Open Access Pub publishes peer-reviewed, free-to-read open-access articles. Showing
articles matching ventilator — open any to read the full text,
or download the PDF or XML.
Jun 2026 DOI 10.14302/issn.2642-9241.jrd-26-6332
de Melo PhilipCorresponding author
Respiratory diseases remain a major contributor to hospital morbidity and mortality worldwide, particularly among elderly patients and individuals with severe pulmonary compromise. Accurate prediction of respiratory mortality is clinically important for triage, resource allocation, ICU utilization, and early intervention. Traditional statistical models frequently demonstrate limited predictive sensitivity because respiratory mortality is influenced by complex interactions among demographic, diagnostic, physiologic, and severity-related variables. In this study, a machine learning framework was developed to predict in-hospital mortality among patients with respiratory disease using administrative and clinically derived variables, including age, sex, length of stay (LOS), diagnostic descriptions, risk of mortality and severity scores. A Random Forest classifier with balanced class weighting was developed and implemented to address nonlinear relationships and class imbalance within the dataset. Initial modeling demonstrated good overall discrimination performance, with receiver operating characteristic area under the curve (ROC-AUC) values approaching 0.84; however, mortality recall remained limited because deceased patients represented a minority class within the original dataset. To improve mortality detection, a physiologically informed synthetic augmentation strategy was developed. Synthetic clinical variables included oxygen saturation, ICU status, ventilator support, sepsis status, systolic blood pressure, creatinine, and lactate levels. Conditional physiologic consistency rules were incorporated during augmentation to preserve clinically plausible relationships among respiratory failure, hemodynamic instability, and organ dysfunction. The augmented dataset substantially improved model sensitivity and balanced mortality classification performance. Final model evaluation demonstrated strong predictive capability, achieving approximately 97% classification accuracy with balanced precision and recall across mortality classes. Confusion matrix analysis revealed marked reduction in false-negative mortality predictions compared with baseline modeling approaches. Feature importance analysis identified physiologic instability markers, respiratory severity classifications, LOS, and diagnostic respiratory categories as dominant predictors of mortality. These findings suggest that hybrid simulation-augmented machine learning frameworks may provide a valuable strategy for respiratory mortality analytics, particularly in datasets with limited real-world mortality prevalence and incomplete physiologic representation.
Jan 2024 DOI 10.14302/issn.2642-9241.jrd-23-4809
Kadiatou SamakeCorresponding author
Introduction People living with HIV (PLHIV) are susceptible to developing non- communicable chronic respiratory diseases. Our objective was to study the spirometric profile of this population. Material and methods This was a descriptive and analytical cross-sectional retro-prospective study conducted from March 15 to June 15, 2022 and relating to the analysis of the medical files of asymptomatic and eligible for spirometry PLHIV, aged 18 years and above. They were received in the voluntary counselling and testing (VCT) centres of one of the two pulmonology departments in Abidjan. Results The study involved 54 subjects including 22 men (40.7%) and 32 women (59.3%) with an average age of 48.9 years. The majority of patients were non-smokers (81.4%) and the main history was pulmonary tuberculosis (35.2%). Only 29.6% had chronic respiratory symptoms and 42.6% had a normal BMI. The frequency of spirometric abnormalities was 57.4%. These spirometric abnormalities included 40.7% peripheral obstructive pattern; 9.3% restrictive pattern; 3.7% asthma and 3.7% COPD. A more than 10 years duration of HIV infection (p=0.001 OR= 0.2 (0.1 – 0.7)) and a duration of ART of at least 10 years (p=0.001 OR= 0, 2 (0.1 – 0.7)) were significantly associated with the existence of ventilatory abnormalities. Conclusion The high frequency of ventilatory anomalies in PLHIV independently of the existence of chronic respiratory signs leads us to propose spirometry in the follow-up assessment of PLHIV while paying particular attention to those on ARVs for more than 10 years.
Oct 2018 DOI 10.14302/issn.2379-7835.ijn-18-2228
Kishan Gupta BalCorresponding author
Senior Professor, In-charge Medical ICU, Department. of Medicine, S.P. Medical College, Bikaner.
Introduction: Organophosphate (OP) pesticide poisoning is a major challenging public-health problem in developing countries. Vitamin D deficiency is pandemic, yet it is the most under-diagnosed and under-treated nutritional deficiency in the world and it has been reported to be clinically correlated with psychiatric illness and manifestation of severe systemic inflammatory response syndrome like ARDS. Thus vitamin D deficiency may affect clinical course and outcome in cases of OPP. Aim: To evaluate status of 25 hydroxyvitamin D (25(OH)D) level in OP poisoning and its correlation with outcome of such patients. Materials and Methods: Serum 25(OH)D levels were measured at the time of hospitalization by electro-chemiluminescent Assay in 96 patients (76 male and 20 female) suffering from OP poisoning. Diagnosis of OP poisoning was made by history of poisoning including container of the poison brought by patient’s relative, clinical examination and measurement of serum butyrylcholinesterase activity. All patients were evaluated as per Performa and follow up till discharge. Results: Mean level of 25(OH)D in our cases was 24.57±9.91ng/ml and 66.7% had low levels of 25(OH)D. Our study shows linear relationship between 25(OH)D level and duration of hospital stay. All cases of OP poisoning who developed severe manifestations like ARDS, Intermediate syndrome (IMS) were having significant 25(OH)D deficiency. Our study also shows lower levels of 25(OH)D were associated with poor outcome (11.27±3.21vs 27.02±8.54, p<0.001). Conclusion: Vitamin D deficiency in OP poisoning is associated with longer hospital stay, more requirement of ventilator support and high prevalence of complication (ARDS and IMS) and poor outcome. Awareness of 25(OH)D level in patients with OP poisoning may be important to improve outcome.
Sep 2017 DOI 10.14302/issn.2642-9241.jrd-17-1683
Zeguang ZhengCorresponding author
First Affiliated Hospital of Guangzhou Medical University (State Key Laboratory of Respiratory Disease), Guangzhou Institute of Respiratory Disease, Guangzhou, Guangdong 510120, China
Objective Investigate the effect of connecting a waterproof device at the front end of the piezometric tube on pressure transmission and patient-machine synchronization during the noninvasive ventilation. Method In test 1, the waterproof device was connected to the piezometric tube and put into a closed container, the pressure inside the container was varied to observe the corresponding pressure change in the piezometric tube. In test 2, a waterproof device was connected in front of the piezometric tube during noninvasive ventilation.12 subjects were received noninvasive ventilator so that dynamic changes of the pressure inside the mask (Pmask) and piezometric tube (Ptube) could be measured. Results In test 1, when the pressure in the container was gradually increased to 50 cmH2O and then decreased to 0, the pressure inside the piezometric tube changed synchronously with the pressure inside the container, with no statistically significant difference between the pressures (0.009 ± 0.138) cmH2O. In test 2, there was no significant increase in triggering time, pressure, and power after connecting the waterproof device at the front end of the piezometric tube. There was no significant difference in the platform pressure and baseline pressure as measured by Pmask, before and after connecting the waterproof device. Finally, there was no significant difference in the platform pressure and baseline pressure between Pmask and Ptube after connecting the waterproof device.