RESUMEN
Emerging infectious diseases (EIDs) are newly emerging and reemerging infectious diseases. The National Institute of Allergy and Infectious Diseases identifies the following as emerging infectious diseases: SARS, MERS, COVID-19, influenza, fungal diseases, plague, schistosomiasis, smallpox, tick-borne diseases, and West Nile fever. The factors that should be taken into consideration are the genetic adaptation of microbial agents and the characteristics of the human host or environment. The new approach to identifying new possible pathogens will have to go through the One Health approach and omics integration data, which are capable of identifying high-priority microorganisms in a short period of time. New bioinformatics technologies enable global integration and sharing of surveillance data for rapid public health decision-making to detect and prevent epidemics and pandemics, ensuring timely response and effective prevention measures. Machine learning tools are being more frequently utilized in the realm of infectious diseases to predict sepsis in patients, diagnose infectious diseases early, and forecast the effectiveness of treatment or the appropriate choice of antibiotic regimen based on clinical data. We will discuss emerging microorganisms, omics techniques applied to infectious diseases, new computational solutions to evaluate biomarkers, and innovative tools that are useful for integrating omics data and electronic medical records data for the clinical management of emerging infectious diseases.
Asunto(s)
Enfermedades Transmisibles Emergentes , Humanos , Enfermedades Transmisibles Emergentes/microbiología , Enfermedades Transmisibles Emergentes/epidemiología , Enfermedades Transmisibles Emergentes/prevención & control , Salud Única , Enfermedades Transmisibles/microbiología , COVID-19/epidemiología , COVID-19/virología , Aprendizaje Automático , Biología Computacional/métodosRESUMEN
BACKGROUND AND OBJECTIVE: In the field of lung cancer research, particularly in the analysis of overall survival (OS), artificial intelligence (AI) serves crucial roles with specific aims. Given the prevalent issue of missing data in the medical domain, our primary objective is to develop an AI model capable of dynamically handling this missing data. Additionally, we aim to leverage all accessible data, effectively analyzing both uncensored patients who have experienced the event of interest and censored patients who have not, by embedding a specialized technique within our AI model, not commonly utilized in other AI tasks. Through the realization of these objectives, our model aims to provide precise OS predictions for non-small cell lung cancer (NSCLC) patients, thus overcoming these significant challenges. METHODS: We present a novel approach to survival analysis with missing values in the context of NSCLC, which exploits the strengths of the transformer architecture to account only for available features without requiring any imputation strategy. More specifically, this model tailors the transformer architecture to tabular data by adapting its feature embedding and masked self-attention to mask missing data and fully exploit the available ones. By making use of ad-hoc designed losses for OS, it is able to account for both censored and uncensored patients, as well as changes in risks over time. RESULTS: We compared our method with state-of-the-art models for survival analysis coupled with different imputation strategies. We evaluated the results obtained over a period of 6 years using different time granularities obtaining a Ct-index, a time-dependent variant of the C-index, of 71.97, 77.58 and 80.72 for time units of 1 month, 1 year and 2 years, respectively, outperforming all state-of-the-art methods regardless of the imputation method used. CONCLUSIONS: The results show that our model not only outperforms the state-of-the-art's performance but also simplifies the analysis in the presence of missing data, by effectively eliminating the need to identify the most appropriate imputation strategy for predicting OS in NSCLC patients.
Asunto(s)
Carcinoma de Pulmón de Células no Pequeñas , Aprendizaje Profundo , Neoplasias Pulmonares , Humanos , Neoplasias Pulmonares/mortalidad , Carcinoma de Pulmón de Células no Pequeñas/mortalidad , Análisis de Supervivencia , Algoritmos , Masculino , Femenino , Pronóstico , Inteligencia ArtificialRESUMEN
Contrast Enhanced Spectral Mammography (CESM) is a dual-energy mammographic imaging technique that first requires intravenously administering an iodinated contrast medium. Then, it collects both a low-energy image, comparable to standard mammography, and a high-energy image. The two scans are combined to get a recombined image showing contrast enhancement. Despite CESM diagnostic advantages for breast cancer diagnosis, the use of contrast medium can cause side effects, and CESM also beams patients with a higher radiation dose compared to standard mammography. To address these limitations, this work proposes using deep generative models for virtual contrast enhancement on CESM, aiming to make CESM contrast-free and reduce the radiation dose. Our deep networks, consisting of an autoencoder and two Generative Adversarial Networks, the Pix2Pix, and the CycleGAN, generate synthetic recombined images solely from low-energy images. We perform an extensive quantitative and qualitative analysis of the model's performance, also exploiting radiologists' assessments, on a novel CESM dataset that includes 1138 images. As a further contribution to this work, we make the dataset publicly available. The results show that CycleGAN is the most promising deep network to generate synthetic recombined images, highlighting the potential of artificial intelligence techniques for virtual contrast enhancement in this field.
Asunto(s)
Neoplasias de la Mama , Medios de Contraste , Aprendizaje Profundo , Mamografía , Mamografía/métodos , Humanos , Femenino , Neoplasias de la Mama/diagnóstico por imagen , Intensificación de Imagen Radiográfica/métodos , Interpretación de Imagen Radiográfica Asistida por Computador/métodosRESUMEN
Williams-Beuren syndrome (WBS) is a rare genetic neurodevelopmental disorder with multi-systemic manifestations. The evidence that most subjects with WBS face gastrointestinal (GI) comorbidities, have prompted us to carry out a metaproteomic investigation of their gut microbiota (GM) profile compared to age-matched healthy subjects (CTRLs). Metaproteomic analysis was carried out on fecal samples collected from 41 individuals with WBS, and compared with samples from 45 CTRLs. Stool were extracted for high yield in bacterial protein group (PG) content, trypsin-digested and analysed by nanoLiquid Chromatography-Mass Spectrometry. Label free quantification, taxonomic assignment by the lowest common ancestor (LCA) algorithm and functional annotations by COG and KEGG databases were performed. Data were statistically interpreted by multivariate and univariate analyses. A WBS GM functional dissimilarity respect to CTRLs, regardless age distribution, was reported. The alterations in function of WBSs GM was primarily based on bacterial pathways linked to carbohydrate transport and metabolism and energy production. Influence of diet, obesity, and GI symptoms was assessed, highlighting changes in GM biochemical patterns, according to WBS subsets' stratification. The LCA-derived ecology unveiled WBS-related functionally active bacterial signatures: Bacteroidetes related to over-expressed PGs, and Firmicutes, specifically the specie Faecalibacterium prausnitzii, linked to under-expressed PGs, suggesting a depletion of beneficial bacteria. These new evidences on WBS gut dysbiosis may offer novel targets for tailored interventions.
Asunto(s)
Microbioma Gastrointestinal , Síndrome de Williams , Humanos , Bacterias/genética , Firmicutes , Tracto GastrointestinalRESUMEN
Gut microbiota (GM) modulation can be investigated as possible solution to enhance recovery after COVID-19. An open-label, single-center, single-arm, pilot, interventional study was performed by enrolling twenty patients recently recovered from COVID-19 to investigate the role of a mixed probiotic, containing Lactobacilli, Bifidobacteria and Streptococcus thermophilus, on gastrointestinal symptoms, local and systemic inflammation, intestinal barrier integrity and GM profile. Gastrointestinal Symptom Rating Scale, cytokines, inflammatory, gut permeability, and integrity markers were evaluated before (T0) and after 8 weeks (T1) of probiotic supplementation. GM profiling was based on 16S-rRNA targeted-metagenomics and QIIME 2.0, LEfSe and PICRUSt computational algorithms. Multiple machine learning (ML) models were trained to classify GM at T0 and T1. A statistically significant reduction of IL-6 (p < 0.001), TNF-α (p < 0.001) and IL-12RA (p < 0.02), citrulline (p value < 0.001) was reported at T1. GM global distribution and microbial biomarkers strictly reflected probiotic composition, with a general increase in Bifidobacteria at T1. Twelve unique KEGG orthologs were associated only to T0, including tetracycline resistance cassettes. ML classified the GM at T1 with 100% score at phylum level. Bifidobacteriaceae and Bifidobacterium spp. inversely correlated to reduction of citrulline and inflammatory cytokines. Probiotic supplementation during post-COVID-19 may trigger anti-inflammatory effects though Bifidobacteria and related-metabolism enhancement.
Asunto(s)
COVID-19 , Microbioma Gastrointestinal , Probióticos , Humanos , Microbioma Gastrointestinal/genética , Citrulina , Probióticos/uso terapéutico , Probióticos/farmacología , Citocinas , Bifidobacterium , Aprendizaje AutomáticoRESUMEN
The COVID-19 pandemic has caused millions of cases and deaths and the AI-related scientific community, after being involved with detecting COVID-19 signs in medical images, has been now directing the efforts towards the development of methods that can predict the progression of the disease. This task is multimodal by its very nature and, recently, baseline results achieved on the publicly available AIforCOVID dataset have shown that chest X-ray scans and clinical information are useful to identify patients at risk of severe outcomes. While deep learning has shown superior performance in several medical fields, in most of the cases it considers unimodal data only. In this respect, when, which and how to fuse the different modalities is an open challenge in multimodal deep learning. To cope with these three questions here we present a novel approach optimizing the setup of a multimodal end-to-end model. It exploits Pareto multi-objective optimization working with a performance metric and the diversity score of multiple candidate unimodal neural networks to be fused. We test our method on the AIforCOVID dataset, attaining state-of-the-art results, not only outperforming the baseline performance but also being robust to external validation. Moreover, exploiting XAI algorithms we figure out a hierarchy among the modalities and we extract the features' intra-modality importance, enriching the trust on the predictions made by the model.
Asunto(s)
COVID-19 , Aprendizaje Profundo , Humanos , COVID-19/diagnóstico , SARS-CoV-2 , Pandemias , Redes Neurales de la ComputaciónRESUMEN
Background: Autism spectrum disorder (ASD) is a multifactorial neurodevelopmental disorder. Major interplays between the gastrointestinal (GI) tract and the central nervous system (CNS) seem to be driven by gut microbiota (GM). Herein, we provide a GM functional characterization, based on GM metabolomics, mapping of bacterial biochemical pathways, and anamnestic, clinical, and nutritional patient metadata. Methods: Fecal samples collected from children with ASD and neurotypical children were analyzed by gas-chromatography mass spectrometry coupled with solid phase microextraction (GC-MS/SPME) to determine volatile organic compounds (VOCs) associated with the metataxonomic approach by 16S rRNA gene sequencing. Multivariate and univariate statistical analyses assessed differential VOC profiles and relationships with ASD anamnestic and clinical features for biomarker discovery. Multiple web-based and machine learning (ML) models identified metabolic predictors of disease and network analyses correlated GM ecological and metabolic patterns. Results: The GM core volatilome for all ASD patients was characterized by a high concentration of 1-pentanol, 1-butanol, phenyl ethyl alcohol; benzeneacetaldehyde, octadecanal, tetradecanal; methyl isobutyl ketone, 2-hexanone, acetone; acetic, propanoic, 3-methyl-butanoic and 2-methyl-propanoic acids; indole and skatole; and o-cymene. Patients were stratified based on age, GI symptoms, and ASD severity symptoms. Disease risk prediction allowed us to associate butanoic acid with subjects older than 5 years, indole with the absence of GI symptoms and low disease severity, propanoic acid with the ASD risk group, and p-cymene with ASD symptoms, all based on the predictive CBCL-EXT scale. The HistGradientBoostingClassifier model classified ASD patients vs. CTRLs by an accuracy of 89%, based on methyl isobutyl ketone, benzeneacetaldehyde, phenyl ethyl alcohol, ethanol, butanoic acid, octadecane, acetic acid, skatole, and tetradecanal features. LogisticRegression models corroborated methyl isobutyl ketone, benzeneacetaldehyde, phenyl ethyl alcohol, skatole, and acetic acid as ASD predictors. Conclusion: Our results will aid the development of advanced clinical decision support systems (CDSSs), assisted by ML models, for advanced ASD-personalized medicine, based on omics data integrated into electronic health/medical records. Furthermore, new ASD screening strategies based on GM-related predictors could be used to improve ASD risk assessment by uncovering novel ASD onset and risk predictors.
RESUMEN
Type 1 diabetes (T1D) is a chronic autoimmune metabolic disorder with onset in pediatric/adolescent age, characterized by insufficient insulin production, due to a progressive destruction of pancreatic ß-cells. Evidence on the correlation between the human gut microbiota (GM) composition and T1D insurgence has been recently reported. In particular, 16S rRNA-based metagenomics has been intensively employed in the last decade in a number of investigations focused on GM representation in relation to a pre-disease state or to a response to clinical treatments. On the other hand, few works have been published using alternative functional omics, which is more suitable to provide a different interpretation of such a relationship. In this work, we pursued a comprehensive metaproteomic investigation on T1D children compared with a group of siblings (SIBL) and a reference control group (CTRL) composed of aged matched healthy subjects, with the aim of finding features in the T1D patients' GM to be related with the onset of the disease. Modulated metaproteins were found either by comparing T1D with CTRL and SIBL or by stratifying T1D by insulin need (IN), as a proxy of ß-cells damage, showing some functional and taxonomic traits of the GM, possibly related to the disease onset at different stages of severity.
Asunto(s)
Diabetes Mellitus Tipo 1 , Microbioma Gastrointestinal , Células Secretoras de Insulina , Adolescente , Humanos , Niño , Anciano , Microbioma Gastrointestinal/fisiología , ARN Ribosómico 16S/genética , Insulina Regular Humana , InsulinaRESUMEN
Anti-double-stranded DNA antibodies (anti-dsDNA) are considered a specific marker for systemic lupus erythematosus (SLE). Though the Farr technique was once the reference method for their detection, it has been almost entirely replaced by more recently developed assays. However, there is still no solid evidence of the commutability of these methods in terms of diagnostic accuracy and their correlation with the Crithidia luciliae immunofluorescence test (CLIFT). Anti-dsDNA antibody levels were measured in 80 subjects: 24 patients with SLE, 36 disease controls drawn from different autoimmune rheumatic diseases (14 systemic sclerosis, 10 Sjögren's syndrome, nine autoimmune myositis, three mixed connective tissue disease), 10 inflammatory arthritis and 10 apparently healthy blood donors by eight different methods: fluorescence enzyme immunoassay, microdot array, chemiluminescent immunoassay (two assays), multiplex flow immunoassay, particle multi-analyte technology immunoassay and two CLIFT. At the recommended manufacturer cut-off, the sensitivity varied from 67% to 92%, while the specificity ranged from 84% to 98%. Positive agreement among CLIFT and the other assays was higher than negative agreement. Mean agreement among methods assessed by the Cohen's kappa was 0.715, ranging from moderate (0.588) to almost perfect (0.888). Evaluation of the concordance among quantitative values by regression analysis showed a poor correlation index (mean r2, 0.66). The present study shows that current technologies for anti-dsDNA antibody detection are not fully comparable. In particular, their different correlation with CLIFT influences their positioning in the diagnostic algorithm for SLE (either in association or sequentially). Considering the high intermethod variability, harmonization and commutability of anti-dsDNA antibody testing remains an unachieved goal.
Asunto(s)
Enfermedades Autoinmunes , Lupus Eritematoso Sistémico , Síndrome de Sjögren , Humanos , Anticuerpos Antinucleares , Lupus Eritematoso Sistémico/diagnósticoRESUMEN
Lung cancer accounts for more deaths worldwide than any other cancer disease. In order to provide patients with the most effective treatment for these aggressive tumours, multimodal learning is emerging as a new and promising field of research that aims to extract complementary information from the data of different modalities for prognostic and predictive purposes. This knowledge could be used to optimise current treatments and maximise their effectiveness. To predict overall survival, in this work, we investigate the use of multimodal learning on the CLARO dataset, which includes CT images and clinical data collected from a cohort of non-small-cell lung cancer patients. Our method allows the identification of the optimal set of classifiers to be included in the ensemble in a late fusion approach. Specifically, after training unimodal models on each modality, it selects the best ensemble by solving a multiobjective optimisation problem that maximises both the recognition performance and the diversity of the predictions. In the ensemble, the labels of each sample are assigned using the majority voting rule. As further validation, we show that the proposed ensemble outperforms the models learning a single modality, obtaining state-of-the-art results on the task at hand.
RESUMEN
Alterations of gut microbiota have been identified before clinical manifestation of type 1 diabetes (T1D). To identify the associations amongst gut microbiome profile, metabolism and disease markers, the 16S rRNA-based microbiota profiling and 1H-NMR metabolomic analysis were performed on stool samples of 52 T1D patients at onset, 17 T1D siblings and 57 healthy subjects (CTRL). Univariate, multivariate analyses and classification models were applied to clinical and -omic integrated datasets. In T1D patients and their siblings, Clostridiales and Dorea were increased and Dialister and Akkermansia were decreased compared to CTRL, while in T1D, Lachnospiraceae were higher and Collinsella was lower, compared to siblings and CTRL. Higher levels of isobutyrate, malonate, Clostridium, Enterobacteriaceae, Clostridiales, Bacteroidales, were associated to T1D compared to CTRL. Patients with higher anti-GAD levels showed low abundances of Roseburia, Faecalibacterium and Alistipes and those with normal blood pH and low serum HbA1c levels showed high levels of purine and pyrimidine intermediates. We detected specific gut microbiota profiles linked to both T1D at the onset and to diabetes familiarity. The presence of specific microbial and metabolic profiles in gut linked to anti-GAD levels and to blood acidosis can be considered as predictive biomarker associated progression and severity of T1D.
Asunto(s)
Diabetes Mellitus Tipo 1 , Microbioma Gastrointestinal , Biomarcadores/metabolismo , Clostridiales/metabolismo , Humanos , Concentración de Iones de Hidrógeno , Isobutiratos , Malonatos , Purinas , Pirimidinas , ARN Ribosómico 16S/genéticaRESUMEN
This is the first study on gut microbiota (GM) in children affected by coronavirus disease 2019 (COVID-19). Stool samples from 88 patients with suspected severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection and 95 healthy subjects were collected (admission: 3-7 days, discharge) to study GM profile by 16S rRNA gene sequencing and relationship to disease severity. The study group was divided in COVID-19 (68), Non-COVID-19 (16), and MIS-C (multisystem inflammatory syndrome in children) (4). Correlations among GM ecology, predicted functions, multiple machine learning (ML) models, and inflammatory response were provided for COVID-19 and Non-COVID-19 cohorts. The GM of COVID-19 cohort resulted as dysbiotic, with the lowest α-diversity compared with Non-COVID-19 and CTRLs and by a specific ß-diversity. Its profile appeared enriched in Faecalibacterium, Fusobacterium, and Neisseria and reduced in Bifidobacterium, Blautia, Ruminococcus, Collinsella, Coprococcus, Eggerthella, and Akkermansia, compared with CTRLs (p < 0.05). All GM paired-comparisons disclosed comparable results through all time points. The comparison between COVID-19 and Non-COVID-19 cohorts highlighted a reduction of Abiotrophia in the COVID-19 cohort (p < 0.05). The GM of MIS-C cohort was characterized by an increase of Veillonella, Clostridium, Dialister, Ruminococcus, and Streptococcus and a decrease of Bifidobacterium, Blautia, Granulicatella, and Prevotella, compared with CTRLs. Stratifying for disease severity, the GM associated to "moderate" COVID-19 was characterized by lower α-diversity compared with "mild" and "asymptomatic" and by a GM profile deprived in Neisseria, Lachnospira, Streptococcus, and Prevotella and enriched in Dialister, Acidaminococcus, Oscillospora, Ruminococcus, Clostridium, Alistipes, and Bacteroides. The ML models identified Staphylococcus, Anaerostipes, Faecalibacterium, Dorea, Dialister, Streptococcus, Roseburia, Haemophilus, Granulicatella, Gemmiger, Lachnospira, Corynebacterium, Prevotella, Bilophila, Phascolarctobacterium, Oscillospira, and Veillonella as microbial markers of COVID-19. The KEGG ortholog (KO)-based prediction of GM functional profile highlighted 28 and 39 KO-associated pathways to COVID-19 and CTRLs, respectively. Finally, Bacteroides and Sutterella correlated with proinflammatory cytokines regardless disease severity. Unlike adult GM profiles, Faecalibacterium was a specific marker of pediatric COVID-19 GM. The durable modification of patients' GM profile suggested a prompt GM quenching response to SARS-CoV-2 infection since the first symptoms. Faecalibacterium and reduced fatty acid and amino acid degradation were proposed as specific COVID-19 disease traits, possibly associated to restrained severity of SARS-CoV-2-infected children. Altogether, this evidence provides a characterization of the pediatric COVID-19-related GM.
Asunto(s)
COVID-19 , Microbioma Gastrointestinal , Adulto , Bacteroides/genética , Bifidobacterium/genética , COVID-19/complicaciones , Niño , Clostridium/genética , Heces/microbiología , Microbioma Gastrointestinal/fisiología , Humanos , ARN Ribosómico 16S/genética , SARS-CoV-2 , Síndrome de Respuesta Inflamatoria SistémicaRESUMEN
Autism spectrum disorders (ASDs) is a multifactorial neurodevelopmental disorder. The communication between the gastrointestinal (GI) tract and the central nervous system seems driven by gut microbiota (GM). Herein, we provide GM profiling, considering GI functional symptoms, neurological impairment, and dietary habits. Forty-one and 35 fecal samples collected from ASD and neurotypical children (CTRLs), respectively, (age range, 3-15 years) were analyzed by 16S targeted-metagenomics (the V3-V4 region) and inflammation and permeability markers (i.e., sIgA, zonulin lysozyme), and then correlated with subjects' metadata. Our ASD cohort was characterized as follows: 30/41 (73%) with GI functional symptoms; 24/41 (58%) picky eaters (PEs), with one or more dietary needs, including 10/41 (24%) with food selectivity (FS); 36/41 (88%) presenting high and medium autism severity symptoms (HMASSs). Among the cohort with GI symptoms, 28/30 (93%) showed HMASSs, 17/30 (57%) were picky eaters and only 8/30 (27%) with food selectivity. The remaining 11/41 (27%) ASDs without GI symptoms that were characterized by HMASS for 8/11 (72%) and 7/11 (63%) were picky eaters. GM ecology was investigated for the overall ASD cohort versus CTRLs; ASDs with GI and without GI, respectively, versus CTRLs; ASD with GI versus ASD without GI; ASDs with HMASS versus low ASSs; PEs versus no-PEs; and FS versus absence of FS. In particular, the GM of ASDs, compared to CTRLs, was characterized by the increase of Proteobacteria, Bacteroidetes, Rikenellaceae, Pasteurellaceae, Klebsiella, Bacteroides, Roseburia, Lactobacillus, Prevotella, Sutterella, Staphylococcus, and Haemophilus. Moreover, Sutterella, Roseburia and Fusobacterium were associated to ASD with GI symptoms compared to CTRLs. Interestingly, ASD with GI symptoms showed higher value of zonulin and lower levels of lysozyme, which were also characterized by differentially expressed predicted functional pathways. Multiple machine learning models classified correctly 80% overall ASDs, compared with CTRLs, based on Bacteroides, Lactobacillus, Prevotella, Staphylococcus, Sutterella, and Haemophilus features. In conclusion, in our patient cohort, regardless of the evaluation of many factors potentially modulating the GM profile, the major phenotypic determinant affecting the GM was represented by GI hallmarks and patients' age.
RESUMEN
The year 2020 was characterized by the COVID-19 pandemic that has caused, by the end of March 2021, more than 2.5 million deaths worldwide. Since the beginning, besides the laboratory test, used as the gold standard, many applications have been applying deep learning algorithms to chest X-ray images to recognize COVID-19 infected patients. In this context, we found out that convolutional neural networks perform well on a single dataset but struggle to generalize to other data sources. To overcome this limitation, we propose a late fusion approach where we combine the outputs of several state-of-the-art CNNs, introducing a novel method that allows us to construct an optimum ensemble determining which and how many base learners should be aggregated. This choice is driven by a two-objective function that maximizes, on a validation set, the accuracy and the diversity of the ensemble itself. A wide set of experiments on several publicly available datasets, accounting for more than 92,000 images, shows that the proposed approach provides average recognition rates up to 93.54% when tested on external datasets.
RESUMEN
BACKGROUND: Prostate magnetic resonance imaging (MRI) is technically demanding, requiring high image quality to reach its full diagnostic potential. An automated method to identify diagnostically inadequate images could help optimize image quality. PURPOSE: To develop a convolutional neural networks (CNNs) based analysis pipeline for the classification of prostate MRI image quality. STUDY TYPE: Retrospective. SUBJECTS: Three hundred sixteen prostate mpMRI scans and 312 men (median age 67). FIELD STRENGTH/SEQUENCE: A 3 T; fast spin echo T2WI, echo planar imaging DWI, ADC, gradient-echo dynamic contrast enhanced (DCE). ASSESSMENT: MRI scans were reviewed by three genitourinary radiologists (V.P., M.D.M., S.C.) with 21, 12, and 5 years of experience, respectively. Sequences were labeled as high quality (Q1) or low quality (Q0) and used as the reference standard for all analyses. STATISTICAL TESTS: Sequences were split into training, validation, and testing sets (869, 250, and 120 sequences, respectively). Inter-reader agreement was assessed with the Fleiss kappa. Following preprocessing and data augmentation, 28 CNNs were trained on MRI slices for each sequence. Model performance was assessed on both a per-slice and a per-sequence basis. A pairwise t-test was performed to compare performances of the classifiers. RESULTS: The number of sequences labeled as Q0 or Q1 was 38 vs. 278 for T2WI, 43 vs. 273 for DWI, 41 vs. 275 for ADC, and 38 vs. 253 for DCE. Inter-reader agreement was almost perfect for T2WI and DCE and substantial for DWI and ADC. On the per-slice analysis, accuracy was 89.95% ± 0.02% for T2WI, 79.83% ± 0.04% for DWI, 76.64% ± 0.04% for ADC, 96.62% ± 0.01% for DCE. On the per-sequence analysis, accuracy was 100% ± 0.00% for T2WI, DWI, and DCE, and 92.31% ± 0.00% for ADC. The three best algorithms performed significantly better than the remaining ones on every sequence (P-value < 0.05). DATA CONCLUSION: CNNs achieved high accuracy in classifying prostate MRI image quality on an individual-slice basis and almost perfect accuracy when classifying the entire sequences. EVIDENCE LEVEL: 4 TECHNICAL EFFICACY: Stage 1.
Asunto(s)
Imágenes de Resonancia Magnética Multiparamétrica , Neoplasias de la Próstata , Anciano , Imagen de Difusión por Resonancia Magnética , Humanos , Imagen por Resonancia Magnética , Masculino , Redes Neurales de la Computación , Próstata/diagnóstico por imagen , Neoplasias de la Próstata/diagnóstico por imagen , Estudios RetrospectivosRESUMEN
Recent epidemiological data report that worldwide more than 53 million people have been infected by SARS-CoV-2, resulting in 1.3 million deaths. The disease has been spreading very rapidly and few months after the identification of the first infected, shortage of hospital resources quickly became a problem. In this work we investigate whether artificial intelligence working with chest X-ray (CXR) scans and clinical data can be used as a possible tool for the early identification of patients at risk of severe outcome, like intensive care or death. Indeed, further to induce lower radiation dose than computed tomography (CT), CXR is a simpler and faster radiological technique, being also more widespread. In this respect, we present three approaches that use features extracted from CXR images, either handcrafted or automatically learnt by convolutional neuronal networks, which are then integrated with the clinical data. As a further contribution, this work introduces a repository that collects data from 820 patients enrolled in six Italian hospitals in spring 2020 during the first COVID-19 emergency. The dataset includes CXR images, several clinical attributes and clinical outcomes. Exhaustive evaluation shows promising performance both in 10-fold and leave-one-centre-out cross-validation, suggesting that clinical data and images have the potential to provide useful information for the management of patients and hospital resources.
Asunto(s)
COVID-19 , Inteligencia Artificial , Humanos , Italia , SARS-CoV-2 , Rayos XRESUMEN
The availability of the epidemiological data strongly affects the reliability of several mathematical models in tracing and forecasting COVID-19 pandemic, hampering a fair assessment of their relative performance. The marked difference between the lethality of the virus when comparing the first and second waves is an evident sign of the poor reliability of the data, also related to the variability over time in the number of performed swabs. During the early epidemic stage, swabs were made only to patients with severe symptoms taken to hospital or intensive care unit. Thus, asymptomatic people, not seeking medical assistance, remained undetected. Conversely, during the second wave of infection, total infectives included also a percentage of detected asymptomatic infectives, being tested due to close contacts with swab positives and thus registered by the health system. Here, we compared the outcomes of two SIR-type models (the standard SIR model and the A-SIR model that explicitly considers asymptomatic infectives) in reproducing the COVID-19 epidemic dynamic in Italy, Spain, Germany, and France during the first two infection waves, simulated separately. We found that the A-SIR model overcame the SIR model in simulating the first wave, whereas these discrepancies are reduced in simulating the second wave, when the accuracy of the epidemiological data is considerably higher. These results indicate that increasing the complexity of the model is useless and unnecessarily wasteful if not supported by an increased quality of the available data.
Asunto(s)
COVID-19 , Brotes de Enfermedades , Humanos , Pandemias , Reproducibilidad de los Resultados , SARS-CoV-2RESUMEN
AIMS: To identify fecal microbiota profiles associated with metabolic abnormalities belonging to the metabolic syndrome (MS), high count of white blood cells (WBCs) and insulin resistance (IR). METHODS: Sixty-eight young patients with obesity were stratified for percentile distribution of MS abnormalities. A MS risk score was defined as low, medium, and high MS risk. High WBCs were defined as a count ≥ 7.0 103/µL; severe obesity as body mass index Z-score ≥ 2 standard deviations; IR as homeostatic assessment model algorithm of IR (HOMA) ≥ 3.7. Stool samples were analyzed by 16S rRNA-based metagenomics. RESULTS: We found reduced bacterial richness of fecal microbiota in patients with IR and high diastolic blood pressure (BP). Distinct microbial markers were associated to high BP (Clostridium and Clostridiaceae), low high-density lipoprotein cholesterol (Lachnospiraceae, Gemellaceae, Turicibacter), and high MS risk (Coriobacteriaceae), WBCs (Bacteroides caccae, Gemellaceae), severe obesity (Lachnospiraceae), and impaired glucose tolerance (Bacteroides ovatus and Enterobacteriaceae). Conversely, taxa such as Faecalibacterium prausnitzii, Parabacterodes, Bacteroides caccae, Oscillospira, Parabacterodes distasonis, Coprococcus, and Haemophilus parainfluenzae were associated to low MS risk score, triglycerides, fasting glucose and HOMA-IR, respectively. Supervised multilevel analysis grouped clearly "variable" patients based on the MS risk. CONCLUSIONS: This was a proof-of-concept study opening the way at the identification of fecal microbiota signatures, precisely associated with cardiometabolic risk factors in young patients with obesity. These evidences led us to infer, while some gut bacteria have a detrimental role in exacerbating metabolic risk factors some others are beneficial ameliorating cardiovascular host health.
Asunto(s)
Heces/microbiología , Inflamación/microbiología , Resistencia a la Insulina/fisiología , Síndrome Metabólico/microbiología , Microbiota/fisiología , Obesidad , Adolescente , Bacterias/clasificación , Bacterias/genética , Biomarcadores/sangre , Niño , Femenino , Intolerancia a la Glucosa/microbiología , Humanos , Hipertensión/microbiología , Masculino , Metagenómica , Obesidad/complicaciones , Proyectos Piloto , ARN Ribosómico 16S/análisis , Factores de Riesgo , Triglicéridos/sangreRESUMEN
Non-nonavalent vaccine (9v) Human papillomavirus (HPV) types have been shown to have high prevalence among HIV-positive women. Here, 1444 cervical samples were tested for HPV DNA positivity. Co-infections of the 9v HPV types with other HPV types were evaluated. The HPV81 L1 and L2 genes were used to investigate the genetic variability of antigenic epitopes. HPV-positive samples were genotyped using the HPVCLART2 assay. The L1 and L2 protein sequences were analyzed using a self-optimized prediction method to predict their secondary structure. Co-occurrence probabilities of the 9v HPV types were calculated. Non9v types represented 49% of the HPV infections; 31.2% of the non9v HPV types were among the low-grade squamous intraepithelial lesion samples, and 27.3% among the high-grade squamous intraepithelial lesion samples, and several genotypes were low risk. The co-occurrence of 9v HPV types with the other genotypes was not correlated with the filogenetic distance. HPV81 showed an amino-acid substitution within the BC loop (N75Q) and the FGb loop (T315N). In the L2 protein, all of the mutations were located outside antigenic sites. The weak cross-protection of the 9v types suggests the relevance of a sustainable and effective screening program, which should be implemented by HPV DNA testing that does not include only high-risk types.