RESUMEN
BACKGROUND AND OBJECTIVES: This study aimed to find the optimal intervention available to both control blood glucose and improve physical function in the geriatric population with T2DM. METHODS AND STUDY DESIGN: A systemic review and network meta-analysis (NMA) was conducted to assess and rank the comparative efficacy of different interventions on glycosylated hemoglobin A1c (HbAc1), fasting blood glucose (FBG), muscle mass, grip strength, gait speed, lower body muscle strength, and dynamic balance. A total of eight databases were searched for eligible randomized controlled trials (RCTs) that the elderly aged more than 60 years or with mean age ≥ 55 years, the minimal duration of the RCT intervention was 6 weeks, and those lacking data about glycemic level and at least one indicator of physical performance were excluded. The Cochrane risk of bias tool was used to assess the bias of each study included. Bayesian NMA was performed as the main results, the Bayesian meta regression and the frequentist NMA as sensitivity analysis. RESULTS: Of the 2266 literature retrieved, 27 RCTs with a total of 2289 older adults were included. Health management provided by health workers exerts beneficial effects that is superior to other interventions at achieving glycemic control, but less marked improvement in physical performance. Exercise combined with cognitive training showed more pronounced improvement in muscle strength, gait speed, and dynamic balance, but ranked behind in decreasing the HbAc1 and FBG. CONCLUSIONS: Personalized health management combined with physical and cognitive training might be the optimal intervention to both accomplish glycemic control and improvement of physical performance. Further RCTs are needed to validate and assess the confidence of our results from this NMA.
Asunto(s)
Glucemia , Diabetes Mellitus Tipo 2 , Rendimiento Físico Funcional , Humanos , Diabetes Mellitus Tipo 2/terapia , Diabetes Mellitus Tipo 2/sangre , Anciano , Metaanálisis en Red , Hemoglobina Glucada/análisis , Fuerza Muscular/fisiología , Control Glucémico/métodos , Ensayos Clínicos Controlados Aleatorios como Asunto , Ejercicio Físico/fisiologíaRESUMEN
BACKGROUND: Studies have highlighted a possible crosstalk between the pathogeneses of COVID-19 and systemic lupus erythematosus (SLE); however, the interactive mechanisms remain unclear. We aimed to elucidate the impact of COVID-19 on SLE using clinical information and the underlying mechanisms of both diseases. METHODS: RNA-seq datasets were used to identify shared hub gene signatures between COVID-19 and SLE, while genome-wide association study datasets were used to delineate the interaction mechanisms of the key signaling pathways. Finally, single-cell RNA-seq datasets were used to determine the primary target cells expressing the shared hub genes and key signaling pathways. RESULTS: COVID-19 may affect patients with SLE through hematologic involvement and exacerbated inflammatory responses. We identified 14 shared hub genes between COVID-19 and SLE that were significantly associated with interferon (IFN)-I/II. We also screened and obtained four core transcription factors related to these hub genes, confirming the regulatory role of the IFN-I/II-mediated Janus kinase/signal transducers and activators of transcription (JAK-STAT) signaling pathway on these hub genes. Further, SLE and COVID-19 can interact via IFN-I/II and IFN-I/II receptors, promoting the levels of monokines, including interleukin (IL)-6/10, tumor necrosis factor-α, and IFN-γ, and elevating the incidence rate and risk of cytokine release syndrome. Therefore, in SLE and COVID-19, both hub genes and core TFs are enriched within monocytes/macrophages. CONCLUSIONS: The interaction between SLE and COVID-19 promotes the activation of the IFN-I/II-triggered JAK-STAT signaling pathway in monocytes/macrophages. These findings provide a new direction and rationale for diagnosing and treating patients with SLE-COVID-19 comorbidity.
Asunto(s)
COVID-19 , Estudio de Asociación del Genoma Completo , Lupus Eritematoso Sistémico , SARS-CoV-2 , Transducción de Señal , Humanos , COVID-19/genética , Lupus Eritematoso Sistémico/genética , SARS-CoV-2/fisiología , Femenino , Quinasas Janus/metabolismo , Factores de Transcripción STAT/metabolismo , Factores de Transcripción STAT/genética , Masculino , Transcriptoma , Perfilación de la Expresión Génica , MultiómicaRESUMEN
Digestive tract cancers are among the most common malignancies worldwide and have high incidence and mortality rates. Thus, the discovery of more effective diagnostic and therapeutic targets is urgently required. The development of technologies to accurately detect RNA modification has led to the identification of numerous RNA chemical modifications in humans (epitranscriptomics) that are involved in the occurrence and development of digestive tract cancers. RNA modifications can cooperatively regulate gene expression to facilitate normal physiological functions of the digestive system. However, the dysfunction of relevant RNA-modifying enzymes ("writers," "erasers," and "readers") can lead to the development of digestive tract cancers. Consequently, targeting dysregulated enzyme activity could represent a potent therapeutic strategy for the treatment of digestive tract cancers. In this review, we summarize the most widely studied roles and mechanisms of RNA modifications (m6A, m1A, m5C, m7G, A-to-I editing, pseudouridine [Ψ]) in relation to digestive tract cancers, highlight the crosstalk between RNA modifications, and discuss their roles in the interactions between the digestive system and microbiota during carcinogenesis. The clinical significance of novel therapeutic methods based on RNA-modifying enzymes is also discussed. This review will help guide future research into digestive tract cancers that are resistant to current therapeutics.
Asunto(s)
Epigénesis Genética , Humanos , Animales , ARN/genética , ARN/metabolismo , Neoplasias Gastrointestinales/genética , Procesamiento Postranscripcional del ARN , Neoplasias del Sistema Digestivo/genética , Neoplasias del Sistema Digestivo/terapiaRESUMEN
The majority of proteins must form higher-order assemblies to perform their biological functions. Despite the importance of protein quaternary structure, there are few machine learning models that can accurately and rapidly predict the symmetry of assemblies involving multiple copies of the same protein chain. Here, we address this gap by training several classes of protein foundation models, including ESM-MSA, ESM2, and RoseTTAFold2, to predict homo-oligomer symmetry. Our best model named Seq2Symm, which utilizes ESM2, outperforms existing template-based and deep learning methods. It achieves an average PR-AUC of 0.48 and 0.44 across homo-oligomer symmetries on two different held-out test sets compared to 0.32 and 0.23 for the template-based method. Because Seq2Symm can rapidly predict homo-oligomer symmetries using a single sequence as input (~ 80,000 proteins/hour), we have applied it to 5 entire proteomes and ~ 3.5 million unlabeled protein sequences to identify patterns in protein assembly complexity across biological kingdoms and species.
RESUMEN
Prior efforts have manifested that functional connectivity (FC) network disruptions are concerned with cognitive disorder in presbycusis. The present research was designed to investigate the topological reorganization and classification performance of low-order functional connectivity (LOFC) and high-order functional connectivity (HOFC) networks in patients with presbycusis. Resting-state functional magnetic resonance imaging (Rs-fMRI) data were obtained in 60 patients with presbycusis and 50 matched healthy control subjects (HCs). LOFC and HOFC networks were then constructed, and the topological metrics obtained from the constructed networks were compared to evaluate topological differences in global, nodal network metrics, modularity and rich-club organization between patients with presbycusis and HCs. The use of HOFC profiles boosted presbycusis classification accuracy, sensitivity and specificity compared to that using LOFC profiles. The brain networks in both patients with presbycusis and HCs exhibited small-world properties within the given threshold range, and striking differences between groups in topological metrics were discovered in the constructed networks (LOFC and HOFC). NBS analysis identified a subnetwork involving 26 nodes and 23 signally altered internodal connections in patients with presbycusis in comparison to HCs in HOFC networks. This study highlighted the topological differences between LOFC and HOFC networks in patients with presbycusis, suggesting that HOFC profiles may help to further identify brain network abnormalities in presbycusis.
RESUMEN
PURPOSE: Automatic and accurate segmentation of lesions in images of metastatic castration-resistant prostate cancer has the potential to enable personalized radiopharmaceutical therapy and advanced treatment response monitoring. The aim of this study is to develop a convolutional neural networks-based framework for fully-automated detection and segmentation of metastatic prostate cancer lesions in whole-body PET/CT images. METHODS: 525 whole-body PET/CT images of patients with metastatic prostate cancer were available for the study, acquired with the [18F]DCFPyL radiotracer that targets prostate-specific membrane antigen (PSMA). U-Net (1)-based convolutional neural networks (CNNs) were trained to identify lesions on paired axial PET/CT slices. Baseline models were trained using batch-wise dice loss, as well as the proposed weighted batch-wise dice loss (wDice), and the lesion detection performance was quantified, with a particular emphasis on lesion size, intensity, and location. We used 418 images for model training, 30 for model validation, and 77 for model testing. In addition, we allowed our model to take n = 0,2, , 12 neighboring axial slices to examine how incorporating greater amounts of 3D context influences model performance. We selected the optimal number of neighboring axial slices that maximized the detection rate on the 30 validation images, and trained five neural networks with different architectures. RESULTS: Model performance was evaluated using the detection rate, Dice similarity coefficient (DSC) and sensitivity. We found that the proposed wDice loss significantly improved the lesion detection rate, lesion-wise DSC and lesion-wise sensitivity compared to the baseline, with corresponding average increases of 0.07 (p-value = 0.01), 0.03 (p-value = 0.01) and 0.04 (p-value = 0.01), respectively. The inclusion of the first two neighboring axial slices in the input likewise increased the detection rate by 0.17, lesion-wise DSC by 0.05, and lesion-wise mean sensitivity by 0.16. However, there was a minimal effect from including more distant neighboring slices. We ultimately chose to use a number of neighboring slices equal to 2 and the wDice loss function to train our final model. To evaluate the model's performance, we trained three models using identical hyperparameters on three different data splits. The results showed that, on average, the model was able to detect 80% of all testing lesions, with a detection rate of 93% for lesions with maximum standardized uptake values (SUVmax) greater than 5.0. In addition, the average median lesion-wise DSC was 0.51 and 0.60 for all the lesions and lesions with SUVmax>5.0, respectively, on the testing set. Four additional neural networks with different architectures were trained, and they both yielded stronger performance of segmenting lesions whose SUVmax>5.0 compared to the rest of lesions. CONCLUSION: Our results demonstrate that prostate cancer metastases in PSMA PET/CT images can be detected and segmented using CNNs. The segmentation performance strongly depends on the intensity, size, and the location of lesions, and can be improved by using specialized loss functions. Specifically, the models performed best in detection of lesions with SUVmax>5.0. Another challenge was to accurately segment lesions close to the bladder. Future work will focus on improving the detection of lesions with lower SUV values by designing custom loss functions that take into account the lesion intensity, using additional data augmentation techniques, and reducing the number of false lesions by developing methods to better separate signal from noise.
Asunto(s)
Tomografía Computarizada por Tomografía de Emisión de Positrones , Neoplasias de la Próstata , Masculino , Humanos , Tomografía Computarizada por Tomografía de Emisión de Positrones/métodos , Neoplasias de la Próstata/diagnóstico por imagen , Redes Neurales de la Computación , RadiofármacosRESUMEN
To evaluate the generalizability of artificial intelligence (AI) algorithms that use deep learning methods to identify middle ear disease from otoscopic images, between internal to external performance. 1842 otoscopic images were collected from three independent sources: (a) Van, Turkey, (b) Santiago, Chile, and (c) Ohio, USA. Diagnostic categories consisted of (i) normal or (ii) abnormal. Deep learning methods were used to develop models to evaluate internal and external performance, using area under the curve (AUC) estimates. A pooled assessment was performed by combining all cohorts together with fivefold cross validation. AI-otoscopy algorithms achieved high internal performance (mean AUC: 0.95, 95%CI: 0.80-1.00). However, performance was reduced when tested on external otoscopic images not used for training (mean AUC: 0.76, 95%CI: 0.61-0.91). Overall, external performance was significantly lower than internal performance (mean difference in AUC: -0.19, p ≤ 0.04). Combining cohorts achieved a substantial pooled performance (AUC: 0.96, standard error: 0.01). Internally applied algorithms for otoscopy performed well to identify middle ear disease from otoscopy images. However, external performance was reduced when applied to new test cohorts. Further efforts are required to explore data augmentation and pre-processing techniques that might improve external performance and develop a robust, generalizable algorithm for real-world clinical applications.
Asunto(s)
Aprendizaje Profundo , Enfermedades del Oído , Humanos , Inteligencia Artificial , Otoscopía/métodos , Algoritmos , Enfermedades del Oído/diagnóstico por imagenRESUMEN
Osteosarcoma (OS) is one of the most common primary bone malignancy. Combining chemotherapy and surgical treatment significantly improved clinical outcomes for osteosarcoma patients. Osteosarcoma stem cells (OSCs) are often more malignant than differentiated cancer cells and are a key determinant of responses to chemotherapy and radiation therapy, therefore, the removal of OSCs could be an effective therapeutic strategy. Myxoprotein 1 (MUC1) is aberrantly overexpressed in many human cancers and it promotes cancer stemness through activation of pluripotency networks. In this study, we observed elevated MUC1 in osteosarcoma and a depressed prognosis in patients with high MUC1 expression profiles. Our observations also revealed that MUC1 promoted OS stemness and tumor metastasis both in vivo and in vitro. These data led us to hypothesize that MUC1 may be a therapeutic target for patients with OS.
Asunto(s)
Neoplasias Óseas , Mucina-1 , Osteosarcoma , Humanos , Neoplasias Óseas/patología , Línea Celular Tumoral , Mucina-1/metabolismo , Células Madre Neoplásicas/patología , Osteosarcoma/metabolismo , PronósticoRESUMEN
BACKGROUND: Despite an abundance of information on the risk factors of SARS-CoV-2, there have been few US-wide studies of long-term effects. In this paper we analyzed a large medical claims database of US based individuals to identify common long-term effects as well as their associations with various social and medical risk factors. METHODS: The medical claims database was obtained from a prominent US based claims data processing company, namely Change Healthcare. In addition to the claims data, the dataset also consisted of various social determinants of health such as race, income, education level and veteran status of the individuals. A self-controlled cohort design (SCCD) observational study was performed to identify ICD-10 codes whose proportion was significantly increased in the outcome period compared to the control period to identify significant long-term effects. A logistic regression-based association analysis was then performed between identified long-term effects and social determinants of health. RESULTS: Among the over 1.37 million COVID patients in our datasets we found 36 out of 1724 3-digit ICD-10 codes to be statistically significantly increased in the post-COVID period (p-value < 0.05). We also found one combination of ICD-10 codes, corresponding to 'other anemias' and 'hypertension', that was statistically significantly increased in the post-COVID period (p-value < 0.05). Our logistic regression-based association analysis with social determinants of health variables, after adjusting for comorbidities and prior conditions, showed that age and gender were significantly associated with the multiple long-term effects. Race was only associated with 'other sepsis', income was only associated with 'Alopecia areata' (autoimmune disease causing hair loss), while education level was only associated with 'Maternal infectious and parasitic diseases' (p-value < 0.05). CONCLUSION: We identified several long-term effects of SARS-CoV-2 through a self-controlled study on a cohort of over one million patients. Furthermore, we found that while age and gender are commonly associated with the long-term effects, other social determinants of health such as race, income and education levels have rare or no significant associations.
Asunto(s)
COVID-19 , Humanos , COVID-19/epidemiología , SARS-CoV-2 , Determinantes Sociales de la Salud , Factores de Riesgo , ComorbilidadRESUMEN
COVID-19 mortality risk stratification tools could improve care, inform accurate and rapid triage decisions, and guide family discussions regarding goals of care. A minority of COVID-19 prognostic tools have been tested in external cohorts. Our objective was to compare machine learning algorithms and develop a tool for predicting subsequent clinical outcomes in COVID-19. We conducted a retrospective cohort study that included hospitalized patients with COVID-19 from March 2020 to March 2021. Seven Hundred Twelve consecutive patients from University of Washington and 345 patients from Tongji Hospital in China were included. We applied three different machine learning algorithms to clinical and laboratory data collected within the initial 24 h of hospital admission to determine the risk of in-hospital mortality, transfer to the intensive care unit, shock requiring vasopressors, and receipt of renal replacement therapy. Mortality risk models were derived, internally validated in UW and externally validated in Tongji Hospital. The risk models for ICU transfer, shock and RRT were derived and internally validated in the UW dataset but were unable to be externally validated due to a lack of data on these outcomes. Among the UW dataset, 122 patients died (17%) during hospitalization and the mean days to hospital mortality was 15.7 +/- 21.5 (mean +/- SD). Elastic net logistic regression resulted in a C-statistic for in-hospital mortality of 0.72 (95% CI, 0.64 to 0.81) in the internal validation and 0.85 (95% CI, 0.81 to 0.89) in the external validation set. Age, platelet count, and white blood cell count were the most important predictors of mortality. In the sub-group of patients > 50 years of age, the mortality prediction model continued to perform with a C-statistic of 0.82 (95% CI:0.76,0.87). Prediction models also performed well for shock and RRT in the UW dataset but functioned with lower accuracy for ICU transfer. We trained, internally and externally validated a prediction model using data collected within 24 h of hospital admission to predict in-hospital mortality on average two weeks prior to death. We also developed models to predict RRT and shock with high accuracy. These models could be used to improve triage decisions, resource allocation, and support clinical trial enrichment.
Asunto(s)
COVID-19 , Hospitalización , Humanos , Aprendizaje Automático , Pronóstico , Estudios RetrospectivosRESUMEN
Acquired aplastic anemia (AA) is caused by autoreactive T cell-mediated destruction of early hematopoietic cells. Somatic loss of human leukocyte antigen (HLA) class I alleles was identified as a mechanism of immune escape in surviving hematopoietic cells of some patients with AA. However, pathogenicity, structural characteristics, and clinical impact of specific HLA alleles in AA remain poorly understood. Here, we evaluated somatic HLA loss in 505 patients with AA from 2 multi-institutional cohorts. Using a combination of HLA mutation frequencies, peptide-binding structures, and association with AA in an independent cohort of 6,323 patients from the National Marrow Donor Program, we identified 19 AA risk alleles and 12 non-risk alleles and established a potentially novel AA HLA pathogenicity stratification. Our results define pathogenicity for the majority of common HLA-A/B alleles across diverse populations. Our study demonstrates that HLA alleles confer different risks of developing AA, but once AA develops, specific alleles are not associated with response to immunosuppression or transplant outcomes. However, higher pathogenicity alleles, particularly HLA-B*14:02, are associated with higher rates of clonal evolution in adult patients with AA. Our study provides insights into the immune pathogenesis of AA, opening the door to future autoantigen identification and improved understanding of clonal evolution in AA.
Asunto(s)
Anemia Aplásica , Adulto , Humanos , Anemia Aplásica/genética , Anemia Aplásica/patología , Alelos , Antígenos de Histocompatibilidad Clase I/genética , Antígenos HLA-B/genética , Antígenos HLA/genéticaRESUMEN
OBJECTIVE: Early identification of diabetic retinopathy (DR) is key to prioritizing therapy and preventing permanent blindness. This study aims to propose a machine learning model for DR early diagnosis using metabolomics and clinical indicators. METHODS: From 2017 to 2018, 950 participants were enrolled from two affiliated hospitals of Wenzhou Medical University and Anhui Medical University. A total of 69 matched blocks including healthy volunteers, type 2 diabetes, and DR patients were obtained from a propensity score matching-based metabolomics study. UPLC-ESI-MS/MS system was utilized for serum metabolic fingerprint data. CART decision trees (DT) were used to identify the potential biomarkers. Finally, the nomogram model was developed using the multivariable conditional logistic regression models. The calibration curve, Hosmer-Lemeshow test, receiver operating characteristic curve, and decision curve analysis were applied to evaluate the performance of this predictive model. RESULTS: The mean age of enrolled subjects was 56.7 years with a standard deviation of 9.2, and 61.4% were males. Based on the DT model, 2-pyrrolidone completely separated healthy controls from diabetic patients, and thiamine triphosphate (ThTP) might be a principal metabolite for DR detection. The developed nomogram model (including diabetes duration, systolic blood pressure and ThTP) shows an excellent quality of classification, with AUCs (95% CI) of 0.99 (0.97-1.00) and 0.99 (0.95-1.00) in training and testing sets, respectively. Furthermore, the predictive model also has a reasonable degree of calibration. CONCLUSIONS: The nomogram presents an accurate and favorable prediction for DR detection. Further research with larger study populations is needed to confirm our findings.
Asunto(s)
Diabetes Mellitus Tipo 2 , Retinopatía Diabética , Diabetes Mellitus Tipo 2/complicaciones , Diabetes Mellitus Tipo 2/diagnóstico , Retinopatía Diabética/diagnóstico , Diagnóstico Precoz , Femenino , Humanos , Aprendizaje Automático , Masculino , Metabolómica , Persona de Mediana Edad , Nomogramas , Espectrometría de Masas en TándemRESUMEN
Purpose: Presbycusis is characterized by bilateral sensorineural hearing loss at high frequencies and is often accompanied by cognitive decline. This study aimed to identify the topological reorganization of brain functional network in presbycusis with/without cognitive decline by using graph theory analysis approaches based on resting-state functional magnetic resonance imaging (rs-fMRI). Methods: Resting-state fMRI scans were obtained from 30 presbycusis patients with cognitive decline, 30 presbycusis patients without cognitive decline, and 50 age-, sex-, and education-matched healthy controls. Graph theory was applied to analyze the topological properties of brain functional networks including global and nodal metrics, modularity, and rich-club organization. Results: At the global level, the brain functional networks of all participants were found to possess small-world properties. Also, significant group differences in global network metrics were observed among the three groups such as clustering coefficient, characteristic path length, normalized characteristic path length, and small-worldness. At the nodal level, several nodes with abnormal betweenness centrality, degree centrality, nodal efficiency, and nodal local efficiency were detected in presbycusis patients with/without cognitive decline. Changes in intra-modular connections in frontal lobe module and inter-modular connections in prefrontal subcortical lobe module were found in presbycusis patients exposed to modularity analysis. Rich-club nodes were reorganized in presbycusis patients, while the connections among them had no significant group differences. Conclusion: Presbycusis patients exhibited topological reorganization of the whole-brain functional network, and presbycusis patients with cognitive decline showed more obvious changes in these topological properties than those without cognitive decline. Abnormal changes of these properties in presbycusis patients may compensate for cognitive impairment by mobilizing additional neural resources.
RESUMEN
Background: Diabetic retinopathy (DR) is a major diabetes-related disease linked to metabolism. However, the cognition of metabolic pathway alterations in DR remains scarce. We aimed to corroborate alterations of metabolic pathways identified in prior studies and investigate novel metabolic dysregulations that may lead to new prevention and treatment strategies for DR. Methods: In this case-control study, we tested 613 serum metabolites in 69 pairs of type 2 diabetic patients (T2DM) with DR and propensity score-matched T2DM without DR via ultra-performance liquid chromatography-tandem mass spectrometry system. Metabolic pathway dysregulation in DR was thoroughly investigated by metabolic pathway analysis, chemical similarity enrichment analysis (ChemRICH), and integrated pathway analysis. The associations of ChemRICH-screened key metabolites with DR were further estimated with restricted cubic spline analyses. Results: A total of 89 differentially expressed metabolites were identified by paired univariate analysis and partial least squares discriminant analysis. We corroborated biosynthesis of unsaturated fatty acids, glycine, serine and threonine metabolism, glutamate and cysteine-related pathways, and nucleotide-related pathways were significantly perturbed in DR, which were identified in prior studies. We also found some novel metabolic alterations associated with DR, including the disturbance of thiamine metabolism and tryptophan metabolism, decreased trehalose, and increased choline and indole derivatives in DR. Conclusions: The results suggest that the metabolism disorder in DR can be better understood through integrating multiple biological knowledge databases. The progression of DR is associated with the disturbance of thiamine metabolism and tryptophan metabolism, decreased trehalose, and increased choline and indole derivatives.
RESUMEN
BACKGROUND AND OBJECTIVE: Radiomics and deep learning have emerged as two distinct approaches to medical image analysis. However, their relative expressive power remains largely unknown. Theoretically, hand-crafted radiomic features represent a mere subset of features that neural networks can approximate, thus making deep learning a more powerful approach. On the other hand, automated learning of hand-crafted features may require a prohibitively large number of training samples. Here we directly test the ability of convolutional neural networks (CNNs) to learn and predict the intensity, shape, and texture properties of tumors as defined by standardized radiomic features. METHODS: Conventional 2D and 3D CNN architectures with an increasing number of convolutional layers were trained to predict the values of 16 standardized radiomic features from real and synthetic PET images of tumors, and tested. In addition, several ImageNet-pretrained advanced networks were tested. A total of 4000 images were used for training, 500 for validation, and 500 for testing. RESULTS: Features quantifying size and intensity were predicted with high accuracy, while shape irregularity and heterogeneity features had very high prediction errors and generalized poorly. For example, mean normalized prediction error of tumor diameter with a 5-layer CNN was 4.23 ± 0.25, while the error for tumor sphericity was 15.64 ± 0.93. We additionally found that learning shape features required an order of magnitude more samples compared to intensity and size features. CONCLUSIONS: Our findings imply that CNNs trained to perform various image-based clinical tasks may generally under-utilize the shape and texture information that is more easily captured by radiomics. We speculate that to improve the CNN performance, shape and texture features can be computed explicitly and added as auxiliary variables to the networks, or supplied as synthetic inputs.
Asunto(s)
Aprendizaje Profundo , Neoplasias , Humanos , Procesamiento de Imagen Asistido por Computador/métodos , Neoplasias/diagnóstico por imagen , Redes Neurales de la ComputaciónRESUMEN
Although previous studies demonstrate that trehalose can help maintain glucose homeostasis in healthy humans, its role and joint effect with glutamate on diabetic retinopathy (DR) remain unclear. We aimed to comprehensively quantify the associations of trehalose and glutamate with DR. This study included 69 pairs of DR and matched type 2 diabetic (T2D) patients. Serum trehalose and glutamate were determined via ultra-performance liquid chromatography-electrospray ionization-tandem mass spectrometry system. Covariates were collected by a standardized questionnaire, clinical examinations and laboratory assessments. Individual and joint association of trehalose and glutamate with DR were quantified by multiple conditional logistic regression models. The adjusted odds of DR averagely decreased by 86% (odds ratio (OR): 0.14; 95% CI: 0.06, 0.33) with per interquartile range increase of trehalose. Comparing with the lowest quartile, adjusted OR (95% CI) were 0.20 (0.05, 0.83), 0.14 (0.03, 0.63) and 0.01 (<0.01, 0.05) for participants in the second, third and fourth quartiles of trehalose, respectively. In addition, as compared to their counterparts, T2D patients with lower trehalose (
RESUMEN
Background: Leprosy is an infectious disease that mostly affects underserved populations. Although it has been largely eliminated, still about 200'000 new patients are diagnosed annually. In the absence of a diagnostic test, clinical diagnosis is often delayed, potentially leading to irreversible neurological damage and its resulting stigma, as well as continued transmission. Accelerating diagnosis could significantly contribute to advancing global leprosy elimination. Digital and Artificial Intelligence (AI) driven technology has shown potential to augment health workers abilities in making faster and more accurate diagnosis, especially when using images such as in the fields of dermatology or ophthalmology. That made us start the quest for an AI-driven diagnosis assistant for leprosy, based on skin images. Methods: Here we describe the accuracy of an AI-enabled image-based diagnosis assistant for leprosy, called AI4Leprosy, based on a combination of skin images and clinical data, collected following a standardized process. In a Brazilian leprosy national referral center, 222 patients with leprosy or other dermatological conditions were included, and the 1229 collected skin images and 585 sets of metadata are stored in an open-source dataset for other researchers to exploit. Findings: We used this dataset to test whether a CNN-based AI algorithm could contribute to leprosy diagnosis and employed three AI models, testing images and metadata both independently and in combination. AI modeling indicated that the most important clinical signs are thermal sensitivity loss, nodules and papules, feet paresthesia, number of lesions and gender, but also scaling surface and pruritus that were negatively associated with leprosy. Using elastic-net logistic regression provided a high classification accuracy (90%) and an area under curve (AUC) of 96.46% for leprosy diagnosis. Interpretation: Future validation of these models is underway, gathering larger datasets from populations of different skin types and collecting images with smartphone cameras to mimic real world settings. We hope that the results of our research will lead to clinical solutions that help accelerate global leprosy elimination. Funding: This study was partially funded by Novartis Foundation and Microsoft (in-kind contribution).
RESUMEN
BackgroundCOVID-19 mortality risk stratification tools could improve care, inform accurate and rapid triage decisions, and guide family discussions regarding goals of care. A minority of COVID-19 prognostic tools have been tested in external cohorts. Our objective was to compare machine learning algorithms and develop a tool for predicting subsequent clinical outcomes in COVID-19. MethodsWe conducted a retrospective cohort study that included hospitalized patients with COVID-19 from March 2020 to March 2021. 712 consecutive patients from University of Washington (UW) and 345 patients from Tongji Hospital in China were included. We applied three different machine learning algorithms to clinical and laboratory data collected within the initial 24 hours of hospital admission to determine the risk of in-hospital mortality, transfer to the intensive care unit (ICU), shock requiring vasopressors, and receipt of renal replacement therapy (RRT). Mortality risk models were derived, internally validated in UW and externally validated in Tongji Hospital. The risk models for ICU transfer, shock and RRT were derived and internally validated in the UW dataset. ResultsAmong the UW dataset, 122 patients died (17%) during hospitalization and the mean days to hospital mortality was 15.7 +/- 21.5 (mean +/- SD). Elastic net logistic regression resulted in a C-statistic for in-hospital mortality of 0.72 (95% CI, 0.64 to 0.81) in the internal validation and 0.85 (95% CI, 0.81 to 0.89) in the external validation set. Age, platelet count, and white blood cell count were the most important predictors of mortality. In the sub-group of patients > 50 years of age, the mortality prediction model continued to perform with a C-statistic of 0.82 (95% CI:0.76,0.87). Mortality prediction models also performed well for shock and RRT in the UW dataset but functioned with lower accuracy for ICU transfer. ConclusionsWe trained, internally and externally validated a prediction model using data collected within 24 hours of hospital admission to predict in-hospital mortality on average two weeks prior to death. We also developed models to predict RRT and shock with high accuracy. These models could be used to improve triage decisions, resource allocation, and support clinical trial enrichment.
RESUMEN
BACKGROUND: Optimal ω-6/ω-3 polyunsaturated fatty acids ratio (PUFAR) is reported to exert protective effects against chronic diseases. However, data on PUFAR and diabetic retinopathy (DR) remains scarce. We aimed to thoroughly quantify whether and how PUFAR was related to DR as well as its role in DR detection. METHODS: This two-centre case-control study was conducted from August 2017 to June 2018 in China, participants were matched using a propensity score matching algorithm. We adopted multivariable logistic regression models and restricted cubic spline analyses to estimate the independent association of PUFAR with DR, adjusting for confounders identified using a directed acyclic graph. The value of PUFAR as a biomarker for DR identification was further evaluated by receiver operating characteristic analyses and Hosmer-Lemeshow tests. FINDINGS: An apparent negative relationship between PUFAR and DR was observed. Adjusted odds of DR decreased by 79% (OR: 0·21, 95% CI: 0·10-0·40) with an interquartile range increase in PUFAR. Similar results were also obtained in tertile analysis. As compared to those in the 1st tertile of PUFAR, the adjusted odds of DR decreased by 76% (OR: 0·24, 95% CI: 0·08-0·66) and 93% (OR: 0·07, 95% CI: 0·03-0·22) for subjects in the 2nd and 3rd tertiles, respectively. Good calibration and discrimination of the PUFAR associated predictive model were detected and PUFAR = 35 would be an ideal cut-off value for DR identification. INTERPRETATION: Our results suggest that serum PUAFR is inversely associated with DR. Although PUFAR-alteration is not observed amongst different stages of DR, it can serve as an ideal biomarker in distinguishing patients with DR from those without DR. FUNDING: This study was funded by Natural Science Foundation of Zhejiang Province, Zhejiang Basic Public Welfare Research Project, the Major Project of the Eye Hospital of Wenzhou Medical University, and the Academician's Science and Technology Innovation Program in Zhejiang province. Part of this work was also funded by the National Nature Science Foundation of China, and Research Project for College Students in Wenzhou Medical University.
RESUMEN
Fanconi anemia (FA) is a devastating hereditary disease characterized by bone marrow failure (BMF) and acute myeloid leukemia (AML). As FA-deficient cells are hypersensitive to DNA interstrand crosslinks (ICLs), ICLs are widely assumed to be the lesions responsible for FA symptoms. Here, we show that FA-mutated cells are hypersensitive to persistent replication stress and that FA proteins play a role in the break-induced-replication (BIR)-like pathway for fork restart. Both the BIR-like pathway and ICL repair share almost identical molecular mechanisms of 53BP1-BRCA1-controlled signaling response, SLX4- and FAN1-mediated fork cleavage and POLD3-dependent DNA synthesis, suggesting that the FA pathway is intrinsically one of the BIR-like pathways. Replication stress not only triggers BMF in FA-deficient mice, but also specifically induces monosomy 7, which is associated with progression to AML in patients with FA, in FA-deficient cells.