RESUMEN

Extubation represents an essential component of airway management. While being a common procedure in anesthesiology and critical care medicine, it is accompanied by a significant risk of morbidity and mortality. Safe extubation requires considerable skills, risk stratification and advanced planning. It is important to emphasize that intentional extubation is always an elective procedure, and as such should only be executed when conditions are optimal. The purpose of this review is to discuss the complications associated with planned extubation in the adult patient, including risk factors and management strategies, mainly focusing on the postoperative setting.

Asunto(s)

RESUMEN

BACKGROUND: Postoperative time to extubation plays a role in prognosis after heart valve surgery; however, its exact impact has not been clarified. This study compared the postoperative outcomes of minimally invasive surgery and conventional sternotomy, focusing on early extubation and factors influencing prolonged mechanical ventilation. METHODS: Data from 744 patients who underwent heart valve surgery at the Zhejiang Provincial People's Hospital between August 2019 and June 2022 were retrospectively analyzed. The outcomes in patients who underwent conventional median sternotomy (MS) and minimally invasive (MI) video-assisted thoracoscopic surgery were compared using inverse probability of treatment weighting (IPTW) and Kaplan-Meier curves. Clinical data, including surgical data, postoperative cardiac function, postoperative complications, and intensive care monitoring data, were analyzed. RESULTS: After propensity score matching and IPTW, 196 cases of conventional MS were compared with 196 cases of MI video-assisted thoracoscopic surgery. Compared to patients in the conventional MS group, those in the MI video-assisted thoracoscopic surgery group in the matched cohort had a higher early postoperative extubation rate (P < 0.01), reduced incidence of postoperative pleural effusion (P < 0.05), significantly shorter length of stay in the intensive care unit (P < 0.01), shorter overall length of hospital stay (P < 0.01), and lower total cost of hospitalization (P < 0.01). CONCLUSIONS: Successful early tracheal extubation is important for the intensive care management of patients after heart valve surgery. The advantages of MI video-assisted thoracoscopic surgery over conventional MS include significant reductions in the duration of use of mechanical ventilation support, reduced length of intensive care unit stay, reduced total length of hospitalization, and a favorable patient recovery rate.

Asunto(s)

RESUMEN

BACKGROUND: Post-extubation dysphagia (PED) emerges as a frequent complication following endotracheal intubation within the intensive care unit (ICU). PED has been strongly linked to adverse outcomes, including aspiration, pneumonia, malnutrition, heightened mortality rates, and prolonged hospitalization, resulting in escalated healthcare expenditures. Nevertheless, the reported incidence of PED varies substantially across the existing body of literature. Therefore, the principal objective of this review was to provide a comprehensive estimate of PED incidence in ICU patients undergoing orotracheal intubation. METHODS: We searched Embase, PubMed, Web of Science, Cochrane Library, China National Knowledge Infrastructure (CNKI), Wanfang Database, China Science, Technology Journal Database (VIP), and SinoMed databases from inception to August 2023. Two reviewers independently screened studies and extracted data. Subsequently, a random-effects model was employed for meta-statistical analysis utilizing the "meta prop" command within Stata SE version 15.0 to ascertain the incidence of PED. In addition, we performed subgroup analyses and meta-regression to elucidate potential sources of heterogeneity among the included studies. RESULTS: Of 4144 studies, 30 studies were included in this review. The overall pooled incidence of PED was 36% (95% confidence interval [CI] 29-44%). Subgroup analyses unveiled that the pooled incidence of PED, stratified by assessment time (≤ 3 h, 4-6 h, ≤ 24 h, and ≤ 48 h), was as follows: 31.0% (95% CI 8.0-59.0%), 28% (95% CI 22.0-35.0%), 41% (95% CI 33.0-49.0%), and 49.0% (95% CI 34.0-63.0%), respectively. When sample size was 100 < N ≤ 300, the PED incidence was more close to the overall PED incidence. Meta-regression analysis highlighted that sample size, assessment time and mean intubation time constituted the source of heterogeneity among the included studies. CONCLUSION: The incidence of PED was high among ICU patients who underwent orotracheal intubation. ICU professionals should raise awareness about PED. In the meantime, it is important to develop guidelines or consensus on the most appropriate PED assessment time and assessment tools to accurately assess the incidence of PED.

Asunto(s)

RESUMEN

OBJECTIVE: To compare the frequency of respiratory complications encountered in two different positions used for extubation i.e. conventional recovery position versus the modified recovery position (recovery position with 10-degree left tilt and head-down). STUDY DESIGN: Comparative study. Place and Duration of the Study: Department of Anaesthesia, Combine Military Hospital, Kohat, Pakistan, from April 2022 to March 2023. METHODOLOGY: Two hundred patients scheduled for elective nose and throat surgeries were equally divided into two groups (Group C and Group M). Patients with history of bronchial asthma, chronic obstructive pulmonary disease (COPD), recent respiratory infection, and gastro-oesophageal reflux disease (GERD) were excluded from this study. Patients with more than two intubation attempts were also excluded. Group C patients were extubated in a conventional left lateral recovery position, whereas Group M patients were extubated in a modified recovery position with patient in a left lateral position with 10-degree head-down and 10-degree left tilt. All patients were observed for persistent coughing (coughing that lasted for at least 2 minutes after extubation), breath holding for 20 seconds or more, desaturation (oxygen saturation less than 90%), laryngospasm, need for reintubation, vomiting, and regurgitation. RESULTS: Frequency of airway complications was significantly higher in Group C as compared to Group M. In Group C, 18 (18%) out of hundred patients had complications compared to 6 (6%) patients only in Group M (p = 0.009). CONCLUSION: Extubation in a modified recovery position is associated with reduced frequency of airway complications as compared to the conventional recovery position. KEY WORDS: Airway complications, Extubation, Cough, Laryngospasm, Recovery position.

Asunto(s)

RESUMEN

OBJECTIVES: We aimed to evaluate the ability of the parasternal intercostal (PIC) thickening fraction during spontaneous breathing trial (SBT) to predict the need for reintubation within 48 h after extubation in surgical patients with sepsis. METHODS: This prospective observational study included adult patients with sepsis who were mechanically ventilated and indicated for SBT. Ultrasound measurements of the PIC thickening fraction and diaphragmatic excursion (DE) were recorded 15 min after the start of the SBT. After extubation, the patients were followed up for 48 h for the need for reintubation. The study outcomes were the ability of the PIC thickening fraction (primary outcome) and DE to predict reintubation within 48 h of extubation using area under receiver characteristic curve (AUC) analysis. The accuracy of the model including the findings of right PIC thickening fraction and right DE was also assessed using the current study cut-off values. Multivariate analysis was performed to identify independent risk factors for reintubation. RESULTS: We analyzed data from 49 patients who underwent successful SBT, and 10/49 (20%) required reintubation. The AUCs (95% confidence interval [CI]) for the ability of right and left side PIC thickening fraction to predict reintubation were 0.97 (0.88-1.00) and 0.96 (0.86-1.00), respectively; at a cutoff value of 6.5-8.3%, the PIC thickening fraction had a negative predictive value of 100%. The AUCs for the PIC thickening fraction and DE were comparable; and both measures were independent risk factors for reintubation. The AUC (95% CI) of the model including the right PIC thickening fraction > 6.5% and right DE ≤ 18 mm to predict reintubation was 0.99 (0.92-1.00), with a positive predictive value of 100% when both sonographic findings are positive and negative predictive value of 100% when both sonographic findings are negative. CONCLUSIONS: Among surgical patients with sepsis, PIC thickening fraction evaluated during the SBT is an independent risk factor for reintubation. The PIC thickening fraction has an excellent predictive value for reintubation. A PIC thickening fraction of ≤ 6.5-8.3% can exclude reintubation, with a negative predictive value of 100%. Furthermore, a combination of high PIC and low DE can also indicate a high risk of reintubation. However, larger studies that include different populations are required to replicate our findings and validate the cutoff values.

Asunto(s)

RESUMEN

AIM: This study aims to evaluate the feasibility and clinical utility of measuring cough decibel level as predictive markers for extubation outcomes in mechanically ventilated patients. DESIGN: A prospective observational study. SETTING: Three interdisciplinary medical-surgical intensive care units across China. MAIN OUTCOME MEASURES: The primary outcomes assessed were extubation results in patients. Secondary measures included the cough decibel level, semiquantitative cough intensity scores, and white card test results recorded prior to extubation. RESULTS: A total of 71 patients were included, 55 patients were in the extubation success group and 16 in the failure group. The mean age was 78(71,83) years, mainly male (73.2 %). Despite the baseline characteristics being mostly consistent across both groups, significant differences were noted in duration of mechanical ventilation, and intensive care units and hospital stay. Remarkably, the cough decibel was substantially lower in the extubation failure group compared to the other group (78.69 ± 8.23 vs 92.28 ± 7.01 dB). The Receiver Operating Characteristic curve analysis revealed that a cough decibel below 85.77 dB is the optimal threshold for predicting extubation failure, exhibiting an 80 % sensitivity and 91.67 % specificity. CONCLUSION: The study corroborates that the cough decibel level serves as a quantifiable metric in patients undergoing mechanical ventilation. It posits that the likelihood of extubation failure escalates when the cough decibel falls below 85.77 dB. IMPLICATIONS FOR CLINICAL PRACTICE: Quantification of coughing capacity in decibels may be a good predictor of extubation outcome, thus offering assistance to healthcare professionals in evaluating the readiness of patients for extubation.

Asunto(s)

RESUMEN

Background and Objectives: Extubation success in ICU patients is crucial for reducing ventilator-associated complications, morbidity, and mortality. The Rapid Shallow Breathing Index (RSBI) is a widely used predictor for weaning from mechanical ventilation. This study aims to determine the predictive value of serial RSBI measurements on extubation success in ICU patients on mechanical ventilation. Materials and Methods: This prospective observational study was conducted on 86 ICU patients at Hitit University between February 2024 and July 2024. Patients were divided into successful and unsuccessful extubation groups. RSBI values were compared between these groups. Results: This study included 86 patients (32 females, 54 males) with a mean age of 54.51 ± 12.1 years. Extubation was successful in 53 patients and unsuccessful in 33. There was no significant difference in age and intubation duration between the groups (p = 0.246, p = 0.210). Significant differences were found in RSBI-1a and RSBI-2 values (p = 0.013, p = 0.011). The median RSBI-2a was 80 in the successful group and 92 in the unsuccessful group (p = 0.001). The ΔRSBI was higher in the unsuccessful group (p = 0.022). ROC analysis identified optimal cut-off values: RSBI-2a ≤ 72 (AUC 0.715) and ΔRSBI ≤ -3 (AUC 0.648). RSBI-2a ≤ 72 increased the likelihood of successful extubation by 10.8 times, while ΔRSBI ≤ -3 increased it by 3.4 times. Using both criteria together increased the likelihood by 28.48 times. Conclusions: Serial RSBI measurement can be an effective tool for predicting extubation success in patients on IMV. These findings suggest that serially measured RSBI may serve as a potential indicator for extubation readiness.

Asunto(s)

RESUMEN

BACKGROUND AND OBJECTIVES: Failed extubations are associated with pulmonary morbidity in hospitalized premature newborns. The objective of this study was to use quality improvement methodology to reduce failed extubations through practice standardization and integrating a real-time extubation success calculator into the electronic medical record (EMR). METHODS: A specific, measurable, achievable, relevant, and time-bound aim was developed to reduce failed extubations (defined as reintubation <5 days from primary extubation) by 50% among infants <32 weeks' gestational age (GA) or <1500 g birth weight by December 31, 2022. Plan-do-study-act cycles were developed to standardize postextubation respiratory support and integrate the EMR-based calculator. Outcome measures included extubation failure rates. Balancing measures included days on mechanical ventilation and number of patients intubated <3 days. Process measures were followed for guideline compliance. Statistical process control charts were used to track time-ordered data and detect special cause variation. RESULTS: We observed a reduction in failed extubations from 10.3% to 2.3%, with special cause variation noted after both plan-do-study-act cycle #1 and #2. Special cause variation was detected in both GA subgroups: <28 weeks' GA (22.0%-8.6%) and ≥28 weeks' GA (4.6%-0.3%). Additionally, the average number of infants intubated <3 days increased (60.2%-73.6%), whereas average ventilator days decreased (10.8-7.0). Finally, the time from infants' extubation score reaching threshold (≥60%) to extubation decreased (14.1-6.4 days) after launching the EMR-integrated calculator. CONCLUSIONS: Practice standardization and implementation of an EMR-based real-time clinical decision support tool improved extubation success, promoted earlier extubation, and reduced ventilator days in premature newborns.

Asunto(s)

RESUMEN

BACKGROUND: Surgical aortic valve replacement (SAVR) is an established therapy for severe calcific aortic stenosis. Enhanced recovery after cardiac surgery (ERACS) protocols have been shown to improve outcomes for elective cardiac procedures. The COVID-19 pandemic prompted early extubation post-elective surgeries to preserve critical care resources. AIM OF THIS STUDY: To investigate the effects of extubating patients within 6 h post-elective SAVR on hospital and ICU length of stay, mortality rates, ICU readmissions, and postoperative pneumonia. STUDY DESIGN AND METHODS: The retrospective analysis at the University Hospital Aachen, Germany, includes data from 2017 to 2022 and compares a total of 73 elective SAVR patients. Among these, 23 patients were extubated within 6 h (EXT group), while 50 patients remained intubated for over 6 h (INT group). RESULTS: The INT group experienced longer postoperative ventilation, needed more vasopressor support, had a higher incidence of postoperative pneumonia, and longer ICU length of stay. No significant differences were noted in overall hospital length of stay, mortality, or ICU readmission rates between the groups. CONCLUSION: This study demonstrates that early extubation in high-risk, multimorbid surgical aortic valve replacement patients is safe, and is associated with a reduction of pneumonia rates, and with shorter ICU and hospital length of stays, reinforcing the benefits of ERACS protocols, especially critical during the COVID-19 pandemic to optimize intensive care use.

Asunto(s)

Asunto(s)

RESUMEN

OBJECTIVE: Our study objective was to evaluate changes in ETT tube depth throughout the initial intubation course in very and extremely preterm infants in order to evaluate the risk of outgrowing an endotracheal tube (ETT). METHODS: This was a retrospective cohort study of preterm infants born at <32 weeks of gestation who were admitted to the NICU between 2012 and 2021 and required intubation for mechanical ventilation. Infants who were intubated only for surfactant administration and those with airway malformations were excluded. Descriptive statistics were used to define the range of ETT depths at the time of extubation, stratified by gestational age (<28 weeks vs 28-32 weeks of gestation). Relative ETT depth was defined as the final depth minus the initial depth. RESULTS: Out of 496 infants, 140 patients met all criteria for inclusion. Descriptive analysis of extubation depths across the populations demonstrated median relative ETT depth of 0 cm for the 28-32-week gestational age group, and -0.25 cm for the <28-week gestational age group. The 95th percentile for both gestational age groups was a relative depth of 0.5 cm and the 99th percentile was 1.0-1.5 cm. CONCLUSION: The results of our study suggest that the vast majority of patients in the NICU are unlikely to "outgrow" ETT tube length which should be taken into account when deciding where to trim the ETT in order to minimize airway resistance.

Asunto(s)

RESUMEN

Background and Purpose: Patients who have been intubated ≥48 hours are at risk of dysphagia. Evaluation of swallowing before starting oral feeding after extubation is necessary to prevent aspiration and the problems caused by aspiration. The Postextubation Dysphagia Screening tool is a validated and reliable tool used to evaluate extubation-induced dysphagia. This study was conducted to evaluate the validity and reliability of the Postextubation Dysphagia Screening Tool for the Turkish population. Methods: The study had a methodological design and was carried out with 50 patients followed in the intensive care unit of a public hospital. The study was carried out in four stages: (1) language validity, (2) content validity, (3) establishing interrater reliability by agreement with two observers (intensive care nurse and intensivist), and (4) establishing sensitivity and specificity with the intensive care nurse and intensivist. Results: The overall content validity index was 0.91, indicating content validity. Interrater reliability was established (Cohen's g = 0.93). The prevalence of postextubation dysphagia was 42%, and the sensitivity of the Postextubation Dysphagia Screening Tool was 82% and the specificity was 64%. Implications for Practice: The Turkish version of the Postextubation Dysphagia Screening Tool exhibited good evidence of validity and reliability and was determined important as it can help nurses evaluate postextubation dysphagia in intensive care patients. The use of this tool by a nurse reduces the risk of unsafe oral intake among patients after prolonged intubation. This tool allows accurate assessment of dysphagia and initiation of early and safe oral feeding in critical care patients.

Asunto(s)

RESUMEN

This study investigated whether the large language model (LLM) utilizes sufficient domain knowledge to reason about critical medical events such as extubation. In detail, we tested whether the LLM accurately comprehends given tabular data and variable importance and whether it can be used in complement to existing ML models such as XGBoost.

Asunto(s)

RESUMEN

BACKGROUND: Preterm infants often require non-invasive breathing support while their lungs and control of respiration are still developing. Non-invasive neurally adjusted ventilatory assist (NIV-NAVA) is an emerging technology that allows infants to breathe spontaneously while receiving support breaths proportional to their effort. This study describes the first Australian Neonatal Intensive Care Unit (NICU) experience of NIV-NAVA. METHODS: Retrospective cohort study of infants admitted to a major tertiary NICU between October 2017 and April 2021 supported with NIV-NAVA. Infants were divided into three groups based on the indication to initiate NIV-NAVA (post-extubation; apnoea; escalation). Successful application of NIV-NAVA was based on the need for re-intubation within 48 h of application. RESULTS: There were 169 NIV-NAVA episodes in 122 infants (82 post-extubation; 21 apnoea; 66 escalation). The median (range) gestational age at birth was 25 + 5 weeks (23 + 1 to 43 + 3 weeks) and median (range) birthweight was 963 g (365-4320 g). At NIV-NAVA application, mean (SD) age was 17 days (18.2), and median (range) weight was 850 g (501-4310 g). Infants did not require intubation within 48 h in 145/169 (85.2%) episodes [72/82 (87.8%) extubation; 21/21 (100%) apnoea; 52/66 (78.8%) escalation). CONCLUSION: NIV-NAVA was successfully integrated for the three main indications (escalation; post-extubation; apnoea). Prospective clinical trials are still required to establish its effectiveness versus other modes of non-invasive support.

Asunto(s)

RESUMEN

BACKGROUND: The ratio (E/Ea) of mitral Doppler inflow velocity to annular tissue Doppler wave velocity by transthoracic echocardiography and diaphragmatic excursion (DE) by diaphragm ultrasound have been confirmed to predict extubation outcomes. However, few studies focused on the predicting value of E/Ea and DE at different positions during a spontaneous breathing trial (SBT), as well as the effects of △E/Ea and △DE (changes in E/Ea and DE during a SBT). METHODS: This study was a reanalysis of the data of 60 difficult-to-wean patients in a previous study published in 2017. All eligible participants were organized into respiratory failure (RF) group and extubation success (ES) group within 48 h after extubation, or re-intubation (RI) group and non-intubation (NI) group within 1 week after extubation. The risk factors for respiratory failure and re-intubation including E/Ea and △E/Ea, DE and △DE at different positions were analyzed by multivariate logistic regression, respectively. The receiver operating characteristic (ROC) curves of E/Ea (septal, lateral, average) and DE (right, left, average) were compared with each other, respectively. RESULTS: Of the 60 patients, 29 cases developed respiratory failure within 48 h, and 14 of those cases required re-intubation within 1 week. Multivariate logistic regression showed that E/Ea were all associated with respiratory failure, while only DE (right) and DE (average) after SBT were related to re-intubation. There were no statistic differences among the ROC curves of E/Ea at different positions, nor between the ROC curves of DE. No statistical differences were shown in △E/Ea between RF and ES groups, while △DE (average) was remarkably higher in NI group than that in RI group. However, multivariate logistic regression analysis showed that △DE (average) was not associated with re-intubation. CONCLUSIONS: E/Ea at different positions during a SBT could predict postextubation respiratory failure with no statistical differences among them. Likewise, only DE (right) and DE (average) after SBT might predict re-intubation with no statistical differences between each other.

Asunto(s)

RESUMEN

Major head and neck surgery poses a threat to perioperative airway patency. Adverse airway events are associated with significant morbidity, potentially leading to hypoxic brain injury and even death. Following a review of the literature, recommendations regarding airway management in head and neck surgery were developed with multicenter, multidisciplinary agreement among all Irish head and neck units. Immediate extubation is appropriate in many cases where there is a low risk of adverse airway events. Where a prolonged definitive airway is required, elective tracheostomy provides increased airway security postoperatively while delayed extubation may be appropriate in select cases to reduce postoperative morbidity. Local institutional protocols should be developed to care for a tracheostomy once inserted. We provide guidance on decision making surrounding airway management at time of head and neck surgery. All decisions should be agreed between the operating, anesthetic, and critical care teams.

Asunto(s)

RESUMEN

OBJECTIVE: To compare the analgesic and sleep quality effects of dexmedetomidine infusion versus placebo in patients undergoing cardiac surgery with ultra-fast track extubation. DESIGN: The randomized, double-blind clinical trial study. SETTING: At a single academic center hospital. PARTICIPANTS: We included patients aged 25 to 65 scheduled for elective cardiac surgery under general anesthesia with cardiopulmonary bypass from October 2021 to December 2022. INTERVENTION: After immediate extubation in the operating room, the patients who were allocated at first after providing their consent to either the dexmedetomidine group (Dex) or the placebo group (Placebo) received continuous infusion of dexmedetomidine (0.2 µg/kg/h) or saline for 12 hours postoperatively. MEASUREMENTS AND MAIN RESULTS: The groups' demographic and perioperative variables were not statistically significant. Total morphine consumption in milligrams at 12 and 24 hours after administered study drug, total sleep time in hours by BIS value ≤85, and sleep quality with the Richard-Campbell Sleep Questionnaire were compared. The analysis included 22 Dex and 23 Placebo patients. The consumption of morphine was not statistically different between the Dex and Placebo groups at 12 and 24 hours (p = 0.707 and p = 0.502, respectively). The Dex group had significantly longer sleep time (8.7 h [7.8, 9.5]) than the Placebo group (5.8 h [2.9, 8.5]; p = 0.007). The Dex group also exhibited better sleep quality (7.9 [6.7, 8.7] vs 6.6 [5.2, 8.0]; p = 0.038). CONCLUSIONS: Sedation with low-dose dexmedetomidine infusion for ultra-fast track extubation following cardiac surgery enhances sleep duration and quality.

Asunto(s)

RESUMEN

Despite advances in weaning protocols, extubation failure (EF) is associated with poor outcomes. Many predictors of EF have been proposed, including hypercapnia at the end of the spontaneous breathing test (SBT). However, performing arterial blood gases at the end of SBT is not routinely recommended, whereas end-tidal carbon dioxide (EtCO2) can be routinely monitored during SBT. We aimed to evaluate the clinical utility of EtCO2 to predict EF. Patients undergoing planned extubation were eligible. Non-inclusion criteria were tracheostomy and patients extubated after successful T-tube SBT. We recorded clinical data and EtCO2 in 189 patients during a successful one-hour low pressure support SBT. EtCO2 measured before successful SBT was lower in patients with EF compared to those with successful extubation (27 [24-29] vs 30 [27-47] mmHg, p = 0.02), while EtCO2 measured at five minutes and at the end of the SBT was not different between the two groups (26 [22-28] vs. 29 [28-49] mmHg, p = 0.06 and 26 [26-29] vs. 29 [27-49] mmHg, p = 0.09, respectively). Variables identified by multivariable analysis as independently associated with EF were acute respiratory failure as the cause of intubation and ineffective cough. Our study suggests that recording EtCO2 during successful SBT appears to have limited predictive value for EF.

Asunto(s)

RESUMEN

PURPOSE: To report two-year survival after scheduled extubation in patients with pneumonia or acute respiratory distress syndrome (ARDS). METHODS: This was a prospective observational study performed in a respiratory ICU of a teaching hospital. Pneumonia or ARDS patients who successfully completed a spontaneous breathing trial were enrolled. Data were collected before extubation. Patients were followed up to two years by phone every 3 months. RESULTS: A total of 230 patients were enrolled in final analysis. One-, 3-, 6-, 12-, and 24-month survival was 77.4%, 63.8%, 61.3%, 57.8%, and 47.8%, respectively. Cox regression shows that Charlson comorbidity index (hazard ratio: 1.20, 95% confidence interval: 1.10-1.32), APACHE II score before extubation (1.11, 1.05-1.17), cough peak flow before extubation (0.993, 0.986-0.999), and extubation failure (3.96, 2.51-6.24) were associated with two-year mortality. To predict death within two years, the area under the curve of receiver operating characteristic was 0.79 tested by Charlson comorbidity index, 0.75 tested by APACHE II score, and 0.75 tested by cough peak flow. Two-year survival was 31% and 77% in patients with Charlson comorbidity index ≥ 1 and < 1, 28% and 62% in patients with APACHE II score ≥ 12 and < 12, and 64% and 17% in patients with cough peak flow > 58 and ≤ 58 L/min, respectively. CONCLUSIONS: Comorbidity, disease severity, weak cough and extubation failure were associated with increased two-year mortality in pneumonia or ARDS patients who experienced scheduled extubation. It provides objective information to caregivers to improve decision-making process during hospitalization and post discharge.

Asunto(s)

RESUMEN

AIM: To develop a decision-support tool for predicting extubation failure (EF) in neonates with bronchopulmonary dysplasia (BPD) using a set of machine-learning algorithms. METHODS: A dataset of 284 BPD neonates on mechanical ventilation was used to develop predictive models via machine-learning algorithms, including extreme gradient boosting (XGBoost), random forest, support vector machine, naïve Bayes, logistic regression, and k-nearest neighbor. The top three models were assessed by the area under the receiver operating characteristic curve (AUC), and their performance was tested by decision curve analysis (DCA). Confusion matrix was used to show the high performance of the best model. The importance matrix plot and SHapley Additive exPlanations values were calculated to evaluate the feature importance and visualize the results. The nomogram and clinical impact curves were used to validate the final model. RESULTS: According to the AUC values and DCA results, the XGboost model performed best (AUC = 0.873, sensitivity = 0.896, specificity = 0.838). The nomogram and clinical impact curve verified that the XGBoost model possessed a significant predictive value. The following were predictive factors for EF: pO2, hemoglobin, mechanical ventilation (MV) rate, pH, Apgar score at 5 min, FiO2, C-reactive protein, Apgar score at 1 min, red blood cell count, PIP, gestational age, highest FiO2 at the first 24 h, heart rate, birth weight, pCO2. Further, pO2, hemoglobin, and MV rate were the three most important factors for predicting EF. CONCLUSIONS: The present study indicated that the XGBoost model was significant in predicting EF in BPD neonates with mechanical ventilation, which is helpful in determining the right extubation time among neonates with BPD to reduce the occurrence of complications.

Asunto(s)