ABSTRACT Background Sepsis is a life-threatening condition triggered by infection and associated with dysregulated immune response of the patient followed often by multiorgan dysfunction or failure. In the clinical evolution of sepsis towards organ dysfunction, early initiation of a suited therapy significantly increases patient outcomes and reduces mortality rates. Since electronic health records provide data in a machine-readable format, this process could be supported by computerized systems. Methods We developed an interoperable, time-sensitive CDSS that able to detect systemic inflammation and the different classifications of sepsis (bacterial/viral, suspected/proven, on admission/PICU acquired) in pediatric patients based on the analysis of routine clinical data. This application is provided as part of this publication as an open demonstrator (web application), and the usability and accuracy of the CDSS is shown by a retrospective creation of sepsis outcome labels for a routine data set of 4,655 pediatric patients. As a reference standard, the patients were manually assessed by blinded clinical experts. Results In comparison with the reference standard, the CDSS achieved sensitivity of 96.9% (95% CI: 80.9-99.6%) and specificity of 99.1% (95% CI: 95.1-99.8%). In the context of a sepsis outcome labeling for 4,655 patients, the CDSS detected 4,342 episodes of inflammation of which 1,723 were classified as sepsis. Conclusions We demonstrated that our routine-data based CDSS is able to perform a complex sepsis detection process with high diagnostic accuracy. Such CDSS with the ability to differentiate between SIRS, sepsis on admission, suspected and proven sepsis can prospectively support clinical management, monitoring and quality management.

Background:Infant lung transplantation (LuTx) has been rarely performed in Europe and poses unique challenges. Methods:We reviewed referrals for LuTx to our center for patients below 1 year of age from January 1, 2018 to December 31, 2022. Clinical data and outcomes of transplanted infants and data on patients who were declined for evaluation, not listed after evaluation, or died before LuTx were collected. The number of donor lungs from organ donors younger than 1 year of age offered to our center and their utilization were analyzed for the same time period. Results:A total of 18 referrals were analyzed. Ten referrals were declined; 2 had contraindications to transplant and 2 infants died after full evaluation. A total of 4 infants (median age 185 days, range 85-225; mean weight 6063 g, standard deviation [SD] ±438 g) underwent bilateral LuTx after a mean waiting time of 52, SD ±43 days. Underlying diseases included surfactant protein deficiencies (n = 3) and lung hypoplasia with pulmonary hypertension due to congenital diaphragmatic hernia (n = 1). Patients required oxygen supplementation (n = 1), noninvasive (n = 1), or invasive (n = 2) ventilation pre-LuTx. ABO blood group incompatible LuTx was performed in 2 patients. After a mean follow-up of 37, SD ±20 months, all patients are alive. Of 13 infant donor lungs offered to our center, 10 (76.9%) were declined due to the lack of a suitable recipient. Two of 3 infant donor lungs were transplanted to infants, 1 was transplanted to a 23-month-old recipient. The other 2 infants received lungs from donors aged over 12 months. Conclusions:Our longitudinal analysis highlights the high pre-LuTx morbidity of infants with respiratory failure and challenges associated with timely evaluation and listing. Nevertheless, infant LuTx shows promising results in selected candidates, including ABO blood group incompatible transplantations.

BACKGROUND:Acute kidney injury (AKI) is common in children with congenital heart disease following open-heart surgery with cardiopulmonary bypass (CPB). Early AKI detection in critically ill children requires clinician expertise to compile various data from different sources within a stressful and time-sensitive environment. However, as electronic health records provide data in a machine-readable format, this process could be supported by computerized systems. Therefore, we developed a time-aware, rule-based clinical decision support system (CDSS) to detect, stage, and track temporal AKI progression in children. METHODS:We integrated retrospective clinical routine data from n = 290 randomly selected cases (n = 263 patients, aged 0-17 years) who underwent cardiac surgery with CPB into a dataset. We adapted Kidney Disease: Improving Global Outcome (KDIGO) criteria, including serum creatinine, urine output, and estimated glomerular filtration rate, and translated them into computable rules for the CDSS. As a reference standard, patients were manually assessed by blinded clinical experts. RESULTS:The AKI incidence, according to the reference standard, was n = 146 cases for stage 1, n = 58 for stage 2, and n = 20 for stage 3. The CDSS achieved sensitivities of 92.2 % (95 % CI: 86.8-95.5 %) for AKI stage 1, 88.1 % (95 % CI: 77.2-94.2 %) for stage 2, and 95 % (95 % CI: 70.5-99.3 %) for stage 3. The specificities were 97.0 % (95 % CI: 94.4-98.4 %), 98.5 % (95 % CI: 96.5-99.4 %), and 99.3 % (95 % CI: 97.3-99.8 %), respectively. CONCLUSIONS:We demonstrated that a CDSS is able to perform a complex AKI detection and staging process, including 11 criteria across three stages. For accurate automated AKI detection, standardized machine-readable data of high data quality are required. CDSS with high diagnostic accuracy, like presented, can support clinical management and be used for surveillance and quality management. The prototypical use for surveillance and further studies, such as the development of prediction models, should demonstrate the system's benefits in the future.

Fairness in terms of various sensitive or protected attributes such as race, gender, age group, etc. has been a subject of great importance in the healthcare domain. Group fairness is considered as one of the principal criteria. However, most of the prevailing mitigation techniques emphasize on tuning the training algorithms while overlooking the fact that the training data may possibly be the primary reason for the biased outcomes. In this work, we address two sensitive attributes (age group and gender) with empirical evaluations of systemic inflammatory response syndrome (SIRS) classification for a dataset extracted from electronic health records (EHRs) for the essential task of improving equity in outcomes. Machine learning (ML)-based technologies are progressively becoming prevalent in hospitals; therefore, our approach carries out a demand for the frameworks to consider performance trade-offs regarding sensitive patient attributes combined with model training and permit organizations to utilize their ML resources in manners that are aware of potential fairness and equity issues. With the intended purpose of fairness, we experiment with a number of strategies to reduce disparities in algorithmic performance with respect to gender and age group. We leverage a sample and label balancing technique using weighted loss along with adversarial learning for an observational cohort derived from EHRs to introduce a “fair” SIRS classification model with minimized discrepancy in error rates over different groups. We experimentally illustrate that our strategy has the ability to align the distribution of SIRS classification outcomes for the models constructed from high-dimensional EHR data across a number of groups simultaneously.

Background: Acute kidney injury (AKI) is a frequent complication in children with congenital heart disease following open-heart surgery. In intensive care units, detecting AKI requires expertise of clinicians who have to compile data from various sources within a critical and time-sensitive setting. However, as electronic health records provide data in a machine-readable format, this process could be executed through computerized systems to support physicians. Therefore, we developed a time-aware, rule-based clinical decision support system (CDSS) to detect, stage, and track the temporal progression of AKI in children.

Accurate and standardized methods for assessing the vital status of patients are crucial for patient care and scientific research. This study introduces the Patient Vital Status (PVS), which quantifies and contextualizes a patient's physical status based on continuous variables such as vital signs and deviations from age-dependent normative values. The vital signs, heart rate, oxygen saturation, respiratory rate, mean arterial blood pressure, and temperature were selected as input to the PVS pipeline. The method was applied to 70 pediatric patients in the intensive care unit (ICU), and its efficacy was evaluated by matching high values with septic events at different time points in patient care. Septic events included systemic inflammatory response syndrome (SIRS) and suspected or proven sepsis. The comparison of maximum PVS values between the presence and absence of a septic event showed significant differences (SIRS/No SIRS: p < 0.0001, η2 = 0.54; Suspected Sepsis/No Suspected Sepsis: p = 0.00047, η2 = 0.43; Proven Sepsis/No Proven Sepsis: p = 0.0055, η2 = 0.34). A further comparison between the most severe PVS in septic patients with the PVS at ICU discharge showed even higher effect sizes (SIRS: p < 0.0001, η2 = 0.8; Suspected Sepsis: p < 0.0001, η2 = 0.8; Proven Sepsis: p = 0.002, η2 = 0.84). The PVS is emerging as a data-driven tool with the potential to assess a patient's vital status in the ICU objectively. Despite real-world data challenges and potential annotation biases, it shows promise for monitoring disease progression and treatment responses. Its adaptability to different disease markers and reliance on age-dependent reference values further broaden its application possibilities. Real-time implementation of PVS in personalized patient monitoring may be a promising way to improve critical care. However, PVS requires further research and external validation to realize its true potential.

Pediatric heart diseases present a broad spectrum of congenital and acquired diseases. More complex congenital malformations require a differentiated and multimodal decision-making process, usually including echocardiography as a central imaging method. Artificial intelligence (AI) offers considerable promise for clinicians by facilitating automated interpretation of pediatric echocardiography data. However, adapting AI technologies for pediatric echocardiography analysis has challenges such as limited public data availability, data privacy, and AI model transparency. Recently, researchers have focused on disruptive technologies, such as federated learning (FL) and explainable AI (XAI), to improve automatic diagnostic and decision support workflows. This study offers a comprehensive overview of the limitations and opportunities of AI in pediatric echocardiography, emphasizing the synergistic workflow and role of XAI and FL, identifying research gaps, and exploring potential future developments. Additionally, three relevant clinical use cases demonstrate the functionality of XAI and FL with a focus on (i) view recognition, (ii) disease classification, (iii) segmentation of cardiac structures, and (iv) quantitative assessment of cardiac function.

Sepsis is a severe and expensive medical emergency that requires prompt identification in order to improve patient mortality. The objective of our research is to develop an attention-based bidirectional LSTM-CNN (AT-BiLSTM-CNN) hybrid architecture for the early prediction of sepsis using electronic health records (EHRs) obtained from intensive care units (ICUs). We combine attention mechanism, bidirectional long short-term memory (BiLSTM) and convolutional neural network (CNN) to analyse clinical time series data, aiming to enhance prediction accuracy. The effectiveness of our model is measured using metrics such as accuracy, sensitivity, specificity, and area under the receiver operating characteristic (AUROC), utilising data from the 2019 PhysioNet Challenge. Upon assessing the performance of the AT-BiLSTM-CNN model throughout prediction windows of 4, 8, and 12 h, we observed its exceptional performance in comparison with existing leading techniques. It achieved average AUROCs of 0.88, 0.85, and 0.84 for the predictions made 4, 8, and 12 h before sepsis onset, respectively. This research contributes significantly to the development of smart clinical support systems, potentially offering lifesaving interventions for septic patients at critical moments.

Hintergrund Eine ultra-schnelle Genomsequenzierung (urWGS, Ergebnis vorliegend ≤ 3 Tagen) bei kritisch kranken Kindern, führt bei ca. 50% der untersuchten Kinder zur Diagnose einer genetisch bedingten Erkrankung (Baby Lion-Studie, DRKS00025163). Die Implementierung der urWGS in die Routine bleibt jedoch eine Herausforderung, unter anderem da eine Refinanzierung in Deutschland zurzeit nicht gegeben ist.

Background Bilateral lung transplantation (LuTx) remains the only established treatment for children with end-stage pulmonary arterial hypertension (PAH). Although PAH is the second most common indication for LuTx, little is known about optimal perioperative management and midterm clinical outcomes. Methods Prospective observational study on consecutive children with PAH who underwent LuTx with scheduled postoperative VA-ECMO support at Hannover Medical School from December 2013 to June 2020. Results Twelve patients with PAH underwent LuTx (mean age 11.9 years; age range 1.9–17.8). Underlying diagnoses included idiopathic ( n = 4) or heritable PAH ( n = 4), PAH associated with congenital heart disease ( n = 2), pulmonary veno-occlusive disease ( n = 1), and pulmonary capillary hemangiomatosis ( n = 1). The mean waiting time was 58.5 days (range 1–220d). Three patients were bridged to LuTx on VA-ECMO. Intraoperative VA-ECMO/cardiopulmonary bypass was applied and VA-ECMO was continued postoperatively in all patients (mean ECMO-duration 185 h; range 73–363 h; early extubation). The median postoperative ventilation time was 28 h (range 17–145 h). Echocardiographic conventional and strain analysis showed that 12 months after LuTx, all patients had normal biventricular systolic function. All PAH patients are alive 2 years after LuTx (median follow-up 53 months, range 26–104 months). Conclusion LuTx in children with end-stage PAH resulted in excellent midterm outcomes (100% survival 2 years post-LuTx). Postoperative VA-ECMO facilitates early extubation with rapid gain of allograft function and sustained biventricular reverse-remodeling and systolic function after RV pressure unloading and LV volume loading.

Despite their increased secondary value for developing applications and knowledge gain, routine, harmonized and standardized datasets are often not available in Pediatrics. We propose a data integration pipeline towards an interoperable routine dataset in pediatric intensive care medicine. Our three-level approach involves identifying relevant data from primary source systems, developing local data integration processes, and converting data into a standardized, interoperable format using openEHR. We modeled 15 openEHR templates and established 31 interoperable ETL processes, resulting in anonymized, standardized data of about 4,200 pediatric patients that were loaded into a harmonized database. Based on our pipeline and templates, we successfully integrated the first part of this data in our openEHR data repository. We seek to inspire other pediatric intensive care units to adopt similar approaches, with the aim of breaking down heterogenous data silos and promoting secondary use of routine data.

Background Constantly elevated intra-abdominal pressure (IAH) can lead to abdominal compartment syndrome (ACS), which is associated with organ dysfunction and even multiorgan failure. Our 2010 survey revealed an inconsistent acceptance of definitions and guidelines among pediatric intensivists regarding the diagnosis and treatment of IAH and ACS in Germany. This is the first survey to assess the impact of the updated guidelines on neonatal/pediatric intensive care units (NICU/PICU) in German-speaking countries after WSACS published those in 2013. Methods We conducted a follow-up survey and sent 473 questionnaires to all 328 German-speaking pediatric hospitals. We compared our findings regarding awareness, diagnostics and therapy of IAH and ACS with the results of our 2010 survey. Results The response rate was 48% ( n = 156). The majority of respondents was from Germany (86%) and working in PICUs with mostly neonatal patients (53%). The number of participants who stated that IAH and ACS play a role in their clinical practice rose from 44% in 2010 to 56% in 2016. Similar to the 2010 investigations, only a few neonatal/pediatric intensivists knew the correct WSACS definition of an IAH (4% vs 6%). Different from the previous study, the number of participants who correctly defined an ACS increased from 18 to 58% ( p < 0,001). The number of respondents measuring intra-abdominal pressure (IAP) increased from 20 to 43% ( p < 0,001). Decompressive laparotomies (DLs) were performed more frequently than in 2010 (36% vs. 19%, p < 0,001), and the reported survival rate was higher when a DL was used (85% ± 17% vs. 40 ± 34%). Conclusions Our follow-up survey of neonatal/pediatric intensivists showed an improvement in the awareness and knowledge of valid definitions of ACS. Moreover, there has been an increase in the number of physicians measuring IAP in patients. However, a significant number has still never diagnosed IAH/ACS, and more than half of the respondents have never measured IAP. This reinforces the suspicion that IAH and ACS are only slowly coming into the focus of neonatal/pediatric intensivists in German-speaking pediatric hospitals. The goal should be to raise awareness of IAH and ACS through education and training and to establish diagnostic algorithms, especially for pediatric patients. The increased survival rate after conducting a prompt DL consolidates the impression that the probability of survival can be increased by timely surgical decompression in the case of full-blown ACS.

An extremely dystrophic, premature female infant, born at 25 3/7 weeks of gestational age (birth weight: 430 g) with severe pulmonary hypertension (PH), was admitted to our neonatal intensive care unit (ICU) requiring cardiorespiratory support, including mechanical ventilation and pulmonary vasodilators such as inhaled nitric oxide (iNO) and continuous intravenous sildenafil infusions. The diagnosis of bronchopulmonary dysplasia (BPD) was made. A hemodynamically relevant, persistent ductus arteriosus (PDA) was surgically ligated after failed pharmacologic PDA closure using indomethacin and ibuprofen. The patient was discharged with an estimated 2/3 systemic pulmonary artery pressure. One month after hospital discharge, on low-flow oxygen supplementation (0.5 L/min FiO2 100%), at the corrected age of 16 weeks, she was readmitted to our emergency department with signs of respiratory distress and circulatory decompensation. Echocardiography demonstrated suprasystemic PH. Severe PH persisted despite initiated invasive mechanical ventilation, triple vasodilating therapy [iNO, macitentan, and continuous intravenous (IV) sildenafil], as well as levosimendan, milrinone, and norepinephrine for recompensation from cardiac shock. Thus, we started off-label oral selexipag therapy (oral IP receptor agonist) in the smallest patient reported so far (4 kg body weight). Subsequently, RV systolic pressure decreased to half-systemic, allowing successful weaning of iNO, norepinephrine, and milrinone, and extubation of the patient over 4 days. The infant was discharged 4 weeks after pediatric intensive care unit (PICU) admission in stable cardiorespiratory condition, with an oral, specific, triple antihypertensive PAH-targeted therapy using selexipag, macitentan, and sildenafil as well as oxygen therapy at low-flow (0.5 l/min) and spironolactone. The first cardiac catheterization at the age of 9 months under aforementioned triple PAH-targeted therapy revealed mild PH with 35% systemic PA pressure (mPAP/mSAP = 0.35) and isolated pulmonary vein stenosis. A transthoracic biopsy at the age of 12 months confirmed the diagnosis of BPD and further showed pulmonary interstitial glycogenosis and severe pulmonary capillary hemangiomatosis, without involvement of the pulmonary venules (chILD A2, A3, and B4 according to the Deutsch-Classification). The patient is currently in stable cardiorespiratory condition undergoing triple PH-targeted therapy including selexipag. This report highlights the potential benefits of the oral prostacyclin mimetic selexipag as an early add-on PH-targeted drug in chronic PH of infancy (cPHi).

BACKGROUND: We investigated whether RV function recovers in children with pulmonary arterial hypertension (PAH) and RV failure undergoing lung transplantation (LuTx). METHODS: Prospective observational study of 15 consecutive children, 1.9 to 17.6 years old, with PAH undergoing bilateral LuTx. We performed advanced echocardiography (Echo) and cardiac magnetic resonance imaging (MRI), followed by conventional and strain analysis, pre- and similar to 6 weeks post-LuTx. RESULTS: After LuTx, RV/LV end-systolic diameter ratio (Echo), RV volumes and systolic RV function (RVEF 63 vs 30 %; p < 0.05) by MRI completely normalized, even in children with severe RV failure (RVEF < 40%). The echocardiographic end-systolic LV eccentricity index nearly normalized post-LuTx (1.0 vs 2.0, p < 0.0001) while RV hypertrophy regressed more slowly and was still evident. We found especially the end-systolic RV/LV ratios by Echo (diameter: 0.6 vs 2.6) or MRI (volumes: 0.8 vs 3.4) excellent diagnostic tools (p < 0.05): Together with RVEF by MRI, these ratios were superior to tricuspid annular plane systolic excursion (TAPSE; p = 0.4551) in assessing global systolic RV dysfunction. Moreover, children with severe PAH had reduced RV 2D longitudinal strain (Echo, MRI; p = 0.0450) and decreased RV 2D radial and circumferential strain (MRI; p = 0.0026 and p = 0.0036 respectively), all of which greatly improved following LuTx. CONCLUSION: We demonstrate full recovery of RV systolic function in children within two months after LuTx for severe PAH, independently of the patients' age, weight, and hemodynamic compromise preceding the LuTx. Even in end-stage pediatric PAH with poor RV function and low cardiac output, LuTx should be preferred over heart-lung transplantation. (C) 2021 The Author(s). Published by Elsevier Inc. on behalf of International Society for Heart and Lung Transplantation.

Introduction Systemic inflammatory response syndrome (SIRS), sepsis and associated organ dysfunctions are life-threating conditions occurring at paediatric intensive care units (PICUs). Early recognition and treatment within the first hours of onset are critical. However, time pressure, lack of personnel resources, and the need for complex age-dependent diagnoses impede an accurate and timely diagnosis by PICU physicians. Data-driven prediction models integrated in clinical decision support systems (CDSS) could facilitate early recognition of disease onset.Objectives To estimate the sensitivity and specificity of previously developed prediction models (index tests) for the detection of SIRS, sepsis and associated organ dysfunctions in critically ill children up to 12 hours before reference standard diagnosis is possible.Methods and analysis We conduct a monocentre, prospective diagnostic test accuracy study. Clinicians in the PICU of the tertiary care centre Hannover Medical School, Germany, continuously screen and recruit patients until the adaptive sample size (originally intended sample size of 500 patients) is enrolled. Eligible are children (0–17 years, all sexes) who stay in the PICU for ≥12 hours and for whom an informed consent is given. All eligible patients are independently assessed for SIRS, sepsis and organ dysfunctions using corresponding predictive and knowledge-based CDSS models. The knowledge-based CDSS models serve as imperfect reference standards. The assessments are used to estimate the sensitivities and specificities of each predictive model using a clustered nonparametric approach (main analysis). Subgroup analyses (‘age groups’, ‘sex’ and ‘age groups by sex’) are predefined.Ethics and dissemination This study obtained ethics approval from the Hannover Medical School Ethics Committee (No. 10188_BO_SK_2022). Results will be disseminated as peer-reviewed publications, at scientific conferences, and to patients in an appropriate dissemination approach.Trial registration number This study was registered with the German Clinical Trial Register (DRKS00029071) on 2022-05-23.Protocol version 10188_BO_SK_2022_V.2.0–20220330_4_Studienprotokoll.

Background One of the major challenges in pediatric intensive care is the detection of life-threatening health conditions under acute time constraints and performance pressure. This includes the assessment of pediatric organ dysfunction (OD) that demands extraordinary clinical expertise and the clinician's ability to derive a decision based on multiple information and data sources. Clinical decision support systems (CDSS) offer a solution to support medical staff in stressful routine work. Simultaneously, detection of OD by using computerized decision support approaches has been scarcely investigated, especially not in pediatrics. Objectives The aim of the study is to enhance an existing, interoperable, and rule-based CDSS prototype for tracing the progression of sepsis in critically ill children by augmenting it with the capability to detect SIRS/sepsis-associated hematologic OD, and to determine its diagnostic accuracy. Methods We reproduced an interoperable CDSS approach previously introduced by our working group: (1) a knowledge model was designed by following the commonKADS methodology, (2) routine care data was semantically standardized and harmonized using openEHR as clinical information standard, (3) rules were formulated and implemented in a business rule management system. Data from a prospective diagnostic study, including 168 patients, was used to estimate the diagnostic accuracy of the rule-based CDSS using the clinicians' diagnoses as reference. Results We successfully enhanced an existing interoperable CDSS concept with the new task of detecting SIRS/sepsis-associated hematologic OD. We modeled openEHR templates, integrated and standardized routine data, developed a rule-based, interoperable model, and demonstrated its accuracy. The CDSS detected hematologic OD with a sensitivity of 0.821 (95% CI: 0.708-0.904) and a specificity of 0.970 (95% CI: 0.942-0.987). Conclusion We could confirm our approach for designing an interoperable CDSS as reproducible and transferable to other critical diseases. Our findings are of direct practical relevance, as they present one of the first interoperable CDSS modules that detect pediatric SIRS/sepsis-associated hematologic OD.

Background: The interindividual variability of children's susceptibility to even slightly elevated IAP (intra-abdominal pressure) is unknown, as is the mechanism of transition from IAH (intra-abdominal hypertension = IAP > 10 mm Hg) to abdominal compartment syndrome (ACS = IAH+ organ dysfunction) and/or multiorgan dysfunction syndrome (MODS). Therefore, to improve the monitoring and assessability of micro- and macrocirculation in the context of IAP/IAH/ACS, we developed a multimodal monitoring concept and evaluated it as a prognostic tool.

Critical care can benefit from analyzing data by machine learning approaches for supporting clinical routine and guiding clinical decision-making. Developing data-driven approaches for an early detection of systemic inflammatory response syndrome (SIRS) in patients of pediatric intensive care and exploring the possibility of an approach using training data sets labeled automatically beforehand by knowledge-based approaches rather than clinical experts. Using naïve Bayes classifier and an artificial neuronal network (ANN), trained with real data labeled by (1) domain experts ad (2) a knowledge-based decision support system (CDSS). Accuracies were evaluated by the data set labeled by domain experts using a 10-fold cross validation. The ANN approach trained with data labeled by domain experts yielded a specificity of 0.9139 and sensitivity of 0.8979, whereas the approach trained with a data set labeled by a knowledge-based CDSS achieves a specificity of 0.9220 and a sensitivity of 0.8887. ANN yielded promising results for data-driven detection of pediatric SIRS with real data. Our comparison shows the feasibility of using training data labeled automatically by knowledge-based approaches rather than manually allocated by experts.