Electronic Sepsis Screening Among Hospital Ward Patients—Reply

In Reply Health care systems vary considerably in terms of patient mix and clinical service structure. Therefore, it is unsurprising to observe wide variations in rapid response team activations (5 to 56 per 1000 admissions) and in the proportions of cardiac arrests (1 to 48.6 per 1000 admissions) and hospital mortality (0.2 to 49.1 per 1000 admissions). The proportions reported in the SCREEN trial and those reported by Drs Bellomo and Jones fall within these ranges. The sepsis alert was designed to identify clinically deteriorating patients early before meeting the rapid response team activation criteria. This explains why alerts occurred more frequently than rapid response team activations (14.6% compared with 4.8%). Therefore, rapid response teams should not be considered a replacement for systems for early identification of sepsis.

Read More

Electronic Sepsis Screening Among Hospital Ward Patients

To the Editor In the Stepped-wedge Cluster Randomized Trial of Electronic Early Notification of Sepsis in Hospitalized Ward Patients (SCREEN) trial, the authors concluded that electronic sepsis screening compared with no screening reduced 90-day mortality in hospitalized patients. While the top-line conclusions are statistically valid, we would highlight 2 additional and related interpretations.

Read More

Development and validation of a 3-D deep learning system for diabetic macular oedema classification on optical coherence tomography images

Objectives
To develop and validate an automated diabetic macular oedema (DME) classification system based on the images from different three-dimensional optical coherence tomography (3-D OCT) devices.

Design
A multicentre, platform-based development study using retrospective and cross-sectional data. Data were subjected to a two-level grading system by trained graders and a retina specialist, and categorised into three types: no DME, non-centre-involved DME and centre-involved DME (CI-DME). The 3-D convolutional neural networks algorithm was used for DME classification system development. The deep learning (DL) performance was compared with the diabetic retinopathy experts.

Setting
Data were collected from Joint Shantou International Eye Center of Shantou University and the Chinese University of Hong Kong, Chaozhou People’s Hospital and The Second Affiliated Hospital of Shantou University Medical College from January 2010 to December 2023.

Participants
7790 volumes of 7146 eyes from 4254 patients were annotated, of which 6281 images were used as the development set and 1509 images were used as the external validation set, split based on the centres.

Main outcomes
Accuracy, F1-score, sensitivity, specificity, area under receiver operating characteristic curve (AUROC) and Cohen’s kappa were calculated to evaluate the performance of the DL algorithm.

Results
In classifying DME with non-DME, our model achieved an AUROCs of 0.990 (95% CI 0.983 to 0.996) and 0.916 (95% CI 0.902 to 0.930) for hold-out testing dataset and external validation dataset, respectively. To distinguish CI-DME from non-centre-involved-DME, our model achieved AUROCs of 0.859 (95% CI 0.812 to 0.906) and 0.881 (95% CI 0.859 to 0.902), respectively. In addition, our system showed comparable performance (Cohen’s : 0.85 and 0.75) to the retina experts (Cohen’s : 0.58–0.92 and 0.70–0.71).

Conclusions
Our DL system achieved high accuracy in multiclassification tasks on DME classification with 3-D OCT images, which can be applied to population-based DME screening.

Read More

High prevalence of diabetes mellitus among patients with Fabry disease in Taiwan: a cross-sectional study

Objectives
This study aimed to investigate the prevalence of diabetes mellitus in patients with Fabry disease using a nationwide population-based dataset. We hypothesised that patients with Fabry disease would have a higher prevalence of diabetes mellitus compared with the general population.

Design
A cross-sectional study.

Setting
Taiwan.

Participants
We identified a study sample from Taiwan’s LHID2010 Database. There were 9408 sampled patients in this study, 2352 study patients with Fabry disease and 7056 propensity-score-matched comparison patients.

Primary outcome measures
Multiple logistic regression analyses were conducted to explore the association between diabetes mellitus and Fabry disease after taking the variables of age, sex, geographic location, monthly income category, urbanisation level of the patient’s residence, hyperlipidaemia and hypertension into consideration.

Results
The results revealed significantly higher prevalence of diabetes mellitus among patients with Fabry disease than among comparison patients (35.8% vs 29.6%, p

Read More