A systematic review of machine learning models for management, prediction and classification of ARDS

Respiratory Research, Год журнала: 2024, Номер 25(1)

Опубликована: Июнь 4, 2024

Abstract Aim Acute respiratory distress syndrome or ARDS is an acute, severe form of failure characterised by poor oxygenation and bilateral pulmonary infiltrates. Advancements in signal processing machine learning have led to promising solutions for classification, event detection predictive models the management ARDS. Method In this review, we provide systematic description different studies application Machine Learning (ML) artificial intelligence management, prediction, classification We searched following databases: Google Scholar, PubMed, EBSCO from 2009 2023. A total 243 was screened, which, 52 were included review analysis. integrated knowledge previous work providing state art overview explainable decision identified areas future research. Results Gradient boosting most common successful method utilised 12 (23.1%) studies. Due limitation data size available, neural network its variation used only 8 (15.4%) Whilst all cross validating technique separated database validation, 1 study validated model with clinician input. Explainability methods presented 15 (28.8%) feature importance which 14 times. Conclusion For databases 5000 fewer samples, extreme gradient has highest probability success. large, multi-region, multi centre required reduce bias take advantage method. framework explaining ML clinicians involved would be very helpful development deployment model.

Язык: Английский

---

A hybrid modeling framework for generalizable and interpretable predictions of ICU mortality across multiple hospitals

Scientific Reports, Год журнала: 2024, Номер 14(1)

Опубликована: Март 8, 2024

The development of reliable mortality risk stratification models is an active research area in computational healthcare. Mortality provides a standard to assist physicians evaluating patient's condition or prognosis objectively. Particular interest lies methods that are transparent clinical interpretation and retain predictive power once validated across diverse datasets they were not trained on. This study addresses the challenge consolidating numerous ICD codes for modeling ICU mortality, employing hybrid approach integrates mechanistic, knowledge with mathematical machine learning . A tree-structured network connecting independent modules carry meaning implemented interpretability. Our training strategy utilizes graph-theoretic data analysis, aiming identify functions individual black-box within by harnessing solutions from specific max-cut problems. model then on external different hospitals, demonstrating successful generalization capabilities, particularly binary-feature where label assessment involves extrapolation.

Язык: Английский

---

Developing an Artificial Intelligence-Based Representation of a Virtual Patient Model for Real-Time Diagnosis of Acute Respiratory Distress Syndrome

Diagnostics, Год журнала: 2023, Номер 13(12), С. 2098 - 2098

Опубликована: Июнь 17, 2023

Acute Respiratory Distress Syndrome (ARDS) is a condition that endangers the lives of many Intensive Care Unit patients through gradual reduction lung function. Due to its heterogeneity, this has been difficult diagnose and treat, although it subject continuous research, leading development several tools for modeling disease progression on one hand, guidelines diagnosis other, mainly "Berlin Definition". This paper describes deep learning-based surrogate model such tool ARDS onset in virtual patient: Nottingham Physiology Simulator. The model-development process takes advantage current machine learning data-analysis techniques, as well efficient hyperparameter-tuning methods, within high-performance computing-enabled data science platform. lightweight models developed present comparable accuracy original simulator (per-parameter R

Язык: Английский

---

A pretrain-finetune approach for improving model generalizability in outcome prediction of acute respiratory distress syndrome patients

International Journal of Medical Informatics, Год журнала: 2024, Номер 186, С. 105397 - 105397

Опубликована: Март 2, 2024

Язык: Английский

---