Your browser doesn't support javascript.
Mostrar: 20 | 50 | 100
Resultados 1 - 20 de 11.088
Filtrar
1.
Radiol Med ; 125(1): 48-56, 2020 Jan.
Artigo em Inglês | MEDLINE | ID: mdl-31522345

RESUMO

PURPOSE: Development of a fully automatic algorithm for the automatic localization and identification of vertebral bodies in computed tomography (CT). MATERIALS AND METHODS: This algorithm was developed using a dataset based on real-world data of 232 thoraco-abdominopelvic CT scans retrospectively collected. In order to achieve an accurate solution, a two-stage automated method was developed: decision forests for a rough prediction of vertebral bodies position, and morphological image processing techniques to refine the previous detection by locating the position of the spinal canal. RESULTS: The mean distance error between the predicted vertebrae centroid position and truth was 13.7 mm. The identification rate was 79.6% on the thoracic region and of 74.8% on the lumbar segment. CONCLUSION: The algorithm provides a new method to detect and identify vertebral bodies from arbitrary field-of-view body CT scans.


Assuntos
Algoritmos , Árvores de Decisões , Aprendizado de Máquina , Tomografia Computadorizada Multidetectores/métodos , Coluna Vertebral/diagnóstico por imagem , Adulto , Idoso , Idoso de 80 Anos ou mais , Pontos de Referência Anatômicos/diagnóstico por imagem , Conjuntos de Dados como Assunto , Humanos , Pessoa de Meia-Idade , Estudos Retrospectivos , Adulto Jovem
2.
Gastroenterology ; 158(1): 76-94.e2, 2020 01.
Artigo em Inglês | MEDLINE | ID: mdl-31593701

RESUMO

Since 2010, substantial progress has been made in artificial intelligence (AI) and its application to medicine. AI is explored in gastroenterology for endoscopic analysis of lesions, in detection of cancer, and to facilitate the analysis of inflammatory lesions or gastrointestinal bleeding during wireless capsule endoscopy. AI is also tested to assess liver fibrosis and to differentiate patients with pancreatic cancer from those with pancreatitis. AI might also be used to establish prognoses of patients or predict their response to treatments, based on multiple factors. We review the ways in which AI may help physicians make a diagnosis or establish a prognosis and discuss its limitations, knowing that further randomized controlled studies will be required before the approval of AI techniques by the health authorities.


Assuntos
Inteligência Artificial , Diagnóstico por Computador/métodos , Gastroenterologia/métodos , Gastroenteropatias/diagnóstico , Hepatopatias/diagnóstico , Tomada de Decisão Clínica/métodos , Sistemas de Apoio a Decisões Clínicas , Árvores de Decisões , Gastroenteropatias/mortalidade , Gastroenteropatias/terapia , Humanos , Hepatopatias/mortalidade , Hepatopatias/terapia , Prognóstico , Resultado do Tratamento
3.
Medicine (Baltimore) ; 98(46): e17510, 2019 Nov.
Artigo em Inglês | MEDLINE | ID: mdl-31725605

RESUMO

Due to the complexity of Crohn's disease (CD), it is difficult to predict disease course with a single stratification factor or biomarker. A logistic regression (LR) model has been proposed by Guizzetti et al to stratify patients with CD-related surgical risk, which could help decision-making on disease treatment. However, there are no reports on relevant studies on Chinese population. The aim of the study is to present and validate a novel surgical predictive model to facilitate therapeutic decision-making for Chinese CD patients. Data was extracted from retrospective full-mode electronic medical records, which contained 239 CD patients and 1524 instances. Two sub-datasets were generated according to different attribute selection strategies, both of which were split into training and testing sets randomly. The imbalanced data in the training sets was addressed by synthetic minority over-sampling technique (SMOTE) algorithm before model development. Seven predictive models were employed using 5 popular machine learning algorithms: random forest (RF), LR, support vector machine (SVM), decision tree (DT) and artificial neural networks (ANN). The performance of each model was evaluated by accuracy, precision, F1-score, true negative (TN) rate, and the area under the receiver operating characteristic curve (AuROC). The result revealed that RF outperformed all other baseline models on both sub-datasets. The 10 leading risk factors for CD-related surgery returned from RF for attribute ranking were changes of radiology, presence of a fistula, presence of an abscess, no infliximab use, enteroscopy findings, C-reactive protein, abdominal pain, white blood cells, erythrocyte sedimentation rate and platelet count. The proposed machine learning model can accurately predict the risk of surgical intervention in Chinese CD patients, which could be used to tailor and modify the treatment strategies for CD patients in clinical practice.


Assuntos
Doença de Crohn/diagnóstico , Doença de Crohn/cirurgia , Técnicas de Apoio para a Decisão , Endoscopia do Sistema Digestório/estatística & dados numéricos , Modelos Anatômicos , Adulto , Algoritmos , Área Sob a Curva , Grupo com Ancestrais do Continente Asiático/estatística & dados numéricos , China , Árvores de Decisões , Feminino , Humanos , Modelos Logísticos , Aprendizado de Máquina/estatística & dados numéricos , Masculino , Valor Preditivo dos Testes , Curva ROC , Estudos Retrospectivos , Medição de Risco/métodos , Fatores de Risco , Máquina de Vetores de Suporte
4.
Comput Biol Chem ; 83: 107160, 2019 Dec.
Artigo em Inglês | MEDLINE | ID: mdl-31743831

RESUMO

A growing number of people suffer from colorectal cancer, which is one of the most common cancers. It is essential to diagnose and treat the cancer as early as possible. The disease may change the microorganism communities in the gut, and it could be an efficient method to employ gut microorganisms to predict colorectal cancer. In this study, we selected operational taxonomic units that include several kinds of microorganisms to predict colorectal cancer. To find the most important microorganisms and obtain the best prediction performance, we explore effective feature selection methods. We employ three main steps. First, we use a single method to reduce features. Next, to reduce the number of features, we integrate the dimension reduction methods correlation-based feature selection and maximum relevance-maximum distance (MRMD 1.0 and MRMD 2.0). Then, we selected the important features according to the taxonomy files. In this study, we created training and test sets to obtain a more objective evaluation. Random forest, naïve Bayes, and decision tree classifiers were evaluated. The results show that the methods proposed in this study are better than hierarchical feature engineering. The proposed method, which combines correlation-based feature selection with MRMD 2.0, performed the best on the CRC2 dataset. The dataset and methods can be found in http://lab.malab.cn/data/microdata/data.html.


Assuntos
Bactérias/classificação , Bactérias/isolamento & purificação , Neoplasias Colorretais/diagnóstico , Neoplasias Colorretais/microbiologia , Microbioma Gastrointestinal , Teorema de Bayes , Árvores de Decisões , Humanos
5.
Einstein (Sao Paulo) ; 18: eAO4745, 2019.
Artigo em Inglês, Português | MEDLINE | ID: mdl-31664322

RESUMO

OBJECTIVE: To estimate the prevalence of and factors associated with the use of methylphenidate for cognitive enhancement among undergraduate students. METHODS: Simple random sample of students of the Universidade Federal de Minas Gerais (n=438), invited to answer an online questionnaire about the use of methylphenidate. Data collection occurred from September 2014 to January 2015. The sample was described by means of proportions, means and standard deviations. A multivariate analysis was performed using the Classification and Regression Tree algorithm to classify the cases of use of methylphenidate for cognitive enhancement in groups, based on the exposure variables. RESULTS: Out of 378 students included, 5.8% (n=22) reported using methylphenidate for cognitive enhancement; in that, 41% (9/22) in the 4 weeks prior to the survey. The housing situation was the variable most often associated with the use of methylphenidate for cognitive enhancement. Eleven students reported using methylphenidate for cognitive enhancement and other purposes 4 weeks prior to the survey, 27% of whom had no medical prescription to purchase it. CONCLUSION: The use of methylphenidate for cognitive enhancement is frequent among Brazilian undergraduate students and should be considered a serious public health problem, especially due to risks of harm and adverse effects associated with its use.


Assuntos
Estimulantes do Sistema Nervoso Central/administração & dosagem , Nootrópicos/administração & dosagem , Nootrópicos/uso terapêutico , Estudantes/estatística & dados numéricos , Universidades/estatística & dados numéricos , Adulto , Brasil/epidemiologia , Estudos Transversais , Árvores de Decisões , Exercício/psicologia , Feminino , Humanos , Masculino , Metilfenidato/administração & dosagem , Uso Off-Label/estatística & dados numéricos , Prevalência , Características de Residência/estatística & dados numéricos , Fatores de Risco , Fatores Socioeconômicos , Estudantes/psicologia , Inquéritos e Questionários , Adulto Jovem
6.
BMC Health Serv Res ; 19(1): 690, 2019 10 12.
Artigo em Inglês | MEDLINE | ID: mdl-31606031

RESUMO

BACKGROUND: In Asia, over 50% of patients with symptoms of tuberculosis (TB) access health care from private providers. These patients are usually not notified to the National TB Control Programs, which contributes to low notification rates in many countries. METHODS: From January 1, 2011 to December 31, 2012, Karachi's Indus Hospital - a private sector partner to the National TB Programme - engaged 80 private family clinics in its catchment area in active case finding using health worker incentives to increase notification of TB disease. The costs incurred were estimated from the perspective of patients, health facility and the program providing TB services. A Markov decision tree model was developed to calculate the cost-effectiveness of the active case finding as compared to case detection through the routine passive TB centers. Pakistan has a large private health sector, which can be mobilized for TB screening using an incentivized active case finding strategy. Currently, TB screening is largely performed in specialist public TB centers through passive case finding. Active and passive case finding strategies are assumed to operate independently from each other. RESULTS: The incentive-based active case finding program costed USD 223 per patient treated. In contrast, the center based non-incentive arm was 23.4% cheaper, costing USD 171 per patient treated. Cost-effectiveness analysis showed that the incentive-based active case finding program was more effective and less expensive per DALY averted when compared to the baseline passive case finding as it averts an additional 0.01966 DALYs and saved 15.74 US$ per patient treated. CONCLUSION: Both screening strategies appear to be cost-effective in an urban Pakistan context. Incentive driven active case findings of TB in the private sector costs less and averts more DALYs per health seeker than passive case finding, when both alternatives are compared to a common baseline situation of no screening.


Assuntos
Setor Privado/economia , Tuberculose/prevenção & controle , Adolescente , Adulto , Análise Custo-Benefício , Árvores de Decisões , Notificação de Doenças/economia , Notificação de Doenças/normas , Diagnóstico Precoce , Feminino , Humanos , Masculino , Programas de Rastreamento/economia , Motivação , Paquistão , Tuberculose/economia , Conduta Expectante/economia , Adulto Jovem
7.
Medicine (Baltimore) ; 98(40): e17368, 2019 Oct.
Artigo em Inglês | MEDLINE | ID: mdl-31577737

RESUMO

This study evaluated the diagnostic performance of a new clinical approach based on decision tree (DT) analysis in adult patients with equivocal computed tomography (CT) findings of acute appendicitis (AA) compared with previous scoring systems.This retrospective study of 244 adult patients with equivocal CT findings included appendicitis (AG, n = 80) and non-appendicitis (NAG, n = 164) groups. The chi-squared automatic interaction detection algorithm was for AA prediction. A receiver operating characteristic curve analysis and area under the curve (AUC) were used to compare the DT analysis with Alvarado, Eskelinen score, and adult appendicitis scores (AAS).The following factors were selected for AA prediction: rebound tenderness severity, migration, urinalysis, symptom duration, leukocytosis, neutrophil count, and C-reactive protein levels. The DT comprised 11 final nodes with the following AA probabilities: node 1, 100% (16/16); node 2, 90% (9/10); node 3, 80% (8/10); node 4, 60.9% (14/23); node 5, 50% (3/6); node 6, 43.8% (7/16); node 7, 22.6% (12/53); node 8, 13% (10/77); node 9, 5.6% (1/18); node 10, 0% (0/12); and node 11, 0% (0/3). The AUC of the DT was higher (0.850 [95% confidence interval {CI}; 0.799-0.893]) than the Alvarado score (0.695 [95% CI; 0.633-0.752]), AAS (0.749 [95% CI; 0.690-0.802]), and the Eskelinen score (0.715 [95% CI; 0.654-0.770]). The results were statistically significant when compared with the AUCs of the Alvarado score, Eskelinen score, and AAS (P < .001, P < .001, P = .003, respectively).The DT-based approach facilitated AA diagnosis and determination of clinical status in patients with equivocal preoperative CT findings and ambiguous results.


Assuntos
Apendicite/diagnóstico , Árvores de Decisões , Dor Abdominal , Doença Aguda , Adulto , Algoritmos , Apendicite/sangue , Apendicite/diagnóstico por imagem , Proteína C-Reativa/análise , Técnicas de Apoio para a Decisão , Diagnóstico Diferencial , Feminino , Testes Hematológicos , Humanos , Masculino , Curva ROC , Estudos Retrospectivos , Sensibilidade e Especificidade , Índice de Gravidade de Doença , Tomografia Computadorizada por Raios X , Urinálise
8.
Medicine (Baltimore) ; 98(40): e17481, 2019 Oct.
Artigo em Inglês | MEDLINE | ID: mdl-31577783

RESUMO

Axillary lymph node metastasis (ALNM) is commonly the earliest detectable clinical manifestation of breast cancer when distant metastasis emerges. This study aimed to explore the influencing factors of ALNM and develop models that can predict its occurrence preoperatively.Cases of sonographically visible clinical stage T1-2N0M0 breast cancers treated with breast and axillary surgery at West China Hospital were retrospectively reviewed. Univariate and multivariate logistic regression analyses were performed to evaluate associations between ALNM and variables. Decision tree analyses were performed to construct predictive models using the C5.0 packages.Of the 1671 tumors, 541 (32.9%) showed axillary lymph node positivity on final surgical histopathologic analysis. In multivariate logistic regression analysis, tumor size (P < .001), infiltration of subcutaneous adipose tissue (P < .001), infiltration of the interstitial adipose tissue (P = .031), and tumor quadrant locations (P < .001) were significantly correlated with ALNM. Furthermore, the accuracy in the decision tree model was 69.52%, and the false-negative rate (FNR) was 74.18%. By using the error-cost matrix algorithm, the FNR significantly decreased to 14.75%, particularly for nodes 5, 8, and 13 (FNR: 11.4%, 9.09%, and 14.29% in the training set and 18.1%,14.71%, and 20% in the test set, respectively).In summary, our study demonstrated that tumor lesion boundary, tumor size, and tumor quadrant locations were the most important factors affecting ALNM in cT1-2N0M0 stage breast cancer. The decision tree built using these variables reached a slightly higher FNR than sentinel lymph node dissection in predicting ALNM in some selected patients.


Assuntos
Neoplasias da Mama/patologia , Metástase Linfática/patologia , Adulto , Axila , Neoplasias da Mama/diagnóstico por imagem , Neoplasias da Mama/cirurgia , China , Árvores de Decisões , Feminino , Humanos , Modelos Logísticos , Excisão de Linfonodo , Pessoa de Meia-Idade , Estadiamento de Neoplasias , Valor Preditivo dos Testes , Estudos Retrospectivos , Fatores de Risco
9.
Environ Monit Assess ; 191(11): 649, 2019 Oct 17.
Artigo em Inglês | MEDLINE | ID: mdl-31624914

RESUMO

Geographic Object-Based Image Analysis and linear unmixing are common methods in image classification. The purpose of this study is to analyze the classification efficiency by integrating these two methods in the mountain area. This research selected Jiangle County, Fujian, as a study area. Two Landsat8 OLI images, which covered the county, were used. Linear spectral mixture model, multi-scale segmentation, and decision tree were applied in the classification. After image preprocessing, linear spectral mixture model was used to unmix the image into three fraction images-vegetation, shade, and soil. The principal component analysis and tasseled cap transformation were used to derived three principal components and the brightness, wetness, and greenness. Multi-scale segmentation is applied by eCognition. Under scale 40, the image was divided into vegetation and non-vegetation area, then under scale 20, the vegetation area was divided into different types by integrating the fraction with different methods. The accuracy assessment of the classification map was done using the forestry resource survey and the high-resolution image of Google Earth. This study indicated that the unmixed bands could improve the classification accuracy. The overall classification accuracy was 92.40% with a Kappa coefficient of 0.9032. Therefore, there is a conclusion that this approach is an efficient way to classify different plantation.


Assuntos
Monitoramento Ambiental/métodos , Tecnologia de Sensoriamento Remoto/métodos , Árvores de Decisões , Modelos Lineares , Plantas , Solo
10.
J Stroke Cerebrovasc Dis ; 28(11): 104387, 2019 Nov.
Artigo em Inglês | MEDLINE | ID: mdl-31542365

RESUMO

BACKGROUND: No study to date has focused on what combinations of motor functions are strongly associated with self-care independence in individuals with stroke. The purpose of this study is to clarify the impact of motor function interactions on self-care independence in individuals with stroke. METHODS: This retrospective observational study included 132 individuals with first stroke. We conducted a decision tree analysis to examine the impact on daily living skills of numerous key functions - the upper and lower limbs on the affected side, bilateral grip strength and lower limb muscle strength on the unaffected side, bilateral upper limb and trunk function, and balance. Further, we confirmed the interaction effects detected via the decision tree approach using logistic regression. RESULTS: As per the decision tree analysis, the interaction between balance and upper limb function of the affected side showed an association with self-care independence. The interaction terms of balance and upper limb function we analyzed were significantly associated with the ability to achieve self-care independence, after some adjustments to eliminate the influence of confounding factors. CONCLUSIONS: These results suggest that the combination of functional status of balance and upper limb function of the affected side are strongly associated with the independence of self-care. The decision tree created in this study could serve as an effective guide when implementing a remedial approach for individuals with stroke aiming to achieve self-care independence.


Assuntos
Atividade Motora , Equilíbrio Postural , Autocuidado , Reabilitação do Acidente Vascular Cerebral/métodos , Acidente Vascular Cerebral/terapia , Extremidade Superior/inervação , Idoso , Idoso de 80 Anos ou mais , Tomada de Decisão Clínica , Técnicas de Apoio para a Decisão , Árvores de Decisões , Feminino , Nível de Saúde , Humanos , Vida Independente , Masculino , Pessoa de Meia-Idade , Força Muscular , Seleção de Pacientes , Recuperação de Função Fisiológica , Estudos Retrospectivos , Acidente Vascular Cerebral/diagnóstico , Acidente Vascular Cerebral/fisiopatologia , Acidente Vascular Cerebral/psicologia , Resultado do Tratamento
11.
Mayo Clin Proc ; 94(10): 2072-2086, 2019 10.
Artigo em Inglês | MEDLINE | ID: mdl-31543255

RESUMO

The United States is in the midst of a national opioid epidemic. Physicians are encouraged both to prevent and treat opioid-use disorders (OUDs). Although there are 3 Food and Drug Administration-approved medications to treat OUD (methadone, buprenorphine, and naltrexone) and there is ample evidence of their efficacy, they are not used as often as they should. We provide a brief review of the 3 primary medications used in the treatment of OUD. Using data from available medical literature, we synthesize existing knowledge and provide a framework for how to determine the optimal approach for outpatient management of OUD with medication-assisted treatments.


Assuntos
Buprenorfina/uso terapêutico , Metadona/uso terapêutico , Naltrexona/uso terapêutico , Tratamento de Substituição de Opiáceos , Transtornos Relacionados ao Uso de Opioides/tratamento farmacológico , Algoritmos , Árvores de Decisões , Humanos
12.
Int J Med Inform ; 130: 103957, 2019 10.
Artigo em Inglês | MEDLINE | ID: mdl-31472443

RESUMO

INTRODUCTION: Machine learning has been increasingly used to develop predictive models to diagnose different disease conditions. The heterogeneity of the kidney transplant population makes predicting graft outcomes extremely challenging. Several kidney graft outcome prediction models have been developed using machine learning, and are available in the literature. However, a systematic review of machine learning based prediction methods applied to kidney transplant has not been done to date. The main aim of our study was to perform an in-depth systematic analysis of different machine learning methods used to predict graft outcomes among kidney transplant patients, and assess their usefulness as an aid to decision-making. METHODS: A systemic review of machine learning methods used to predict graft outcomes among kidney transplant patients was carried out using a search of the Medline, the Cumulative Index to Nursing and Allied Health Literature, EMBASE, PsycINFO and Cochrane databases. RESULTS: A total of 295 articles were identified and extracted. Of these, 18 met the inclusion criteria. Most of the studies were published in the United States after 2010. The population size used to develop the models varied from 80 to 92,844, and the number of features in the models ranged from 6 to 71. The most common machine learning methods used were artificial neural networks, decision trees and Bayesian belief networks. Most of the machine learning based predictive models predicted graft failure with high sensitivity and specificity. Only one machine learning based prediction model had modelled time-to-event (survival) information. Seven studies compared the predictive performance of machine learning models with traditional regression methods and the performance of machine learning methods was found to be mixed, when compared with traditional regression methods. CONCLUSION: There was a wide variation in the size of the study population and the input variables used. However, the prediction accuracy provided mixed results when machine learning and traditional predictive methods are compared. Based on reported gains in predictive performance, machine learning has the potential to improve kidney transplant outcome prediction and aid medical decision making.


Assuntos
Bases de Dados Factuais , Rejeição de Enxerto/diagnóstico , Transplante de Rim/efeitos adversos , Aprendizado de Máquina , Teorema de Bayes , Árvores de Decisões , Rejeição de Enxerto/etiologia , Humanos , Valor Preditivo dos Testes
13.
Forensic Sci Int ; 302: 109891, 2019 Sep.
Artigo em Inglês | MEDLINE | ID: mdl-31400616

RESUMO

The presence of fracture on neck elements is an indication of violence. Both the hyoid bone and the larynx can be damaged by a strangulation mechanism. Thyroid cartilage, more specifically, may present lesions in response to this mechanical stress. These lesions result in fractures at the bases of the horns of the thyroid cartilage. This study focuses on the thyroid cartilage behavior in cases of bi-digital strangulation, using an anthropometric and biomechanical approach. To develop a biomechanical model, we performed an anthropometric study taking into account 14 distances measurements as well as 3 measurements of angles. These measures allowed us to determine a significant sexual dimorphism between individuals. Then, we define 6 morphologies models, composed of 3 females and 3 males individuals. In order to visualize the ossification of the cartilage, each model has been tested with bone properties. Strangulation cases were simulated by applying an imposed velocity of 0.4m/s then 1m/s. We observed different behaviors of the thyroid cartilage according to the sex and the morphology.


Assuntos
Asfixia/fisiopatologia , Fenômenos Biomecânicos/fisiologia , Simulação por Computador , Lesões do Pescoço/prevenção & controle , Cartilagem Tireóidea/diagnóstico por imagem , Cartilagem Tireóidea/lesões , Árvores de Decisões , Feminino , Análise de Elementos Finitos , Medicina Legal , Fraturas de Cartilagem/fisiopatologia , Humanos , Imagem Tridimensional , Masculino , Pessoa de Meia-Idade , Modelos Teóricos , Lesões do Pescoço/fisiopatologia , Análise de Componente Principal , Caracteres Sexuais , Cartilagem Tireóidea/fisiopatologia
14.
Medicine (Baltimore) ; 98(33): e16843, 2019 Aug.
Artigo em Inglês | MEDLINE | ID: mdl-31415409

RESUMO

BACKGROUND: The aim of this study was, from the Chinese healthcare perspective, to assess the cost-effectiveness of positron-emission tomography-computed tomography (PET-CT) with F-fluorodeoxyglucose (F-FDG) in preoperation staging for nonsmall-cell lung cancer (NSCLC) with resected monometastatic disease based on a retrospective study. This study was conducted from January 2017 to February 2019 at an academic hospital. METHODS: A Markov model and 3 decision-tree models were designed to calculate the long-term medical costs, outcomes, and incremental cost-effectiveness ratios (ICERs) of the 2 diagnostic strategies (PET-CT and conventional CT). Model robustness was assessed in sensitivity analyses. RESULTS: For the base-case analysis, preoperative PET-CT evaluation for NSCLC with resected monometastatic disease provided an additional 1.475, 2.129, and 2.412 life-years (LYs), in the time horizon of 10-, 20-, and 30-year, respectively, and the ICERs for the PET-CT group compared with the conventional CT group were $1153, $1393, and $1430 per LY, separately. The acceptability curves demonstrated that when the willingness-to-pay (WTP) thresholds ranged from $500 to $3000/LY, the probability of cost-effectiveness changed varied dramatically, and at WTP > $3000, the probability that the PET-CT group achieved cost-effectiveness was 100%. Sensitivity analyses suggested that the models we designed were robust. CONCLUSION: Compared with conventional CT scan, preoperative F-FDG PET-CT evaluation for patients with resected monometastatic NSCLC is cost-effective from the Chinese healthcare perspective. Preoperative F-FDG PET-CT evaluation should be popularized for patients with resected monometastatic NSCLC.


Assuntos
Carcinoma Pulmonar de Células não Pequenas/diagnóstico por imagem , Neoplasias Pulmonares/diagnóstico por imagem , Tomografia Computadorizada com Tomografia por Emissão de Pósitrons/economia , China , Análise Custo-Benefício , Árvores de Decisões , Humanos , Linfonodos/diagnóstico por imagem , Cadeias de Markov , Estadiamento de Neoplasias/instrumentação , Cuidados Pré-Operatórios/economia , Cuidados Pré-Operatórios/métodos , Estudos Retrospectivos
15.
Stud Health Technol Inform ; 266: 83-88, 2019 Aug 08.
Artigo em Inglês | MEDLINE | ID: mdl-31397306

RESUMO

The paper applies an artificial intelligence centered method to classify 12 clinical safety incident (CSI) classes. The paper aims to establish a taxonomy that classifies the CSI reports into their correct classes automatically and with high accuracy. The study investigates feasibility of applying the C4.5 decision tree (DT) classifier and the random forest (RF) classifier for this purpose. The classifiers were trained using randomly selected 3600 CSIs from an Incident Information Management System (IIMS) used by seven hospitals. The taxonomies investigated were the Generic Reference Model (GRM) and the World Health Organization (WHO) patient safety classification. The classifiers trained 13 GRM CSI classes and 9 WHO CSI classes using a bag-of-words approach. The overall taxonomies performance on the RF classifier was better than on the DT classifier. The performance achieved by the classifier applying the WHO taxonomy was better than the GRM taxonomy. Four of the five poorly performing classes in the GRM taxonomy significantly improved their performance on changing the taxonomy. To improve the WHO taxonomy performance the improved WHO (WHO-I) taxonomy was built by adding a new class that did not exist in WHO but existed in GRM. The performance of the RF classifier applied to the WHO-I taxonomy further improved.


Assuntos
Inteligência Artificial , Árvores de Decisões , Gestão de Riscos , Humanos , Segurança do Paciente
16.
Forensic Sci Int ; 302: 109918, 2019 Sep.
Artigo em Inglês | MEDLINE | ID: mdl-31421437

RESUMO

In forensic settings, diluted bloodstains are regularly encountered for example when bloodstains are mixed with tap-/rainwater, after deliberate cleaning attempts, or when blood is dropped on a wet surface such as a towel. Such diluted bloodstain scenarios can be subdivided into sequences of events in which a blood drop was either (1) readily diluted (a mixture of blood and water is deposited); (2) deposited on a surface that was readily moistened (first water, then blood) or (3) deposited and subsequently moistened (first blood, then water). Current bloodstain pattern analysis (BPA) lacks data and tools to distinguish these three ways of derivation of a diluted bloodstain that vary in the sequence of deposition of blood and water on textile. In this study, 880 bloodstains were examined for characteristics that can be used to determine the derivation of diluted bloodstains. A guideline to assist BPA-analysts in interpreting diluted bloodstains was extracted. The added value of this guideline was confirmed by conducting two surveys: one survey with and one without the guideline. A third survey confirmed that the characteristics also function on a broader range of textile types that have different weave and knit styles. This guideline can aid BPA-experts to determine, in an objective way, how diluted bloodstains derived which can aid in determining which activities took place at a crime scene.


Assuntos
Manchas de Sangue , Árvores de Decisões , Medicina Legal/métodos , Medicina Legal/normas , Humanos , Inquéritos e Questionários , Têxteis
17.
Acta Trop ; 199: 105152, 2019 Nov.
Artigo em Inglês | MEDLINE | ID: mdl-31445898

RESUMO

Molecular taxonomy based identification of species in the form of DNA barcodes are extensively used in evolutionary systematics. Almost all the DNA barcodes contain detailed information of the barcoding gene along with uninformative sequences of a particular species. Therefore, a technique is highly essential to remove or to reduce the number of uninformative sequences and ought to create species-specific barcodes for differentiation. The actual variation in genetic sequences, called single nucleotide polymorphism (SNP) genotyping, can be utilized to develop a new tool for rapid, reliable, and high-throughput assay to distinguish the known species. SNPs act as important hereditary markers for uncovering the evolutionary history and normal genetic polymorphisms. Keeping in mind, we propose a decision tree-based barcoding (DTB) algorithm for generating SNP barcodes from the DNA barcoding sequence of several evolutionarily related species to accurately identify a single species. To address this issue, we analyzed mitochondrial COI gene sequences of 64 species of Anopheles mosquitoes. After alignment and truncating, 32 SNPs were discovered in COI gene sequences of Anopheles mosquitoes and then computed to set up the decision rule for constructing the decision tree. The decision tree based barcoding algorithm generates 126 nodes and 32 loci for discriminating 64 Anopheles mosquito species. Finally, we concluded that the DTB method is useful and effective for generating sequence tags for Anopheles mosquito species identification.


Assuntos
Anopheles/genética , Código de Barras de DNA Taxonômico/métodos , Árvores de Decisões , Polimorfismo de Nucleotídeo Único , Algoritmos , Animais , Evolução Biológica , Complexo IV da Cadeia de Transporte de Elétrons/genética , Filogenia , Especificidade da Espécie
19.
Zhonghua Yu Fang Yi Xue Za Zhi ; 53(8): 804-810, 2019 Aug 06.
Artigo em Chinês | MEDLINE | ID: mdl-31378040

RESUMO

Objective: To evaluate the cost-utility of different immunization strategies for rabies in China, and to provide a reference for determining the optimal immunization strategy. Methods: The system dynamics model was used to simulate the epidemic of canine rabies and a decision tree model was conducted to analysis different immune strategies. Relevant probabilities were obtained through literature search and on-site investigation. Sensitivity analysis was used to explore the important influenced factors. Results: At baseline, from a social perspective, 70% vaccination of dogs was the optimal strategy compared to current vaccination strategy (43% vaccination in dogs, human category-Ⅱ exposure vaccination/category-Ⅲ exposure vaccination combined with RIG). The total cost was 14 084 354 CNY, and the total utility value was 22 078 616.23 QALYs, and the incremental cost-utility ratio was-62 148 147 CNY/QALY; if human vaccination was considered, 55% vaccination of dogs combined with strategy one was the optimal strategy, its incremental cost-utility ratio was-444 620 557 CNY/QALY. The probability that an injured dog carries rabies virus was the most sensitive parameter. When it was greater than 0.005 03, strategy four was the optimal strategy. When it was less than 82/100 000, strategy one was the optimal strategy; when it was between 82/100 000 and 120/100 000, strategy two was the optimal strategy; when it was between 120/100 000 and 503/100 000, strategy two was the optimal strategy. Conclusion: It was conducive to increase the vaccination coverage of canine for the prevention and control of rabies.


Assuntos
Análise Custo-Benefício , Vacinas Antirrábicas/uso terapêutico , Raiva/prevenção & controle , Animais , China , Árvores de Decisões , Cães , Humanos , Anos de Vida Ajustados por Qualidade de Vida , Raiva/economia , Vacinas Antirrábicas/economia , Vacinação
20.
J Sci Food Agric ; 99(14): 6589-6600, 2019 Nov.
Artigo em Inglês | MEDLINE | ID: mdl-31328271

RESUMO

BACKGROUND: Rice smut and rice blast are listed as two of the three major diseases of rice. Owing to the small size and similar structure of rice blast and rice smut spores, traditional microscopic methods are troublesome to detect them. Therefore, this paper uses microscopy image identification based on the synergistic judgment of texture and shape features and the decision tree-confusion matrix method. RESULTS: The distance transformation-Gaussian filtering-watershed algorithm method was proposed to separate the adherent rice blast spores, and the accuracy was increased by about 10%. Four shape features (area, perimeter, ellipticity, complexity) and three texture features (entropy, homogeneity, contrast) were selected for decision-tree model classification. The confusion-matrix algorithm was used to calculate the classification accuracy, in which global accuracy is 82% and the Kappa coefficient is 0.81. At the same time, the detection accuracy is as high as 94%. CONCLUSIONS: The synergistic judgment of texture and shape features and the decision tree-confusion matrix method can be used to detect rice disease quickly and precisely. The proposed method can be combined with a spore trap, which is vital to devise strategies early and to control rice disease effectively. © 2019 Society of Chemical Industry.


Assuntos
Fungos/isolamento & purificação , Processamento de Imagem Assistida por Computador/métodos , Microscopia/métodos , Oryza/microbiologia , Doenças das Plantas/microbiologia , Esporos Fúngicos/citologia , Algoritmos , Árvores de Decisões , Fungos/química , Fungos/citologia , Microscopia/instrumentação , Esporos Fúngicos/química , Esporos Fúngicos/isolamento & purificação
SELEÇÃO DE REFERÊNCIAS
DETALHE DA PESQUISA