RESUMO
Background The extent of left ventricular (LV) trabeculation and its relationship with cardiovascular (CV) risk factors is unclear. Purpose To apply automated segmentation to UK Biobank cardiac MRI scans to (a) assess the association between individual characteristics and CV risk factors and trabeculated LV mass (LVM) and (b) establish normal reference ranges in a selected group of healthy UK Biobank participants. Materials and Methods In this cross-sectional secondary analysis, prospectively collected data from the UK Biobank (2006 to 2010) were retrospectively analyzed. Automated segmentation of trabeculations was performed using a deep learning algorithm. After excluding individuals with known CV diseases, White adults without CV risk factors (reference group) and those with preexisting CV risk factors (hypertension, hyperlipidemia, diabetes mellitus, or smoking) (exposed group) were compared. Multivariable regression models, adjusted for potential confounders (age, sex, and height), were fitted to evaluate the associations between individual characteristics and CV risk factors and trabeculated LVM. Results Of 43 038 participants (mean age, 64 years ± 8 [SD]; 22 360 women), 28 672 individuals (mean age, 66 years ± 7; 14 918 men) were included in the exposed group, and 7384 individuals (mean age, 60 years ± 7; 4729 women) were included in the reference group. Higher body mass index (BMI) (ß = 0.66 [95% CI: 0.63, 0.68]; P < .001), hypertension (ß = 0.42 [95% CI: 0.36, 0.48]; P < .001), and higher physical activity level (ß = 0.15 [95% CI: 0.12, 0.17]; P < .001) were associated with higher trabeculated LVM. In the reference group, the median trabeculated LVM was 6.3 g (IQR, 4.7-8.5 g) for men and 4.6 g (IQR, 3.4-6.0 g) for women. Median trabeculated LVM decreased with age for men from 6.5 g (IQR, 4.8-8.7 g) at age 45-50 years to 5.9 g (IQR, 4.3-7.8 g) at age 71-80 years (P = .03). Conclusion Higher trabeculated LVM was observed with hypertension, higher BMI, and higher physical activity level. Age- and sex-specific reference ranges of trabeculated LVM in a healthy middle-aged White population were established. © RSNA, 2024 Supplemental material is available for this article. See also the editorial by Kawel-Boehm in this issue.
Assuntos
Doenças Cardiovasculares , Hipertensão , Adulto , Masculino , Pessoa de Meia-Idade , Feminino , Humanos , Idoso , Idoso de 80 Anos ou mais , Bancos de Espécimes Biológicos , Doenças Cardiovasculares/diagnóstico por imagem , Estudos Transversais , Valores de Referência , Estudos Retrospectivos , Biobanco do Reino Unido , Fatores de Risco , Imageamento por Ressonância Magnética , Fatores de Risco de Doenças Cardíacas , Hipertensão/complicações , Hipertensão/epidemiologiaRESUMO
Addressing the ecological and evolutionary processes underlying biodiversity patterns is essential to identify the mechanisms shaping community structure and function. In bacteria, the formation of new ecologically distinct populations (ecotypes) is proposed as one of the main drivers of diversification. New ecotypes arise when mutations in key functional genes or acquisition of new metabolic pathways by horizontal gene transfer allow the population to exploit new resources, permitting their coexistence with the parental population. We previously reported the presence of microcystin-producing organisms of the Microcystis aeruginosa complex (toxic MAC) through an 800-km environmental gradient ranging from freshwater to estuarine-marine waters in South America. We hypothesize that the success of toxic MAC in such a gradient is due to the existence of very closely related populations that are ecologically distinct (ecotypes), each specialized to a specific arrangement of environmental variables. Here, we analyzed toxic MAC genetic diversity through quantitative PCR (qPCR) and high-resolution melting analysis (HRMA) of a functional gene (mcyJ, microcystin synthetase cluster). We explored the variability of the mcyJ gene along the environmental gradient by multivariate classification and regression trees (mCART). Six groups of mcyJ genotypes were distinguished and associated with different combinations of water temperature, conductivity, and turbidity. We propose that each mcyJ variant associated with a defined environmental condition is an ecotype (or species) whose relative abundances vary according to their fitness in the local environment. This mechanism would explain the success of toxic MAC in such a wide array of environmental conditions. IMPORTANCE Organisms of the Microcystis aeruginosa complex form harmful algal blooms (HABs) in nutrient-rich water bodies worldwide. MAC HABs are difficult to manage owing to the production of potent toxins (microcystins) that resist water treatment. In addition, the role of microcystins in the ecology of MAC organisms is still elusive, meaning that the environmental conditions driving the toxicity of the bloom are not clear. Furthermore, the lack of coherence between morphology-based and genomic-based species classification makes it difficult to draw sound conclusions about when and where each member species of the MAC will dominate the bloom. Here, we propose that the diversification process and success of toxic MAC in a wide range of water bodies involves the generation of ecotypes, each specialized in a particular niche, whose relative abundance varies according to its fitness in the local environment. This knowledge can improve the generation of accurate prediction models of MAC growth and toxicity, helping to prevent human and animal intoxication.
Assuntos
Microcystis , Biodiversidade , Água Doce/microbiologia , Genótipo , Proliferação Nociva de Algas , Microcistinas , Microcystis/genéticaRESUMO
OBJECTIVE: With the strengths of deep learning, computer-aided diagnosis (CAD) is a hot topic for researchers in medical image analysis. One of the main requirements for training a deep learning model is providing enough data for the network. However, in medical images, due to the difficulties of data collection and data privacy, finding an appropriate dataset (balanced, enough samples, etc.) is quite a challenge. Although image synthesis could be beneficial to overcome this issue, synthesizing 3D images is a hard task. The main objective of this paper is to generate 3D T1 weighted MRI corresponding to FDG-PET. In this study, we propose a separable convolution-based Elicit generative adversarial network (E-GAN). The proposed architecture can reconstruct 3D T1 weighted MRI from 2D high-level features and geometrical information retrieved from a Sobel filter. Experimental results on the ADNI datasets for healthy subjects show that the proposed model improves the quality of images compared with the state of the art. In addition, the evaluation of E-GAN and the state of art methods gives a better result on the structural information (13.73% improvement for PSNR and 22.95% for SSIM compared to Pix2Pix GAN) and textural information (6.9% improvements for homogeneity error in Haralick features compared to Pix2Pix GAN).
Assuntos
Fluordesoxiglucose F18 , Processamento de Imagem Assistida por Computador , Humanos , Processamento de Imagem Assistida por Computador/métodos , Imageamento Tridimensional , Imageamento por Ressonância Magnética/métodos , Tomografia por Emissão de PósitronsRESUMO
OBJECTIVE: Quality of life (QoL) is still assessed using paper-based and fixed-length questionnaires, which is one reason why QoL measurements have not been routinely implemented in clinical practice. Providing new QoL measures that combine computer technology with modern measurement theory may enhance their clinical use. The aim of this study was to develop a QoL multidimensional computerized adaptive test (MCAT), the SQoL-MCAT, from the fixed-length SQoL questionnaire for patients with schizophrenia. METHODS: In this multicentre cross-sectional study, we collected sociodemographic information, clinical characteristics (i.e., duration of illness, the PANSS, and the Calgary Depression Scale), and quality of life (i.e., SQoL). The development of the SQoL-CAT was divided into three stages: (1) multidimensional item response theory (MIRT) analysis, (2) multidimensional computerized adaptive test (MCAT) simulations with analyses of accuracy and precision, and (3) external validity. RESULTS: Five hundred and seventeen patients participated in this study. The MIRT analysis found that all items displayed good fit with the multidimensional graded response model, with satisfactory reliability for each dimension. The SQoL-MCAT was 39% shorter than the fixed-length SQoL questionnaire and had satisfactory accuracy (levels of correlation >0.9) and precision (standard error of measurement <0.55 and root mean square error <0.3). External validity was confirmed via correlations between the SQoL-MCAT dimension scores and symptomatology scores. CONCLUSION: The SQoL-MCAT is the first computerized adaptive QoL questionnaire for patients with schizophrenia. Tailored for patient characteristics and significantly shorter than the paper-based version, the SQoL-MCAT may improve the feasibility of assessing QoL in clinical practice.
Assuntos
Computadores/estatística & dados numéricos , Psicometria/métodos , Qualidade de Vida/psicologia , Psicologia do Esquizofrênico , Adulto , Estudos Transversais , Feminino , Humanos , Masculino , Pessoa de Meia-Idade , Inquéritos e QuestionáriosRESUMO
BACKGROUND: Studies have suggested that clinicians do not feel comfortable with the interpretation of symptom severity, functional status, and quality of life (QoL). Implementation strategies of these types of measurements in clinical practice imply that consensual norms and guidelines regarding data interpretation are available. The aim of this study was to define subgroups of patients according to the levels of symptom severity using a method of interpretable clustering that uses unsupervised binary trees. METHODS: The patients were classified using a top-down hierarchical method: Clustering using Unsupervised Binary Trees (CUBT). We considered a three-group structure: "high", "moderate", and "low" level of symptom severity. The clustering tree was based on three stages using the 9-symptom scale scores of the EORTC QLQ-C30: a maximal tree was first developed by applying a recursive partitioning algorithm; the tree was then pruned using a criterion of minimal dissimilarity; finally, the most similar clusters were joined together. Inter-cluster comparisons were performed to test the sample partition and QoL data. RESULTS: Two hundred thirty-five patients with different types of cancer were included. The three-cluster structure classified 143 patients with "low", 46 with "moderate", and 46 with "high" levels of symptom severity. This partition was explained by cut-off values on Fatigue and Appetite Loss scores. The three clusters consistently differentiated patients based on the clinical characteristics and QoL outcomes. CONCLUSION: Our study suggests that CUBT is relevant to define the levels of symptom severity in cancer. This finding may have important implications for helping clinicians to interpret symptom profiles in clinical practice, to identify individuals at risk for poorer outcomes and implement targeted interventions.
Assuntos
Análise por Conglomerados , Neoplasias/epidemiologia , Qualidade de Vida/psicologia , Estudos Transversais , Feminino , Humanos , Masculino , Pessoa de Meia-IdadeRESUMO
BACKGROUND: To enhance the use of quality of life (QoL) measures in clinical practice, it is pertinent to help clinicians interpret QoL scores. OBJECTIVE: The aim of this study was to define clusters of QoL levels from a specific questionnaire (MusiQoL) for multiple sclerosis (MS) patients using a new method of interpretable clustering based on unsupervised binary trees and to test the validity regarding clinical and functional outcomes. METHODS: In this international, multicenter, cross-sectional study, patients with MS were classified using a hierarchical top-down method of Clustering using Unsupervised Binary Trees. The clustering tree was built using the 9 dimension scores of the MusiQoL in 2 stages, growing and tree reduction (pruning and joining). A 3-group structure was considered, as follows: "high," "moderate," and "low" QoL levels. Clinical and QoL data were compared between the 3 clusters. RESULTS: A total of 1361 patients were analyzed: 87 were classified with "low," 1173 with "moderate," and 101 with "high" QoL levels. The clustering showed satisfactory properties, including repeatability (using bootstrap) and discriminancy (using factor analysis). The 3 clusters consistently differentiated patients based on sociodemographic and clinical characteristics, and the QoL scores were assessed using a generic questionnaire, ensuring the clinical validity of the clustering. CONCLUSIONS: The study suggests that Clustering using Unsupervised Binary Trees is an original, innovative, and relevant classification method to define clusters of QoL levels in MS patients.
Assuntos
Esclerose Múltipla/psicologia , Qualidade de Vida , Adulto , Análise por Conglomerados , Estudos Transversais , Feminino , Humanos , Masculino , Pessoa de Meia-Idade , Psicometria , Inquéritos e QuestionáriosRESUMO
Childhood brain tumors show great histological variability. The goal of this retrospective study was to assess the diagnostic accuracy of multimodal MR imaging (diffusion, perfusion, MR spectroscopy) in the distinction of pediatric brain tumor grades and types. Seventy-six patients (range 1 month to 18 years) with brain tumors underwent multimodal MR imaging. Tumors were categorized by grade (I-IV) and by histological type (A-H). Multivariate statistical analysis was performed to evaluate the diagnostic accuracy of single and combined MR modalities, and of single imaging parameters to distinguish the different groups. The highest diagnostic accuracy for tumor grading was obtained with diffusion-perfusion (73.24%) and for tumor typing with diffusion-perfusion-MR spectroscopy (55.76%). The best diagnostic accuracy was obtained for tumor grading in I and IV and for tumor typing in embryonal tumor and pilocytic astrocytoma. Poor accuracy was seen in other grades and types. ADC and rADC were the best parameters for tumor grading and typing followed by choline level with an intermediate echo time, CBV for grading and Tmax for typing. Multiparametric MR imaging can be accurate in determining tumor grades (primarily grades I and IV) and types (mainly pilocytic astrocytomas and embryonal tumors) in children.
Assuntos
Neoplasias Encefálicas/diagnóstico por imagem , Neoplasias Encefálicas/patologia , Imagem de Difusão por Ressonância Magnética/métodos , Adolescente , Astrocitoma/diagnóstico por imagem , Astrocitoma/patologia , Neoplasias Encefálicas/classificação , Criança , Pré-Escolar , Feminino , Seguimentos , Glioma/diagnóstico por imagem , Glioma/patologia , Humanos , Lactente , Espectroscopia de Ressonância Magnética , Masculino , Gradação de Tumores , Estadiamento de Neoplasias , Prognóstico , Estudos Retrospectivos , Taxa de SobrevidaRESUMO
OBJECTIVE: Quality of life (QoL) measurements are considered important outcome measures both for research on multiple sclerosis (MS) and in clinical practice. Computerized adaptive testing (CAT) can improve the precision of measurements made using QoL instruments while reducing the burden of testing on patients. Moreover, a cross-cultural approach is also necessary to guarantee the wide applicability of CAT. The aim of this preliminary study was to develop a calibrated item bank that is available in multiple languages and measures QoL related to mental health by combining one generic (SF-36) and one disease-specific questionnaire (MusiQoL). METHODS: Patients with MS were enrolled in this international, multicenter, cross-sectional study. The psychometric properties of the item bank were based on classical test and item response theories and approaches, including the evaluation of unidimensionality, item response theory model fitting, and analyses of differential item functioning (DIF). Convergent and discriminant validities of the item bank were examined according to socio-demographic, clinical, and QoL features. RESULTS: A total of 1992 patients with MS and from 15 countries were enrolled in this study to calibrate the 22-item bank developed in this study. The strict monotonicity of the Cronbach's alpha curve, the high eigenvalue ratio estimator (5.50), and the adequate CFA model fit (RMSEA = 0.07 and CFI = 0.95) indicated that a strong assumption of unidimensionality was warranted. The infit mean square statistic ranged from 0.76 to 1.27, indicating a satisfactory item fit. DIF analyses revealed no item biases across geographical areas, confirming the cross-cultural equivalence of the item bank. External validity testing revealed that the item bank scores correlated significantly with QoL scores but also showed discriminant validity for socio-demographic and clinical characteristics. CONCLUSION: This work demonstrated satisfactory psychometric characteristics for a QoL item bank for MS in multiple languages. This work may offer a common measure for the assessment of QoL in different cultural contexts and for international studies conducted on MS.
Assuntos
Saúde Mental , Esclerose Múltipla/psicologia , Qualidade de Vida/psicologia , Adulto , Comparação Transcultural , Estudos Transversais , Feminino , Humanos , Masculino , Pessoa de Meia-Idade , Psicometria , Inquéritos e QuestionáriosRESUMO
PURPOSE: The classification of patients into distinct categories of quality of life (QoL) levels may be useful for clinicians to interpret QoL scores from multidimensional questionnaires. The aim of this study had been to define clusters of QoL levels from a specific multidimensional questionnaire (SQoL18) for patients with schizophrenia by using a new method of interpretable clustering and to test its validity regarding socio-demographic, clinical, and QoL information. METHODS: In this multicentre cross-sectional study, patients with schizophrenia have been classified using a hierarchical top-down method called clustering using unsupervised binary trees (CUBT). A three-group structure has been employed to define QoL levels as "high", "moderate", or "low". Socio-demographic, clinical, and QoL data have been compared between the three clusters to ensure their clinical relevance. RESULTS: A total of 514 patients have been analysed: 78 are classified as "low", 265 as "moderate", and 171 as "high". The clustering shows satisfactory statistical properties, including reproducibility (using bootstrap analysis) and discriminancy (using factor analysis). The three clusters consistently differentiate patients. As expected, individuals in the "high" QoL level cluster report the lowest scores on the Positive and Negative Syndrome Scale (p = 0.01) and the Calgary Depression Scale (p < 0.01), and the highest scores on the Global Assessment of Functioning (p < 0.03), the SF36 (p < 0.01), the EuroQol (p < 0.01), and the Quality of Life Inventory (p < 0.01). CONCLUSION: Given the ease with which this method can be applied, classification using CUBT may be useful for facilitating the interpretation of QoL scores in clinical practice.
Assuntos
Esquizofrenia/epidemiologia , Adulto , Análise por Conglomerados , Estudos Transversais , Feminino , Humanos , Masculino , Qualidade de Vida , Inquéritos e QuestionáriosRESUMO
BACKGROUND: Multiple sclerosis (MS), a common neurodegenerative disease, has well-described associations with quality of life (QoL) impairment. QoL changes found in longitudinal studies are difficult to interpret due to the potential response shift (RS) corresponding to respondents' changing standards, values, and conceptualization of QoL. This study proposes to test the capacity of Random Forest (RF) for detecting RS reprioritization as the relative importance of QoL domains' changes over time. METHODS: This was a longitudinal observational study. The main inclusion criteria were patients 18 years old or more with relapsing-remitting multiple sclerosis. Every 6 months up to month 24, QoL was recorded using generic and MS-specific questionnaires (MusiQoL and SF-36). At 24 months, individuals were divided into two 'disability change' groups: worsened and not-worsened patients. The RF method was performed based on Breiman's description. Analyses were performed to determine which QoL scores of SF-36 predicted the MusiQoL index. The average variable importance (AVI) was estimated. RESULTS: A total of 417 (79.6%) patients were defined as not-worsened and 107 (20.4%) as worsened. A clear RS was identified in worsened patients. While the mental score AVI was almost one third higher than the physical score AVI at 12 months, it was 1.5 times lower at 24 months. CONCLUSION: This work confirms that the RF method offers a useful statistical approach for RS detection. How to integrate the RS in the interpretation of QoL scores remains a challenge for future research. TRIAL REGISTRATION: ClinicalTrials.gov identifier: NCT00702065.
Assuntos
Acontecimentos que Mudam a Vida , Esclerose Múltipla Recidivante-Remitente/psicologia , Qualidade de Vida , Adolescente , Adulto , Idoso , Avaliação da Deficiência , Feminino , Humanos , Estudos Longitudinais , Masculino , Pessoa de Meia-Idade , Esclerose Múltipla Recidivante-Remitente/diagnóstico , Esclerose Múltipla Recidivante-Remitente/fisiopatologia , Análise de Regressão , Fatores Socioeconômicos , Inquéritos e QuestionáriosRESUMO
OBJECTIVE: This study aims to develop high-performing Machine Learning and Deep Learning models in predicting hospital length of stay (LOS) while enhancing interpretability. We compare performance and interpretability of models trained only on structured tabular data with models trained only on unstructured clinical text data, and on mixed data. METHODS: The structured data was used to train fourteen classical Machine Learning models including advanced ensemble trees, neural networks and k-nearest neighbors. The unstructured data was used to fine-tune a pre-trained Bio Clinical BERT Transformer Deep Learning model. The structured and unstructured data were then merged into a tabular dataset after vectorization of the clinical text and a dimensional reduction through Latent Dirichlet Allocation. The study used the free and publicly available Medical Information Mart for Intensive Care (MIMIC) III database, on the open AutoML Library AutoGluon. Performance is evaluated with respect to two types of random classifiers, used as baselines. RESULTS: The best model from structured data demonstrates high performance (ROC AUC = 0.944, PRC AUC = 0.655) with limited interpretability, where the most important predictors of prolonged LOS are the level of blood urea nitrogen and of platelets. The Transformer model displays a good but lower performance (ROC AUC = 0.842, PRC AUC = 0.375) with a richer array of interpretability by providing more specific in-hospital factors including procedures, conditions, and medical history. The best model trained on mixed data satisfies both a high level of performance (ROC AUC = 0.963, PRC AUC = 0.746) and a much larger scope in interpretability including pathologies of the intestine, the colon, and the blood; infectious diseases, respiratory problems, procedures involving sedation and intubation, and vascular surgery. CONCLUSIONS: Our results outperform most of the state-of-the-art models in LOS prediction both in terms of performance and of interpretability. Data fusion between structured and unstructured text data may significantly improve performance and interpretability.
Assuntos
Aprendizado de Máquina , Redes Neurais de Computação , Humanos , Tempo de Internação , Cuidados Críticos , RegistrosRESUMO
INTRODUCTION: Prolonged Hospital Length of Stay (PLOS) is an indicator of deteriorated efficiency in Quality of Care. One goal of public health management is to reduce PLOS by identifying its most relevant predictors. The objective of this study is to explore Machine Learning (ML) models that best predict PLOS. METHODS: Our dataset was collected from the French Medico-Administrative database (PMSI) as a retrospective cohort study of all discharges in the year 2015 from a large university hospital in France (APHM). The study outcomes were LOS transformed into a binary variable (long vs. short LOS) according to the 90th percentile (14 days). Logistic regression (LR), classification and regression trees (CART), random forest (RF), gradient boosting (GB) and neural networks (NN) were applied to the collected data. The predictive performance of the models was evaluated using the area under the ROC curve (AUC). RESULTS: Our analysis included 73,182 hospitalizations, of which 7,341 (10.0%) led to PLOS. The GB classifier was the most performant model with the highest AUC (0.810), superior to all the other models (all p-values <0.0001). The performance of the RF, GB and NN models (AUC ranged from 0.808 to 0.810) was superior to that of the LR model (AUC = 0.795); all p-values <0.0001. In contrast, LR was superior to CART (AUC = 0.786), p < 0.0001. The variable most predictive of the PLOS was the destination of the patient after hospitalization to other institutions. The typical clinical profile of these patients (17.5% of the sample) was the elderly patient, admitted in emergency, for a trauma, a neurological or a cardiovascular pathology, more often institutionalized, with more comorbidities notably mental health problems, dementia and hemiplegia. DISCUSSION: The integration of ML, particularly the GB algorithm, may be useful for health-care professionals and bed managers to better identify patients at risk of PLOS. These findings underscore the need to strengthen hospitals through targeted allocation to meet the needs of an aging population.
RESUMO
Objectives: 1) To develop a deep learning (DL) pipeline allowing quantification of COVID-19 pulmonary lesions on low-dose computed tomography (LDCT). 2) To assess the prognostic value of DL-driven lesion quantification. Methods: This monocentric retrospective study included training and test datasets taken from 144 and 30 patients, respectively. The reference was the manual segmentation of 3 labels: normal lung, ground-glass opacity(GGO) and consolidation(Cons). Model performance was evaluated with technical metrics, disease volume and extent. Intra- and interobserver agreement were recorded. The prognostic value of DL-driven disease extent was assessed in 1621 distinct patients using C-statistics. The end point was a combined outcome defined as death, hospitalization>10 days, intensive care unit hospitalization or oxygen therapy. Results: The Dice coefficients for lesion (GGO+Cons) segmentations were 0.75±0.08, exceeding the values for human interobserver (0.70±0.08; 0.70±0.10) and intraobserver measures (0.72±0.09). DL-driven lesion quantification had a stronger correlation with the reference than inter- or intraobserver measures. After stepwise selection and adjustment for clinical characteristics, quantification significantly increased the prognostic accuracy of the model (0.82 vs. 0.90; p<0.0001). Conclusions: A DL-driven model can provide reproducible and accurate segmentation of COVID-19 lesions on LDCT. Automatic lesion quantification has independent prognostic value for the identification of high-risk patients.
RESUMO
Background: To develop a deep-learning (DL) pipeline that allowed an automated segmentation of epicardial adipose tissue (EAT) from low-dose computed tomography (LDCT) and investigate the link between EAT and COVID-19 clinical outcomes. Methods: This monocentric retrospective study included 353 patients: 95 for training, 20 for testing, and 238 for prognosis evaluation. EAT segmentation was obtained after thresholding on a manually segmented pericardial volume. The model was evaluated with Dice coefficient (DSC), inter-and intraobserver reproducibility, and clinical measures. Uni-and multi-variate analyzes were conducted to assess the prognosis value of the EAT volume, EAT extent, and lung lesion extent on clinical outcomes, including hospitalization, oxygen therapy, intensive care unit admission and death. Results: The mean DSC for EAT volumes was 0.85 ± 0.05. For EAT volume, the mean absolute error was 11.7 ± 8.1 cm3 with a non-significant bias of −4.0 ± 13.9 cm3 and a correlation of 0.963 with the manual measures (p < 0.01). The multivariate model providing the higher AUC to predict adverse outcome include both EAT extent and lung lesion extent (AUC = 0.805). Conclusions: A DL algorithm was developed and evaluated to obtain reproducible and precise EAT segmentation on LDCT. EAT extent in association with lung lesion extent was associated with adverse clinical outcomes with an AUC = 0.805.
Assuntos
COVID-19 , Aprendizado Profundo , Tecido Adiposo/diagnóstico por imagem , COVID-19/diagnóstico por imagem , Humanos , Reprodutibilidade dos Testes , Estudos Retrospectivos , Tomografia Computadorizada por Raios X/métodosRESUMO
In clinical applications, using erroneous segmentations of medical images can have dramatic consequences. Current approaches dedicated to medical image segmentation automatic quality control do not predict segmentation quality at slice-level (2D), resulting in sub-optimal evaluations. Our 2D-based deep learning method simultaneously performs quality control at 2D-level and 3D-level for cardiovascular MR image segmentations. We compared it with 3D approaches by training both on 36,540 (2D) / 3842 (3D) samples to predict Dice Similarity Coefficients (DSC) for 4 different structures from the left ventricle, i.e., trabeculations (LVT), myocardium (LVM), papillary muscles (LVPM) and blood (LVC). The 2D-based method outperformed the 3D method. At the 2D-level, the mean absolute errors (MAEs) of the DSC predictions for 3823 samples, were 0.02, 0.02, 0.05 and 0.02 for LVM, LVC, LVT and LVPM, respectively. At the 3D-level, for 402 samples, the corresponding MAEs were 0.02, 0.01, 0.02 and 0.04. The method was validated in a clinical practice evaluation against semi-qualitative scores provided by expert cardiologists for 1016 subjects of the UK BioBank. Finally, we provided evidence that a multi-level QC could be used to enhance clinical measurements derived from image segmentations.
Assuntos
Ventrículos do Coração , Coração , Coração/diagnóstico por imagem , Humanos , Processamento de Imagem Assistida por Computador , Imageamento TridimensionalRESUMO
PURPOSE: To develop and evaluate a complete deep learning pipeline that allows fully automated end-diastolic left ventricle (LV) cardiac MRI segmentation, including trabeculations and automatic quality control of the predicted segmentation. MATERIALS AND METHODS: This multicenter retrospective study includes training, validation, and testing datasets of 272, 27, and 150 cardiac MR images, respectively, collected between 2012 and 2018. The reference standard was the manual segmentation of four LV anatomic structures performed on end-diastolic short-axis cine cardiac MRI: LV trabeculations, LV myocardium, LV papillary muscles, and the LV blood cavity. The automatic pipeline was composed of five steps with a DenseNet architecture. Intraobserver agreement, interobserver agreement, and interaction time were recorded. The analysis includes the correlation between the manual and automated segmentation, a reproducibility comparison, and Bland-Altman plots. RESULTS: The automated method achieved mean Dice coefficients of 0.96 ± 0.01 (standard deviation) for LV blood cavity, 0.89 ± 0.03 for LV myocardium, and 0.62 ± 0.08 for LV trabeculation (mean absolute error, 3.63 g ± 3.4). Automatic quantification of LV end-diastolic volume, LV myocardium mass, LV trabeculation, and trabeculation mass-to-total myocardial mass (TMM) ratio showed a significant correlation with the manual measures (r = 0.99, 0.99, 0.90, and 0.83, respectively; all P < .01). On a subset of 48 patients, the mean Dice value for LV trabeculation was 0.63 ± 0.10 or higher compared with the human interobserver (0.44 ± 0.09; P < .01) and intraobserver measures (0.58 ± 0.09; P < .01). Automatic quantification of the trabeculation mass-to-TMM ratio had a higher correlation (0.92) compared with the intra- and interobserver measures (0.74 and 0.39, respectively; both P < .01). CONCLUSION: Automated deep learning framework can achieve reproducible and quality-controlled segmentation of cardiac trabeculations, outperforming inter- and intraobserver analyses.Supplemental material is available for this article.© RSNA, 2020.
RESUMO
Predicting unplanned rehospitalizations has traditionally employed logistic regression models. Machine learning (ML) methods have been introduced in health service research and may improve the prediction of health outcomes. The objective of this work was to develop a ML model to predict 30-day all-cause rehospitalizations based on the French hospital medico-administrative database.This was a retrospective cohort study of all discharges in the year 2015 from acute-care inpatient hospitalizations in a tertiary-care university center comprising 4 French hospitals. The study endpoint was unplanned 30-day all-cause rehospitalization. Logistic regression (LR), classification and regression trees (CART), random forest (RF), gradient boosting (GB), and neural networks (NN) were applied to the collected data. The predictive performance of the models was evaluated using the H-measure and the area under the ROC curve (AUC).Our analysis included 118,650 hospitalizations, of which 4127 (3.5%) led to rehospitalizations via emergency departments. The RF model was the most performant model according to the H-measure (0.29) and the AUC (0.79). The performances of the RF, GB and NN models (H-measures ranged from 0.18 to 0. 29, AUC ranged from 0.74 to 0.79) were better than those of the LR model (H-measureâ=â0.18, AUCâ=â0.74); all P values <.001. In contrast, LR was superior to CART (H-measureâ=â0.16, AUCâ=â0.70), Pâ<â.0001.The use of ML may be an alternative to regression models to predict health outcomes. The integration of ML, particularly the RF algorithm, in the prediction of unplanned rehospitalization may help health service providers target patients at high risk of rehospitalizations and propose effective interventions at the hospital level.
Assuntos
Serviço Hospitalar de Emergência/estatística & dados numéricos , Aprendizado de Máquina , Readmissão do Paciente/estatística & dados numéricos , Fatores Etários , Algoritmos , Comorbidade , Feminino , França , Nível de Saúde , Humanos , Masculino , Curva ROC , Estudos Retrospectivos , Índice de Gravidade de Doença , Fatores Sexuais , Fatores Socioeconômicos , Centros de Atenção TerciáriaRESUMO
BACKGROUND: The aim of this study was to propose an alternative approach to item response theory (IRT) in the development of computerized adaptive testing (CAT) in quality of life (QoL) for patients with multiple sclerosis (MS). This approach relied on decision regression trees (DRTs). A comparison with IRT was undertaken based on precision and validity properties. MATERIALS AND METHODS: DRT- and IRT-based CATs were applied on items from a unidi-mensional item bank measuring QoL related to mental health in MS. The DRT-based approach consisted of CAT simulations based on a minsplit parameter that defines the minimal size of nodes in a tree. The IRT-based approach consisted of CAT simulations based on a specified level of measurement precision. The best CAT simulation showed the lowest number of items and the best levels of precision. Validity of the CAT was examined using sociodemographic, clinical and QoL data. RESULTS: CAT simulations were performed using the responses of 1,992 MS patients. The DRT-based CAT algorithm with minsplit = 10 was the most satisfactory model, superior to the best IRT-based CAT algorithm. This CAT administered an average of nine items and showed satisfactory precision indicators (R = 0.98, root mean square error [RMSE] = 0.18). The DRT-based CAT showed convergent validity as its score correlated significantly with other QoL scores and showed satisfactory discriminant validity. CONCLUSION: We presented a new adaptive testing algorithm based on DRT, which has equivalent level of performance to IRT-based approach. The use of DRT is a natural and intuitive way to develop CAT, and this approach may be an alternative to IRT.
RESUMO
The aim was to develop a multidimensional computerized adaptive short-form questionnaire, the MusiQoL-MCAT, from a fixed-length QoL questionnaire for multiple sclerosis.A total of 1992 patients were enrolled in this international cross-sectional study. The development of the MusiQoL-MCAT was based on the assessment of between-items MIRT model fit followed by real-data simulations. The MCAT algorithm was based on Bayesian maximum a posteriori estimation of latent traits and Kullback-Leibler information item selection. We examined several simulations based on a fixed number of items. Accuracy was assessed using correlations (r) between initial IRT scores and MCAT scores. Precision was assessed using the standard error measurement (SEM) and the root mean square error (RMSE).The multidimensional graded response model was used to estimate item parameters and IRT scores. Among the MCAT simulations, the 16-item version of the MusiQoL-MCAT was selected because the accuracy and precision became stable with 16 items with satisfactory levels (râ≥â0.9, SEMâ≤â0.55, and RMSEâ≤â0.3). External validity of the MusiQoL-MCAT was satisfactory.The MusiQoL-MCAT presents satisfactory properties and can individually tailor QoL assessment to each patient, making it less burdensome to patients and better adapted for use in clinical practice.
Assuntos
Esclerose Múltipla/diagnóstico , Qualidade de Vida , Inquéritos e Questionários , Adulto , Computadores , Estudos Transversais , Feminino , Humanos , MasculinoRESUMO
BACKGROUND: Interpretation of quality of life (QoL) scores over time can be difficult because of possible changes in internal standards, values, and conceptualization of QoL by individuals. This effect is called a response shift (RS). The purpose of this study was to examine whether an RS effect occurred over a 24-mo period in patients who were suffering from schizophrenia. METHODS: The random forest method was applied to detect any RS reprioritization in a multicenter cohort study. QoL was recorded using a generic questionnaire (SF36) at baseline (T0), 12 mo (T12), and 24 mo (T24). Patients were categorized into 3 groups based on psychotic symptoms and relapse (stable, improved, and worsened groups) from their clinical profiles. The random forest method was performed to predict the General Health score of the SF36 from the other QoL domain scores of the SF36. We estimated the average variable importance of the QoL domain for each of the 3 groups. RESULTS: A total of 124 (53.2%) patients were defined as stable, 59 (25.3%) as improved, and 50 (21.5%) as worsened. Among the stable group, the Social Functioning domain became more important over time. Of those classified as improved, the Mental Health domain became more important over time, while the Vitality domain became less important. Among those in the group who worsened, the Mental Health domain became less important while the Vitality and Bodily Pain domains became more important. CONCLUSIONS: Our study identified differential RS reprioritization among patients with different clinical profiles. Further work is needed to determine whether RS should be interpreted as a measurement bias or as an effect integrated in a true change.