Your browser doesn't support javascript.
loading
Mostrar: 20 | 50 | 100
Resultados 1 - 20 de 58.849
Filtrar
1.
BMC Bioinformatics ; 21(Suppl 14): 368, 2020 Sep 30.
Artigo em Inglês | MEDLINE | ID: mdl-32998690

RESUMO

BACKGROUND: Lung cancer is the leading cause of the largest number of deaths worldwide and lung adenocarcinoma is the most common form of lung cancer. In order to understand the molecular basis of lung adenocarcinoma, integrative analysis have been performed by using genomics, transcriptomics, epigenomics, proteomics and clinical data. Besides, molecular prognostic signatures have been generated for lung adenocarcinoma by using gene expression levels in tumor samples. However, we need signatures including different types of molecular data, even cohort or patient-based biomarkers which are the candidates of molecular targeting. RESULTS: We built an R pipeline to carry out an integrated meta-analysis of the genomic alterations including single-nucleotide variations and the copy number variations, transcriptomics variations through RNA-seq and clinical data of patients with lung adenocarcinoma in The Cancer Genome Atlas project. We integrated significant genes including single-nucleotide variations or the copy number variations, differentially expressed genes and those in active subnetworks to construct a prognosis signature. Cox proportional hazards model with Lasso penalty and LOOCV was used to identify best gene signature among different gene categories. We determined a 12-gene signature (BCHE, CCNA1, CYP24A1, DEPTOR, MASP2, MGLL, MYO1A, PODXL2, RAPGEF3, SGK2, TNNI2, ZBTB16) for prognostic risk prediction based on overall survival time of the patients with lung adenocarcinoma. The patients in both training and test data were clustered into high-risk and low-risk groups by using risk scores of the patients calculated based on selected gene signature. The overall survival probability of these risk groups was highly significantly different for both training and test datasets. CONCLUSIONS: This 12-gene signature could predict the prognostic risk of the patients with lung adenocarcinoma in TCGA and they are potential predictors for the survival-based risk clustering of the patients with lung adenocarcinoma. These genes can be used to cluster patients based on molecular nature and the best candidates of drugs for the patient clusters can be proposed. These genes also have a high potential for targeted cancer therapy of patients with lung adenocarcinoma.


Assuntos
Adenocarcinoma de Pulmão/patologia , Genômica/métodos , Neoplasias Pulmonares/patologia , Transcriptoma , Adenocarcinoma de Pulmão/genética , Adenocarcinoma de Pulmão/mortalidade , Área Sob a Curva , Análise por Conglomerados , Variações do Número de Cópias de DNA , Bases de Dados Genéticas , Regulação Neoplásica da Expressão Gênica , Humanos , Neoplasias Pulmonares/genética , Neoplasias Pulmonares/mortalidade , Estadiamento de Neoplasias , Prognóstico , Modelos de Riscos Proporcionais , Mapas de Interação de Proteínas/genética , Curva ROC , Fatores de Risco , Taxa de Sobrevida
2.
BMC Bioinformatics ; 21(Suppl 14): 359, 2020 Sep 30.
Artigo em Inglês | MEDLINE | ID: mdl-32998692

RESUMO

BACKGROUND: The abundance of molecular profiling of breast cancer tissues entailed active research on molecular marker-based early diagnosis of metastasis. Recently there is a surging interest in combining gene expression with gene networks such as protein-protein interaction (PPI) network, gene co-expression (CE) network and pathway information to identify robust and accurate biomarkers for metastasis prediction, reflecting the common belief that cancer is a systems biology disease. However, controversy exists in the literature regarding whether network markers are indeed better features than genes alone for predicting as well as understanding metastasis. We believe much of the existing results may have been biased by the overly complicated prediction algorithms, unfair evaluation, and lack of rigorous statistics. In this study, we propose a simple approach to use network edges as features, based on two types of networks respectively, and compared their prediction power using three classification algorithms and rigorous statistical procedure on one of the largest datasets available. To detect biomarkers that are significant for the prediction and to compare the robustness of different feature types, we propose an unbiased and novel procedure to measure feature importance that eliminates the potential bias from factors such as different sample size, number of features, as well as class distribution. RESULTS: Experimental results reveal that edge-based feature types consistently outperformed gene-based feature type in random forest and logistic regression models under all performance evaluation metrics, while the prediction accuracy of edge-based support vector machine (SVM) model was poorer, due to the larger number of edge features compared to gene features and the lack of feature selection in SVM model. Experimental results also show that edge features are much more robust than gene features and the top biomarkers from edge feature types are statistically more significantly enriched in the biological processes that are well known to be related to breast cancer metastasis. CONCLUSIONS: Overall, this study validates the utility of edge features as biomarkers but also highlights the importance of carefully designed experimental procedures in order to achieve statistically reliable comparison results.


Assuntos
Biomarcadores Tumorais/metabolismo , Neoplasias da Mama/patologia , Máquina de Vetores de Suporte , Área Sob a Curva , Neoplasias da Mama/genética , Feminino , Redes Reguladoras de Genes/genética , Humanos , Modelos Logísticos , Metástase Neoplásica , Mapas de Interação de Proteínas/genética , Curva ROC
3.
BMC Bioinformatics ; 21(Suppl 14): 367, 2020 Sep 30.
Artigo em Inglês | MEDLINE | ID: mdl-32998698

RESUMO

BACKGROUND: Essential genes are those genes that are critical for the survival of an organism. The prediction of essential genes in bacteria can provide targets for the design of novel antibiotic compounds or antimicrobial strategies. RESULTS: We propose a deep neural network for predicting essential genes in microbes. Our architecture called DEEPLYESSENTIAL makes minimal assumptions about the input data (i.e., it only uses gene primary sequence and the corresponding protein sequence) to carry out the prediction thus maximizing its practical application compared to existing predictors that require structural or topological features which might not be readily available. We also expose and study a hidden performance bias that effected previous classifiers. Extensive results show that DEEPLYESSENTIAL outperform existing classifiers that either employ down-sampling to balance the training set or use clustering to exclude multiple copies of orthologous genes. CONCLUSION: Deep neural network architectures can efficiently predict whether a microbial gene is essential (or not) using only its sequence information.


Assuntos
Bactérias/genética , Genes Essenciais , Redes Neurais de Computação , Área Sob a Curva , Análise por Conglomerados , Códon , Bactérias Gram-Negativas/genética , Bactérias Gram-Positivas/genética , Curva ROC
4.
BMC Bioinformatics ; 21(Suppl 14): 364, 2020 Sep 30.
Artigo em Inglês | MEDLINE | ID: mdl-32998700

RESUMO

BACKGROUND: Machine learning has been utilized to predict cancer drug response from multi-omics data generated from sensitivities of cancer cell lines to different therapeutic compounds. Here, we build machine learning models using gene expression data from patients' primary tumor tissues to predict whether a patient will respond positively or negatively to two chemotherapeutics: 5-Fluorouracil and Gemcitabine. RESULTS: We focused on 5-Fluorouracil and Gemcitabine because based on our exclusion criteria, they provide the largest numbers of patients within TCGA. Normalized gene expression data were clustered and used as the input features for the study. We used matching clinical trial data to ascertain the response of these patients via multiple classification methods. Multiple clustering and classification methods were compared for prediction accuracy of drug response. Clara and random forest were found to be the best clustering and classification methods, respectively. The results show our models predict with up to 86% accuracy; despite the study's limitation of sample size. We also found the genes most informative for predicting drug response were enriched in well-known cancer signaling pathways and highlighted their potential significance in chemotherapy prognosis. CONCLUSIONS: Primary tumor gene expression is a good predictor of cancer drug response. Investment in larger datasets containing both patient gene expression and drug response is needed to support future work of machine learning models. Ultimately, such predictive models may aid oncologists with making critical treatment decisions.


Assuntos
Antineoplásicos/farmacologia , Regulação Neoplásica da Expressão Gênica/efeitos dos fármacos , Aprendizado de Máquina , Antineoplásicos/uso terapêutico , Área Sob a Curva , Análise por Conglomerados , Bases de Dados Genéticas , Desoxicitidina/análogos & derivados , Desoxicitidina/farmacologia , Desoxicitidina/uso terapêutico , Fluoruracila/uso terapêutico , Humanos , Neoplasias/tratamento farmacológico , Curva ROC
5.
Zhongguo Shi Yan Xue Ye Xue Za Zhi ; 28(5): 1699-1703, 2020 Oct.
Artigo em Chinês | MEDLINE | ID: mdl-33067977

RESUMO

OBJECTIVE: To investigate the diagnostic value of thromboelastography(TEG) for acute disseminated intravascular coagulation(DIC). METHODS: The clinical data and data of blood routine indexes, blood coagulation indexes and TEG indexes of acute 155 DIC patients were collected and analyzed retrospectively. RESULTS: The CDSS scores of DIC and non-DIC groups were 9.2±1.4 and 4.2±1.1 respectively, and the CDSS scores of DIC group was significantly higher than those in non-DIC group(P<0.05). The PLT level in DIC group was significantly lower than that in non-DIC group(P<0.05), the PT, APTT, INT, DD and FIB levels in DIC group were significantly higher than those in non-DIC group(P<0.05). The R time, K time and LY30 in DIC group were significantly higher than those in non-DIC group(P<0.05), and the α and MA in DIC group were significantly lower than those in non-DIC group(P<0.05). ROC curve analysis showed that the best cutoff value of R time, K time, α, MA and LY30 were 8.4 min, 6.2 min, 52.5°, 43.2 mm and 6.7% respectively. The AUC of total scores≥1, ≥2, ≥3 and ≥4 were 0.552, 0.650, 0.687 and 0.613 respectively. CONCLUSION: The TEG possesses the certain value in the diagnosing of DIC.


Assuntos
Coagulação Intravascular Disseminada , Tromboelastografia , Testes de Coagulação Sanguínea , Coagulação Intravascular Disseminada/diagnóstico , Humanos , Curva ROC , Estudos Retrospectivos
6.
Zhongguo Shi Yan Xue Ye Xue Za Zhi ; 28(5): 1746-1749, 2020 Oct.
Artigo em Chinês | MEDLINE | ID: mdl-33067984

RESUMO

AbstractObjective: To evaluate the diagnostic value of serum PCT, CRP and SAA for bloodstream infection(BSI) in patients with hematopathy. METHODS: Sixty hematopathy patients with bloodstream infection from July 2016 to June 2018 were selected and enroued in bloodstream infection group. Sixty-five patients with negative blood culture during the same period were selected and enrolled in non-bloodstream infection group. The ROC curves were drawn and used to eualuate the diagnostic value of above montioned indexes. RESULTS: The levels of PCT, CRP and SAA in the bloodstream infection group were higher than those in the non-bloodstream infection group (P<0.05). ROC curve showed that AUC values of PCT, CRP, SAA and the combined test detection were 0.868, 0.746, 0.678 and 0.900, respectively, there was no significant difference in AUC between combined test and PCT test (P>0.05). AUC of combined test and PCT test were higher than those of CRP and SAA test, and the difference was statistically significant (P<0.05), but there was no significant difference in AUC between CRP and SAA (P>0.05). The optimal PCT detection threshold was 0.49 ng/ml, the sensitivity and specificity were 75.0% and 83.1%, respectively. The optimal critical value for CRP detection was 15.76 mg/L, the sensitivity and specificity were 60.0% and 80.0% respectively. The optimal SAA detection threshold was 35.66 mg/L, the sensitivity and specificity were 81.7% and 53.8%, respectively. CONCLUSION: PCT, CRP and SAA detection have good diagnostic value for blood stream infection in patients with hematopathy. The diagnostic value of PCT is better than CRP and SAA, and there is no significant difference in diagnostic value between combined test and PCT test.


Assuntos
Bacteriemia , Calcitonina , Bacteriemia/diagnóstico , Proteína C-Reativa/análise , Humanos , Curva ROC , Sensibilidade e Especificidade
7.
Clin Appl Thromb Hemost ; 26: 1076029620964868, 2020.
Artigo em Inglês | MEDLINE | ID: mdl-33030047

RESUMO

To discuss the coagulation dysfunction in COVID-19 patients and to find new biomarkers to separate severe COVID-19 patients from mild ones. We use a retrospective analysis of 88 COVID-19 patients, and compare the coagulation function between severe and mild groups. We found the prothrombin time (PT), thrombin time (TT), D-dimer were significantly higher in the severe group (P < 0.05), and the highest area under the curve (AUC) is 0.91 for D-dimer, while the AUC of PT and TT were 0.80 and 0.61 respectively. We identified that D-dimer has a better value in predicting patients who are likely to develop into severe cases, with the sensitivity and specificity were 84.4% and 88.8%, respectively. D-dimer may be a good biomarker to separate the severe COVID-19 patients from the mild ones.


Assuntos
Transtornos da Coagulação Sanguínea/etiologia , Testes de Coagulação Sanguínea/métodos , Infecções por Coronavirus/complicações , Produtos de Degradação da Fibrina e do Fibrinogênio/análise , Pneumonia Viral/complicações , Adulto , Idoso , Área Sob a Curva , Biomarcadores/sangue , Transtornos da Coagulação Sanguínea/sangue , Transtornos da Coagulação Sanguínea/fisiopatologia , China , Estudos de Coortes , Infecções por Coronavirus/diagnóstico , Feminino , Humanos , Masculino , Pessoa de Meia-Idade , Pandemias , Pneumonia Viral/diagnóstico , Valor Preditivo dos Testes , Tempo de Protrombina , Curva ROC , Estudos Retrospectivos , Índice de Gravidade de Doença , Tempo de Trombina
8.
Medicine (Baltimore) ; 99(40): e22242, 2020 Oct 02.
Artigo em Inglês | MEDLINE | ID: mdl-33019399

RESUMO

BACKGROUND: To evaluate the clinical value of circulating tumor cell (CTC) detection in peripheral blood for the diagnosis and prognosis of hepatocellular carcinoma (HCC). METHODS: Public databases were searched, and a meta-analysis was performed to determine the specificity, sensitivity, negative- likelihood ratio (NLR) and positive-likelihood ratio (PLR), and diagnostic odds ratio (dOR) of CTC detection for the diagnosis of HCC. Hazard ratios (HRs) and 95% confidence intervals (CIs) were analyzed for the association of CTC detection with overall survival (OS) and HCC recurrence. The Meta-DiSc 1.4 and Review Manager 5.2 software programs were used for statistical analysis. RESULTS: Meta-analysis of 20 studies including 1191 patients showed that the specificity, sensitivity, NLR, PLR, and dOR of CTC testing for HCC diagnosis were 0.60 (95% CI = 0.57-0.63), 0.95 (95%CI = 0.93-0.96), 0.36 (95%CI = 0.28-0.48), 11.64 (95%CI = 5.85-23.14), and 38.94 (95%CI = 18.33-82.75), respectively. Meta-analysis of 18 studies including 1466 patients indicated that the OS of CTC-positive HCC patients was less than that of CTC-negative patients (HR = 2.31; 95% CI = 1.55-3.42; P < .01). Meta-analysis of 5 studies including 339 patients revealed that the presence of CTCs in peripheral blood significantly increased the risk of HCC recurrence (HR = 3.03, 95% CI = 1.89-4.86; P < .01). CONCLUSION: CTCs in peripheral blood may be a useful marker for HCC diagnosis. In addition, the prognosis of CTC-positive HCC patients was significantly worse than that of CTC-negative HCC patients. Therefore, further studies are warranted to confirm the clinical potential of CTC detection in peripheral blood in patients with primary HCC.


Assuntos
Carcinoma Hepatocelular/diagnóstico , Carcinoma Hepatocelular/patologia , Neoplasias Hepáticas/diagnóstico , Neoplasias Hepáticas/patologia , Células Neoplásicas Circulantes/metabolismo , Biomarcadores Tumorais , Carcinoma Hepatocelular/sangue , Contagem de Células , Humanos , Neoplasias Hepáticas/sangue , Recidiva Local de Neoplasia , Células Neoplásicas Circulantes/patologia , Razão de Chances , Prognóstico , Modelos de Riscos Proporcionais , Curva ROC , Sensibilidade e Especificidade , Análise de Sobrevida
9.
Medicine (Baltimore) ; 99(40): e22334, 2020 Oct 02.
Artigo em Inglês | MEDLINE | ID: mdl-33019409

RESUMO

This study aims to establish a diagnostic model of coronary heart disease (CHD) for diabetic foot (DF) patients.The clinical data of 489 hospitalized patients with DF were retrospectively analyzed in this case-control study. The patients were divided into the CHD group (DF with CHD, n = 212) and the control group (DF without CHD, n = 277). Univariate analysis was performed to screen for CHD-related risk factors, and multivariate logistic regression analysis was conducted to determine significant CHD risk factors. Scores were assigned according to the ratio of risk factors (OR) to establish a diagnostic model of CHD for patients with DF. The area under the ROC curve was used to test the application value of the diagnostic model.The logistic regression analysis showed that the risk factors for CHD in DF patients were age, duration of diabetes, toe-brachial index, hyperuricemia, and chronic renal insufficiency. The area under the ROC curve of the diagnostic model was 0.798 (0.759-0.837), the diagnostic point of CHD was 6 points, the diagnostic sensitivity was 69.3%, and the specificity was 76.5%.The established model has good diagnostic value and provides the basis for preliminary screening for CHD in patients with DF.


Assuntos
Doença das Coronárias/diagnóstico , Doença das Coronárias/epidemiologia , Pé Diabético/epidemiologia , Adulto , Fatores Etários , Idoso , Idoso de 80 Anos ou mais , Índice Tornozelo-Braço , Estudos de Casos e Controles , Feminino , Humanos , Hiperuricemia/epidemiologia , Modelos Logísticos , Masculino , Pessoa de Meia-Idade , Curva ROC , Insuficiência Renal Crônica/epidemiologia , Estudos Retrospectivos , Fatores de Risco , Fatores de Tempo
10.
Nihon Hoshasen Gijutsu Gakkai Zasshi ; 76(10): 997-1008, 2020.
Artigo em Japonês | MEDLINE | ID: mdl-33087659

RESUMO

PURPOSE: We investigated the clinical utility of a radiological technologist's (RT)'s reports (RRs) as a second opinion by the free-response receiver operating characteristic (FROC) observer study that compared the performance of medical doctors' (MDs') reading of digital mammogram with and without consulting the RR. METHOD: One hundred women (39 malignant, 61 benign or normal) who underwent diagnostic mammography were selected from among 1674 routine clinical images classified by the degree of difficulty and categories for inclusion in the FROC study. The first FROC study performed by three RTs (RT 1-3) was conducted to collect the data for RR utilized in the second FROC study. The second FROC study was performed by five MDs, and the statistical significance of MDs' performances with and without reference to the RR was investigated by figure of merit (FOM). RESULT: The FOM values of three RTs obtained in the first FROC study were 0.529, 0.576, and 0.539, respectively. In the second FROC study, RT 2 had the highest FOM, RT 1 the lowest false positives/case, and RT 3 the highest sensitivity. The average FOM values in the second FROC study for the five MDs with/without reference to the RR were as follows: RT 2's RR was 0.534/0.588 (p=0.003), RT 1's RR was 0.500/0.545 (p=0.099), and RT 3's RR was 0.569/0.592 (p=0.324). CONCLUSION: We concluded that the MDs' performance of reading mammogram was statistically improved by consulting the RR when the RT's reading skill was high.


Assuntos
Mamografia , Leitura , Feminino , Humanos , Organizações , Curva ROC , Encaminhamento e Consulta
11.
Medicine (Baltimore) ; 99(40): e22203, 2020 Oct 02.
Artigo em Inglês | MEDLINE | ID: mdl-33019395

RESUMO

Breast cancer (BC) is a disease of high mortality rate because of high malignant, while early diagnosis and personal management may make a better prognosis possible. This study aimed to establish and validate lncRNAs signatures to improve the prognostic prediction for BC.RNA sequencing data along with the corresponding clinical information of patients with BC were gained from The Cancer Genome Atlas (TCGA). Prognostic differentially expressed lncRNAs were obtained using differentially expressed lncRNAs analysis (P value <.01 and |fold change| > 2) and univariate cox regression (P value <.05). By applying least absolute shrinkage and selection operation (LASSO) Cox regression analysis along with 10-fold cross-validation, 2 lncRNA-based signatures were constructed in the training, test and whole set.A 14-lncRNAs signature and a 10-lncRNAs signature were built for overall survival (OS) and relapse-free survival (RFS) respectively in the 3 sets. BC patients were divided into high-risk groups and low-risk groups depended on median risk score value. Significant differences were found for OS and RFS between 2 groups in the 3 sets. The time-dependent receiver operating characteristic (ROC) curves analysis demonstrated that our lncRNAs signatures had better predictive capacities of survival and recurrence for BC patients as well as enhancing the predictive ability of the tumor node metastasis (TNM) stage system.These results indicate that the 2 lncRNAs signatures with the potential to be biomarkers to predict the prognosis of BC for OS and RFS.


Assuntos
Neoplasias da Mama/genética , Carcinoma Ductal de Mama/genética , RNA Longo não Codificante/genética , Adulto , Idoso , Biomarcadores Tumorais/genética , Neoplasias da Mama/mortalidade , Intervalo Livre de Doença , Feminino , Regulação Neoplásica da Expressão Gênica , Humanos , Pessoa de Meia-Idade , Intervalo Livre de Progressão , Modelos de Riscos Proporcionais , Curva ROC
12.
Medicine (Baltimore) ; 99(40): e22432, 2020 Oct 02.
Artigo em Inglês | MEDLINE | ID: mdl-33019423

RESUMO

Nesfatin-1 was identified as a satiety factor involved in the regulation of metabolism. Altered levels of circulating nesfatin-1 had been observed in a variety of diseases characterized by energy imbalance. However, there was no published data about nesfatin-1 levels in acromegaly.We evaluated serum nesfatin-1 levels in 13 patients with acromegaly at baseline and postoperatively, and in 21 age- and body mass index (BMI)-matched healthy subjects.Compared with the healthy subjects, patients with acromegaly had significantly increased levels of serum insulin, high-density lipoprotein cholesterol, triglyceride, and growth hormone (GH). Moreover, the acromegaly group had nesfatin-1 levels higher than controls (1.96 ±â€Š0.56 ng/mL vs 0.61 ±â€Š0.10 ng/mL, P = .004). There was a positive correlation of serum nesfatin-1 levels with diastolic blood pressure (r = 0.579, P = .038) and homeostasis model assessment of insulin resistance (HOMA-IR) (r = 0.598, P = .031) in patients with acromegaly. While a successful surgery decreased serum GH levels, the serum nesfatin-1 levels did not change in acromegaly (P = .965). At last, we compared serum GH/nesfatin-1 levels with predictive markers for aggressive behaviors in pituitary adenomas. There was no relationship between serum nesfatin-1 levels and tumor's size, Ki-67 index, mutant p53, or MGMT proteins. However, increased serum GH levels were positively correlated with tumors' size (P = .023) and mutant p53 proteins expression (P = .028).Circulating nesfatin-1 was increased in acromegaly, which was involved in metabolism regulation.


Assuntos
Acromegalia/sangue , Nucleobindinas/sangue , Adenoma/sangue , Adenoma/patologia , Adenoma/cirurgia , Adulto , Pressão Sanguínea , Estudos de Casos e Controles , Feminino , Hormônio do Crescimento Humano/sangue , Humanos , Masculino , Pessoa de Meia-Idade , Neoplasias Hipofisárias/sangue , Neoplasias Hipofisárias/patologia , Neoplasias Hipofisárias/cirurgia , Curva ROC
13.
Annu Int Conf IEEE Eng Med Biol Soc ; 2020: 5446-5449, 2020 07.
Artigo em Inglês | MEDLINE | ID: mdl-33019212

RESUMO

Given the extensive use of machine learning in patient outcome prediction, and the understanding that the challenging nature of predictions in this field may considerably modify the performance of predictive models, research in this area requires some forms of context-sensitive performance metrics. The area under the receiver operating characteristic curve (AUC), precision, recall, specificity, and F1 are widely used measures of performance for patient outcome prediction. These metrics have several merits: they are easy to interpret and do not need any subjective input from the user. However, they weight all samples equally and do not adequately reflect the ability of predictive models in classifying difficult samples. In this paper, we propose the Difficulty Weight Adjustment (DWA) algorithm, a simple method that incorporates the difficulty level of samples when evaluating predictive models. Using a large dataset of 139,367 unique ICU admissions within the eICU Collaborative Research Database (eICU-CRD), we show that the classification difficulty and the discrimination ability of samples are critical aspects that need to be considered when comparing machine learning models that predict patient outcomes.


Assuntos
Algoritmos , Aprendizado de Máquina , Humanos , Modelos Logísticos , Prognóstico , Curva ROC
14.
Annu Int Conf IEEE Eng Med Biol Soc ; 2020: 5606-5609, 2020 07.
Artigo em Inglês | MEDLINE | ID: mdl-33019248

RESUMO

Acute Kidney Injury (AKI) is a common complication after surgery. Recognition of patients at risk of AKI at an earlier stage is a priority for researchers and health care providers. The objective of this study is to develop machine learning prediction models of acute kidney injury (AKI) in patients who undergo surgery. The dataset used in this study consists of in-hospital patients' data of five different cohorts coming from different major procedure types. This data was collected from the SunRiseClinical Manager (SCM) electronic medical records system that is used in the Calgary Zone, Alberta, Canada from 2008 to 2015 where the patients are >=18 years of age. Five classifiers were experimented with: support vector machine, random forest, logistic regression, k-nearest neighbors, and adaptive boosting. The area under the receiver operating characteristics curve (AUROC) ranged between 0.62-0.84 and sensitivity and specificity ranged between 0.81-0.83 and 0.43-0.85, respectively. Predictions from these models can facilitate early intervention in AKI treatment.


Assuntos
Lesão Renal Aguda , Lesão Renal Aguda/diagnóstico , Alberta , Área Sob a Curva , Humanos , Aprendizado de Máquina , Curva ROC
15.
Nat Commun ; 11(1): 5088, 2020 10 09.
Artigo em Inglês | MEDLINE | ID: mdl-33037212

RESUMO

Early detection of COVID-19 based on chest CT enables timely treatment of patients and helps control the spread of the disease. We proposed an artificial intelligence (AI) system for rapid COVID-19 detection and performed extensive statistical analysis of CTs of COVID-19 based on the AI system. We developed and evaluated our system on a large dataset with more than 10 thousand CT volumes from COVID-19, influenza-A/B, non-viral community acquired pneumonia (CAP) and non-pneumonia subjects. In such a difficult multi-class diagnosis task, our deep convolutional neural network-based system is able to achieve an area under the receiver operating characteristic curve (AUC) of 97.81% for multi-way classification on test cohort of 3,199 scans, AUC of 92.99% and 93.25% on two publicly available datasets, CC-CCII and MosMedData respectively. In a reader study involving five radiologists, the AI system outperforms all of radiologists in more challenging tasks at a speed of two orders of magnitude above them. Diagnosis performance of chest x-ray (CXR) is compared to that of CT. Detailed interpretation of deep network is also performed to relate system outputs with CT presentations. The code is available at https://github.com/ChenWWWeixiang/diagnosis_covid19 .


Assuntos
Inteligência Artificial , Infecções por Coronavirus/diagnóstico por imagem , Pneumonia Viral/diagnóstico por imagem , Adulto , Idoso , Idoso de 80 Anos ou mais , Betacoronavirus , Aprendizado Profundo , Diagnóstico Diferencial , Feminino , Humanos , Masculino , Pessoa de Meia-Idade , Pandemias , Pneumonia/diagnóstico por imagem , Curva ROC , Tomografia Computadorizada por Raios X , Adulto Jovem
16.
JMIR Public Health Surveill ; 6(4): e19424, 2020 10 20.
Artigo em Inglês | MEDLINE | ID: mdl-33001830

RESUMO

BACKGROUND: Computed tomography (CT) scans are increasingly available in clinical care globally. They enable a rapid and detailed assessment of tissue and organ involvement in disease processes that are relevant to diagnosis and management, particularly in the context of the COVID-19 pandemic. OBJECTIVE: The aim of this paper is to identify differences in the CT scan findings of patients who were COVID-19 positive (confirmed via nucleic acid testing) to patients who were confirmed COVID-19 negative. METHODS: A retrospective cohort study was proposed to compare patient clinical characteristics and CT scan findings in suspected COVID-19 cases. A multivariable logistic model with LASSO (least absolute shrinkage and selection operator) selection for variables was used to identify the good predictors from all available predictors. The area under the curve (AUC) with 95% CI was calculated for each of the selected predictors and the combined selected key predictors based on receiver operating characteristic curve analysis. RESULTS: A total of 94 (56%) patients were confirmed positive for COVID-19 from the suspected 167 patients. We found that elderly people were more likely to be infected with COVID-19. Among the 94 confirmed positive patients, 2 (2%) patients were admitted to an intensive care unit. No patients died during the study period. We found that the presence, distribution, and location of CT lesions were associated with the presence of COVID-19. White blood cell count, cough, and a travel history to Wuhan were also the top predictors for COVID-19. The overall AUC of these selected predictors is 0.97 (95% CI 0.93-1.00). CONCLUSIONS: Taken together with nucleic acid testing, we found that CT scans can allow for the rapid diagnosis of COVID-19. This study suggests that chest CT scans should be more broadly adopted along with nucleic acid testing in the initial assessment of suspected COVID-19 cases, especially for patients with nonspecific symptoms.


Assuntos
Técnicas de Laboratório Clínico/métodos , Tórax/diagnóstico por imagem , Tomografia Computadorizada por Raios X , Adolescente , Adulto , Infecções por Coronavirus/diagnóstico , Feminino , Humanos , Masculino , Pessoa de Meia-Idade , Curva ROC , Reprodutibilidade dos Testes , Estudos Retrospectivos , Adulto Jovem
17.
Annu Int Conf IEEE Eng Med Biol Soc ; 2020: 1477-1480, 2020 07.
Artigo em Inglês | MEDLINE | ID: mdl-33018270

RESUMO

Physiological parameters can be estimated from dynamic contrast enhanced magnetic resonance imaging (DCEMRI) data using pharmacokinetic models. This work evaluates the performance of various pharmacokinetic models through a retrospective study on cervix cancer, including two generalized kinetic models and three 2-compartment exchange models (2CXMs). In the current clinical practice, region of interest (ROI) is treated as a whole and the models are assessed by their top pharmacokinetic parameters. We explore the intervoxel relationship in the pharmacokinetic parameter maps and demonstrate that, for those insignificant parameters, texture descriptors can largely improve their discriminative power. Multi-parametric classifiers are developed to fuse the information carried by physiological parameters and the descriptors. Assessed merely by the top parameter, the DP (distributed parameter) model is the best one with an area under the ROC (receiver operating characteristic) curve (AUC) of 0.80; by combining multiple pharmacokinetic parameters, the ExTofts model is the winner with an AUC of 0.837. Finally, the classifier of the AATH (adiabatic approximation to the tissue homogeneity) model build on combined features achieves an AUC of 0.92.Clinical Relevance - Using data from 36 cervical cancer patients and 17 normal subjects, this work quantitatively compared the various pharmacokinetic models and provided recommendations for model selection in cervical cancer diagnosis.


Assuntos
Neoplasias do Colo do Útero , Meios de Contraste , Feminino , Humanos , Imagem por Ressonância Magnética , Curva ROC , Estudos Retrospectivos
18.
Zhongguo Yi Xue Ke Xue Yuan Xue Bao ; 42(4): 444-451, 2020 Aug 30.
Artigo em Chinês | MEDLINE | ID: mdl-32895095

RESUMO

Objective To explore the utility of apparent diffusion coefficient(ADC)histogram analysis for differentiating genetic subtypes of diffuse lower-grade gliomas. Methods A total of 55 patients with WHO grade Ⅱ/Ⅲ diffuse lower-grade gliomas who underwent preoperative routine brain magnetic resonance imaging and diffusion weighted imaging in our center were retrospectively evaluated.Among whom there were 14 patients with isocitrate dehydrogenase(IDH)wild-type gliomas(IDH wt group),19 patients with IDH-mutant 1p19q intact gliomas(IDH mut1p19q int group),and 22 patients with IDH-mutant 1p19q co-deleted gliomas(IDH mut1p19q del group).The whole-lesion ADC values derived from histogram analysis(including ADCmean,ADCminimum,ADC5%,ADC10%,ADC25%,ADC50%,ADC75%,ADC90%,ADC95%,ADCmaximum,mode,range,skewness,kurtosis,standard deviation,inhomogeneity,and entrophy)were measured for each patient.All parameters between the different genetic subtypes were compared by using the Student's t test or Mann-Whitney U test.Receiver operating curve(ROC)analysis was used to assess the diagnostic performance of ADC histogram in distinguishing the different genetic subtypes. Results Compared with IDH wt group,the ADC75%(P=0.021),ADC90%(P=0.015),ADC95%(P=0.014),ADCmaximum (P=0.035),range(P=0.009),standard deviation(P=0.001)and inhomogeneity(P=0.001)were significantly lower in IDH mut group;in contrast,the ADCminimum (P=0.031)and kurtosis(P=0.020)of IDH mut group were significantly higher than those in IDH wt group.The ADCmean(P=0.010),ADC5%(P=0.016),ADC10%(P=0.012),ADC25%(P=0.007),ADC50%(P=0.005),ADC75%(P=0.015),and mode(P=0.002)were significantly higher in IDH mut1p19q int group than in IDH mut1p19q del group.Inhomogeneity achieved the highest area under ROC(AUC)(0.811)in differentiating IDH mut gliomas and IDH wt gliomas,with a cutoff value of 0.229;the sensitivity and specificity were 85.7% and 73.2%.The mode achieved the highest AUC(0.744)in differentiating IDH mut1p19q int gliomas and IDH mut1p19q del gliomas,with a cutoff value was 1448.75×10 -6 mm 2/s;the sensitivity and specificity were 57.9% and 90.9%.Conclusion ADC histograms analysis may be helpful to differentiate genetic subtypes in lower-grade gliomas.


Assuntos
Neoplasias Encefálicas , Glioma , Imagem de Difusão por Ressonância Magnética , Humanos , Curva ROC , Estudos Retrospectivos
19.
Medicine (Baltimore) ; 99(35): e21895, 2020 Aug 28.
Artigo em Inglês | MEDLINE | ID: mdl-32871920

RESUMO

MicroRNAs (miRNAs) refers to a small, short non-coding RNA of endogenous class. They have shown to have an increasingly altered expression in many types of cancer, including colorectal cancer (CRC).In the present study, miRNA TaqManMGB and qRT-PCR was used to quantify the expression and clinical significance of 3 mature human miRNA in 82 pairs of colorectal adenocarcinoma tissues and normal adjacent tissue samples (NATS) collected from patients of the south-east part of Romania. Differences between CRC and NATS were analyzed using Wilcoxon test, while correlations between miRNAs expression levels and clinicopathological features were examined using non-parametric tests. In addition, the ability of selected miRNAs to function as biomarkers and, as potential indicators in CRC prognosis was also examined.When the miRNA expression was compared in CRC related NATS, miR-143, and miR-145 were significantly underexpressed (4.99 ±â€Š-1.02 vs -5.66 ±â€Š-1.66, P < .001; -4.85 ±â€Š-0.59 vs -9.27 ±â€Š-1.51, P < .001, respectively), while the pattern of miR-92a was significantly overexpressed (-5.55 ±â€Š-2.83 vs -4.92 ±â€Š-2.44, P < .001). Moreover, the expression levels of selected miRNAs were identified to be correlated with gradual increases in fold change expression with the depth of tumor invasion, lymph node invasion, and maximal increases with distant metastasis. Furthermore, the receiver operating characteristic analysis demonstrated that potential diagnostic of miR-143, miR-145, and miR-92a in discriminating CRC from NATS, with the area under the curve of 0.74, 0.85, and 0.84 respectively. The Kaplan-Meier and the log-rank test showed that a high level of miR-92a and low levels of miR-143 and miR-145 predicted poor survival rate in our cohorts.In conclusion, we can summarize that miR-145 and miR-143 are decreased, while miR-92 is increased in CRC compared to NATS, and associated with different stages of CRC pathogenesis. Thus, the expression of selected miRNAs can represent potential diagnostic and prognostic tools in patients with CRC from Romania.


Assuntos
Adenocarcinoma/diagnóstico , Biomarcadores Tumorais/genética , Neoplasias Colorretais/diagnóstico , MicroRNAs/genética , Adenocarcinoma/genética , Adenocarcinoma/patologia , Idoso , Área Sob a Curva , Neoplasias Colorretais/genética , Neoplasias Colorretais/patologia , Feminino , Expressão Gênica , Humanos , Estimativa de Kaplan-Meier , Masculino , Pessoa de Meia-Idade , Prognóstico , Curva ROC , Romênia , Transcriptoma
20.
BMJ ; 370: m3339, 2020 09 09.
Artigo em Inglês | MEDLINE | ID: mdl-32907855

RESUMO

OBJECTIVE: To develop and validate a pragmatic risk score to predict mortality in patients admitted to hospital with coronavirus disease 2019 (covid-19). DESIGN: Prospective observational cohort study. SETTING: International Severe Acute Respiratory and emerging Infections Consortium (ISARIC) World Health Organization (WHO) Clinical Characterisation Protocol UK (CCP-UK) study (performed by the ISARIC Coronavirus Clinical Characterisation Consortium-ISARIC-4C) in 260 hospitals across England, Scotland, and Wales. Model training was performed on a cohort of patients recruited between 6 February and 20 May 2020, with validation conducted on a second cohort of patients recruited after model development between 21 May and 29 June 2020. PARTICIPANTS: Adults (age ≥18 years) admitted to hospital with covid-19 at least four weeks before final data extraction. MAIN OUTCOME MEASURE: In-hospital mortality. RESULTS: 35 463 patients were included in the derivation dataset (mortality rate 32.2%) and 22 361 in the validation dataset (mortality rate 30.1%). The final 4C Mortality Score included eight variables readily available at initial hospital assessment: age, sex, number of comorbidities, respiratory rate, peripheral oxygen saturation, level of consciousness, urea level, and C reactive protein (score range 0-21 points). The 4C Score showed high discrimination for mortality (derivation cohort: area under the receiver operating characteristic curve 0.79, 95% confidence interval 0.78 to 0.79; validation cohort: 0.77, 0.76 to 0.77) with excellent calibration (validation: calibration-in-the-large=0, slope=1.0). Patients with a score of at least 15 (n=4158, 19%) had a 62% mortality (positive predictive value 62%) compared with 1% mortality for those with a score of 3 or less (n=1650, 7%; negative predictive value 99%). Discriminatory performance was higher than 15 pre-existing risk stratification scores (area under the receiver operating characteristic curve range 0.61-0.76), with scores developed in other covid-19 cohorts often performing poorly (range 0.63-0.73). CONCLUSIONS: An easy-to-use risk stratification score has been developed and validated based on commonly available parameters at hospital presentation. The 4C Mortality Score outperformed existing scores, showed utility to directly inform clinical decision making, and can be used to stratify patients admitted to hospital with covid-19 into different management groups. The score should be further validated to determine its applicability in other populations. STUDY REGISTRATION: ISRCTN66726260.


Assuntos
Betacoronavirus , Infecções por Coronavirus/diagnóstico , Infecções por Coronavirus/mortalidade , Hospitalização , Pneumonia Viral/diagnóstico , Pneumonia Viral/mortalidade , Idoso , Idoso de 80 Anos ou mais , Protocolos Clínicos , Estudos de Coortes , Feminino , Mortalidade Hospitalar , Humanos , Masculino , Pessoa de Meia-Idade , Pandemias , Valor Preditivo dos Testes , Curva ROC , Medição de Risco , Taxa de Sobrevida , Reino Unido
SELEÇÃO DE REFERÊNCIAS
DETALHE DA PESQUISA