < 0.01 for Chi-square test). A 5-gene class model (C14orf159, AKNA, PILRA, STOM and USP4) was developed with GA. In external validation cohorts, the 5-gene class model (AUC: 0.707; 95% CI: 0.664 – 0.750) performed better in predicting mortality than sepsis response signature (SRS) endotypes (AUC: 0.610; 95% CI: 0.521 – 0.700), and performed equivalently to the APACHE II score (AUC: 0.681; 95% CI: 0.595 – 0.767). In the dataset E-MTAB-7581, the use of hydrocortisone was associated with increased risk of mortality (OR: 3.15 [1.13, 8.82]; p = 0.029) in class 2. The effect was not statistically significant in class 1 (OR: 1.88 [0.70, 5.09]; p = 0.211). Interpretation Our study identified two classes of sepsis that showed different mortality rates and responses to hydrocortisone therapy. Class 1 was characterized by immunosuppression with higher mortality rate than class 2. We further developed a 5-gene class model to predict class membership. Funding The study was funded by the National Natural Science Foundation of China (Grant No. 81,901,929).

Deep learning predicts gene expression as an intermediate data modality to identify susceptibility patterns in Mycobacterium tuberculosis infected Diversity Outbred mice

“…A multi-layer perceptron was then trained on these supertiles to predict gene expression data. During training, only the top k [ 1 , 2 , 5 , 10 , 20 , 50 ] , 100 tiles in terms of predicted gene expression are selected and a weighted mean computed of their predictions, giving more weight to higher valued predictions. Finally, the model is fine-tuned for specific organs using the 8000 normal tiles, again sampling the top k [ 10 , 20 , 50 ], 100, 200, 500, 1000, 2000, 5000 during training.…”

“…Abdullal et al compared a multilayer perceptron to traditional regression to predict susceptibility to COVID-19 [49] . Zhang et al utilized genetic algorithms to develop an autoencoder to extract and cluster features related to gene expression to predict susceptibility to sepsis [50] . Shashikumar et al developed an interpretable recurrent neural network to pre-emptively predict sepsis based on temporal features such as heart rate and arterial pressure [51] .…”

Individualized Mechanical power-based ventilation strategy for acute respiratory failure formalized by finite mixture modeling and dynamic treatment regimen

“…However, one of the most important challenges in the management of critically ill patients is the population heterogeneity [16] , [17] , [18] , [19] . The idea of protective ventilation is theoretically sound but may be difficult to implement in clinical practice.…”

Identification of COVID-19 subtypes based on immunogenomic profiling

“…Previous studies have explored associations between immune signatures and clinical prognosis based on blood transcriptomic profiling in patients [10] , [11] . For example, based on whole blood gene expression profiling, Zhang et al identified two subtypes of sepsis, which displayed different immune responses and clinical outcomes [10] . Shankar et al identified transcriptomic features in blood to predict paediatric patients with multiple organ dysfunction in need of intensive care [11] .…”