ABSTRACT
The shocking severity of the Covid-19 pandemic has woken up an unprecedented interest and accelerated effort of the scientific community to model and forecast epidemic spreading to find ways to control it regionally and between regions. Here we present a model that in addition to describing the dynamics of epidemic spreading with the traditional compartmental approach takes into account the social behaviour of the population distributed over a geographical region. The region to be modelled is defined as a two-dimensional grid of cells, in which each cell is weighted with the population density. In each cell a compartmental SEIRS system of delay difference equations is used to simulate the local dynamics of the disease. The infections between cells are modelled by a network of connections, which could be terrestrial, between neighbouring cells, or long range, between cities by air, road or train traffic. In addition, since people make trips without apparent reason, noise is considered to account for them to carry contagion between two randomly chosen distant cells. Hence, there is a clear separation of the parameters related to the biological characteristics of the disease from the ones that represent the spatial spread of infections due to social behaviour. We demonstrate that these parameters provide sufficient information to trace the evolution of the pandemic in different situations. In order to show the predictive power of this kind of approach we have chosen three, in a number of ways different countries, Mexico, Finland and Iceland, in which the pandemics have followed different dynamic paths. Furthermore we find that our model seems quite capable of reproducing the path of the pandemic for months with few initial data. Unlike similar models, our model shows the emergence of multiple waves in the case when the disease becomes endemic.
ABSTRACT
The rapid dynamics of COVID-19 calls for quick and effective tracking of virus transmission chains and early detection of outbreaks, especially in the "phase 2" of the pandemic, when lockdown and other restriction measures are progressively withdrawn, in order to avoid or minimize contagion resurgence. For this purpose, contact-tracing apps are being proposed for large scale adoption by many countries. A centralized approach, where data sensed by the app are all sent to a nation-wide server, raises concerns about citizens' privacy and needlessly strong digital surveillance, thus alerting us to the need to minimize personal data collection and avoiding location tracking. We advocate the conceptual advantage of a decentralized approach, where both contact and location data are collected exclusively in individual citizens' "personal data stores", to be shared separately and selectively (e.g., with a backend system, but possibly also with other citizens), voluntarily, only when the citizen has tested positive for COVID-19, and with a privacy preserving level of granularity. This approach better protects the personal sphere of citizens and affords multiple benefits: it allows for detailed information gathering for infected people in a privacy-preserving fashion; and, in turn this enables both contact tracing, and, the early detection of outbreak hotspots on more finely-granulated geographic scale. The decentralized approach is also scalable to large populations, in that only the data of positive patients need be handled at a central level. Our recommendation is two-fold. First to extend existing decentralized architectures with a light touch, in order to manage the collection of location data locally on the device, and allow the user to share spatio-temporal aggregates-if and when they want and for specific aims-with health authorities, for instance. Second, we favour a longer-term pursuit of realizing a Personal Data Store vision, giving users the opportunity to contribute to collective good in the measure they want, enhancing self-awareness, and cultivating collective efforts for rebuilding society.
ABSTRACT
We investigate the dynamics of regular fractal-like networks of hierarchically coupled van der Pol oscillators. The hierarchy is imposed in terms of the coupling strengths or link weights. We study the low frequency modes, as well as frequency and phase synchronization, in the network by a process of repeated coarse-graining of oscillator units. At any given stage of this process, we sum over the signals from the oscillator units of a clique to obtain a new oscillating unit. The frequencies and the phases for the coarse-grained oscillators are found to progressively synchronize with the number of coarse-graining steps. Furthermore, the characteristic frequency is found to decrease and finally stabilize to a value that can be tuned via the parameters of the system. We compare our numerical results with those of an approximate analytic solution and find good qualitative agreement. Our study on this idealized model shows how oscillations with a precise frequency can be obtained in systems with heterogeneous couplings. It also demonstrates the effect of imposing a hierarchy in terms of link weights instead of one that is solely topological, where the connectivity between oscillators would be the determining factor, as is usually the case.
ABSTRACT
Timings of human activities are marked by circadian clocks which in turn are entrained to different environmental signals. In an urban environment the presence of artificial lighting and various social cues tend to disrupt the natural entrainment with the sunlight. However, it is not completely understood to what extent this is the case. Here we exploit the large-scale data analysis techniques to study the mobile phone calling activity of people in large cities to infer the dynamics of urban daily rhythms. From the calling patterns of about 1,000,000 users spread over different cities but lying inside the same time-zone, we show that the onset and termination of the calling activity synchronizes with the east-west progression of the sun. We also find that the onset and termination of the calling activity of users follows a yearly dynamics, varying across seasons, and that its timings are entrained to solar midnight. Furthermore, we show that the average mid-sleep time of people living in urban areas depends on the age and gender of each cohort as a result of biological and social factors.
Subject(s)
Cell Phone , Human Activities , Movement , Adult , Aged , Aged, 80 and over , Algorithms , Circadian Clocks , Circadian Rhythm , Cities , Data Collection , Environment , Female , Humans , Light , Lighting , Male , Middle Aged , Probability , Seasons , Sleep , Temperature , Time Factors , Urban Population , Young AdultABSTRACT
Reputation is an important social construct in science, which enables informed quality assessments of both publications and careers of scientists in the absence of complete systemic information. However, the relation between reputation and career growth of an individual remains poorly understood, despite recent proliferation of quantitative research evaluation methods. Here, we develop an original framework for measuring how a publication's citation rate Δc depends on the reputation of its central author i, in addition to its net citation count c. To estimate the strength of the reputation effect, we perform a longitudinal analysis on the careers of 450 highly cited scientists, using the total citations Ci of each scientist as his/her reputation measure. We find a citation crossover c×, which distinguishes the strength of the reputation effect. For publications with c < c×, the author's reputation is found to dominate the annual citation rate. Hence, a new publication may gain a significant early advantage corresponding to roughly a 66% increase in the citation rate for each tenfold increase in Ci. However, the reputation effect becomes negligible for highly cited publications meaning that, for c ≥ c×, the citation rate measures scientific impact more transparently. In addition, we have developed a stochastic reputation model, which is found to reproduce numerous statistical observations for real careers, thus providing insight into the microscopic mechanisms underlying cumulative advantage in science.
Subject(s)
Bibliometrics , Career Mobility , Publishing/statistics & numerical data , Research Personnel/standards , Research/standards , Computer Simulation , Models, Statistical , Monte Carlo Method , Research/statistics & numerical dataABSTRACT
Recent studies on electronic communication records have shown that human communication has complex temporal structure. We study how communication patterns that involve multiple individuals are affected by attributes such as sex and age. To this end, we represent the communication records as a colored temporal network where node color is used to represent individuals' attributes, and identify patterns known as temporal motifs. We then construct a null model for the occurrence of temporal motifs that takes into account the interaction frequencies and connectivity between nodes of different colors. This null model allows us to detect significant patterns in call sequences that cannot be observed in a static network that uses interaction frequencies as link weights. We find sex-related differences in communication patterns in a large dataset of mobile phone records and show the existence of temporal homophily, the tendency of similar individuals to participate in communication patterns beyond what would be expected on the basis of their average interaction frequencies. We also show that temporal patterns differ between dense and sparse neighborhoods in the network. Because also this result is independent of interaction frequencies, it can be seen as an extension of Granovetter's hypothesis to temporal networks.
Subject(s)
Cell Phone/statistics & numerical data , Communication , Interpersonal Relations , Models, Theoretical , Social Behavior , Age Factors , Data Mining/methods , Female , Humans , Male , Pattern Recognition, Automated , Sex Factors , Time FactorsABSTRACT
Almost 100 genetic loci are known to affect serum cholesterol and triglyceride levels. For many of these loci, the biological function and causal variants remain unknown. We performed an association analysis of the reported 95 lipid loci against 216 metabolite measures, including 95 measurements on lipids and lipoprotein subclasses, obtained via serum nuclear magnetic resonance metabolomics and four enzymatic lipid traits in 8330 individuals from Finland. The genetic variation in the loci was investigated using a dense set of 440 807 directly genotyped and imputed variants around the previously identified lead single nucleotide polymorphisms (SNPs). For 30 of the 95 loci, we identified new metabolic or genetic associations (P < 5 × 10(-8)). In the majority of the loci, the strongest association was to a more specific metabolite measure than the enzymatic lipids. In four loci, the smallest high-density lipoprotein measures showed effects opposite to the larger ones, and 14 loci had associations beyond the individual lipoprotein measures. In 27 loci, we identified SNPs with a stronger association than the previously reported markers and 12 loci harboured multiple, statistically independent variants. Our data show considerable diversity in association patterns between the loci originally identified through associations with enzymatic lipid measures and reveal association profiles of far greater detail than from routine clinical lipid measures. Additionally, a dense marker set and a homogeneous population allow for detailed characterization of the genetic association signals to a resolution exceeding that achieved so far. Further understanding of the rich variability in genetic effects on metabolites provides insights into the biological processes modifying lipid levels.
Subject(s)
Genetic Loci/genetics , Lipid Metabolism/physiology , Lipoproteins/genetics , Lipoproteins/metabolism , Metabolic Syndrome/genetics , Metabolic Syndrome/metabolism , Adolescent , Adult , Aged , Aged, 80 and over , Case-Control Studies , Child , Cohort Studies , Female , Finland/epidemiology , Follow-Up Studies , Genome-Wide Association Study , Humans , Longitudinal Studies , Magnetic Resonance Spectroscopy , Male , Metabolic Syndrome/epidemiology , Metabolomics , Middle Aged , Phenotype , Polymorphism, Single Nucleotide/genetics , Quantitative Trait Loci/genetics , Risk FactorsABSTRACT
Honesty plays a crucial role in any situation where organisms exchange information or resources. Dishonesty can thus be expected to have damaging effects on social coherence if agents cannot trust the information or goods they receive. However, a distinction is often drawn between prosocial lies ('white' lies) and antisocial lying (i.e. deception for personal gain), with the former being considered much less destructive than the latter. We use an agent-based model to show that antisocial lying causes social networks to become increasingly fragmented. Antisocial dishonesty thus places strong constraints on the size and cohesion of social communities, providing a major hurdle that organisms have to overcome (e.g. by evolving counter-deception strategies) in order to evolve large, socially cohesive communities. In contrast, white lies can prove to be beneficial in smoothing the flow of interactions and facilitating a larger, more integrated network. Our results demonstrate that these group-level effects can arise as emergent properties of interactions at the dyadic level. The balance between prosocial and antisocial lies may set constraints on the structure of social networks, and hence the shape of society as a whole.
Subject(s)
Deception , Social Behavior , Social Support , Animals , Humans , Models, Theoretical , TrustABSTRACT
Cephalometric analysis is critically important and common procedure prior to orthodontic treatment and orthognathic surgery. Recently, deep learning approaches have been proposed for automatic 3D cephalometric analysis based on landmarking from CBCT scans. However, these approaches have relied on uniform datasets from a single center or imaging device but without considering patient ethnicity. In addition, previous works have considered a limited number of clinically relevant cephalometric landmarks and the approaches were computationally infeasible, both impairing integration into clinical workflow. Here our aim is to analyze the clinical applicability of a light-weight deep learning neural network for fast localization of 46 clinically significant cephalometric landmarks with multi-center, multi-ethnic, and multi-device data consisting of 309 CBCT scans from Finnish and Thai patients. The localization performance of our approach resulted in the mean distance of 1.99 ± 1.55 mm for the Finnish cohort and 1.96 ± 1.25 mm for the Thai cohort. This performance turned out to be clinically significant i.e., ≤ 2 mm with 61.7% and 64.3% of the landmarks with Finnish and Thai cohorts, respectively. Furthermore, the estimated landmarks were used to measure cephalometric characteristics successfully i.e., with ≤ 2 mm or ≤ 2° error, on 85.9% of the Finnish and 74.4% of the Thai cases. Between the two patient cohorts, 33 of the landmarks and all cephalometric characteristics had no statistically significant difference (p < 0.05) measured by the Mann-Whitney U test with Benjamini-Hochberg correction. Moreover, our method is found to be computationally light, i.e., providing the predictions with the mean duration of 0.77 s and 2.27 s with single machine GPU and CPU computing, respectively. Our findings advocate for the inclusion of this method into clinical settings based on its technical feasibility and robustness across varied clinical datasets.
Subject(s)
Anatomic Landmarks , Cephalometry , Cone-Beam Computed Tomography , Deep Learning , Imaging, Three-Dimensional , Humans , Cephalometry/methods , Cone-Beam Computed Tomography/methods , Imaging, Three-Dimensional/methods , Male , Female , Anatomic Landmarks/diagnostic imaging , Finland , Adult , Thailand , Young Adult , AdolescentABSTRACT
A global disaster, such as the recent Covid-19 pandemic, affects every aspect of our lives and there is a need to investigate these highly complex phenomena if one aims to diminish their impact in the health of the population, as well as their socio-economic stability. In this paper we present an attempt to understand the role of the governmental authorities and the response of the rest of the population facing such emergencies. We present a mathematical model that takes into account the epidemiological features of the pandemic and also the actions of people responding to it, focusing only on three aspects of the system, namely, the fear of catching this serious disease, the impact on the economic activities and the compliance of the people to the mitigating measures adopted by the authorities. We apply the model to the specific case of Spain, since there are accurate data available about these three features. We focused on tourism as an example of the economic activity, since this sector of economy is one of the most likely to be affected by the restrictions imposed by the authorities, and because it represents an important part of Spanish economy. The results of numerical calculations agree with the empirical data in such a way that we can acquire a better insight of the different processes at play in such a complex situation, and also in other different circumstances.
Subject(s)
COVID-19 , Disasters , Humans , Spain/epidemiology , Pandemics , COVID-19/epidemiology , Socioeconomic FactorsABSTRACT
BACKGROUND: Radiotherapy is a core treatment modality for oropharyngeal cancer (OPC), where the primary gross tumor volume (GTVp) is manually segmented with high interobserver variability. This calls for reliable and trustworthy automated tools in clinician workflow. Therefore, accurate uncertainty quantification and its downstream utilization is critical. METHODS: Here we propose uncertainty-aware deep learning for OPC GTVp segmentation, and illustrate the utility of uncertainty in multiple applications. We examine two Bayesian deep learning (BDL) models and eight uncertainty measures, and utilize a large multi-institute dataset of 292 PET/CT scans to systematically analyze our approach. RESULTS: We show that our uncertainty-based approach accurately predicts the quality of the deep learning segmentation in 86.6% of cases, identifies low performance cases for semi-automated correction, and visualizes regions of the scans where the segmentations likely fail. CONCLUSIONS: Our BDL-based analysis provides a first-step towards more widespread implementation of uncertainty quantification in OPC GTVp segmentation.
Radiotherapy is used as a treatment for people with oropharyngeal cancer. It is important to distinguish the areas where cancer is present so the radiotherapy treatment can be targeted at the cancer. Computational methods based on artificial intelligence can automate this task but need to be able to distinguish areas where it is unclear whether cancer is present. In this study we compare these computational methods that are able to highlight areas where it is unclear whether or not cancer is present. Our approach accurately predicts how well these areas are distinguished by the models. Our results could be applied to improve the computational methods used during radiotherapy treatment. This could enable more targeted treatment to be used in the future, which could result in better outcomes for people with oropharyngeal cancer.
ABSTRACT
Information-communication technology promotes collaborative environments like Wikipedia where, however, controversy and conflicts can appear. To describe the rise, persistence, and resolution of such conflicts, we devise an extended opinion dynamics model where agents with different opinions perform a single task to make a consensual product. As a function of the convergence parameter describing the influence of the product on the agents, the model shows spontaneous symmetry breaking of the final consensus opinion represented by the medium. In the case when agents are replaced with new ones at a certain rate, a transition from mainly consensus to a perpetual conflict occurs, which is in qualitative agreement with the scenarios observed in Wikipedia.
Subject(s)
Conflict, Psychological , Consensus , Models, Theoretical , Social Support , Information Services , Social MediaABSTRACT
Information on cyber-related crimes, incidents, and conflicts is abundantly available in numerous open online sources. However, processing large volumes and streams of data is a challenging task for the analysts and experts, and entails the need for newer methods and techniques. In this article we present and implement a novel knowledge graph and knowledge mining framework for extracting the relevant information from free-form text about incidents in the cyber domain. The computational framework includes a machine learning-based pipeline for generating graphs of organizations, countries, industries, products and attackers with a non-technical cyber-ontology. The extracted knowledge graph is utilized to estimate the incidence of cyberattacks within a given graph configuration. We use publicly available collections of real cyber-incident reports to test the efficacy of our methods. The knowledge extraction is found to be sufficiently accurate, and the graph-based threat estimation demonstrates a level of correlation with the actual records of attacks. In practical use, an analyst utilizing the presented framework can infer additional information from the current cyber-landscape in terms of the risk to various entities and its propagation between industries and countries.
ABSTRACT
Preoperative radiological identification of mandibular canals is essential for maxillofacial surgery. This study demonstrates the reproducibility of a deep learning system (DLS) by evaluating its localisation performance on 165 heterogeneous cone beam computed tomography (CBCT) scans from 72 patients in comparison to an experienced radiologist's annotations. We evaluated the performance of the DLS using the symmetric mean curve distance (SMCD), the average symmetric surface distance (ASSD), and the Dice similarity coefficient (DSC). The reproducibility of the SMCD was assessed using the within-subject coefficient of repeatability (RC). Three other experts rated the diagnostic validity twice using a 0-4 Likert scale. The reproducibility of the Likert scoring was assessed using the repeatability measure (RM). The RC of SMCD was 0.969 mm, the median (interquartile range) SMCD and ASSD were 0.643 (0.186) mm and 0.351 (0.135) mm, respectively, and the mean (standard deviation) DSC was 0.548 (0.138). The DLS performance was most affected by postoperative changes. The RM of the Likert scoring was 0.923 for the radiologist and 0.877 for the DLS. The mean (standard deviation) Likert score was 3.94 (0.27) for the radiologist and 3.84 (0.65) for the DLS. The DLS demonstrated proficient qualitative and quantitative reproducibility, temporal generalisability, and clinical validity.
Subject(s)
Deep Learning , Spiral Cone-Beam Computed Tomography , Humans , Mandibular Canal , Reproducibility of Results , Cone-Beam Computed TomographyABSTRACT
Background: Demand for head and neck cancer (HNC) radiotherapy data in algorithmic development has prompted increased image dataset sharing. Medical images must comply with data protection requirements so that re-use is enabled without disclosing patient identifiers. Defacing, i.e., the removal of facial features from images, is often considered a reasonable compromise between data protection and re-usability for neuroimaging data. While defacing tools have been developed by the neuroimaging community, their acceptability for radiotherapy applications have not been explored. Therefore, this study systematically investigated the impact of available defacing algorithms on HNC organs at risk (OARs). Methods: A publicly available dataset of magnetic resonance imaging scans for 55 HNC patients with eight segmented OARs (bilateral submandibular glands, parotid glands, level II neck lymph nodes, level III neck lymph nodes) was utilized. Eight publicly available defacing algorithms were investigated: afni_refacer, DeepDefacer, defacer, fsl_deface, mask_face, mri_deface, pydeface, and quickshear. Using a subset of scans where defacing succeeded (N=29), a 5-fold cross-validation 3D U-net based OAR auto-segmentation model was utilized to perform two main experiments: 1.) comparing original and defaced data for training when evaluated on original data; 2.) using original data for training and comparing the model evaluation on original and defaced data. Models were primarily assessed using the Dice similarity coefficient (DSC). Results: Most defacing methods were unable to produce any usable images for evaluation, while mask_face, fsl_deface, and pydeface were unable to remove the face for 29%, 18%, and 24% of subjects, respectively. When using the original data for evaluation, the composite OAR DSC was statistically higher (p ≤ 0.05) for the model trained with the original data with a DSC of 0.760 compared to the mask_face, fsl_deface, and pydeface models with DSCs of 0.742, 0.736, and 0.449, respectively. Moreover, the model trained with original data had decreased performance (p ≤ 0.05) when evaluated on the defaced data with DSCs of 0.673, 0.693, and 0.406 for mask_face, fsl_deface, and pydeface, respectively. Conclusion: Defacing algorithms may have a significant impact on HNC OAR auto-segmentation model training and testing. This work highlights the need for further development of HNC-specific image anonymization methods.
ABSTRACT
Background: Oropharyngeal cancer (OPC) is a widespread disease, with radiotherapy being a core treatment modality. Manual segmentation of the primary gross tumor volume (GTVp) is currently employed for OPC radiotherapy planning, but is subject to significant interobserver variability. Deep learning (DL) approaches have shown promise in automating GTVp segmentation, but comparative (auto)confidence metrics of these models predictions has not been well-explored. Quantifying instance-specific DL model uncertainty is crucial to improving clinician trust and facilitating broad clinical implementation. Therefore, in this study, probabilistic DL models for GTVp auto-segmentation were developed using large-scale PET/CT datasets, and various uncertainty auto-estimation methods were systematically investigated and benchmarked. Methods: We utilized the publicly available 2021 HECKTOR Challenge training dataset with 224 co-registered PET/CT scans of OPC patients with corresponding GTVp segmentations as a development set. A separate set of 67 co-registered PET/CT scans of OPC patients with corresponding GTVp segmentations was used for external validation. Two approximate Bayesian deep learning methods, the MC Dropout Ensemble and Deep Ensemble, both with five submodels, were evaluated for GTVp segmentation and uncertainty performance. The segmentation performance was evaluated using the volumetric Dice similarity coefficient (DSC), mean surface distance (MSD), and Hausdorff distance at 95% (95HD). The uncertainty was evaluated using four measures from literature: coefficient of variation (CV), structure expected entropy, structure predictive entropy, and structure mutual information, and additionally with our novel Dice-risk measure. The utility of uncertainty information was evaluated with the accuracy of uncertainty-based segmentation performance prediction using the Accuracy vs Uncertainty (AvU) metric, and by examining the linear correlation between uncertainty estimates and DSC. In addition, batch-based and instance-based referral processes were examined, where the patients with high uncertainty were rejected from the set. In the batch referral process, the area under the referral curve with DSC (R-DSC AUC) was used for evaluation, whereas in the instance referral process, the DSC at various uncertainty thresholds were examined. Results: Both models behaved similarly in terms of the segmentation performance and uncertainty estimation. Specifically, the MC Dropout Ensemble had 0.776 DSC, 1.703 mm MSD, and 5.385 mm 95HD. The Deep Ensemble had 0.767 DSC, 1.717 mm MSD, and 5.477 mm 95HD. The uncertainty measure with the highest DSC correlation was structure predictive entropy with correlation coefficients of 0.699 and 0.692 for the MC Dropout Ensemble and the Deep Ensemble, respectively. The highest AvU value was 0.866 for both models. The best performing uncertainty measure for both models was the CV which had R-DSC AUC of 0.783 and 0.782 for the MC Dropout Ensemble and Deep Ensemble, respectively. With referring patients based on uncertainty thresholds from 0.85 validation DSC for all uncertainty measures, on average the DSC improved from the full dataset by 4.7% and 5.0% while referring 21.8% and 22% patients for MC Dropout Ensemble and Deep Ensemble, respectively. Conclusion: We found that many of the investigated methods provide overall similar but distinct utility in terms of predicting segmentation quality and referral performance. These findings are a critical first-step towards more widespread implementation of uncertainty quantification in OPC GTVp segmentation.
ABSTRACT
Importance: Sarcopenia is an established prognostic factor in patients with head and neck squamous cell carcinoma (HNSCC); the quantification of sarcopenia assessed by imaging is typically achieved through the skeletal muscle index (SMI), which can be derived from cervical skeletal muscle segmentation and cross-sectional area. However, manual muscle segmentation is labor intensive, prone to interobserver variability, and impractical for large-scale clinical use. Objective: To develop and externally validate a fully automated image-based deep learning platform for cervical vertebral muscle segmentation and SMI calculation and evaluate associations with survival and treatment toxicity outcomes. Design, Setting, and Participants: For this prognostic study, a model development data set was curated from publicly available and deidentified data from patients with HNSCC treated at MD Anderson Cancer Center between January 1, 2003, and December 31, 2013. A total of 899 patients undergoing primary radiation for HNSCC with abdominal computed tomography scans and complete clinical information were selected. An external validation data set was retrospectively collected from patients undergoing primary radiation therapy between January 1, 1996, and December 31, 2013, at Brigham and Women's Hospital. The data analysis was performed between May 1, 2022, and March 31, 2023. Exposure: C3 vertebral skeletal muscle segmentation during radiation therapy for HNSCC. Main Outcomes and Measures: Overall survival and treatment toxicity outcomes of HNSCC. Results: The total patient cohort comprised 899 patients with HNSCC (median [range] age, 58 [24-90] years; 140 female [15.6%] and 755 male [84.0%]). Dice similarity coefficients for the validation set (n = 96) and internal test set (n = 48) were 0.90 (95% CI, 0.90-0.91) and 0.90 (95% CI, 0.89-0.91), respectively, with a mean 96.2% acceptable rate between 2 reviewers on external clinical testing (n = 377). Estimated cross-sectional area and SMI values were associated with manually annotated values (Pearson r = 0.99; P < .001) across data sets. On multivariable Cox proportional hazards regression, SMI-derived sarcopenia was associated with worse overall survival (hazard ratio, 2.05; 95% CI, 1.04-4.04; P = .04) and longer feeding tube duration (median [range], 162 [6-1477] vs 134 [15-1255] days; hazard ratio, 0.66; 95% CI, 0.48-0.89; P = .006) than no sarcopenia. Conclusions and Relevance: This prognostic study's findings show external validation of a fully automated deep learning pipeline to accurately measure sarcopenia in HNSCC and an association with important disease outcomes. The pipeline could enable the integration of sarcopenia assessment into clinical decision making for individuals with HNSCC.
Subject(s)
Deep Learning , Head and Neck Neoplasms , Sarcopenia , Humans , Male , Female , Middle Aged , Squamous Cell Carcinoma of Head and Neck/diagnostic imaging , Retrospective Studies , Sarcopenia/diagnostic imaging , Sarcopenia/complications , Head and Neck Neoplasms/complications , Head and Neck Neoplasms/diagnostic imagingABSTRACT
Purpose: Sarcopenia is an established prognostic factor in patients diagnosed with head and neck squamous cell carcinoma (HNSCC). The quantification of sarcopenia assessed by imaging is typically achieved through the skeletal muscle index (SMI), which can be derived from cervical neck skeletal muscle (SM) segmentation and cross-sectional area. However, manual SM segmentation is labor-intensive, prone to inter-observer variability, and impractical for large-scale clinical use. To overcome this challenge, we have developed and externally validated a fully-automated image-based deep learning (DL) platform for cervical vertebral SM segmentation and SMI calculation, and evaluated the relevance of this with survival and toxicity outcomes. Materials and Methods: 899 patients diagnosed as having HNSCC with CT scans from multiple institutes were included, with 335 cases utilized for training, 96 for validation, 48 for internal testing and 393 for external testing. Ground truth single-slice segmentations of SM at the C3 vertebra level were manually generated by experienced radiation oncologists. To develop an efficient method of segmenting the SM, a multi-stage DL pipeline was implemented, consisting of a 2D convolutional neural network (CNN) to select the middle slice of C3 section and a 2D U-Net to segment SM areas. The model performance was evaluated using the Dice Similarity Coefficient (DSC) as the primary metric for the internal test set, and for the external test set the quality of automated segmentation was assessed manually by two experienced radiation oncologists. The L3 skeletal muscle area (SMA) and SMI were then calculated from the C3 cross sectional area (CSA) of the auto-segmented SM. Finally, established SMI cut-offs were used to perform further analyses to assess the correlation with survival and toxicity endpoints in the external institution with univariable and multivariable Cox regression. Results: DSCs for validation set (n = 96) and internal test set (n = 48) were 0.90 (95% CI: 0.90 - 0.91) and 0.90 (95% CI: 0.89 - 0.91), respectively. The predicted CSA is highly correlated with the ground-truth CSA in both validation (r = 0.99, p < 0.0001) and test sets (r = 0.96, p < 0.0001). In the external test set (n = 377), 96.2% of the SM segmentations were deemed acceptable by consensus expert review. Predicted SMA and SMI values were highly correlated with the ground-truth values, with Pearson r ß 0.99 (p < 0.0001) for both the female and male patients in all datasets. Sarcopenia was associated with worse OS (HR 2.05 [95% CI 1.04 - 4.04], p = 0.04) and longer PEG tube duration (median 162 days vs. 134 days, HR 1.51 [95% CI 1.12 - 2.08], p = 0.006 in multivariate analysis. Conclusion: We developed and externally validated a fully-automated platform that strongly correlates with imaging-assessed sarcopenia in patients with H&N cancer that correlates with survival and toxicity outcomes. This study constitutes a significant stride towards the integration of sarcopenia assessment into decision-making for individuals diagnosed with HNSCC. SUMMARY STATEMENT: In this study, we developed and externally validated a deep learning model to investigate the impact of sarcopenia, defined as the loss of skeletal muscle mass, on patients with head and neck squamous cell carcinoma (HNSCC) undergoing radiotherapy. We demonstrated an efficient, fullyautomated deep learning pipeline that can accurately segment C3 skeletal muscle area, calculate cross-sectional area, and derive a skeletal muscle index to diagnose sarcopenia from a standard of care CT scan. In multi-institutional data, we found that pre-treatment sarcopenia was associated with significantly reduced overall survival and an increased risk of adverse events. Given the increased vulnerability of patients with HNSCC, the assessment of sarcopenia prior to radiotherapy may aid in informed treatment decision-making and serve as a predictive marker for the necessity of early supportive measures.
ABSTRACT
Type 1 diabetic patients with varying severity of kidney disease were investigated to create multimetabolite models of the disease process. Urinary albumin excretion rate was measured for 3358 patients with type 1 diabetes. Prospective records were available for 1051 patients, of whom 163 showed progression of albuminuria (8.3-year follow-up), and 162 were selected as stable controls. At baseline, serum lipids, lipoprotein subclasses, and low-molecular weight metabolites were quantified by NMR spectroscopy (325 samples). The data were analyzed by the self-organizing map. In cross-sectional analyses, patients with no complications had low serum lipids, less inflammation, and better glycemic control, whereas patients with advanced kidney disease had high serum cystatin-C and sphingomyelin. These phenotype extremes shared low unsaturated fatty acids (UFAs) and phospholipids. Prospectively, progressive albuminuria was associated with high UFAs, phospholipids, and IDL and LDL lipids. Progression at longer duration was associated with high HDL lipids, whereas earlier progression was associated with poor glycemic control, increased saturated fatty acids (SFAs), and inflammation. Diabetic kidney disease consists of diverse metabolic phenotypes: UFAs, phospholipids, IDL, and LDL may be important in the subclinical phase, high SFAs and low HDL suggest accelerated progression, and the sphingolipid pathway in advanced kidney injury deserves further research.
Subject(s)
Diabetes Mellitus, Type 1/blood , Diabetic Nephropathies/blood , Adult , Albuminuria , Amino Acids, Branched-Chain/blood , Biomarkers/blood , Diabetes Mellitus, Type 1/complications , Disease Progression , Fatty Acids/blood , Female , Glycated Hemoglobin/metabolism , Humans , Lipoproteins/blood , Logistic Models , Male , Metabolome , Models, Biological , Phenotype , ROC Curve , Statistics, NonparametricABSTRACT
Humans are social animals and the interpersonal bonds formed between them are crucial for their development and well being in a society. These relationships are usually structured into several layers (Dunbar's layers of friendship) depending on their significance in an individual's life with closest friends and family being the most important ones taking major part of their time and communication effort. However, we have little idea how the initiation and termination of these relationships occurs across the lifespan. Mobile phones, in particular, have been used extensively to shed light on the different types of social interactions between individuals and to explore this, we analyse a national cellphone database to determine how and when changes in close relationships occur in the two genders. In general, membership of this inner circle of intimate relationships is extremely stable, at least over a three-year period. However, around 1-4% of alters change every year, with the rate of change being higher among 17-21 year olds than older adults. Young adult females terminate more of their opposite-gender relationships, while older males are more persistent in trying to maintain relationships in decline. These results emphasise the variability in relationship dynamics across age and gender, and remind us that individual differences play an important role in the structure of social networks. Overall, our study provides a holistic understanding of the dynamic nature of close relationships during different stages of human life.