Search

Automated image analysis plays an increasing role in radiology in detecting and quantifying image features outside of the perception of human eyes. Common AI-based approaches address a single medical problem, although patients often present with multiple interacting, frequently subclinical medical conditions. A holistic imaging diagnostics tool based on artificial intelligence (AI) has the potential of providing an overview of multi-system comorbidities within a single workflow. An interdisciplinary, multicentric team of medical experts and computer scientists designed a pipeline, comprising AI-based tools for the automated detection, quantification and characterization of the most common pulmonary, metabolic, cardiovascular and musculoskeletal comorbidities in chest computed tomography (CT). To provide a comprehensive evaluation of each patient, a multidimensional workflow was established with algorithms operating synchronously on a decentralized Joined Imaging Platform (JIP). The results of each patient are transferred to a dedicated database and summarized as a structured report with reference to available reference values and annotated sample images of detected pathologies. Hence, this tool allows for the comprehensive, large-scale analysis of imaging-biomarkers of comorbidities in chest CT, first in science and then in clinical routine. Moreover, this tool accommodates the quantitative analysis and classification of each pathology, providing integral diagnostic and prognostic value, and subsequently leading to improved preventive patient care and further possibilities for future studies.

Predictive monitoring techniques produce signals in case of a high predicted probability of an undesirable event, such as mortality, heart attacks, or machine failure. When using these predicted probabilities to classify the unknown outcome, a decision threshold needs to be chosen in statistical and machine learning models. In many cases, this is set to 0.5 by default. However, this may not lead to an acceptable model performance. To mitigate this issue, different threshold optimization approaches have been proposed in the literature. In this paper, we compare existing thresholding techniques to achieve a desired false alarm rate, and also evaluate the corresponding precision and recall performance metrics. A simulation study is conducted and a real‐world example on a medical dataset is provided. [ABSTRACT FROM AUTHOR]

Abstract: Survival of patients with pediatric acute lymphoblastic leukemia (ALL) after allogeneic hematopoietic stem cell transplantation (allo-SCT) is mainly compromised by leukemia relapse, carrying dismal prognosis. As novel individualized therapeutic approaches are urgently needed, we performed whole-exome sequencing of leukemic blasts of 10 children with post–allo-SCT relapses with the aim of thoroughly characterizing the mutational landscape and identifying druggable mutations. We found that post–allo-SCT ALL relapses display highly diverse and mostly patient-individual genetic lesions. Moreover, mutational cluster analysis showed substantial clonal dynamics during leukemia progression from initial diagnosis to relapse after allo-SCT. Only very few alterations stayed constant over time. This dynamic clonality was exemplified by the detection of thiopurine resistance-mediating mutations in the nucleotidase NT5C2 in 3 patients' first relapses, which disappeared in the post–allo-SCT relapses on relief of selective pressure of maintenance chemotherapy. Moreover, we identified TP53 mutations in 4 of 10 patients after allo-SCT, reflecting acquired chemoresistance associated with selective pressure of prior antineoplastic treatment. Finally, in 9 of 10 children's post–allo-SCT relapse, we found alterations in genes for which targeted therapies with novel agents are readily available. We could show efficient targeting of leukemic blasts by APR-246 in 2 patients carrying TP53 mutations. Our findings shed light on the genetic basis of post–allo-SCT relapse and may pave the way for unraveling novel therapeutic strategies in this challenging situation.

Abstract Background Long non-coding RNAs (lncRNAs) have emerged as a novel class of RNA due to its diverse mechanism in cancer development and progression. However, the role and expression pattern of lncRNAs in molecular subtypes of B cell acute lymphoblastic leukemia (BCP-ALL) have not yet been investigated. Here, we assess to what extent lncRNA expression and DNA methylation is driving the progression of relapsed BCP-ALL subtypes and we determine if the expression and DNA methylation profile of lncRNAs correlates with established BCP-ALL subtypes. Methods We performed RNA sequencing and DNA methylation (Illumina Infinium microarray) of 40 diagnosis and 42 relapse samples from 45 BCP-ALL patients in a German cohort and quantified lncRNA expression. Unsupervised clustering was applied to ascertain and confirm that the lncRNA-based classification of the BCP-ALL molecular subtypes is present in both our cohort and an independent validation cohort of 47 patients. A differential expression and differential methylation analysis was applied to determine the subtype-specific, relapse-specific, and differentially methylated lncRNAs. Potential functions of subtype-specific lncRNAs were determined by using co-expression-based analysis on nearby (cis) and distally (trans) located protein-coding genes. Results Using an integrative Bioinformatics analysis, we developed a comprehensive catalog of 1235 aberrantly dysregulated BCP-ALL subtype-specific and 942 relapse-specific lncRNAs and the methylation profile of three subtypes of BCP-ALL. The 1235 subtype-specific lncRNA signature represented a similar classification of the molecular subtypes of BCP-ALL in the independent validation cohort. We identified a strong correlation between the DUX4-specific lncRNAs and genes involved in the activation of TGF-β and Hippo signaling pathways. Similarly, Ph-like-specific lncRNAs were correlated with genes involved in the activation of PI3K-AKT, mTOR, and JAK-STAT signaling pathways. Interestingly, the relapse-specific lncRNAs correlated with the activation of metabolic and signaling pathways. Finally, we found 23 promoter methylated lncRNAs epigenetically facilitating their expression levels. Conclusion Here, we describe a set of subtype-specific and relapse-specific lncRNAs from three major BCP-ALL subtypes and define their potential functions and epigenetic regulation. The subtype-specific lncRNAs are reproducible and can effectively stratify BCP-ALL subtypes. Our data uncover the diverse mechanism of action of lncRNAs in BCP-ALL subtypes defining which lncRNAs are involved in the pathogenesis of disease and are relevant for the stratification of BCP-ALL subtypes.

Antibodies against polyethylene glycol (PEG) in healthy subjects raise concerns about the efficacy of pegylated drugs. We evaluated the prevalence of antibodies against PEG among patients with acute lymphoblastic leukemia (ALL) prior to and/or immediately after their first dose of pegylated E.coli asparaginase (PEG-ASNase). Serum samples of 701 children, 673 with primary ALL, 28 with relapsed ALL, and 188 adults with primary ALL were analyzed for anti-PEG IgG and IgM. Measurements in 58 healthy infants served as reference to define cut-points for antibody-positive and -negative samples. Anti-PEG antibodies were detected in ALL patients prior the first PEG-ASNase with a prevalence of 13.9% (anti-PEG IgG) and 29.1% (anti-PEG IgM). After administration of PEG-ASNase the prevalence of anti-PEG antibodies decreased to 4.2% for anti-PEG IgG and to 4.5% for anti-PEG IgM. Pre-existing anti-PEG antibodies did not inhibit PEG-ASNase activity but significantly reduced PEGASNase activity levels in a concentration dependent manner. Although pre-existing anti-PEG antibodies did not boost, pre-existing anti-PEG IgG were significantly associated with firstexposure hypersensitivity reactions (CTCAE grade 2) (p

As the metabolic role of kidney fat remains unclear, we investigated the effects of dietary weight loss on kidney fat content (KFC) and its connection to kidney function and metabolism. Overweight or obese participants (n = 137) of a dietary intervention trial were classified into quartiles of weight loss in a post hoc manner. Kidney sinus (KSF) and cortex fat (KCF) were measured by magnetic resonance imaging at baseline, week 12 and week 50. Weight loss effects on KFC were evaluated by linear mixed models. Repeated measures correlations between KFC, other body fat measures and metabolic biomarkers were obtained. KSF, but not KCF, decreased significantly across weight loss quartiles at week 12 (quartile 4: −21.3%; p = 0.02) and 50 (−22.0%, p = 0.001), which remained significant after adjusting for VAT. There were smaller improvements regarding creatinine (−2.5%, p = 0.02) at week 12, but not week 50. KSF, but not KCF, correlated with visceral (rrm = 0.38) and subcutaneous fat volumes (rrm = 0.31) and liver fat content (rrm = 0.32), as well as diastolic blood pressure and biomarkers of lipid, glucose and liver metabolism. Dietary weight loss is associated with decreases in KSF, but not KCF, which suggests that KSF may be the metabolically relevant ectopic fat depot of the kidney. KSF may be targeted for obesity-related disease prevention.

Abstract Backround Non-alcoholic fatty liver disease (NAFLD) comprises non-progressive steatosis and non-alcoholic steatohepatitis (NASH), the latter of which may cause cirrhosis and hepatocellular carcinoma (HCC). As NAFLD detection is imperative for the prevention of its complications, we evaluated whether a combination of blood-based biomarkers and anthropometric parameters can be used to predict NAFLD among overweight and obese adults. Methods 143 overweight or obese non-smokers free of diabetes (50% women, age: 35–65 years) were recruited. Anthropometric indices and routine biomarkers of metabolism and liver function were measured to predict magnetic resonance (MR) - derived NAFLD by multivariable logistic regression models. In addition, we evaluated to which degree the use of more novel biomarkers (adiponectin, leptin, resistin, C-reactive protein, TNF-α, IL-6, IL-8 and interferon-γ) could improve prediction models. Results NAFLD was best predicted by a combination of age, sex, waist circumference, ALT, HbA1c, and HOMA-IR at an area under the receiver operating characteristic curve (AUROC) of 0.87 (95% CI: 0.81, 0.93) before and 0.85 (95% CI: 0.78, 0.91) after internal bootstrap validation. The use of additional biomarkers of inflammation and metabolism did not improve NAFLD prediction. Previously published indices predicted NAFLD at AUROCs between 0.71 and 0.82. Conclusions The AUROC of > 0.8 obtained by our regression model suggests the feasibility of a non-invasive detection of NAFLD by anthropometry and circulating biomarkers, even though further increments in the capacity of prediction models may be needed before NAFLD indices can be applied in routine clinical practice.

Children with other extramedullary relapse of acute lymphoblastic leukemia are currently poorly characterized. We aim to assess the prevalence and the clinical, therapeutic and prognostic features of extramedullary localizations other than central nervous system or testis in children with relapse of acute lymphoblastic leukemia (ALL) and lymphoblastic lymphoma (LBL) treated on a relapsed ALL protocol. Patients and Methods: Patients with relapse of ALL and LBL, treated according to the multicentric ALL-REZ BFM trials between 1983 and 2015, were analyzed for other extramedullary relapse (OEMR) of the disease regarding clinical features, treatment and outcome. Local treatment/irradiation has been recommended on an individual basis and performed only in a minority of patients. Results: A total of 132 out of 2323 (5.6%) patients with ALL relapse presented with an OEMR (combined bone marrow relapse n = 78; isolated extramedullary relapse n = 54). Compared to the non-OEMR group, patients with OEMR had a higher rate of T-immunophenotype (p < 0.001), a higher rate of LBL (p < 0.001) and a significantly different distribution of time to relapse, i.e., more very early and late relapses compared to the non-OEMR group (p = 0.01). Ten-year probabilities of event-free survival (pEFS) and overall survival (pOS) in non-OEMR vs. OEMR were 0.38 ± 0.01 and 0.32 ± 0.04 (p = 0.0204) vs. 0.45 ± 0.01 and 0.37 ± 0.04 (p = 0.0112), respectively. OEMRs have been classified into five subgroups according to the main affected compartment: lymphatic organs (n = 32, 10y-pEFS 0.50 ± 0.09), mediastinum (n = 35, 10y-pEFS 0.11 ± 0.05), bone (n = 12, 0.17 ± 0.11), skin and glands (n = 21, 0.32 ± 0.11) and other localizations (n = 32, 0.41 ± 0.09). Patients with OEMR and T-lineage ALL/LBL showed a significantly worse 10y-pEFS (0.15 ± 0.04) than those with B-Precursor-ALL (0.49 ± 0.06, p < 0.001). Stratified into standard risk (SR) and high risk (HR) groups, pEFS and pOS of OEMR subgroups were in the expected range whereas the mediastinal subgroup had a significantly worse outcome. Subsequent relapses involved more frequently the bone marrow (58.4%) than isolated extramedullary compartments (41.7%). In multivariate Cox regression, OEMR confers an independent prognostic factor for inferior pEFS and pOS. Conclusion: OEMR is adversely related to prognosis. However, the established risk classification can be applied for all subgroups except mediastinal relapses requiring treatment intensification. Generally, isolated OEMR of T-cell-origin needs an intensified treatment including allogeneic stem cell transplantation (HSCT) as a curative approach independent from time to relapse. Local therapy such as surgery and irradiation may be of benefit in selected cases. The indication needs to be clarified in further investigations.