A customised down-sampling machine learning approach for sepsis prediction.

OBJECTIVE: Sepsis is a life-threatening condition in the ICU and requires treatment in time. Despite the accuracy of existing sepsis prediction models, insufficient focus on reducing alarms could worsen alarm fatigue and desensitisation in ICUs, potentially compromising patient safety. In this retrospective study, we aim to develop an accurate, robust, and readily deployable method in ICUs, only based on the vital signs and laboratory tests. METHODS: Our method consists of a customised down-sampling process and a specific dynamic sliding window and XGBoost to offer sepsis prediction. The down-sampling process was applied to the retrospective data for training the XGBoost model. During the testing stage, the dynamic sliding window and the trained XGBoost were used to predict sepsis on the retrospective datasets, PhysioNet and FHC. RESULTS: With the filtered data from PhysioNet, our method achieved 80.74% accuracy (77.90% sensitivity and 84.42% specificity) and 83.95% (84.82% sensitivity and 82.00% specificity) on the test set of PhysioNet-A and PhysioNet-B, respectively. The AUC score was 0.89 for both datasets. On the FHC dataset, our method achieved 92.38% accuracy (88.37% sensitivity and 95.16% specificity) and 0.98 AUC score on the test set of FHC. CONCLUSION: Our results indicate that the down-sampling process and the dynamic sliding window with XGBoost brought robust and accurate performance to give sepsis prediction under various hospital settings. The localisation and robustness of our method can assist in sepsis diagnosis in different ICU settings.

A new rhodopsin R135W mutation induces endoplasmic reticulum stress and apoptosis in retinal pigment epithelial cells.

Rhodopsin mutations are associated with the autosomal-dominant form of retinitis pigmentosa (RP). Here we report simultaneous occurrence of RP associated with bilateral nanophthalmos and acute angle-closure glaucoma in patient with a new mutation in rhodopsin (R135W). ARPE-19 cells were transfected with myc-tagged wild-type (WT) and R135W rhodopsin constructs. The half-life of WT and R135W rhodopsin was analyzed via cycloheximide chase analysis. We found that R135W rhodopsin was accumulated in the endoplasmic reticulum (ER) and induced unfolded protein response (UPR) and apoptosis. Moreover, chaperone HSP70 alleviated ER stress and prevented apoptosis induced by R135W rhodopsin by attenuating UPR signaling. These findings reveal the novel pathogenic mechanism of RP and suggest that chaperone HSP70 has potential therapeutic significance for RP.