Prediction model for death in patients with pulmonary tuberculosis accompanied by respiratory failure in ICU: retrospective study

Liu, Qiuyue; Gao, Jingtao; Luo, Bin; Liu, Junting; Zhang, Lin; Kang, Wanli; Han, Fang

doi:10.21037/apm-20-182

Cited by 3 publications

(8 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The in-hospital mortality rate in the present study was 47.75% (53 out of 111), which is consistent to those previously reported (26–59%) though mechanical ventilated patients was markedly greater than 90% [6] , [9] , [22] , [23] , [24] . These variety rate were associated with clinical characteristics baseline, progressivity and respiratory support.…”

Section: Discussionsupporting

confidence: 93%

In-hospital mortality of pulmonary tuberculosis with acute respiratory failure and related clinical risk factors

Elhidsi

Rasmin

Prasenohadi

2021

Journal of Clinical Tuberculosis and Other Mycobacterial Diseas

View full text Add to dashboard Cite

Background/objective Data on acute respiratory failure (ARF) in pulmonary tuberculosis (PTB) patients is limited. This study aims to investigate in-hospital mortality, its clinical risk factors and the accuracy of the existing scoring system in predicting in-hospital mortality. Methods An observational prospective cohort study involving PTB patients with ARF in tertiary hospital, between January 2017 and December 2018, was conducted. The in-hospital mortality was predicted using the National Early Warning Score 2 (NEWS2), quick Sequential Organ Failure Assessment (qSOFA) and CRB-65. Regression models were run to analyze the clinical risk factors for in-hospital Mortality. Sensitivity and specificity of scoring systems were calculated using a Wilson score interval. Results A total of 111 subjects were included. Most of subjects were hypoxemic type respiratory failure (68.5%), advanced lesions (62.2%), new cases (70.3%) and pneumonia co-infection (72.1%) patients. Invasive mechanical ventilation was utilized for 29.73% of cases. There were 53 (47.75%) in-hospital mortality cases and its risk factors were intensive phase treatment (3.34 OR; CI95% 1.27–8.78), P/F ratio < 100 (OR 4.30; CI 95% 1.75–10.59) and renal insufficiency (4.09 OR; CI95% 1.46–11.49). The sensitivity and specificity of NEWS2 ≥ 6, qSOFA ≥ 2 and CRB-65 ≥ 2 were 62.26% and 67.24%; 60.38% and 72.41%; 41.51% and 84.48% respectively. Conclusions Most of PTB with ARF were new cases, advanced lesion and hypoxemic type respiratory failure. Intensive phase treatment, severe hypoxemia and renal insufficiency are independent predictors of in-hospital mortality in PTB patients with ARF. NEWS2, qSOFA and CRB-65 scores were poor to predict the in-hospital mortality.

show abstract

Section: Discussionsupporting

confidence: 93%

In-hospital mortality of pulmonary tuberculosis with acute respiratory failure and related clinical risk factors

Elhidsi

Rasmin

Prasenohadi

2021

Journal of Clinical Tuberculosis and Other Mycobacterial Diseas

View full text Add to dashboard Cite

show abstract

“…Due to the COVID-19 pandemic, there was a great growth of publications focused on machine learning models for predicting ICU mortality in a disease-specific manner, such as those by Pan et al [ 16 ], Lichtner et al [ 26 ], and Subudhi et al [ 27 ]. Meanwhile, many of the previous studies in this field also focus on predicting ICU outcomes for specific diseases or morbid conditions, like sepsis or death from pulmonary tuberculosis[ 11 , 13 , 28 ], which lead to an assessment of parameters specific for the disease studied, somewhat restricting the research. Many of the renowned models and scales for ICU mortality prediction demand a series of measurements to make their use possible, but not always all the data required are available.…”

Section: Discussionmentioning

confidence: 99%

“…The use of machine learning has been consolidated as an alternative for the development of predictive models of mortality in the critical care setting. An example is the retrospective study by Liu et al [ 11 ], who developed a logistic model of the death risk grade in patients with pulmonary tuberculosis using data from patients admitted to ICUs in three hospitals. In this multivariate analysis study, where the sensitivity was 83.3% and specificity was 73.1%, the Apache II score, C-reactive protein levels, albumin levels, and pressure of oxygen in arterial blood (PaO 2 ) were considered the main factors influencing the outcome.…”

Section: Introductionmentioning

confidence: 99%

Prediction of hospital mortality in intensive care unit patients from clinical and laboratory data: A machine learning approach

Silveira¹,

Pretti²,

Santos³

et al. 2022

WJCCM

View full text Add to dashboard Cite

BACKGROUND Intensive care unit (ICU) patients demand continuous monitoring of several clinical and laboratory parameters that directly influence their medical progress and the staff’s decision-making. Those data are vital in the assistance of these patients, being already used by several scoring systems. In this context, machine learning approaches have been used for medical predictions based on clinical data, which includes patient outcomes. AIM To develop a binary classifier for the outcome of death in ICU patients based on clinical and laboratory parameters, a set formed by 1087 instances and 50 variables from ICU patients admitted to the emergency department was obtained in the “WiDS (Women in Data Science) Datathon 2020: ICU Mortality Prediction” dataset. METHODS For categorical variables, frequencies and risk ratios were calculated. Numerical variables were computed as means and standard deviations and Mann-Whitney U tests were performed. We then divided the data into a training (80%) and test (20%) set. The training set was used to train a predictive model based on the Random Forest algorithm and the test set was used to evaluate the predictive effectiveness of the model. RESULTS A statistically significant association was identified between need for intubation, as well predominant systemic cardiovascular involvement, and hospital death. A number of the numerical variables analyzed (for instance Glasgow Coma Score punctuations, mean arterial pressure, temperature, pH, and lactate, creatinine, albumin and bilirubin values) were also significantly associated with death outcome. The proposed binary Random Forest classifier obtained on the test set ( n = 218) had an accuracy of 80.28%, sensitivity of 81.82%, specificity of 79.43%, positive predictive value of 73.26%, negative predictive value of 84.85%, F1 score of 0.74, and area under the curve score of 0.85. The predictive variables of the greatest importance were the maximum and minimum lactate values, adding up to a predictive importance of 15.54%. CONCLUSION We demonstrated the efficacy of a Random Forest machine learning algorithm for handling clinical and laboratory data from patients under intensive monitoring. Therefore, we endorse the emerging notion that machine learning has great potential to provide us support to critically question existing methodologies, allowing improvements that reduce mortality.

show abstract

“…Information regarding positivity rate for acidfast bacilli was available in ten studies. The average acid-fast bacilli smear positivity rate was 89.05% (n = 366/411) (6,14,(16)(17)(18)(19)(20). All the studies had included patients with active tuberculosis only.…”

Section: Description Of Included Studiesmentioning

confidence: 99%

“…A statistically significant difference was observed between groups with higher CRP levels among nonsurvivors (I 2 = 84%; p = 0.006; MD = -35.58 [-61.21 to -9.96]). Five studies compared the requirement for renal replacement therapy (8,(16)(17)(18)22). The requirement for renal replacement therapy was significantly higher in nonsurvivors (I 2 = 72%; p = 0.01; OR = 0.18 [0.05-0.67).…”

Section: Factors Affecting Outcomementioning

confidence: 99%

Factors Affecting Mortality in Critically Ill Patients With Tuberculosis: A Systematic Review and Meta-Analysis

Mishra,

Gala,

Chacko

2024

Critical Care Medicine

View full text Add to dashboard Cite

Objectives: Critically ill patients with tuberculosis carry high mortality. Identification of factors associated with mortality in critically ill tuberculosis patients may enable focused treatment. Data Sources: An extensive literature search of PubMed (MEDLINE), Embase, the Cochrane Library, and Google Scholar was performed using Medical Subject Headings terms “tuberculosis,” “critical care,” “critical care outcome,” and “ICU.” We aimed to identify factors affecting mortality in critically ill tuberculosis patients. Study Selection: All the studies comparing factors affecting mortality between survivors and nonsurvivors in critically ill tuberculosis patients were included. The database search yielded a total of 3017 records, of which 17 studies were included in the meta-analysis. Data Extraction: Data were collected including the name of the author, year and country of publication, duration of the study, number of patients studied, type of tuberculosis, patient demography, smoking history, laboratory parameters, comorbidities, the requirement for mechanical ventilation, duration of ventilation, ICU and hospital length of stay (LOS), type of lung involvement, complications, and outcomes. Data Synthesis: The major factors that contributed to mortality in critically ill tuberculosis patients were age, platelet count, albumin, C-reactive protein (CRP), the requirement and duration of invasive mechanical ventilation, Pao 2/Fio 2 ratio, presence of acute respiratory distress syndrome, shock, hospital-acquired infections, renal replacement therapy, and ICU and hospital LOS. Conclusions: Patient age, platelet count, albumin and CRP levels, the requirement and duration of invasive mechanical ventilation, Pao 2/Fio 2 ratio, hospital-acquired infections, renal replacement therapy, and ICU LOS were variables associated with mortality.

show abstract

Prediction model for death in patients with pulmonary tuberculosis accompanied by respiratory failure in ICU: retrospective study

Cited by 3 publications

References 29 publications

In-hospital mortality of pulmonary tuberculosis with acute respiratory failure and related clinical risk factors

In-hospital mortality of pulmonary tuberculosis with acute respiratory failure and related clinical risk factors

Prediction of hospital mortality in intensive care unit patients from clinical and laboratory data: A machine learning approach

Factors Affecting Mortality in Critically Ill Patients With Tuberculosis: A Systematic Review and Meta-Analysis

Contact Info

Product

Resources

About