UBE2M Is a Stress-Inducible Dual E2 for Neddylation and Ubiquitylation that Promotes Targeted Degradation of UBE2F.

UBE2M and UBE2F are two family members of neddylation E2 conjugating enzyme that, together with E3s, activate CRLs (Cullin-RING Ligases) by catalyzing cullin neddylation. However, whether and how two E2s cross-talk with each other are largely unknown. Here, we report that UBE2M is a stress-inducible gene subjected to cis-transactivation by HIF-1 and AP1, and MLN4924, a small molecule inhibitor of E1 NEDD8-activating enzyme (NAE), upregulates UBE2M via blocking degradation of HIF-1α and c-JUN. UBE2M is a dual E2 for targeted ubiquitylation and degradation of UBE2F, acting as a neddylation E2 to activate CUL3-Keap1 E3 under physiological conditions but as a ubiquitylation E2 for Parkin-DJ-1 E3 under stressed conditions. UBE2M-induced UBE2F degradation leads to CRL5 inactivation and subsequent NOXA accumulation to suppress the growth of lung cancer cells. Collectively, our study establishes a negative regulatory axis between two neddylation E2s with UBE2M ubiquitylating UBE2F, and two CRLs with CRL3 inactivating CRL5.

Incident dementia and long-term exposure to constituents of fine particle air pollution: A national cohort study in the United States.

Growing evidence suggests that fine particulate matter (PM2.5) likely increases the risks of dementia, yet little is known about the relative contributions of different constituents. Here, we conducted a nationwide population-based cohort study (2000 to 2017) by integrating the Medicare Chronic Conditions Warehouse database and two independently sourced datasets of high-resolution PM2.5 major chemical composition, including black carbon (BC), organic matter (OM), nitrate (NO3-), sulfate (SO42-), ammonium (NH4+), and soil dust (DUST). To investigate the impact of long-term exposure to PM2.5 constituents on incident all-cause dementia and Alzheimer's disease (AD), hazard ratios for dementia and AD were estimated using Cox proportional hazards models, and penalized splines were used to evaluate potential nonlinear concentration-response (C-R) relationships. Results using two exposure datasets consistently indicated higher rates of incident dementia and AD for an increased exposure to PM2.5 and its major constituents. An interquartile range increase in PM2.5 mass was associated with a 6 to 7% increase in dementia incidence and a 9% increase in AD incidence. For different PM2.5 constituents, associations remained significant for BC, OM, SO42-, and NH4+ for both end points (even after adjustments of other constituents), among which BC and SO42- showed the strongest associations. All constituents had largely linear C-R relationships in the low exposure range, but most tailed off at higher exposure concentrations. Our findings suggest that long-term exposure to PM2.5 is significantly associated with higher rates of incident dementia and AD and that SO42-, BC, and OM related to traffic and fossil fuel combustion might drive the observed associations.

The epidemiological characteristics of pediatric head injury in Hangzhou, China: a retrospective study based on cranial CT examinations.

PRIMARY OBJECTIVE: This study aims to create a pediatric head injury database based on cranial CT examinations and explore their epidemiologic characteristics. METHODS: Data related to cranial CT examinations of pediatric head injuries from March 2014 to March 2021 were collected at outpatient and emergency department of a pediatric medical center. The causes of injury, observable post-injury symptoms, and cranial injury findings were extracted with the assistance of natural language processing techniques. RESULTS: Reviewing the data from records on 52,821 children with head injuries over a period of 7 years, the most common causes of pediatric head injury were falls (58.3%), traffic accidents (26.0%), smash/crush/strike (13.9%), violence (1.5%) and sports-related incidents (0.3%). Overall, most of those injured were boys which accounting for 62.2% of all cases. Skull fractures most commonly occur in the parietal bone (9.0%), followed by the occipital (5.2%), frontal (3.3%) and temporal bones (3.0%). Most intracranial hemorrhages occurred in epidural (5.8%), followed by subdural (5.1%), subarachnoid (0.9%), intraparenchymal (0.5%) and intraventricular (0.2%) hemorrhages. Spring and autumn showed more events than any other season. CONCLUSIONS: To the best of our knowledge, this is the largest sample of epidemiological study of head injury in the Chinese pediatric population to date.

Total intracorporeal laparoscopic ileal ureter replacement in a single position for ureteral stricture based on membrane anatomy.

PURPOSE: The aim of this study was to present our initial experience and prove the feasibility of total intracorporeal laparoscopic ileal ureter replacement (TILIUR) in a single position for ureteral stricture based on membrane anatomy. MATERIALS AND METHODS: Between January 2021 and April 2023, six patients underwent TILIUR in a single position for ureteral strictures based on membrane anatomy. All patients with a past medical history underwent radical hysterectomy with bilateral pelvic lymph node dissection as well as extensive ureteral stricture due to radiotherapy. The procedure is performed completely laparoscopically. Dissection of the digestive system as well as ureteral stricture or renal pelvis is based on membrane anatomy. The surgery is performed in a single position. RESULTS: TILIUR in a single position for ureteral stricture based on membrane anatomy was successfully performed without open conversion in all patients. Among the 6 patients, 3 patients underwent combined ileal ureter replacement (IUR) and abdominal wall ostomy, 2 underwent unilateral IUR, and 1 underwent bilateral IUR. The mean length of the ileal substitution was 22.83 cm (range: 15-28). The average operative time was 458 ± 72.77 min (range 385-575 min), and the average intraoperative blood loss was 158 mL (range 50-400 mL). The median postoperative hospital stay was 15.1 d (range: 8-32). The median duration of postoperative follow-up was 15 months (range: 3-29 months). The success rate was 100%. CONCLUSIONS: TILIUR in a single position may be a promising option for ureteral stricture based on membrane anatomy in selected patients. Moreover, it has a positive effect on patients with renal insufficiency and urinary incontinence. Although IUR is difficult and risky, proficient surgeons can perform the procedure safely and effectively.

Intramedullary Nailing Versus Open Reduction and Plate Fixation for Lateral Malleolar Fractures: A Meta-Analysis.

The fixation for lateral malleolar fracture in ankle fractures is still controversial. The purpose of this meta-analysis is to compare clinical and radiological outcomes between intramedullary nail (IMN) and plate for lateral malleolar fractures in ankle fractures. The PubMed, EMBASE, and Cochrane Library were searched for randomized controlled trials (RCTs) from databases inception to June 2023. Data on outcomes were extracted and the methodological quality of the included studies were assessed. A meta-analysis was performed using RevMan 5.3 software when the data extracted from included studies could be synthesized. Seven RCTs were included. The methodological quality of the included studies was moderate to high. The meta-analysis results showed that the infection rate of the IMN group was significantly lower than that of the plate group (RR = 0.38; 95%CI 0.18-0.82; p = .01). There were no significant differences between the 2 groups in Olerud and Molander Ankle Score (OMAS), union rate, radiological outcomes, nerve injury rate, reoperation rate, loss of reduction, and total complication rate. Our present meta-analysis demonstrated that the IMN might be a better method for the fixation of lateral malleolar fracture in ankle fracture, as the infection rate was significantly lower than a plate.

Capturing Doublet Intermediate Emitters by Chemically Crosslinking Confinement towards Spatiotemporal Encryption.

Photoluminescence is one of the most meticulous ways to manipulate light energy. Typical photoluminescent emitters are mostly stable substances with a pure photophysical process of spontaneous photon-emission from their excited states. Intermediate emitters are elusive attributing to their synchronous energy transfer process including photophysical and incomplete photochemical pathways. An intermediate emitter containing radicals is more difficult to be observed due to its inherent chemical reactivity. Here, these challenges are overcome by spontaneously formed space limitations in polymer crosslinking networks meanwhile chemically active intermediates are captured. These doublet intermediates exhibit unique long-wavelength emissions under chemically crosslinking confinement conditions, and their luminous mechanism provides a novel perspective for designing intermediate emitters with liquid-crystal character and photoresponsive features towards spatiotemporal encryption, promising for the detection of photochemical reactions and the development of fascinating luminescent systems.

Adversarial reinforcement learning for dynamic treatment regimes.

Treatment recommendation, as a critical task of delivering effective interventions according to patient state and expected outcome, plays a vital role in precision medicine and healthcare management. As a well-suited tactic to learn optimal policies of recommender systems, reinforcement learning is promising to address the challenge of treatment recommendation. However, existing solutions mostly require frequent interactions between treatment recommender systems and clinical environment, which are expensive, time-consuming, and even infeasible in clinical practice. In this study, we present a novel model-based offline reinforcement learning approach to optimize a treatment policy by utilizing patient treatment trajectories in Electronic Health Records (EHRs). Specifically, a patient treatment trajectory simulator is firstly constructed based on the ground-truth trajectories in EHRs. Thereafter, the constructed simulator is utilized to model the online interactions between the treatment recommender system and clinical environment. In this way, the counterfactual trajectories can be generated. To alleviate the bias deriving from the ground-truth and the counterfactual trajectories, an adversarial network is incorporated into the proposed model, such that a large space of treatment actions can be explored with the scaled rewards. The proposed model is evaluated on a simulated dataset and a real-world dataset. The experimental results demonstrate that the proposed model is superior to other methods, giving rise to a new solution for dynamic treatment regimes and beyond.

A robust phenotype-driven likelihood ratio analysis approach assisting interpretable clinical diagnosis of rare diseases.

Phenotype-based prioritization of candidate genes and diseases has become a well-established approach for multi-omics diagnostics of rare diseases. Most current algorithms exploit semantic analysis and probabilistic statistics based on Human Phenotype Ontology and are commonly superior to naive search methods. However, these algorithms are mostly less interpretable and do not perform well in real clinical scenarios due to noise and imprecision of query terms, and the fact that individuals may not display all phenotypes of the disease they belong to. We present a Phenotype-driven Likelihood Ratio analysis approach (PheLR) assisting interpretable clinical diagnosis of rare diseases. With a likelihood ratio paradigm, PheLR estimates the posterior probability of candidate diseases and how much a phenotypic feature contributes to the prioritization result. Benchmarked using simulated and realistic patients, PheLR shows significant advantages over current approaches and is robust to noise and inaccuracy. To facilitate clinical practice and visualized differential diagnosis, PheLR is implemented as an online web tool (https://phelr.nbscn.org).

Nerve-Sparing Laparoscopic Cystoprostatectomy Based on Inferior Hypogastric Plexus Dissection: Our Initial Experience.

INTRODUCTION: The aim of this study was to implement our technique for the initial dissection of the inferior hypogastric plexus and protection of the autonomic nerve supply to the corpora cavernosa in laparoscopic radical cystoprostatectomy with an orthotopic ileal neobladder and report the initial outcomes. METHODS: Eleven normally potent patients with preoperative cT2N0 bladder cancer who underwent bilateral nerve-sparing laparoscopic cystoprostatectomy performed by the same surgeon were selected from May 2018 to September 2020. In this procedure, the anterior part of the inferior hypogastric plexus was dissected first between the prehypogastric nerve fascia and rectal proper fascia medial to the distal ureter. Then the Denonvilliers' fascia and the nerves around the prostate were preserved according to current intrafascial principles. The preliminary operative, oncologic, and functional results are presented. RESULTS: The median follow-up duration was 18 months. We observed early and late complications in 5 patients, but none exceeded grade III. Of the 11 patients, ten gained daytime continence (90.9%), and 8 (72.7%) showed nocturnal continence at the last follow-up. Regarding postoperative potency, 10 of the 11 patients (90.9%) remained potent with or without oral medications, excluding one who had partial tumescence but did not follow our recommendations regarding medication use. No local recurrence or positive surgical margins were noted. CONCLUSION: In addition to emphasizing our cavernosal nerve-sparing procedure, this report on the precise dissection and protection of the inferior hypogastric plexus could be of clinical significance, providing potentially ideal short-term functional results.

AKG induces cell apoptosis by inducing reactive oxygen species-mediated endoplasmic reticulum stress and by suppressing PI3K/AKT/mTOR-mediated autophagy in renal cell carcinoma.

BACKGROUND: Alpha-ketoglutarate (AKG) or 2-oxoglutarate is a key substance in the tricarboxylic acid cycle (TCA) and has been known to play an important role in cancerogenesis and tumor progression. Renal cell carcinoma (RCC) is the most common type of kidney cancer, and it has a high mortality rate. Autophagy is a phenomenon of self-digestion, and its significance in tumor genesis and progression remains debatable. However, the mechanisms underlying how AKG regulates autophagy in RCC remain unknown. Thus, the purpose of this study was to assess the therapeutic efficacy of AKG and its molecular mechanisms. METHODS: RCC cell lines 786O and ACHN were treated with varying doses of AKG for 24 h. CCK-8, Transwell, and scratch wound healing assays were utilized to evaluate the role of AKG in RCC cells. Autophagy protein and PI3K/AKT/mTOR pathway protein levels were analyzed by Western blot. RESULTS: AKG inhibited the proliferation of RCC cells 786O and ACHN in a dose-dependent manner according to the CCK-8 assay. In addition, flow cytometry and Western blot analysis revealed that AKG dose-dependently triggered apoptosis and autophagy in RCC cells. By promoting cell apoptosis and autophagy, AKG dramatically suppressed tumor growth. Mechanistically, AKG induces autophagy by promoting ROS generation and inhibiting the PI3K/AKT/mTOR pathway. CONCLUSIONS: The anti-tumor effect of AKG promotes autophagy in renal cancer cells via mediating ROS-PI3K/Akt/mTOR, and may be used as a potential anticancer drug for kidney cancer.

Strengthen the purification of eutrophic water and improve the characteristics of sediment by functional ecological floating bed suspended calcium peroxide and sponge iron jointly.

To overcome the shortcomings of conventional ecological floating bed (CEFB) in purifying landscape water, this study constructed a functional ecological floating bed (FEFB) through the suspension of calcium peroxide (CP) and sponge iron (SI) jointly below the CEFB. The purification effect of water quality and influence of sediment were compared in control check, CEFB, and FEFB systems, which were loaded the same sediment and reclaimed water in a field experiment. Results showed that the FEFB suspended with CP and SI had evident purification effect on the quality of landscape water supplied with reclaimed water and can maintain stably the nutrient status of the water body at mesotrophic levels and low turbidity. The FEFB promoted the degradation of humus, thus eliminating the chroma risk in water body caused by the decay of plants from the CEFB. Moreover, the FEFB can control the sediment mass produced, reduce the total nitrogen (TN) mass of sediment, and decrease the transformable TN (TTN) content in the sediment. The FEFB enhanced the stability of phosphorus (P) in the sediment, where the relative content of Ca-P and stable P reached 42.18% and 64.27%, respectively. To sum up, the FEFB suspended with SI and CP can not only effectively control the eutrophication and sensory index of landscape water but also change the TTN content and P forms in sediment, making the sediment more stable. Thus, the FEFB provides an innovative approach to reduce endogenous nutrient release for landscape water along with recharging with reclaimed water.

Evidence of within-facility patient-patient Clostridiodes difficile infection spread across diverse settings.

Previous studies have suggested that a hospital patient's risk of developing healthcare facility-onset (HCFO) Clostridioides difficile infections (CDIs) increases with the number of concurrent spatially proximate patients with CDI, termed CDI pressure. However, these studies were performed either in a single institution or in a single state with a very coarse measure of concurrence. We conducted a retrospective case-control study involving over 17.5 million inpatient visits across 700 hospitals in eight US states. We built a weighted, directed network connecting overlapping inpatient visits to measure facility-level CDI pressure. We then matched HCFO-CDIs with non-CDI controls on facility, comorbidities and demographics and performed a conditional logistic regression to determine the odds of developing HCFO-CDI given the number of coincident patient visits with CDI. On average, cases' visits coincided with 9.2 CDI cases, which for an individual with an average length of stay corresponded to an estimated 17.7% (95% CI 12.9-22.7%) increase in the odds of acquiring HCFO-CDI compared to an inpatient visit without concurrent CDI cases or fully isolated from both direct and indirect risks from concurrent CDI cases. These results suggest that, either directly or indirectly, hospital patients with CDI lead to CDIs in non-infected patients with temporally overlapping visits.

Risk factors for central venous catheter-associated deep venous thrombosis in pediatric critical care settings identified by fusion model.

BACKGROUND: An increase in the incidence of central venous catheter (CVC)-related thrombosis (CRT) has been reported in pediatric intensive care patients over the past decade. Risk factors for the development of CRT are not well understood, especially in children. The study objective was to identify potential clinical risk factors associated with CRT with novel fusion machine learning models. METHODS: Patients aged 0-18 who were admitted to intensive care units from December 2015 to December 2018 and underwent at least one CVC placement were included. Two fusion model approaches (stacking and blending) were used to build a better performance model based on three widely used machine learning models (logistic regression, random forest and gradient boosting decision tree). High-impact risk factors were identified based on their contribution in both fusion artificial intelligence models. RESULTS: A total of 478 factors of 3871 patients and 3927 lines were used to build fusion models, one of which achieved quite satisfactory performance (AUC = 0.82, recall = 0.85, accuracy = 0.65) in 5-fold cross validation. A total of 11 risk factors were identified based on their independent contributions to the two fusion models. Some risk factors, such as D-dimer, thrombin time, blood acid-base balance-related factors, dehydrating agents, lymphocytes and basophils were identified or confirmed to play an important role in CRT in children. CONCLUSIONS: The fusion model, which achieves better performance in CRT prediction, can better understand the risk factors for CRT and provide potential biomarkers and measures for thromboprophylaxis in pediatric intensive care settings.

Understanding the risk factors for adverse events during exchange transfusion in neonatal hyperbilirubinemia using explainable artificial intelligence.

OBJECTIVE: To understand the risk factors associated with adverse events during exchange transfusion (ET) in severe neonatal hyperbilirubinemia. STUDY DESIGN: We conducted a retrospective study of infants with hyperbilirubinemia who underwent ET within 30 days of birth from 2015 to 2020 in a children's hospital. Both traditional statistical analysis and state-of-the-art explainable artificial intelligence (XAI) were used to identify the risk factors. RESULTS: A total of 188 ET cases were included; 7 major adverse events, including hyperglycemia (86.2%), top-up transfusion after ET (50.5%), hypocalcemia (42.6%), hyponatremia (42.6%), thrombocytopenia (38.3%), metabolic acidosis (25.5%), and hypokalemia (25.5%), and their risk factors were identified. Some novel and interesting findings were identified by XAI. CONCLUSIONS: XAI not only achieved better performance in predicting adverse events during ET but also helped clinicians to more deeply understand nonlinear relationships and generate actionable knowledge for practice.

Initial Experience with the Comprehensive Modified Laparoscopic Pyeloplasty Technique Based on Membrane Anatomy for Treating Ureteropelvic Junction Obstruction.

OBJECTIVE: The aim of the objective was to present our initial experience and evaluate the feasibility of the novel comprehensive modified laparoscopic pyeloplasty (CMLP) technique based on membrane anatomy. MATERIALS AND METHODS: Forty-eight patients underwent CMLP from February 2016 to October 2020. CMLP involves the following: dissection of the ureter was based on the fascia or fusion fascia formed by embryonic development. The ureter was separated from the ureteral sheath, and the pelvis and ureter were incised with incomplete amputation. The first stitch was placed between the lower point of the spatulated ureter and the lowest corner of the renal pelvis to ensure correct orientation of the anastomosis; anastomosis of the renal pelvis and ureter was performed using the touchless technique. RESULTS: All CMLPs were completed successfully without conversion. The mean overall operating time was 230.96 min. The median estimated blood loss was 50.00 (interquartile range 20.00-57.50) mL. The average postoperative hospital stay was 9.31 days. The average follow-up time was 24.73 months. No major complications occurred. In 1 case, revision laparoscopic pyeloplasty was performed, but the obstruction persisted after double J stent removal, so ultimately, the double J stent required regular replacement. Another asymptomatic patient with hydronephrosis experienced failed treatment and is still under follow-up. The overall success rate was 95.83% (46/48). The success rate in patients with recurrent ureteropelvic junction obstruction (UPJO) was 87.5% (7/8). CONCLUSIONS: CMLP is a practical and effective treatment option for UPJO with a high success rate. An advantage of CMLP is the clear surgical field.

DeepSE: Detecting super-enhancers among typical enhancers using only sequence feature embeddings.

Super-enhancer (SE) is a cluster of active typical enhancers (TE) with high levels of the Mediator complex, master transcriptional factors, and chromatin regulators. SEs play a key role in the control of cell identity and disease. Traditionally, scientists used a variety of high-throughput data of different transcriptional factors or chromatin marks to distinguish SEs from TEs. This kind of experimental methods are usually costly and time-consuming. In this paper, we proposed a model DeepSE, which is based on a deep convolutional neural network model, to distinguish the SEs from TEs. DeepSE represent the DNA sequences using the dna2vec feature embeddings. With only the DNA sequence information, DeepSE outperformed all state-of-the-art methods. In addition, DeepSE can be generalized well across different cell lines, which implied that cell-type specific SEs may share hidden sequence patterns across different cell lines. The source code and data are stored in GitHub (https://github.com/QiaoyingJi/DeepSE).

Short-term exposure to nitrogen dioxide and mortality: A systematic review and meta-analysis.

BACKGROUND: Ambient air pollution has been characterized as a leading cause of mortality worldwide and has been associated with cardiovascular and respiratory diseases. There is increasing evidence that short-term exposure to nitrogen dioxide (NO2), is related to adverse health effects and mortality. METHODS: We conducted a systematic review of short-term NO2 and daily mortality, which were indexed in PubMed and Embase up to June 2021. We calculated random-effects estimates by different continents and globally, and tested for heterogeneity and publication bias. RESULTS: We included 87 articles in our quantitative analysis. NO2 and all-cause as well as cause-specific mortality were positively associated in the main analysis. For all-cause mortality, a 10 ppb increase in NO2 was associated with a 1.58% (95%CI 1.28%-1.88%, I2 = 96.3%, Eggers' test p < 0.01, N = 57) increase in the risk of death. For cause-specific mortality, a 10 ppb increase in NO2 was associated with a 1.72% (95%CI 1.41%-2.04%, I2 = 87.4%, Eggers' test p < 0.01, N = 42) increase in cardiovascular mortality and a 2.05% (95%CI 1.52%-2.59%, I2 = 78.5%, Eggers' test p < 0.01, N = 38) increase in respiratory mortality. In the sensitivity analysis, the meta-estimates for all-cause mortality, cardiovascular and respiratory mortality were nearly identical. The heterogeneity would decline to varying degrees through regional and study-design stratification. CONCLUSIONS: This study provides evidence of an association between short-term exposure to NO2, a proxy for traffic-sourced air pollutants, and all-cause, cardiovascular and respiratory mortality.

Using Z-score to optimize population-specific DDH screening: a retrospective study in Hangzhou, China.

BACKGROUND: DDH (Developmental Dysplasia of the Hip) screening can potentially avert many morbidities and reduce costs. The debate about universal vs. selective DDH ultrasonography screening in different countries revolves to a large extent around effectiveness, cost, and the possibility of overdiagnosis and overtreatment. In this study, we proposed and evaluated a Z-score enhanced Graf method to optimize population-specific DDH screening. METHODS: A total of 39,710 history ultrasonography hip examinations were collected to establish a sex, side specific and age-based Z-scores model using the local regression method. The correlation between Z-scores and classic Graf types was analyzed. Four thousand two hundred twenty-nine cases with follow-up ultrasonographic examinations and 5284 cases with follow-up X-ray examinations were used to evaluate the false positive rate of the first examination based on the subsequent examinations. The results using classic Graf types and the Z-score enhanced types were compared. RESULTS: The Z-score enhanced Graf types were highly correlated with the classic Graf's classification (R = 0.67, p < 0.001). Using the Z-scores ≥2 as a threshold could reduce by 86.56 and 80.44% the false positives in the left and right hips based on the follow-up ultrasonographic examinations, and reduce by 78.99% false-positive cases based on the follow-up X-ray examinations, respectively. CONCLUSIONS: Using an age, sex and side specific Z-scores enhanced Graf's method can better control the false positive rate in DDH screening among different populations.

Prediction of central venous catheter-associated deep venous thrombosis in pediatric critical care settings.

BACKGROUND: An increase in the incidence of central venous catheter (CVC)-associated deep venous thrombosis (CADVT) has been reported in pediatric patients over the past decade. At the same time, current screening guidelines for venous thromboembolism risk have low sensitivity for CADVT in hospitalized children. This study utilized a multimodal deep learning model to predict CADVT before it occurs. METHODS: Children who were admitted to intensive care units (ICUs) between December 2015 and December 2018 and with CVC placement at least 3 days were included. The variables analyzed included demographic characteristics, clinical conditions, laboratory test results, vital signs and medications. A multimodal deep learning (MMDL) model that can handle temporal data using long short-term memory (LSTM) and gated recurrent units (GRUs) was proposed for this prediction task. Four benchmark machine learning models, logistic regression (LR), random forest (RF), gradient boosting decision tree (GBDT) and a published cutting edge MMDL, were used to compare and evaluate the models with a fivefold cross-validation approach. Accuracy, recall, area under the ROC curve (AUC), and average precision (AP) were used to evaluate the discrimination of each model at three time points (24 h, 48 h and 72 h) before CADVT occurred. Brier score and Spiegelhalter's z test were used measure the calibration of these prediction models. RESULTS: A total of 1830 patients were included in this study, and approximately 15% developed CADVT. In the CADVT prediction task, the model proposed in this paper significantly outperforms both traditional machine learning models and existing multimodal deep learning models at all 3 time points. It achieved 77% accuracy and 90% recall at 24 h before CADVT was discovered. It can be used to accurately predict the occurrence of CADVT 72 h in advance with an accuracy of greater than 75%, a recall of more than 87%, and an AUC value of 0.82. CONCLUSION: In this study, a machine learning method was successfully established to predict CADVT in advance. These findings demonstrate that artificial intelligence (AI) could provide measures for thromboprophylaxis in a pediatric intensive care setting.

[Application of the artificial intelligence-rapid whole-genome sequencing diagnostic system in the neonatal/pediatric intensive care unit].

Pediatric patients in the neonatal intensive care unit (NICU) and the pediatric intensive care unit (PICU) have a high incidence rate of genetic diseases, and early rapid etiological diagnosis and targeted interventions can help to reduce mortality or improve prognosis. Whole-genome sequencing covers more comprehensive information including point mutation, copy number, and structural and rearrangement variations in the intron region and has become one of the powerful diagnostic tools for genetic diseases. Sequencing data require highly professional judgment and interpretation and are returned for clinical application after several weeks, which cannot meet the need for the diagnosis and treatment of genetic diseases in children. This article introduces the clinical application of rapid whole-genome sequencing in the NICU/PICU and briefly describes related techniques of artificial intelligence-rapid whole-genome sequencing diagnostic system, a rapid high-throughput automated platform for the diagnosis of genetic diseases. The diagnostic system introduces artificial intelligence into the processing of data after whole-genome sequencing and can solve the problems of long time and professional interpretation required for routine genome sequencing and provide a rapid diagnostic regimen for critically ill children suspected of genetic diseases within 24 hours, and therefore, it holds promise for clinical application.