Germline homozygosity and allelic imbalance of HLA-I are common in esophagogastric adenocarcinoma and impair the repertoire of immunogenic peptides.

BACKGROUND: The individual HLA-I genotype is associated with cancer, autoimmune diseases and infections. This study elucidates the role of germline homozygosity or allelic imbalance of HLA-I loci in esophago-gastric adenocarcinoma (EGA) and determines the resulting repertoires of potentially immunogenic peptides. METHODS: HLA genotypes and sequences of either (1) 10 relevant tumor-associated antigens (TAAs) or (2) patient-specific mutation-associated neoantigens (MANAs) were used to predict good-affinity binders using an in silico approach for MHC-binding (www.iedb.org). Imbalanced or lost expression of HLA-I-A/B/C alleles was analyzed by transcriptome sequencing. FluoroSpot assays and TCR sequencing were used to determine peptide-specific T-cell responses. RESULTS: We show that germline homozygosity of HLA-I genes is significantly enriched in EGA patients (n=80) compared with an HLA-matched reference cohort (n=7605). Whereas the overall mutational burden is similar, the repertoire of potentially immunogenic peptides derived from TAAs and MANAs was lower in homozygous patients. Promiscuity of peptides binding to different HLA-I molecules was low for most TAAs and MANAs and in silico modeling of the homozygous to a heterozygous HLA genotype revealed normalized peptide repertoires. Transcriptome sequencing showed imbalanced expression of HLA-I alleles in 75% of heterozygous patients. Out of these, 33% showed complete loss of heterozygosity, whereas 66% had altered expression of only one or two HLA-I molecules. In a FluoroSpot assay, we determined that peptide-specific T-cell responses against NY-ESO-1 are derived from multiple peptides, which often exclusively bind only one HLA-I allele. CONCLUSION: The high frequency of germline homozygosity in EGA patients suggests reduced cancer immunosurveillance leading to an increased cancer risk. Therapeutic targeting of allelic imbalance of HLA-I molecules should be considered in EGA.

Membrane damage by MBP-1 is mediated by pore formation and amplified by mtDNA.

Eosinophils play a crucial role in host defense while also contributing to immunopathology through the release of inflammatory mediators. Characterized by distinctive cytoplasmic granules, eosinophils securely store and rapidly release various proteins exhibiting high toxicity upon extracellular release. Among these, major basic protein 1 (MBP-1) emerges as an important mediator in eosinophil function against pathogens and in eosinophil-associated diseases. While MBP-1 targets both microorganisms and host cells, its precise mechanism remains elusive. We demonstrate that formation of small pores by MBP-1 in lipid bilayers induces membrane permeabilization and disrupts potassium balance. Additionally, we reveal that mitochondrial DNA (mtDNA) present in eosinophil extracellular traps (EETs) amplifies MBP-1 toxic effects, underscoring the pivotal role of mtDNA in EETs. Furthermore, we present evidence indicating that absence of CpG methylation in mtDNA contributes to the regulation of MBP-1-mediated toxicity. Taken together, our data suggest that the mtDNA scaffold within extracellular traps promotes MBP-1 toxicity.

IMU-Based Fitness Activity Recognition Using CNNs for Time Series Classification.

Mobile fitness applications provide the opportunity to show users real-time feedback on their current fitness activity. For such applications, it is essential to accurately track the user's current fitness activity using available mobile sensors, such as inertial measurement units (IMUs). Convolutional neural networks (CNNs) have been shown to produce strong results in different time series classification tasks, including the recognition of daily living activities. However, fitness activities can present unique challenges to the human activity recognition task (HAR), including greater similarity between individual activities and fewer available data for model training. In this paper, we evaluate the applicability of CNNs to the fitness activity recognition task (FAR) using IMU data and determine the impact of input data size and sensor count on performance. For this purpose, we adapted three existing CNN architectures to the FAR task and designed a fourth CNN variant, which we call the scaling fully convolutional network (Scaling-FCN). We designed a preprocessing pipeline and recorded a running exercise data set with 20 participants, in which we evaluated the respective recognition performances of the four networks, comparing them with three traditional machine learning (ML) methods commonly used in HAR. Although CNN architectures achieve at least 94% test accuracy in all scenarios, two traditional ML architectures surpass them in the default scenario, with support vector machines (SVMs) achieving 99.00 ± 0.34% test accuracy. The removal of all sensors except one foot sensor reduced the performance of traditional ML architectures but improved the performance of CNN architectures on our data set, with our Scaling-FCN reaching the highest accuracy of 99.86 ± 0.11% on the test set. Our results suggest that CNNs are generally well suited for fitness activity recognition, and noticeable performance improvements can be achieved if sensors are dropped selectively, although traditional ML architectures can still compete with or even surpass CNNs when favorable input data are utilized.

Ganglioglioma cells potentiate neuronal network synchronicity and elicit burst discharges via released factors.

Gangliogliomas (GGs) represent the most frequent glioneuronal tumor entity associated with chronic recurrent seizures; rare anaplastic GGs variants retain the glioneuronal character. So far, key mechanisms triggering chronic hyperexcitability in the peritumoral area are unresolved. Based on a recent mouse model for anaplastic GG (BRAFV600E, mTOR activation and Trp53KO) we here assessed the influence of GG-secreted factors on non-neoplastic cells in-vitro. We generated conditioned medium (CM) from primary GG cell cultures to developing primary cortical neurons cultured on multielectrode-arrays and assessed their electrical activity in comparison to neurons incubated with naïve and neuronal CMs. Our results showed that the GG CM, while not affecting the mean firing rates of networks, strongly accelerated the formation of functional networks as indicated increased synchrony of firing and burst activity. Washing out the GG CM did not reverse these effects indicating an irreversible effect on the neuronal network. Mass spectrometry analysis of GG CM detected several enriched proteins associated with neurogenesis as well as gliogenesis, including Gap43, App, Apoe, S100a8, Tnc and Sod1. Concomitantly, immunocytochemical analysis of the neuronal cultures exposed to GG CM revealed abundant astrocytes suggesting that the GG-secreted factors induce astroglial proliferation. Pharmacological inhibition of astrocyte proliferation only partially reversed the accelerated network maturation in neuronal cultures exposed to GG CM indicating that the GG CM exerts a direct effect on the neuronal component. Taken together, we demonstrate that GG-derived paracrine signaling alone is sufficient to induce accelerated neuronal network development accompanied by astrocytic proliferation. Perspectively, a deeper understanding of factors involved may serve as the basis for future therapeutic approaches.

Human selection bias drives the linear nature of the more ground truth effect in explainable deep learning optical coherence tomography image segmentation.

Supervised deep learning (DL) algorithms are highly dependent on training data for which human graders are assigned, for example, for optical coherence tomography (OCT) image annotation. Despite the tremendous success of DL, due to human judgment, these ground truth labels can be inaccurate and/or ambiguous and cause a human selection bias. We therefore investigated the impact of the size of the ground truth and variable numbers of graders on the predictive performance of the same DL architecture and repeated each experiment three times. The largest training dataset delivered a prediction performance close to that of human experts. All DL systems utilized were highly consistent. Nevertheless, the DL under-performers could not achieve any further autonomous improvement even after repeated training. Furthermore, a quantifiable linear relationship between ground truth ambiguity and the beneficial effect of having a larger amount of ground truth data was detected and marked as the more-ground-truth effect.

Give Me a Sign: Using Data Gloves for Static Hand-Shape Recognition.

Human-to-human communication via the computer is mainly carried out using a keyboard or microphone. In the field of virtual reality (VR), where the most immersive experience possible is desired, the use of a keyboard contradicts this goal, while the use of a microphone is not always desirable (e.g., silent commands during task-force training) or simply not possible (e.g., if the user has hearing loss). Data gloves help to increase immersion within VR, as they correspond to our natural interaction. At the same time, they offer the possibility of accurately capturing hand shapes, such as those used in non-verbal communication (e.g., thumbs up, okay gesture, …) and in sign language. In this paper, we present a hand-shape recognition system using Manus Prime X data gloves, including data acquisition, data preprocessing, and data classification to enable nonverbal communication within VR. We investigate the impact on accuracy and classification time of using an outlier detection and a feature selection approach in our data preprocessing. To obtain a more generalized approach, we also studied the impact of artificial data augmentation, i.e., we created new artificial data from the recorded and filtered data to augment the training data set. With our approach, 56 different hand shapes could be distinguished with an accuracy of up to 93.28%. With a reduced number of 27 hand shapes, an accuracy of up to 95.55% could be achieved. The voting meta-classifier (VL2) proved to be the most accurate, albeit slowest, classifier. A good alternative is random forest (RF), which was even able to achieve better accuracy values in a few cases and was generally somewhat faster. outlier detection was proven to be an effective approach, especially in improving the classification time. Overall, we have shown that our hand-shape recognition system using data gloves is suitable for communication within VR.

Brain-derived Tau for Monitoring Brain Injury in Acute Ischemic Stroke.

The evolution of infarcts varies widely among patients with acute ischemic stroke (IS) and influences treatment decisions. Neuroimaging is not applicable for frequent monitoring and there is no blood-based biomarker to track ongoing brain injury in acute IS. Here, we examined the utility of plasma brain-derived tau (BD-tau) as a biomarker for brain injury in acute IS. We conducted the prospective, observational Precision Medicine in Stroke [PROMISE] study with serial blood sampling upon hospital admission and at days 2, 3, and 7 in patients with acute ischemic stroke (IS) and for comparison, in patients with stroke mimics (SM). We determined the temporal course of plasma BD-tau, its relation to infarct size and admission imaging-based metrics of brain injury, and its value to predict functional outcome. Upon admission (median time-from-onset, 4.4h), BD-tau levels in IS patients correlated with ASPECTS (ρ=-0.21, P<.0001) and were predictive of final infarct volume (ρ=0.26, P<.0001). In contrast to SM patients, BD-tau levels in IS patients increased from admission (median, 2.9 pg/ml [IQR, 1.8-4.8]) to day 2 (median time-from-onset, 22.7h; median BD-tau, 5.0 pg/ml [IQR, 2.6-10.3]; P<.0001). The rate of change of BD-tau from admission to day 2 was significantly associated with collateral supply (R2=0.10, P<.0001) and infarct progression (ρ=0.58, P<.0001). At day 2, BD-tau was predictive of final infarct volume (ρ=0.59, P<.0001) and showed superior value for predicting the 90-day mRS score compared with final infarct volume. In conclusion, in 502 patients with acute IS, plasma BD-tau was associated with imaging-based metrics of brain injury upon admission, increased within the first 24 hours in correlation with infarct progression, and at 24 hours was superior to final infarct volume in predicting 90-day functional outcome. Further research is needed to determine whether BD-tau assessments can inform decision-making in stroke care.

ADAMTS-7 Modulates Atherosclerotic Plaque Formation by Degradation of TIMP-1.

BACKGROUND: The ADAMTS7 locus was genome-wide significantly associated with coronary artery disease. Lack of the ECM (extracellular matrix) protease ADAMTS-7 (A disintegrin and metalloproteinase-7) was shown to reduce atherosclerotic plaque formation. Here, we sought to identify molecular mechanisms and downstream targets of ADAMTS-7 mediating the risk of atherosclerosis. METHODS: Targets of ADAMTS-7 were identified by high-resolution mass spectrometry of atherosclerotic plaques from Apoe-/- and Apoe-/-Adamts7-/- mice. ECM proteins were identified using solubility profiling. Putative targets were validated using immunofluorescence, in vitro degradation assays, coimmunoprecipitation, and Förster resonance energy transfer-based protein-protein interaction assays. ADAMTS7 expression was measured in fibrous caps of human carotid artery plaques. RESULTS: In humans, ADAMTS7 expression was higher in caps of unstable as compared to stable carotid plaques. Compared to Apoe-/- mice, atherosclerotic aortas of Apoe-/- mice lacking Adamts-7 (Apoe-/-Adamts7-/-) contained higher protein levels of Timp-1 (tissue inhibitor of metalloprotease-1). In coimmunoprecipitation experiments, the catalytic domain of ADAMTS-7 bound to TIMP-1, which was degraded in the presence of ADAMTS-7 in vitro. ADAMTS-7 reduced the inhibitory capacity of TIMP-1 at its canonical target MMP-9 (matrix metalloprotease-9). As a downstream mechanism, we investigated collagen content in plaques of Apoe-/- and Apoe-/-Adamts7-/- mice after a Western diet. Picrosirius red staining of the aortic root revealed less collagen as a readout of higher MMP-9 activity in Apoe-/- as compared to Apoe-/- Adamts7-/- mice. To facilitate high-throughput screening for ADAMTS-7 inhibitors with the aim of decreasing TIMP-1 degradation, we designed a Förster resonance energy transfer-based assay targeting the ADAMTS-7 catalytic site. CONCLUSIONS: ADAMTS-7, which is induced in unstable atherosclerotic plaques, decreases TIMP-1 stability reducing its inhibitory effect on MMP-9, which is known to promote collagen degradation and is likewise associated with coronary artery disease. Disrupting the interaction of ADAMTS-7 and TIMP-1 might be a strategy to increase collagen content and plaque stability for the reduction of atherosclerosis-related events.

Highly functionalized diaminocyclopentanes: A new route to potent and selective inhibitors of human O-GlcNAcase.

A new class of compounds inhibiting de-O-glycosylation of proteins has been identified. Highly substituted diaminocyclopentanes are impressively selective reversible non-transition state O-ß-N-acetyl-d-glucosaminidase (O-GlcNAcase) inhibitors. The ease of preparative access and remarkable biological activities provide highly viable leads for the development of anti-tau-phosphorylation agents with a view to eventually ameliorating Alzheimer's disease.

Rational design of PD-1-CD28 immunostimulatory fusion proteins for CAR T cell therapy.

BACKGROUND: In many situations, the therapeutic efficacy of CAR T cells is limited due to immune suppression and poor persistence. Immunostimulatory fusion protein (IFP) constructs have been advanced as a tool to convert suppressive signals into stimulation and thus promote the persistence of T cells, but no universal IFP design has been established so far. We now took advantage of a PD-1-CD28 IFP as a clinically relevant structure to define key determinants of IFP activity. METHODS: We compared different PD-1-CD28 IFP variants in a human leukemia model to assess the impact of distinctive design choices on CAR T cell performance in vitro and a xenograft mouse model. RESULTS: We observed that IFP constructs that putatively exceed the extracellular length of PD-1 induce T-cell response without CAR target recognition, rendering them unsuitable for tumour-specific therapy. IFP variants with physiological PD-1 length ameliorated CAR T cell effector function and proliferation in response to PD-L1+ tumour cells in vitro and prolonged survival in vivo. Transmembrane or extracellular CD28 domains were found to be replaceable by corresponding PD-1 domains for in vivo efficacy. CONCLUSION: PD-1-CD28 IFP constructs must mimic the physiological interaction of PD-1 with PD-L1 to retain selectivity and mediate CAR-conditional therapeutic activity.

Architecture of industrial Bi-Mo-Co-Fe-K-O propene oxidation catalysts.

Industrial heterogeneous catalysts show high performance coupled with high material complexity. Deconvoluting this complexity into simplified models eases mechanistic studies. However, this approach dilutes the relevance because models are often less performing. We present a holistic approach to reveal the origin of high performance without losing the relevance by pivoting the system at an industrial benchmark. Combining kinetic and structural analyses, we show how the performance of Bi-Mo-Co-Fe-K-O industrial acrolein catalysts occurs. The surface BiMoO ensembles decorated with K supported on ß-Co1-xFexMoO4 perform the propene oxidation, while the K-doped iron molybdate pools electrons to activate dioxygen. The nanostructured vacancy-rich and self-doped bulk phases ensure the charge transport between the two active sites. The features particular to the real system enable the high performance.

Progression, reliability, predicting parameters and sample size calculations for quantitative fundus autofluorescence measures in ABCA4-related retinopathy.

BACKGROUND/AIMS: To investigate the progression of quantitative autofluorescence (qAF) measures and the potential as clinical trial endpoint in ABCA4-related retinopathy. METHODS: In this longitudinal monocentre study, 64 patients with ABCA4-related retinopathy (age (mean±SD), 34.84±16.36 years) underwent serial retinal imaging, including optical coherence tomography (OCT) and qAF (488 nm excitation) imaging using a modified confocal scanning laser ophthalmoscope with a mean (±SD) review period of 20.32±10.90 months. A group of 110 healthy subjects served as controls. Retest variability, changes of qAF measures over time and its association with genotype and phenotype were analysed. Furthermore, individual prognostic feature importance was assessed, and sample size calculations for future interventional trials were performed. RESULTS: Compared with controls, qAF levels of patients were significantly elevated. The test-retest reliability revealed a 95% coefficient of repeatability of 20.37. During the observation time, young patients, patients with a mild phenotype (morphological and functional) and patients with mild mutations showed an absolute and relative increase in qAF values, while patients with advanced disease manifestation (morphological and functional), and homozygous mutations at adulthood revealed a decrease in qAF. Considering these parameters, required sample size and study duration could significantly be reduced. CONCLUSION: Under standardised settings with elaborated conditions towards operators and analysis to counterbalance variability, qAF imaging might be reliable, suitable for quantifying disease progression and constitutes a potential clinical surrogate marker in ABCA4-related retinopathy. Trial design based on patients' baseline characteristics and genotype has the potential to provide benefits regarding required cohort size and absolute number of visits.

Bispecific antibodies redirect synthetic agonistic receptor modified T cells against melanoma.

BACKGROUND: Melanoma is an immune sensitive disease, as demonstrated by the activity of immune check point blockade (ICB), but many patients will either not respond or relapse. More recently, tumor infiltrating lymphocyte (TIL) therapy has shown promising efficacy in melanoma treatment after ICB failure, indicating the potential of cellular therapies. However, TIL treatment comes with manufacturing limitations, product heterogeneity, as well as toxicity problems, due to the transfer of a large number of phenotypically diverse T cells. To overcome said limitations, we propose a controlled adoptive cell therapy approach, where T cells are armed with synthetic agonistic receptors (SAR) that are selectively activated by bispecific antibodies (BiAb) targeting SAR and melanoma-associated antigens. METHODS: Human as well as murine SAR constructs were generated and transduced into primary T cells. The approach was validated in murine, human and patient-derived cancer models expressing the melanoma-associated target antigens tyrosinase-related protein 1 (TYRP1) and melanoma-associated chondroitin sulfate proteoglycan (MCSP) (CSPG4). SAR T cells were functionally characterized by assessing their specific stimulation and proliferation, as well as their tumor-directed cytotoxicity, in vitro and in vivo. RESULTS: MCSP and TYRP1 expression was conserved in samples of patients with treated as well as untreated melanoma, supporting their use as melanoma-target antigens. The presence of target cells and anti-TYRP1 × anti-SAR or anti-MCSP × anti-SAR BiAb induced conditional antigen-dependent activation, proliferation of SAR T cells and targeted tumor cell lysis in all tested models. In vivo, antitumoral activity and long-term survival was mediated by the co-administration of SAR T cells and BiAb in a syngeneic tumor model and was further validated in several xenograft models, including a patient-derived xenograft model. CONCLUSION: The SAR T cell-BiAb approach delivers specific and conditional T cell activation as well as targeted tumor cell lysis in melanoma models. Modularity is a key feature for targeting melanoma and is fundamental towards personalized immunotherapies encompassing cancer heterogeneity. Because antigen expression may vary in primary melanoma tissues, we propose that a dual approach targeting two tumor-associated antigens, either simultaneously or sequentially, could avoid issues of antigen heterogeneity and deliver therapeutic benefit to patients.

Correction: Digital Phenotyping for Differential Diagnosis of Major Depressive Episode: Narrative Review.

[This corrects the article DOI: 10.2196/37225.].

Why loss of Y? A pan-cancer genome analysis of tumors with loss of Y chromosome.

Loss of the Y chromosome (LoY) is frequently observed in somatic cells of elderly men. However, LoY is highly increased in tumor tissue and correlates with an overall worse prognosis. The underlying causes and downstream effects of LoY are widely unknown. Therefore, we analyzed genomic and transcriptomic data of 13 cancer types (2375 patients) and classified tumors of male patients according to loss or retain of the Y chromosome (LoY or RoY, average LoY fraction: 0.46). The frequencies of LoY ranged from almost absence (glioblastoma, glioma, thyroid carcinoma) to 77% (kidney renal papillary cell carcinoma). Genomic instability, aneuploidy, and mutation burden were enriched in LoY tumors. In addition, we found more frequently in LoY tumors the gate keeping tumor suppressor gene TP53 mutated in three cancer types (colon adenocarcinoma, head and neck squamous carcinoma, lung adenocarcinoma) and oncogenes MET, CDK6, KRAS, and EGFR amplified in multiple cancer types. On the transcriptomic level, we observed MMP13, known to be involved in invasion, to be up-regulated in LoY of three adenocarcinomas and down-regulation of the tumor suppressor gene GPC5 in LoY of three cancer types. Furthermore, we found enrichment of a smoking-related mutation signature in LoY tumors of head and neck and lung cancer. Strikingly, we observed a correlation between cancer type-specific sex bias in incidence rates and frequencies of LoY, in line with the hypothesis that LoY increases cancer risk in males. Overall, LoY is a frequent phenomenon in cancer that is enriched in genomically unstable tumors. It correlates with genomic features beyond the Y chromosome and might contribute to higher incidence rates in males.

NanoDefiner Framework and e-Tool Revisited According to the European Commission's Nanomaterial Definition 2022/C 229/01.

The new recommended definition of a nanomaterial, 2022/C 229/01, adopted by the European Commission in 2022, will have a considerable impact on European Union legislation addressing chemicals, and therefore tools to implement this new definition are urgently needed. The updated NanoDefiner framework and its e-tool implementation presented here are such instruments, which help stakeholders to find out in a straightforward way whether a material is a nanomaterial or not. They are two major outcomes of the NanoDefine project, which is explicitly referred to in the new definition. This work revisits the framework and e-tool, and elaborates necessary adjustments to make these outcomes applicable for the updated recommendation. A broad set of case studies on representative materials confirms the validity of these adjustments. To further foster the sustainability and applicability of the framework and e-tool, measures for the FAIRification of expert knowledge within the e-tool's knowledge base are elaborated as well. The updated framework and e-tool are now ready to be used in line with the updated recommendation. The presented approach may serve as an example for reviewing existing guidance and tools developed for the previous definition 2011/696/EU, particularly those adopting NanoDefine project outcomes.

Single-cell transcriptomic atlas-guided development of CAR-T cells for the treatment of acute myeloid leukemia.

Chimeric antigen receptor T cells (CAR-T cells) have emerged as a powerful treatment option for individuals with B cell malignancies but have yet to achieve success in treating acute myeloid leukemia (AML) due to a lack of safe targets. Here we leveraged an atlas of publicly available RNA-sequencing data of over 500,000 single cells from 15 individuals with AML and tissue from 9 healthy individuals for prediction of target antigens that are expressed on malignant cells but lacking on healthy cells, including T cells. Aided by this high-resolution, single-cell expression approach, we computationally identify colony-stimulating factor 1 receptor and cluster of differentiation 86 as targets for CAR-T cell therapy in AML. Functional validation of these established CAR-T cells shows robust in vitro and in vivo efficacy in cell line- and human-derived AML models with minimal off-target toxicity toward relevant healthy human tissues. This provides a strong rationale for further clinical development.

Metabolic patterns on [18F]FDG PET/CT in patients with unresectable stage III NSCLC undergoing chemoradiotherapy ± durvalumab maintenance treatment.

PURPOSE: In patients with unresectable stage III non-small-cell lung cancer (NSCLC), durvalumab maintenance treatment after chemoradiotherapy (CRT) significantly improves survival. So far, however, metabolic changes of tumoral lesions and secondary lymphoid organs under durvalumab are unknown. Hence, we assessed changes on [18F]FDG PET/CT in comparison to patients undergoing CRT alone. METHODS: Forty-three patients with [18F]FDG PET/CT both before and after standard CRT for unresectable stage III NSCLC were included, in 16/43 patients durvalumab maintenance treatment was initiated (CRT-IO) prior to the second PET/CT. Uptake of tumor sites and secondary lymphoid organs was compared between CRT and CRT-IO. Also, readers were blinded for durvalumab administration and reviewed scans for findings suspicious for immunotherapy-related adverse events (irAE). RESULTS: Initial uptake characteristics were comparable. However, under durvalumab, diverging metabolic patterns were noted: There was a significantly higher reduction of tumoral uptake intensity in CRT-IO compared to CRT, e.g. median decrease of SUVmax -70.0% vs. -24.8%, p = 0.009. In contrast, the spleen uptake increased in CRT-IO while it dropped in CRT (median + 12.5% vs. -4.4%, p = 0.029). Overall survival was significantly longer in CRT-IO compared to CRT with few events (progression/death) noted in CRT-IO. Findings suggestive of irAE were present on PET/CT more often in CRT-IO (12/16) compared to CRT (8/27 patients), p = 0.005. CONCLUSION: Durvalumab maintenance treatment after CRT leads to diverging tumoral metabolic changes, but also increases splenic metabolism and leads to a higher proportion of findings suggestive of irAE compared to patients without durvalumab. Due to significantly prolonged survival with durvalumab, survival analysis will be substantiated in correlation to metabolic changes as soon as more clinical events are present.

Surrogate Modelling for Oxygen Uptake Prediction Using LSTM Neural Network.

Oxygen uptake (V˙O2) is an important metric in any exercise test including walking and running. It can be measured using portable spirometers or metabolic analyzers. Those devices are, however, not suitable for constant use by consumers due to their costs, difficulty of operation and their intervening in the physical integrity of their users. Therefore, it is important to develop approaches for the indirect estimation of V˙O2-based measurements of motion parameters, heart rate data and application-specific measurements from consumer-grade sensors. Typically, these approaches are based on linear regression models or neural networks. This study investigates how motion data contribute to V˙O2 estimation accuracy during unconstrained running and walking. The results suggest that a long short term memory (LSTM) neural network can predict oxygen consumption with an accuracy of 2.49 mL/min/kg (95% limits of agreement) based only on speed, speed change, cadence and vertical oscillation measurements from an inertial navigation system combined with a Global Positioning System (INS/GPS) device developed by our group, worn on the torso. Combining motion data and heart rate data can significantly improve the V˙O2 estimation resulting in approximately 1.7-1.9 times smaller prediction errors than using only motion or heart rate data.