Appropriate use of blood cultures in the emergency department through machine learning (ABC): study protocol for a randomised controlled non-inferiority trial.

INTRODUCTION: The liberal use of blood cultures in emergency departments (EDs) leads to low yields and high numbers of false-positive results. False-positive, contaminated cultures are associated with prolonged hospital stays, increased antibiotic usage and even higher hospital mortality rates. This trial aims to investigate whether a recently developed and validated machine learning model for predicting blood culture outcomes can safely and effectively guide clinicians in withholding unnecessary blood culture analysis. METHODS AND ANALYSIS: A randomised controlled, non-inferiority trial comparing current practice with a machine learning-guided approach. The primary objective is to determine whether the machine learning based approach is non-inferior to standard practice based on 30-day mortality. Secondary outcomes include hospital length-of stay and hospital admission rates. Other outcomes include model performance and antibiotic usage. Participants will be recruited in the EDs of multiple hospitals in the Netherlands. A total of 7584 participants will be included. ETHICS AND DISSEMINATION: Possible participants will receive verbal information and a paper information brochure regarding the trial. They will be given at least 1 hour consideration time before providing informed consent. Research results will be published in peer-reviewed journals. This study has been approved by the Amsterdam University Medical Centers' local medical ethics review committee (No 22.0567). The study will be conducted in concordance with the principles of the Declaration of Helsinki and in accordance with the Medical Research Involving Human Subjects Act, General Data Privacy Regulation and Medical Device Regulation. TRIAL REGISTRATION NUMBER: NCT06163781.

Baseline presentation of atypical anorexia nervosa in Singaporean adolescents: a retrospective cohort study.

BACKGROUND: While atypical anorexia nervosa (AAN) has been found to present with significant physical and psychological complications, the presentation of AAN has not been described in a multi-ethnic Singaporean population. METHODS: This retrospective cohort analysis aimed to characterize the baseline presentation of adolescents with anorexia nervosa (AN) (N = 317) and AAN (N = 141) in a Singaporean cohort that presented to a specialist paediatric eating disorder program between January 2010 and October 2020 for assessment. RESULTS: In patients with AAN, there were increased proportions of males (16% vs. 7%) and of Malay ethnicity (11% vs. 4%) compared to AN. Compared to adolescents with AN, adolescents with AAN had lower rates of admission (61% vs. 81%), bradycardia (45% vs. 75%), and hypotension (7% vs. 21%) but had a higher rate of syncope (13% vs. 7%). Likewise, adolescents with AAN had higher rates of self-harm and drug overdose (14% vs. 1.5%) requiring admission, more purging (45.1% vs. 14.8%) and more shape concerns. CONCLUSION: Highlighting the severity of the illness, Singaporean adolescents with AAN presented with physical complications of malnutrition and had more severe eating disorder psychopathology and a higher frequency of other psychological comorbidities than did adolescents with AN.

Singaporean adolescents with atypical anorexia nervosa experience both physical and psychological complications of the illness.

Diagnostic stewardship for blood cultures in the emergency department: A multicenter validation and prospective evaluation of a machine learning prediction tool.

BACKGROUND: Overuse of blood cultures (BCs) in emergency departments (EDs) leads to low yields and high numbers of contaminated cultures, accompanied by increased diagnostics, antibiotic usage, prolonged hospitalization, and mortality. We aimed to simplify and validate a recently developed machine learning model to help safely withhold BC testing in low-risk patients. METHODS: We extracted data from the electronic health records (EHR) for 44.123 unique ED visits with BC sampling in the Amsterdam UMC (locations VUMC and AMC; the Netherlands), Zaans Medical Center (ZMC; the Netherlands), and Beth Israel Deaconess Medical Center (BIDMC; United States) in periods between 2011 and 2021. We trained a machine learning model on the VUMC data to predict blood culture outcomes and validated it in the AMC, ZMC, and BIDMC with subsequent real-time prospective evaluation in the VUMC. FINDINGS: The model had an Area Under the Receiver Operating Characteristics curve (AUROC) of 0.81 (95%-CI = 0.78-0.83) in the VUMC test set. The most important predictors were temperature, creatinine, and C-reactive protein. The AUROCs in the validation cohorts were 0.80 (AMC; 0.78-0.82), 0.76 (ZMC; 0.74-0.78), and 0.75 (BIDMC; 0.74-0.76). During real-time prospective evaluation in the EHR of the VUMC, it reached an AUROC of 0.76 (0.71-0.81) among 590 patients with BC draws in the ED. The prospective evaluation showed that the model can be used to safely withhold blood culture analyses in at least 30% of patients in the ED. INTERPRETATION: We developed a machine learning model to predict blood culture outcomes in the ED, which retained its performance during external validation and real-time prospective evaluation. Our model can identify patients at low risk of having a positive blood culture. Using the model in practice can significantly reduce the number of blood culture analyses and thus avoid the hidden costs of false-positive culture results. FUNDING: This research project was funded by the Amsterdam Public Health - Quality of Care program and the Dutch "Doen of Laten" project (project number: 839205002).

Identification of a multidimensional transcriptome signature for survival prediction of postoperative glioblastoma multiforme patients.

BACKGROUND: Glioblastoma multiform (GBM) is a devastating brain tumor with maximum surgical resection, radiotherapy plus concomitant and adjuvant temozolomide (TMZ) as the standard treatment. Diverse clinicopathological and molecular features are major obstacles to accurate predict survival and evaluate the efficacy of chemotherapy or radiotherapy. Reliable prognostic biomarkers are urgently needed for postoperative GBM patients. METHODS: The protein coding genes (PCGs) and long non-coding RNA (lncRNA) gene expression profiles of 233 GBM postoperative patients were obtained from The Cancer Genome Atlas (TCGA), TANRIC and Gene Expression Omnibus (GEO) database. We randomly divided the TCGA set into a training (n = 76) and a test set (n = 77) and used GSE7696 (n = 80) as an independent validation set. Survival analysis and the random survival forest algorithm were performed to screen survival associated signature. RESULTS: Six PCGs (EIF2AK3, EPRS, GALE, GUCY2C, MTHFD2, RNF212) and five lncRNAs (CTD-2140B24.6, LINC02015, AC068888.1, CERNA1, LINC00618) were screened out by a risk score model and formed a PCG-lncRNA signature for its predictive power was strongest (AUC = 0.78 in the training dataset). The PCG-lncRNA signature could divide patients into high- risk or low-risk group with significantly different survival (median 7.47 vs. 18.27 months, log-rank test P < 0.001) in the training dataset. Similar result was observed in the test dataset (median 11.40 vs. 16.80 months, log-rank test P = 0.001) and the independent set (median 8.93 vs. 16.22 months, log-rank test P = 0.007). Multivariable Cox regression analysis verified that it was an independent prognostic factor for the postsurgical patients with GBM. Compared with IDH mutation status, O-(6)-methylguanine DNA methyltransferase promoter methylation status and age, the signature was proved to have a superior predictive power. And stratified analysis found that the signature could further separated postoperative GBM patients who received TMZ-chemoradiation into high- and low-risk groups in TCGA and GEO dataset. CONCLUSIONS: The PCG-lncRNA signature was a novel prognostic marker to predict survival and TMZ-chemoradiation response in GBM patients after surgery.

Feasibility of three-dimensional ultrashort echo time magnetic resonance imaging at 1.5 T for the diagnosis of skull fractures.

OBJECTIVES: To investigate the feasibility of ultrashort echo time (UTE) magnetic resonance imaging (MRI) for the diagnosis of skull fractures. METHODS: The skull fracture models of ten Bama pigs and 364 patients with craniocerebral trauma were subjected to computed tomography (CT), UTE and conventional MRI sequences. The accuracy of UTE imaging in skull fracture diagnosis was analysed using receiver operating characteristic (ROC) curve analysis, McNemar's test and Kappa values. Differences among CT, UTE imaging and anatomical measurement (AM) values for linear fractures (LFs) and depressed fractures (DFs) were compared using one-way ANOVA and a paired-samples t-test. RESULTS: UTE imaging clearly demonstrated skull structures and fractures. The accuracy, validity and reliability of UTE MRI were excellent, with no significant differences between expert readings (P > 0.05; Kappa, 0.899). The values obtained for 42 LFs and 13 DFs in the ten specimens were not significantly different among CT, UTE MRI and AMs, while those obtained for 55 LFs and ten DFs in 44 patients were not significantly different between CT and UTE MRI (P > 0.05). CONCLUSIONS: UTE MRI sequences are feasible for the evaluation of skull structures and fractures, with no radiation exposure, particularly for paediatric and pregnant patients. KEY POINTS: Despite ionising radiation, CT is standard for skull fracture assessment. Conventional MRI cannot depict skull structures. 3D-UTE sequences clearly demonstrate skull structures and fractures. UTE plus conventional MRI are superior to CT in craniocerebral trauma assessment. Paediatric and pregnant patients will benefit from this imaging modality.

IDH1R¹³²H decreases the proliferation of U87 glioma cells through upregulation of microRNA-128a.

Mutations in isocitrate dehydrogenase 1 (IDH1) are found in >70% of secondary glioblastomas and lower-grade gliomas (grades II-III). Among the numerous phenotypic differences between IDH1 mutant and wild-type glioma patients, the most salient is an improved survival rate for patients with a mutation. MicroRNAs (miRNAs) are a class of small, non­coding, single­stranded RNAs that can negatively regulate gene expression at the post­transcriptional level, predominantly by binding to the 3'­untranslated region of their target mRNAs. The dysregulated expression of several miRNAs has been reported to modulate glioma progression; however, it is unclear whether mutations in IDH1 regulate glioma cell proliferation through miRNA dysregulation. In the present study, stable overexpression of IDH1WT or IDH1R132H was established in the U87 glioma cell line. It was found that IDH1R132H decreased cell proliferation of U87 glioma cells by inducing the expression of the miRNA miR­128a. This process was dependent on the transcription factor hypoxia inducible factor­1α (HIF­1α), which binds to a hypoxia response element in the promoter of miR­128a. Furthermore, miR­128a negatively regulated the expression of B­cell­specific Moloney murine leukemia virus integration site 1 protein (Bmi­1), which is involved in suppressing cell proliferation. These findings suggest that the IDH1R132H­HIF­1α­miR­128a­Bmi­1 pathway is involved in glioma cell proliferation.

Risk factors related to aneurysmal rebleeding.

OBJECTIVE: Rebleeding from ruptured intracranial aneurysms is a major cause of death and disability. The aim of this study was to investigate the incidence of rebleeding and the risk factors related to rebleeding before early aneurysm repair. METHODS: The incidence of rebleeding, demographic data, and clinical data from 326 patients with aneurysmal subarachnoid hemorrhage (SAH) were retrospectively collected. All clinical variables were examined by univariate analysis, and a binary logistic regression analysis was performed to identify the risk factors related to rebleeding. RESULTS: Rebleeding occurred in 70 (21.5%) of the 326 aneurysm patients during transfer or during the in-hospital stay (within 72 hours); 24 episodes (34.3%) occurred within 3 hours, and 44 episodes (62.9%) occurred within 6 hours after the initial SAH. Univariate analysis showed that there were significant differences between the rebleeding and nonrebleeding patients in terms of age, aneurysm size, systolic arterial blood pressure (SBP), Hunt-Hess grade and outcome at discharge. The binary logistic regression analysis revealed that age (odds ratio [OR] = 1.167), aneurysm size (OR = 1.624), SBP (OR = 3.338), and Hunt-Hess grade (OR = 2.512) were independent risk factors for aneurysmal rebleeding (for each P < 0.05). CONCLUSIONS: The incidence of early aneurysmal rebleeding within hours after the initial SAH is high during transfer or during the in-hospital stay. Advanced age, an aneurysm size larger than 10 mm, SBP higher than 160 mmHg, and poor Hunt-Hess grade were independent risk factors for aneurysmal rebleeding. The importance of early aneurysm repair should be emphasized because aneurysmal rebleeding contributes to a poor outcome.