Apnea Testing Practice to Increase Baseline PaCO2 and Frequency of Blood Gas Analyses.

OBJECTIVE: To study the influence of the initial partial pressure of carbon dioxide (PaCO2) and frequency of blood gas analyses on the positivity rate and safety of apnea testing (AT). DESIGN: A prospective multicenter cohort study. SETTING: Seven teaching hospitals. PARTICIPANTS: A total of 55 patients who underwent AT. INTERVENTIONS: Patients were divided into 2 groups according to their initial PaCO2-the experimental group (≥40 mmHg, 27 patients) and the control group (<40 mmHg, 28 patients). Blood gas analysis was performed at 3, 5, and 8 minutes, and vital signs were taken. AT results and complications were compared between the groups. RESULTS: The initial PaCO2 of the experimental group was 42.8 ± 2.2 mmHg v 36.4 ± 2.9 mmHg in the controls. The AT positivity rate was 100%. The experimental group needed less time to reach the target PaCO2 than the control group (4.07 ± 1.27 minutes v 5.68 ± 2.06 minutes; p = 0.001). Twenty-six patients (96.3%) in the experimental group reached the target PaCO2 in 5 minutes v 17 in the control group (60.7%) (p = 0.001). Seven patients (12.7%) were unable to complete 8-minute disconnection due to hypotension. The experimental group had a slightly lower incidence of hypotension than the control group, but there was no statistical difference (7.4% v 17.9%, p = 0.245). CONCLUSION: Increasing the baseline PaCO2 and doing more blood gas analyses can significantly shorten the time needed for AT and improve the AT positivity rate.

Cardiorespiratory monitoring with a wireless and nonadhesive belt measuring diaphragm activity in preterm and term infants: A multicenter non-inferiority study.

INTRODUCTION: We determined if the heart rate (HR) monitoring performance of a wireless and nonadhesive belt is non-inferior compared to standard electrocardiography (ECG). Secondary objective was to explore the belt's respiratory rate (RR) monitoring performance compared to chest impedance (CI). METHOD: In this multicenter non-inferiority trial, preterm and term infants were simultaneously monitored with the belt and conventional ECG/CI for 24 h. HR monitoring performance was estimated with the HR difference and ability to detect cardiac events compared to the ECG, and the incidence of HR-data loss per second. These estimations were statistically compared to prespecified margins to confirm equivalence/non-inferiority. Exploratory RR analyses estimated the RR trend difference and ability to detect apnea/tachypnea compared to CI, and the incidence of RR-data loss per second. RESULTS: Thirty-nine infants were included. HR monitoring with the belt was non-inferior to the ECG with a mean HR difference of 0.03 beats per minute (bpm) (standard error [SE] = 0.02) (95% limits of agreement [LoA]: [-5 to 5] bpm) (p < 0.001). Second, sensitivity and positive predictive value (PPV) for cardiac event detection were 94.0% (SE = 0.5%) and 92.6% (SE = 0.6%), respectively (p ≤ 0.001). Third, the incidence of HR-data loss was 2.1% (SE = 0.4%) per second (p < 0.05). The exploratory analyses of RR showed moderate trend agreement with a mean RR-difference of 3.7 breaths/min (SE = 0.8) (LoA: [-12 to 19] breaths/min), but low sensitivities and PPV's for apnea/tachypnea detection. The incidence of RR-data loss was 2.2% (SE = 0.4%) per second. CONCLUSION: The nonadhesive, wireless belt showed non-inferior HR monitoring and a moderate agreement in RR trend compared to ECG/CI. Future research on apnea/tachypnea detection is required.

Incidence of postoperative opioid-induced respiratory depression episodes in patients on room air or supplemental oxygen: a post-hoc analysis of the PRODIGY trial.

BACKGROUND: Supplemental oxygen (SO) potentiates opioid-induced respiratory depression (OIRD) in experiments on healthy volunteers. Our objective was to examine the relationship between SO and OIRD in patients on surgical units. METHODS: This post-hoc analysis utilized a portion of the observational PRediction of Opioid-induced respiratory Depression In patients monitored by capnoGraphY (PRODIGY) trial dataset (202 patients, two trial sites), which involved blinded continuous pulse oximetry and capnography monitoring of postsurgical patients on surgical units. OIRD incidence was determined for patients receiving room air (RA), intermittent SO, or continuous SO. Generalized estimating equation (GEE) models, with a Poisson distribution, a log-link function and time of exposure as offset, were used to compare the incidence of OIRD when patients were receiving SO vs RA. RESULTS: Within the analysis cohort, 74 patients were always on RA, 88 on intermittent and 40 on continuous SO. Compared with when on RA, when receiving SO patients had a higher risk for all OIRD episodes (incidence rate ratio [IRR] 2.7, 95% confidence interval [CI] 1.4-5.1), apnea episodes (IRR 2.8, 95% CI 1.5-5.2), and bradypnea episodes (IRR 3.0, 95% CI 1.2-7.9). Patients with high or intermediate PRODIGY scores had higher IRRs of OIRD episodes when receiving SO, compared with RA (IRR 4.5, 95% CI 2.2-9.6 and IRR 2.3, 95% CI 1.1-4.9, for high and intermediate scores, respectively). CONCLUSIONS: Despite oxygen desaturation events not differing between SO and RA, SO may clinically promote OIRD. Clinicians should be aware that postoperative patients receiving SO therapy remain at increased risk for apnea and bradypnea. TRIAL REGISTRATION: Clinicaltrials.gov: NCT02811302, registered June 23, 2016.

The effect of capnography on the incidence of hypoxia during sedation for EGD and colonoscopy in mildly obese patients: a randomized, controlled study.

BACKGROUND: By continually monitoring end-tidal carbon dioxide concentrations, capnography can detect abnormal ventilation or apnoea early. This randomized, controlled study explored the effect of early intervention with capnography on the incidence of hypoxia in mildly obese patients undergoing sedation for esophagogastroduodenoscopy (EGD) and colonoscopy. METHODS: This is a single-center, randomized, single-blind, parallel-assignment, controlled trial. Mildly obese patients (28 kg/m2 ≤ BMI < 40 kg/m2) undergoing sedation for EGD and colonoscopy were randomly assigned to either the standard or capnography group. Standard cardiopulmonary monitoring equipment was used in both groups, and additional capnography was performed in the capnography group. In the event of inadequate alveolar ventilation during sedation, five interventions were administered in sequence (a-e) : a: increasing oxygen flow (5 L/min); b: a chin lift or jaw thrust maneuver; c: placement of the nasopharyngeal airway and chin lift; d: mask positive-pressure ventilation, and e: ventilator-assisted ventilation with tube insertion. The primary outcome was the incidence of hypoxia (SpO2 < 90%, ≥ 10 s) in each group. The secondary outcomes included the incidence of severe hypoxia (SpO2 ≤ 85%), subclinical respiratory depression (90% ≤ SpO2 < 95%), interventions, minimum SpO2 during operation, patient satisfaction, endoscopist satisfaction, and other adverse events of anesthesia sedation. RESULTS: 228 patients were included (capnography group = 112; standard group = 113; three patients were excluded) in this study. The incidence of hypoxia was significantly lower in the capnography group than in the standard group (13.4% vs. 30.1%, P = 0.002). Subclinical respiratory depression in the capnography group was higher than that of the standard group (30.4% vs. 17.7%, P = 0.026). There was only a 5.4% incidence of severe hypoxia in the capnography group compared with 14.2% in the standard group (P = 0.026). During sedation, 96 and 34 individuals in the capnography and standard groups, respectively, underwent the intervention. There was a statistically significant difference (P < 0.0001) in the number of the last intraoperative intervention between the two groups ( a:47 vs. 1, b:46 vs. 26, c:2 vs. 5, d:1 vs. 2, e:0 vs. 0 ). No significant differences were found between the two groups in terms of minimum SpO2 during operation, patient satisfaction, or endoscopist satisfaction rating. There was no statistically significant difference in adverse events of anesthesia sedation between the two groups. CONCLUSION: Capnography during sedation for EGD and colonoscopy allows for the detection of apnea and altered breathing patterns in mildly obese patients before SpO2 is reduced. Effective intervention measures are given to patients within this time frame, which reduces the incidence of hypoxia and severe hypoxia in patients. TRIAL REGISTRATION: Ethical approval was granted by the Medical Ethics Committee (Chairperson Professor Tian Hui) of Qilu Hospital, Shandong University ((Ke) Lun Audit 2021 (186)) on 15/07/2021. The study was registered ( https://www.chictr.org.cn ) on 23/10/2021(ChiCTR2100052234). Designed and reported using CONSORT statements.

Effectiveness and safety of early versus late caffeine therapy in managing apnoea of prematurity among preterm infants: a retrospective cohort study.

BACKGROUND: Early administration of intravenous (IV) caffeine (initiation within 2 days of life) is an effective treatment strategy for the management of apnoea of prematurity among infants. However, the safety and effectiveness of early administration of oral caffeine treatment is not be fully established. AIM: We aimed to compare the effectiveness and safety of early versus late caffeine therapy on preterm infants' clinical outcomes. METHOD: A retrospective matched cohort study was conducted using data of patients admitted to neonatal intensive care units of two tertiary care hospitals between January 2016 and December 2018. The clinical outcomes and mortality risk between early caffeine (initiation within 2 days of life) and late caffeine (initiation ≥ 3 days of life) were compared. RESULTS: Ninety-five pairs matched based on gestational age were included in the study. Compared to late initiation, preterm infants with early caffeine therapy had: a shorter duration of non-invasive mechanical ventilation (median 5 days vs. 12 days; p < 0.001); shorter length of hospital stay (median 26 days vs. 44 days; p < 0.001); shorter duration to achieve full enteral feeding (median 5 days vs. 11 days; p < 0.001); and lower frequency of bronchopulmonary dysplasia (BPD) (4.5% vs. 12.9%; p = 0.045). They also had a reduced risk of osteopenia of prematurity (OP) (OR 0.209; 95% CI 0.085-0.509; p = 0.001). CONCLUSION: Early oral caffeine therapy can potentially improve respiratory outcomes among infants with apnoea of prematurity. However, an increase in mortality associated with early caffeine therapy requires further investigation.

The epidemiology of apnoea of prematurity.

WHAT IS KNOWN AND OBJECTIVE: Many premature infants less than 37 weeks gestational age (GA), and almost all infants less than 28 weeks GA, will experience apnoea of prematurity (AOP)-a cessation of respiration for 20 or more seconds (or less than 20 s if accompanied by other signs). Because the treatment options for AOP are so limited, we explore its epidemiology, with the ultimate hope of learning how to decrease its incidence. COMMENT: Although AOP usually resolves with maturation of the respiratory system, many short- and long-term negative effects are correlated statistically with AOP (although direct causality has not been established). The primary risk factor for AOP is preterm birth, but delivery technique, genetics, socioeconomic status, racial disparities and other influences are suspected to be involved. Anaemia, asthma and gastric reflux have also been associated with preterm birth, but the relationship with AOP is unclear. The postulated associations and the strength of the evidence are briefly reviewed and discussed. WHAT IS NEW AND CONCLUSION: Attempts to elucidate the epidemiology of apnoea of prematurity have been challenging. Studies of AOP are hampered in part by challenges in monitoring the condition, the interplay of multiple comorbidities in preterm neonates and lack of expert consensus definitions. However, since the primary risk factor is preterm birth, efforts to decrease the prevalence of preterm birth would have a positive secondary effect on the prevalence of AOP. Until then, better pharmacotherapeutic options are needed.

Achondroplasia is associated with increased occurrence of apparent life-threatening events.

AIM: To assess the clinical picture underlying apparent life-threatening events (ALTEs) occurring in infants with achondroplasia and provide guidance for evaluation after an event. METHODS: A population of 477 individuals with achondroplasia was retrospectively reviewed, and information regarding possible ALTEs was recorded in a REDCap database. RESULTS: ALTEs occurred in the first year of life in 18 of 477 individuals (3.8%). Most (14/18, 78%) occurred in the first 6 months of life and presented as episodes of apnoea and/or seizures. Of affected infants, 8/18 (44%) had more than one episode. Many of the initial ALTEs arose while infants were in car seats (11/18, 61%). Assessment following ALTEs most often demonstrated either craniocervical junction concerns and/or seizures, with 12/18 (67%) patients undergoing cervicomedullary decompression and 5/18 (28%) starting on anti-epileptic medications after the event. CONCLUSION: Although this study is limited in size and was retrospective, it shows that infants with achondroplasia appear to be at high risk for ALTEs. Evaluation after an event should include neuroimaging of the foramen magnum, inpatient hospital observation including respiratory monitoring and electroencephalography, and a car seat challenge.

Effect of positive end-expiratory pressure during anaesthesia induction on non-hypoxic apnoea time in infants: A randomised controlled trial.

BACKGROUND: Hypoxaemia occurs frequently in infants during anaesthetic induction. OBJECTIVE: We evaluated the effect of positive end-expiratory pressure during anaesthesia induction on nonhypoxic apnoea time in infants. DESIGN: Randomised controlled trial. SETTING: Tertiary care children's hospital, single centre, from November 2018 to October 2019. PATIENTS: We included patients under 1 year of age receiving general anaesthesia. INTERVENTION: We assigned infants to a 7 cmH2O or 0 cmH2O positive end-expiratory pressure group. Anaesthesia was induced with 0.02 mg kg-1 atropine, 5 mg kg-1 thiopental sodium and 3 to 5% sevoflurane, and neuromuscular blockade with 0.6 mg kg-1 rocuronium. Thereafter, 100% oxygen was provided via face mask with volume-controlled ventilation of 6 ml kg-1 tidal volume, and either 7 cmH2O or no positive end-expiratory pressure. After 3 min of ventilation, the infants' trachea was intubated but disconnected from the breathing circuit, and ventilation resumed when pulse oximetry reached 95%. MAIN OUTCOME MEASURE: The primary outcome was nonhypoxic apnoea time defined as the time from cessation of ventilation to a pulse oximeter reading of 95%, whereas the secondary outcome was the incidence of significant atelectasis (consolidation score ≥2) assessed by lung ultrasound. RESULTS: Sixty patients were included in the final analysis. Apnoea time in the 7 cmH2O positive end-expiratory pressure group (105.2 s) increased compared with that in the control group (92.1 s) (P = 0.011, mean difference 13.0 s, 95% CI, 3.1 to 22.9 s). Significant atelectasis was observed in all patients without positive end-expiratory pressure and 66.7% of those with 7 cmH2O positive end-expiratory pressure (P = 0.019, 95% CI, 1.7 to 563.1, odds ratio 31.2). CONCLUSION: Positive end-expiratory pressure during anaesthesia induction with face mask ventilation increased nonhypoxic apnoea time in infants. CLINICAL TRIAL REGISTRATION: www.clinicaltrials.gov, NCT03540940.

Use of spinal anaesthesia in neonates and infants in Antananarivo, Madagascar: a retrospective descriptive study.

OBJECTIVE: The aim of this study was to present the first cases of spinal anesthesia, in newborns and infants, preterm/ex-prematures, in order to determine its feasibility and its potential harmlessness, in Antananarivo-Madagascar. Indeed, spinal anesthesia is a low cost technique and can limit respiratory complications, postoperative apnea a contrario with pediatric general anesthesia which can lead to perioperative risks. RESULTS: In a retrospective, descriptive, 7-year (2013 to 2019) period study, conducted in the University Hospital Joseph Ravoahangy Andrianavalona, 69 patients' data files planned to have spinal anesthesia were recorded. These pediatric patients were predominantly male (sex ratio = 2.8) and 37 [28-52] days old. The smallest anesthetized child weighed 880 g; the youngest was 4 days old. Twenty-seven (27) of them were premature and 20.3% presented respiratory diseases. They were mostly scheduled for hernia repair (90%). Spinal anesthesia was performed, with a Gauge 25 Quincke spinal needle, after 2 [1-2] attempts with hyperbaric bupivacaine of 4 [3.5-4] mg. Failure rate was 5.8%. The heart rate was stable throughout perioperative period and no complications were observed.

Development: Epidemiology and management of postoperative apnoea in premature and term newborns.

Postoperative apnoea (PA) is defined as a respiratory pause of more than 15seconds or as a respiratory pause associated with bradycardia < 120/min, desaturation (Sat02<90%), cyanosis or hypotonia. This is a relatively frequent phenomenon that affects 10% of infants under 60 weeks of post-conceptual age, born prematurely or not, and occurs during the first 12-48h postoperatively. The population exposed to PA is heterogeneous and it is necessary to standardise the management both during the intra- and postoperative period, and to adapt this management according to the risk factors for PA and the status as prematurely born infants or not, based on recent data from the literature.

Apnea Testing Using Continuous Positive Airway Pressure When Determining Death by Neurologic Criteria in Children: Retrospective Analysis of Potential Adverse Events.

OBJECTIVES: To determine the prevalence of adverse events during apnea testing for determination of death by neurologic criteria using continuous positive airway pressure in children. DESIGN: Single-center retrospective descriptive study. SETTING: Academic children's hospital. PATIENTS: Children evaluated for death by neurologic criteria in the PICU from 2013 to 2018. INTERVENTIONS: None. MEASUREMENTS AND MAIN RESULTS: For each patient evaluated for death by neurologic criteria, we abstracted the number of apnea tests performed, vital signs and arterial blood gases during apnea testing, and outcome from the medical record. Adverse events were defined as oxygen-hemoglobin desaturation (arterial oxygen saturation < 85%), hypotension, or other significant event (e.g. arrhythmia, cardiac arrest) based on documentation in the medical record. We determined which adverse events resulted in early termination of the apnea test. We used oxygenation index, ventilator variables, and presence of vasopressors to determine preapnea test cardiopulmonary dysfunction. Seventy-two patients (age 7 yr [2.7-13.2 yr]; 48% male) underwent 121 apnea tests. Nine patients (12%) had 13 potential apnea tests deferred due to concern for cardiopulmonary instability as determined by the attending physician. Patients who underwent apnea testing had an oxygenation index of 3.5 (2.5-4.8) and were receiving vasopressors at the time of 108 apnea tests (89%). Hypotension was reported during seven apnea tests (6%) and resulted in the early termination of one apnea test (<1%). No other adverse events were reported. One hundred and twenty apnea tests (99%) were consistent with death by neurologic criteria. CONCLUSIONS: Apnea testing following a protocol that uses continuous positive airway pressure for apneic oxygenation has a low rate of adverse events in children meeting prerequisite criteria and determined by a pediatric intensivist to be physiologically appropriate for testing.

Overnight polysomnography and the recording of sleep and sleep-related respiration in orchestra musicians - possible protective effects of wind instruments on respiration.

Our study is the first to objectively assess sleep and sleep-related respiration in orchestra musicians. We hypothesized low sleep quality due to high work demands and irregular work-sleep schedules, and a better respiration for wind instrument (WI) players than string instrument (SI) players due to habitual upper airway muscles training. We recorded overnight polysomnography with 29 professional orchestra musicians (21 men, 14 WI/ 15 SI). The musicians presented a sleep efficiency of 88% (IQR 82-92%) with WI having a significant higher sleep efficiency than SI (89%, 85-93% vs. 85%, 74-89%; p = 0.029). The group had a total sleep time around 6 hours (377min, 340-421min) with signs of increased NREM 1 (light sleep) and decreased REM (dream sleep). The musicians displayed an apnea-hypopnea-index of 2.1events/hour (0.7-5.5) and an oxygen saturation of 98% (97-100%). While SI player exhibited declining sleep-related respiration with age (breathing events: r = 0.774, p = 0.001, oxygen: r = -0.647, p = 0.009), WI player showed improved respiration with age (breathing events: r = -0.548, p = 0.043; oxygen: r = 0.610, p = 0.020). Our study is the first objective investigation of sleep pattern and respiration during sleep with overnight polysomnography in professional orchestra musicians. While sleep and respiration were unexpectedly good, our results revealed possible signs of sleep deprivation and an interesting age-related pattern on respiration depending on instrument. While sample size was small and results modest, these findings present first objective evidence towards the assumption that habitual playing of a WI-and training of the upper airway muscles-may have a protective effect on respiration.

Perioperative apnea in infants with hypertrophic pyloric stenosis: A systematic review.

BACKGROUND: Infantile hypertrophic pyloric stenosis (IHPS) leads to excessive vomiting and metabolic alkalosis, which may subsequently cause apnea. Although it is generally assumed that metabolic derangements should be corrected prior to surgery to prevent apnea, the exact incidence of perioperative apneas in infants with IHPS and the association with metabolic alkalosis are unknown. We performed this systematic review to assess the incidence of apnea in infants with IHPS and to verify the possible association between apnea and metabolic alkalosis. METHODS: We searched MEDLINE, Embase, and Cochrane library to identify studies regarding infants with metabolic alkalosis, respiratory problems, and hypertrophic pyloric stenosis. We conducted a descriptive synthesis of the findings of the included studies. RESULTS: Thirteen studies were included for analysis. Six studies described preoperative apnea, three studies described postoperative apnea, and four studies described both. All studies were of low quality or had other research questions. We found an incidence of 27% of preoperative and 0.2%-16% of postoperative apnea, respectively. None of the studies examined the association between apnea and metabolic alkalosis in infants with IHPS. CONCLUSIONS: Infants with IHPS may have a risk to develop perioperative apnea. However, the incidence rates should be interpreted with caution because of the low quality and quantity of the studies. Therefore, further studies are required to determine the incidence of perioperative apnea in infants with IHPS. The precise underlying mechanism of apnea in these infants is still unknown, and the role of metabolic alkalosis should be further evaluated.

Recent Trends in Infant Car Seat Tolerance Screening Failure Within a Large Health Care System, 2014-2018.

OBJECTIVES: To describe temporal trends in car seat tolerance screening (CSTS) failure within a large hospital system (2014-2018). METHODS: We conducted a retrospective cohort study using electronic medical record data for infants who underwent a CSTS. Our primary outcome measure was the CSTS failure rate. Covariates included year, CSTS location (well nursery or NICU), gestational age (GA), race, sex, birth weight, CSTS date, and age at CSTS. Associations of covariates with CSTS failure were examined by using χ2 tests, t tests, analysis of variance, and Wilcoxon rank tests. Multivariable logistic regression was used to determine the adjusted odds of CSTS failure. RESULTS: Of 4849 infants tested, the failure rate was 8.1% (n = 394). Most CSTS occurred in the well nursery (79.5%) and involved late preterm (55.2%) or term infants (23.7%). In bivariate analyses, year, unit location, higher birth weight, younger chronological age at testing, and higher GA were positively associated with CSTS failure (P < .05). After stratification by CSTS location, the CSTS failure rate rose in the well nursery but remained stable in the NICU, and use of screening rose among term infants. In the adjusted model, year, GA, and corrected gestational age at CSTS were associated with failure. Each subsequent year was associated with a 19% increase in odds of CSTS failure (P < .001). CONCLUSIONS: We found a higher rate of CSTS failure in the well nursery compared with the NICU, and the difference in failure rates increased over time. Improved understanding of infants at the highest risk of CSTS failure could impact routine screening guidelines.

Optimizing neural networks for medical data sets: A case study on neonatal apnea prediction.

OBJECTIVE: The neonatal period of a child is considered the most crucial phase of its physical development and future health. As per the World Health Organization, India has the highest number of pre-term births [1], with over 3.5 million babies born prematurely, and up to 40% of them are babies with low birth weights, highly prone to a multitude of diseases such as Jaundice, Sepsis, Apnea, and other Metabolic disorders. Apnea is the primary concern for caretakers of neonates in intensive care units. The real-time medical data is known to be noisy and nonlinear and to address the resultant complexity in classification and prediction of diseases; there is a need for optimizing learning models to maximize predictive performance. Our study attempts to optimize neural network architectures to predict the occurrence of apneic episodes in neonates, after the first week of admission to Neonatal Intensive Care Unit (NICU). The primary contribution of this study is the formulation and description of a set of generic steps involved in selecting various model-specific, training and hyper-parametric optimization algorithms, as well as model architectures for optimal predictive performance on complex and noisy medical datasets. METHODS: The data used for the study being inherently complex and noisy, Kernel Principal Component Analysis (PCA) is used to reduce dataset dimensionality for the analysis such as interpretations and visualization of the dataset. Hyper-parametric and parametric optimization, in different categories, are considered, including learning rate updater algorithms, regularization methods, activation functions, gradient descent algorithms and depth of the network, based on their performance on the validation set, to obtain a holistically optimized neural network, that best model the given complex medical dataset. Deep Neural Network Architectures such as Deep Multilayer Perceptron's, Stacked Auto-encoders and Deep Belief Networks are employed to model the dataset, and their performance is compared to the optimized neural network obtained from the parametric exploration. Further, the results are compared with Support Vector Machine (SVM), K Nearest Neighbor, Decision Tree (DT) and Random Forest (RF) algorithms. RESULTS: The results indicate that the optimized eight layer Multilayer Perceptron (MLP) model, with Adam Decay and Stochastic Gradient Descent (AUC 0.82) can outperform the conventional machine learning models, and perform comparably to the Deep Auto-encoder model (AUC 0.83) in predicting the presence of apnea in neonates. CONCLUSION: The study shows that an MLP model can undergo significant improvements in predictive performance, by the proposed step-wise optimization. The optimized MLP is proved to be as accurate as deep neural network models such as Deep Belief Networks and Deep Auto-encoders for noisy and nonlinear data sets, and outperform all conventional models like Support Vector Machine (SVM), Decision Tree (DT), K Nearest Neighbor and Random Forest (RF) algorithms. The generic nature of the proposed step-wise optimization provides a framework to optimize neural networks on such complex nonlinear datasets. The investigated models can help neonatologists as a diagnostic tool.

Brief Resolved Unexplained Events: Analysis of an Apparent Life Threatening Event Database.

OBJECTIVE: To identify the proportion of patients previously diagnosed with apparent life-threatening events (ALTE) who would meet criteria for brief resolved unexplained events (BRUE) and to identify rates of adverse outcomes in subgroups: ALTE not meeting criteria for BRUE, lower-risk BRUE, and higher-risk ALTE. METHODS: We performed a secondary analysis of a single-center prospective registry of patients diagnosed with ALTE in a tertiary care emergency department from March 1, 1997 to October 31, 2007. We identified the proportion of patients meeting criteria for BRUE, and the proportion of patients with BRUE meeting lower-risk criteria. We assessed outcomes of patients in subgroups. RESULTS: Seven hundred and sixty-two patients were included. Adverse outcomes included recurrent ALTE (n = 49), aspiration (n = 9), trauma (n = 8), and death (n = 4). Three hundred and twenty-six of 762 (42.8%) met criteria for BRUE. Seventy of 326 (21.5%) met criteria for lower-risk BRUE. Adverse outcomes occurred in 40 of 436 (9.2%) with ALTE not meeting criteria for BRUE, 2 of 70 (2.9%) with lower-risk BRUE, and 23 of 256 (9.0%) with higher-risk BRUE. Of 4 patients who died, 1 had an ALTE not meeting criteria for BRUE and 3 had non-lower-risk BRUE. The BRUE risk criteria identified all BRUE patients that died or had substantial morbidity as higher-risk. CONCLUSIONS: Less than half of patients with ALTE meet criteria for BRUE. Of those who do, one-fifth is lower-risk. In this series, the risk-stratification in the BRUE criteria identified those patients at highest risk of adverse outcomes. Further research is required to risk-stratify patients with BRUE.

Protocols for early discharging of premature infants: an empirical assessment on safety and savings.

Background Preterm newborns may be discharged when clinical conditions are stable. Several criteria for early discharge have been proposed in the literature. This study carried out the first quantitative comparison of their impact in terms of hospitalization savings, safety and costs. Methods This study was based on the clinical histories of 213 premature infants born in the Neonatal Intensive Care Unit of Padova University Hospital between 2013 and 2014. Seventeen early discharge criteria were drawn from the literature and retrospectively applied to these data, and computation of hospitalization savings, safety and costs implied by each criterion was carried out. Results Among the criteria considered, average gains ranged from 1.1 to 10.3 hospital days and between 0.3 and 1.1 fewer infections per discharged infant. Criteria that led to saving more hospital days had higher cost-effectiveness in terms of crisis and infection, and they spared infants from more infections. However, episodes of apnea and bradycardia were detected after the potential early discharge date for all criteria, with a mean number of episodes numbering between 0.3 and 1.4. Conclusion The results highlight a clear trade-off between days saved and health risks for infants, with potential consequences for health care costs.