The possibility of constructing statistical models for prediction of alveolar oxygen and carbon dioxide tensions has been investigated in 20 mechanically ventilated patients in acute respiratory failure (ARF). Linear multiple regression analysis using PaCO2 and PaO2 as dependent variables was used to construct (a) models for individual patients, (b) models for specific diagnostic groups and (c) general models (all patients). The coefficient of determination (R2) was highest for the individual patient models (0.38-0.99) and lowest for the general models (0.28-0.49). In order to achieve a high predictive accuracy, models matching individual patients should be constructed on the basis of initial invasive blood gas measurement. Statistically derived models may bring better understanding of the behaviour of factors influencing arterial gas tensions in ARF and may be of value in the management of patients on mechanical ventilation.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1016/0169-2607(91)90043-s | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Fully Synthetic Data for Complex Surveys.
Surv Methodol
December 2024
Department of Statistical Science, 214a Old Chemistry Building, Duke University, Durham, NC 27708-0251.
When seeking to release public use files for confidential data, statistical agencies can generate fully synthetic data. We propose an approach for making fully synthetic data from surveys collected with complex sampling designs. Our approach adheres to the general strategy proposed by Rubin (1993).
View Article and Find Full Text PDFMethodological Approaches to Comparative Trend Analyses: The Case of Adolescent Toothbrushing.
Int J Public Health
January 2025
Department of Public Health, University of Copenhagen, Copenhagen, Denmark.
Objectives: Research questions about how and why health trends differ between populations require decisions about data analytic procedure. The objective was to document and compare the information returned from stratified, fixed effect and random effect approaches to data modelling for two prototypical descriptive research questions about comparative trends in toothbrushing.
Methods: Data included five cycles of the Health Behaviour in School-aged Children 2006 to 2022, which provided a sample of 980192 11- to 15- year olds from 35 countries.
Influence of parity on weight gain during pregnancy in women with Gestational Diabetes: A retrospective cohort study.
Pak J Med Sci
January 2025
Lianghui Zheng Fujian Maternity and Child Health Hospital, College of Clinical Medicine for Obstetrics, Gynecology and Pediatrics, Fujian Medical University. P.R. China.
Objective: This retrospective cohort study aimed to investigate the effects of parity on gestational weight gain (GWG) and its association with maternal and neonatal outcomes in women with gestational diabetes mellitus (GDM).
Methods: This retrospective cohort study data from 2,909 pregnant women with GDM who delivered between 2021 and 2023 at Fujian Maternity and Child Health hospital, were analyzed. Participants were categorized into nulliparous (no previous births), primiparous (one previous birth), and multiparous (two or more previous births) groups.
Effectiveness of three machine learning models for prediction of daily streamflow and uncertainty assessment.
Water Res X
May 2025
Institute for Artificial Intelligence R&D of Serbia, Fruškogorska 1, Novi Sad 21000, Serbia.
This study evaluates three Machine Learning (ML) models-Temporal Kolmogorov-Arnold Networks (TKAN), Long Short-Term Memory (LSTM), and Temporal Convolutional Networks (TCN)-focusing on their capabilities to improve prediction accuracy and efficiency in streamflow forecasting. We adopt a data-centric approach, utilizing large, validated datasets to train the models, and apply SHapley Additive exPlanations (SHAP) to enhance the interpretability and reliability of the ML models. The results show that TKAN outperforms LSTM but slightly lags behind TCN in streamflow forecasting.
View Article and Find Full Text PDFPredicting risk of maternal critical care admission in Scotland: Development of a risk prediction model.
J Intensive Care Soc
January 2025
Department of Anaesthesia, Critical Care, and Pain Medicine, Royal Infirmary of Edinburgh, University of Edinburgh, Edinburgh, UK.
Background: Identifying women at highest or lowest risk of perinatal intensive care unit (ICU) admission may enable clinicians to risk stratify women antenatally so that enhanced care or elective admission to ICU may be considered or excluded in birthing plans. We aimed to develop a statistical model to predict the risk of maternal ICU admission.
Methods: We studied 762,918 pregnancies between 2005 and 2018.
Want AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!