English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

PURPOSE: Subarachnoid hemorrhage (SAH) entails high morbidity and mortalityrates. Convolutional neural networks (CNN), a form of deep learning, arecapable of generating highly accurate predictions from imaging data. Ourobjective was to predict mortality in SAH patients by processing the initial CTscan on a CNN based algorithm.  METHODS: Retrospective multicentric study of a consecutive cohort of patientswith SAH between 2011-2022. Demographic, clinical and radiological variableswere analyzed. Pre-processed baseline CT scan images were used as the input fortraining a CNN using AUCMEDI Framework. Our model's architecture leverages theDenseNet-121 structure, employing transfer learning principles. The outputvariable was mortality in the first three months. Performance of the model wasevaluated by statistical parameters conventionally used in studies involvingartificial intelligence methods.  RESULTS: Images from 219 patients were processed, 175 for training andvalidation of the CNN and 44 for its evaluation. 52%(115/219) of patients werefemale, and the median age was 58(SD=13.06) years. 18.5%(39/219) wereidiopathic SAH. Mortality rate was 28.5%(63/219). The model showed goodaccuracy at predicting mortality in SAH patients exclusively using the imagesof the initial CT scan (Accuracy=74%, F1=75% and AUC=82%). CONCLUSION: Modernimage processing techniques based on AI and CNN make possible to predictmortality in SAH patients with high accuracy using CT scan images as the onlyinput. These models might be optimized by including more data and patientsresulting in better training, development and performance on tasks which arebeyond the skills of conventional clinical knowledge.

Enhanced Mortality Prediction In Patients With Subarachnoid Haemorrhage Using A Deep Learning Model Based On The Initial CT Scan