Risk assessment of ICU patients through deep learning technique: A big data approach

Abstract

Background Intensive Care Unit (ICU) patients are exposed to various medications, especially during infusion, and the amount of infusion drugs and the rate of their application may negatively affect their health status. A deep learning model can monitor a patient's continuous reaction to tranquillizer therapy, analyze the treatment plans of experts to avoid severe situations such as reverse medication associations, work with a convenient mediator, and change the treatment plans of specialists as needed.Methods Generally, patients' treatment histories are linked together via a period grouping connection, which is usually burdened by missing information. Displaying time-succession via Repetitive Neural Organization (RNO) is the best available solution. However, it's possible that a patient's treatment may be prolonged, which RNN may not be able to demonstrate in this manner. ResultsWe propose the use of the LSTM-RNN driven by heterogeneous medicine events to predict the patient's outcome, as well as the Regular Language Handling and Gaussian Cycle, which can handle boisterous, deficient, inadequate, heterogeneous, and unevenly tested prescription records of patients while addressing the missing value issue using a piece-based Gaussian cycle. ConclusionsWe emphasize the semantic relevance of every medication event and the grouping of drug events on patients in our study. We will focus specifically on LSTM-RNN and Phased LSTM-RNN for showing treatment results and information attribution using bit-based Gaussian cycles. We worked on Staged LSTM-RNN.

Chinese experts’ consensus on the application of intensive care big data

“…And through direct interaction with electronic medical records, they broadened the way to use big data and provided the right dose for each patient at the right expounded the importance of big data to explore clinical trials systematically and, respectively. In the exploration of big data in the past 2 years, a number of studies have carried out analysis of individualized computational models constructed through big data, pointing out risk factors for high mortality in patients with critical symptoms (31)(32)(33). Finally, in terms of the relationship between clinical drug R&D and big data, we have not seen any evidence that relevant big data is used in drug R&D in the field of critical care medicine.…”

A Hybrid Modeling Framework for Generalizable and Interpretable Predictions of ICU Mortality: Leveraging ICD Codes in a Multi-Hospital Study of Mechanically Ventilated Influenza Patients

“…Some are calculated from data collected upon admission 5,6 ; others are repeatedly computed every day and can be used to assess the severity of a patient dynamically 7,8 . More recently, with the advent of machine learning and deep learning models, clinical prediction models and risk scoring systems are evolving to sophisticated models incorporating not only routinely measured parameters, but heterogeneous types of data, such as medical notes 9 or radiological images 10,11 . Several prognostic models and scores have been developed for COVID-19 as well 10,12,13 .…”