Predicting outcomes using neural networks in the intensive care unit DOI
GR Sridhar,

Venkat Yarabati,

Lakshmi Gumpeny

и другие.

World Journal of Clinical Cases, Год журнала: 2024, Номер 13(11)

Опубликована: Дек. 25, 2024

Patients in intensive care units (ICUs) require rapid critical decision making. Modern ICUs are data rich, where information streams from diverse sources. Machine learning (ML) and neural networks (NN) can leverage the rich for prognostication clinical care. They handle complex nonlinear relationships medical have advantages over traditional predictive methods. A number of models used: (1) Feedforward networks; (2) Recurrent NN convolutional to predict key outcomes such as mortality, length stay ICU likelihood complications. Current exist silos; their integration into workflow requires greater transparency on that analyzed. Most accurate enough use operate 'black-boxes' which logic behind making is opaque. Advances occurred see through opacity peer processing black-box. In near future ML positioned help far beyond what currently possible. Transparency first step toward validation followed by trust adoption. summary, NNs transformative ability enhance accuracy improve patient management ICUs. The concept should soon be turning reality.

Язык: Английский

Optimizing Spectral Utilization in Healthcare Internet of Things DOI Creative Commons
Adeel Iqbal, Ali Nauman, Yazdan Ahmad Qadri

и другие.

Sensors, Год журнала: 2025, Номер 25(3), С. 615 - 615

Опубликована: Янв. 21, 2025

The mainstream adoption of Internet Things (IoT) devices for health and lifestyle tracking has revolutionized monitoring systems. Sixth-generation (6G) cellular networks enable IoT healthcare services to reduce the pressures on already resource-constrained facilities, leveraging enhanced ultra-reliable low-latency communication (eURLLC) make sure critical data are transmitted with minimal delay. Any delay or information loss can result in serious consequences, making spectrum availability a crucial bottleneck. This study systematically identifies challenges optimizing utilization (H-IoT) networks, focusing issues such as dynamic allocation, interference management, prioritization medical devices. To address these challenges, paper highlights emerging solutions, including artificial intelligence-based edge computing integration, advanced network architectures massive multiple-input multiple-output (mMIMO) terahertz (THz) communication. We identify gaps existing methodologies provide potential research directions enhance efficiency reliability eURLLC environments. These findings offer roadmap future advancements H-IoT systems form basis our recommendations, emphasizing importance tailored solutions management 6G era.

Язык: Английский

Процитировано

0
The role of the dopamine system in autism spectrum disorder revealed using machine learning: an ABIDE database–based study DOI
Yunjie Li, Heli Li, Cong Hu

и другие.

Cerebral Cortex, Год журнала: 2025, Номер 35(2)

Опубликована: Фев. 1, 2025

This study explores the diagnostic value of dopamine system imaging characteristics in children with autism spectrum disorder. Functional magnetic resonance data from 551 Autism Brain Imaging Data Exchange database were analyzed, focusing on six dopamine-related brain regions as interest. connectivity between these ROIs and across whole was assessed. Machine learning techniques then evaluated ability system's features to predict significantly higher disorder ventral tegmental area substantia nigra, prefrontal cortex, nucleus accumbens, nigra hypothalamus compared typically developing children. Additionally, clustering methods identified two subtypes, achieving over 0.8 accuracy. Subtype 1 showed stereotyped behavior scores than subtype 2 both genders, subtype-specific functional differences male female groups. These findings suggest that abnormal serves a biomarker for can support clinical decision-making personalized treatment optimization.

Язык: Английский

Процитировано

0
Comparative Analysis of Machine Learning and Deep Learning Models for Lung Cancer Prediction Based on Symptomatic and Lifestyle Features DOI Creative Commons
Bireswar Dutta

Applied Sciences, Год журнала: 2025, Номер 15(8), С. 4507 - 4507

Опубликована: Апрель 19, 2025

Lung cancer remains a leading cause of global mortality, with early detection being critical for improving the patient survival rates. However, applying machine learning and deep effectively lung prediction using symptomatic lifestyle data requires careful consideration feature selection model optimization, which is not consistently addressed in existing research. This research addresses this gap by systematically evaluating comparing predictive efficacy several models, employing rigorous preprocessing, including Pearson’s correlation, outlier removal, normalization, on symptom factor dataset from Kaggle. Machine classifiers, Decision Trees, K-Nearest Neighbors, Random Forest, Naïve Bayes, AdaBoost, Logistic Regression, Support Vector Machines, were implemented Weka simultaneously neural network models 1, 2, 3 hidden layers, developed Python within Jupyter Notebook environment. The performance was assessed K-fold cross-validation 80/20 train/test splitting. results highlight importance enhancing accuracy demonstrate that single-hidden-layer network, trained 800 epochs, achieved 92.86%, outperforming models. study contributes to developing more effective computational methods detection, ultimately supporting improved outcomes.

Язык: Английский

Процитировано

0
Important Guide for Natural Compounds Inclusion in Precision Medicine DOI Open Access
O. Gabriel

OBM Genetics, Год журнала: 2024, Номер 08(04), С. 1 - 8

Опубликована: Дек. 6, 2024

Precision medicine describes the definition of disease at a higher resolution by genomic and other technologies to enable more precise targeting subgroups with new therapies. Preventative or therapeutic interventions can be developed knowledge how compound acts safely in body target receptors produce desirable effect. With completion Human Genome Project 2003 rapid increase sequencing bioinformatics tools, obtaining information about person's genome is becoming accessible. To make use genetic precision personalised medicine, it important examine roles natural remedies individualization treatment - as right drug, correct dose, for person, time. Integrating biomarkers, especially within clinical workflows, plays crucial role implementing medicine. Though horizon looks promising, one major issue resides mapping into clearly defined medical conditions associated biomarker identification precedence ranking. This communication met provide guidelines that could improve discovery enhance participation integration novel compounds processes personalized

Язык: Английский

Процитировано

0
Predicting outcomes using neural networks in the intensive care unit DOI
GR Sridhar,

Venkat Yarabati,

Lakshmi Gumpeny

и другие.

World Journal of Clinical Cases, Год журнала: 2024, Номер 13(11)

Опубликована: Дек. 25, 2024

Patients in intensive care units (ICUs) require rapid critical decision making. Modern ICUs are data rich, where information streams from diverse sources. Machine learning (ML) and neural networks (NN) can leverage the rich for prognostication clinical care. They handle complex nonlinear relationships medical have advantages over traditional predictive methods. A number of models used: (1) Feedforward networks; (2) Recurrent NN convolutional to predict key outcomes such as mortality, length stay ICU likelihood complications. Current exist silos; their integration into workflow requires greater transparency on that analyzed. Most accurate enough use operate 'black-boxes' which logic behind making is opaque. Advances occurred see through opacity peer processing black-box. In near future ML positioned help far beyond what currently possible. Transparency first step toward validation followed by trust adoption. summary, NNs transformative ability enhance accuracy improve patient management ICUs. The concept should soon be turning reality.

Язык: Английский

Процитировано

0