Your browser doesn't support javascript.
Mostrar: 20 | 50 | 100
Resultados 1 - 20 de 53.740
Filtrar
1.
Water Sci Technol ; 80(3): 478-486, 2019 Aug.
Artigo em Inglês | MEDLINE | ID: mdl-31596259

RESUMO

This paper presents a method of quantifying the uncertainty associated with inundation damage data for an urban catchment when undertaking stormwater drainage design and management. Usually flood damage is estimated by multiplying the inundated asset value by the damage rate corresponding to the inundation depth. The uncertainty of the asset value and the damage rate is described by probability distributions estimated from an analysis of actual flood damage data from a national government survey. With the inclusion of uncertainty in the damage rate and asset value, the damage potential curve defining the damage-frequency relationship is no longer a deterministic single-value curve. Through Monte Carlo simulations, which incorporate the uncertainty of the inundation damage from the damage rate and asset value, a probabilistic damage potential relation can be established, which can be expressed in terms of a series of curves with different percentile levels. The method is demonstrated through the establishment of probabilistic damage potential curves for a typical urban catchment, the Zenpukuji river basin in Tokyo Metropolis, under two scenarios, namely, with and without a planned flood control reservoir.


Assuntos
Inundações , Gestão de Riscos , Probabilidade , Tóquio , Incerteza
3.
Ying Yong Sheng Tai Xue Bao ; 30(7): 2426-2436, 2019 Jul.
Artigo em Chinês | MEDLINE | ID: mdl-31418246

RESUMO

Based on catch data from the bottom trawl survey by eight cruises in offshore of northern South China Sea during 2014-2017, we analyzed the stock density distribution and explored its probability distribution with statistical method, which was further used to estimate the mean stock density in this region. The results showed that the coefficient of variation (CV) for stock density ranged from 0.67 to 1.03 for all the periods, indicating a highly uneven spatial distribution of stock density. The frequency distribution of fishery resource density was characterized by obvious right-skewed, which was dominated by stock density of 0-1000 kg·km-2. The results of one sample Kolmogorov-Smirnov test indicated that three probability distribution patterns were suitable for stock density in this region, including Lognormal, Gamma and Weibull distributions. In terms of the mean stock density estimation, the values from Lognormal showed no statistically significant difference from those from others, but the opposite result was obtained between Gamma and Weibull distributions. Compared with 1960s-1970s, the appropriate probability distribution pattern of stock density has changed from single to multiple types. Variation of the proportion of low catch resulted from the changes in the structure of fishery resources, fishing effort and climate change might cause the alte-ration of probability distribution.


Assuntos
Mudança Climática , Pesqueiros/estatística & dados numéricos , China , Probabilidade
5.
Stud Health Technol Inform ; 263: 35-48, 2019 Jul 30.
Artigo em Inglês | MEDLINE | ID: mdl-31411151

RESUMO

Information value chain theory provides a straightforward approach to information system evaluation and design. It first separates the different benefits and costs that might be associated with the use of a given information technology at different stages along a value chain stretching from user interaction to real world outcome. Next, using classical decision theoretic measures such as probabilities and utilities, the resulting value chain can be used to create a profile for a particular technology or technology bundle. Value chain analysis helps focus on the reasons for system implementation success or failure. It also assists in making comparative assessments amongst different solutions, to understand which might be best suited for different clinical contexts.


Assuntos
Tecnologia Biomédica , Tomada de Decisões , Avaliação da Tecnologia Biomédica , Probabilidade , Tecnologia
6.
BMC Bioinformatics ; 20(1): 409, 2019 Jul 30.
Artigo em Inglês | MEDLINE | ID: mdl-31362694

RESUMO

BACKGROUND: Internal ribosome entry sites (IRES) are segments of mRNA found in untranslated regions that can recruit the ribosome and initiate translation independently of the 5' cap-dependent translation initiation mechanism. IRES usually function when 5' cap-dependent translation initiation has been blocked or repressed. They have been widely found to play important roles in viral infections and cellular processes. However, a limited number of confirmed IRES have been reported due to the requirement for highly labor intensive, slow, and low efficiency laboratory experiments. Bioinformatics tools have been developed, but there is no reliable online tool. RESULTS: This paper systematically examines the features that can distinguish IRES from non-IRES sequences. Sequence features such as kmer words, structural features such as QMFE, and sequence/structure hybrid features are evaluated as possible discriminators. They are incorporated into an IRES classifier based on XGBoost. The XGBoost model performs better than previous classifiers, with higher accuracy and much shorter computational time. The number of features in the model has been greatly reduced, compared to previous predictors, by including global kmer and structural features. The contributions of model features are well explained by LIME and SHapley Additive exPlanations. The trained XGBoost model has been implemented as a bioinformatics tool for IRES prediction, IRESpy (https://irespy.shinyapps.io/IRESpy/), which has been applied to scan the human 5' UTR and find novel IRES segments. CONCLUSIONS: IRESpy is a fast, reliable, high-throughput IRES online prediction tool. It provides a publicly available tool for all IRES researchers, and can be used in other genomics applications such as gene annotation and analysis of differential gene expression.


Assuntos
Biologia Computacional/métodos , Sítios Internos de Entrada Ribossomal/genética , Software , Regiões 5' não Traduzidas/genética , Algoritmos , Sequência de Bases , Humanos , Modelos Teóricos , Probabilidade , RNA Viral/genética
9.
Environ Monit Assess ; 191(8): 491, 2019 Jul 12.
Artigo em Inglês | MEDLINE | ID: mdl-31297617

RESUMO

Leaf segmentation is significantly important in assisting ecologists to automatically detect symptoms of disease and other stressors affecting trees. This paper employs state-of-the-art techniques in image processing to introduce an accurate framework for segmenting leaves and diseased leaf spots from images. The proposed framework integrates an appearance model that visually represents the current input image with the color prior information generated from RGB color images that were formerly saved in our database. Our framework consists of four main steps: (1) Enhancing the accuracy of the segmentation at minimum time by making use of contrast changes to automatically identify the region of interest (ROI) of the entire leaf, where the pixel-wise intensity relations are described by an electric field energy model. (2) Modeling the visual appearance of the input image using a linear combination of discrete Gaussians (LCDG) to predict the marginal probability distributions of the grayscale ROI main three classes. (3) Calculating the pixel-wise probabilities of these three classes for the color ROI based on the color prior information of database images that are segmented manually, where the current and prior pixel-wise probabilities are used to find the initial labels. (4) Refining the labels with the generalized Gauss-Markov random field model (GGMRF), which maintains the continuity. The proposed segmentation approach was applied to the leaves of mangrove trees in Abu Dhabi in the United Arab Emirates. Experimental validation showed high accuracy, with a Dice similarity coefficient 90% for distinguishing leaf spot from healthy leaf area.


Assuntos
Monitoramento Ambiental/métodos , Processamento de Imagem Assistida por Computador/métodos , Doenças das Plantas , Folhas de Planta/química , Árvores/química , Algoritmos , Cor , Humanos , Distribuição Normal , Probabilidade , Sensibilidade e Especificidade , Emirados Árabes Unidos
10.
Int. j. morphol ; 37(2): 632-640, June 2019. tab, graf
Artigo em Espanhol | LILACS | ID: biblio-1002269

RESUMO

El porcentaje de estatura adulta (PEA) es un indicador del estado de maduración, que refleja la variación en la tasa y progreso de crecimiento. Existen diversos métodos para estimar la estatura adulta, sin haberse documentado en la literatura de manera concreta sus similitudes o diferencias. Los objetivos del presente trabajo fueron comparar tres métodos de estimación del PEA, identificar cambios seculares en niños y adolescentes y establecer valores de referencia del PEA para población portuguesa. Se midieron en 799 niños y 736 niñas, de 7,0 a 16,49 años, la edad ósea, el peso y la estatura, para estimar el porcentaje de estatura adulta por las metodologías TW3, KR y RWT. Los valores del método TW3 del presente estudio, fueron comparados con los reportados en décadas atrás para identificar cambios seculares. Se utilizó un ANOVA de medidas repetidas para estimar las diferencias entre los métodos en el presente estudio, así como gráficas de Bland y Altman. Se utilizó la prueba de Kruskal-Wallis para analizar las diferencias entre los valores encontrados en la presente investigación y los presentados en décadas atrás en otros estudios. No se encontraron diferencias entre los métodos TW3 y KR en los diferentes grupos de edad cuando se clasificaron los sujetos por edad cronológica, en ambos sexos (P>0,05). Así mismo, no se observaron cambios seculares en el PEA (P>0.05). Los métodos TW3 y KR pueden ser intercambiables entre sí, debido a que no presentan diferencias en la estimación a diferentes edades y en ambos sexos. Además, no existió cambio secular en la estimación de PEA por estas metodologías, lo que las hace útiles en la actualidad.


The adult height percentage (AHP) is an indicator of maturity state, which reflects variation in growth rate. Several methods estimates adult height; however, its similarities or differences have not been documented in a concrete way in literature. The aims of the present work were to compare three common methods of AHP estimation, to identify children and adolescents secular changes and to develop AHP reference values in Portuguese population. Skeletal age, weight and height were measure in 799 children and 736 girls from 7.0 to 16.5 years; in addition, parents height was self-reported by them to estimate the AHP by TW3, RWT and KR methods. ANOVA was used to estimate differences between TW3, KR and RWT methods, as well as Bland-Altman graphs. Also, Kruskal-Wallis test was applied. No differences were found between TW3 and KR methods in all age groups, in both sexes, when subjects were classified by chronological age (P> 0.05). Likewise, no secular changes were observed in AHP (P> 0.05). Not only TW3 and KR protocols can be interchangeable each other because they did not present differences in the AHP estimation at different ages and in both sexes. However, secular changes were not observed in AHP estimation by these methods.


Assuntos
Humanos , Masculino , Feminino , Criança , Adolescente , Estatura , Antropometria/métodos , Crescimento , Probabilidade , Fatores Etários
11.
Int. j. morphol ; 37(2): 504-508, June 2019. tab, graf
Artigo em Inglês | LILACS | ID: biblio-1002251

RESUMO

The purpose of this research is to determine a regression equation for estimation of stature from sitting height measurements. This research was carried out on 1623 subjects (830 male and 793 female) among the population of Kosovan adolescents. The stature and sitting height measurements were taken according to the ISAK protocol, and the data were analyzed statistically; the relationships between stature and sitting height measurements were derived using simple correlation. A comparison of the means of sitting height measurements between sexes was performed using a t-test, while a linear regression analysis was employedto examine the extent to which sitting height measurements can reliably predict stature. The results of this research study confirmed that sitting height reliably predicts stature in both genders of Kosovan adolescents and revealed a very useful finding for physical anthropologists and experts from related fields.


El propósito de esta investigación fue determinar una ecuación de regresión para la estimación de la estatura a partir de las medidas de altura sentada. Esta investigación se llevó a cabo en 1623 sujetos (830 hombres y 793 mujeres) en la población de adolescentes Kosovares. Las medidas de estatura y altura sentada se tomaron de acuerdo con el protocolo ISAK, y los datos se analizaron estadísticamente; las relaciones entre la estatura y las medidas de la altura sentada se derivaron utilizando una correlación simple. Se realizó una comparación de las medias de las mediciones de la altura al sentarse entre los sexos utilizando una prueba t, mientras que se empleó un análisis de regresión lineal para examinar hasta que punto las mediciones de la altura sentada pueden predecir la estatura de manera confiable. Los resultados de este estudio de investigación confirmaron que la altura sentada predice de forma confiable la estatura en ambos sexos de adolescentes Kosovares y reveló un hallazgo muy útil para antropólogos físicos y expertos de campos relacionados.


Assuntos
Humanos , Masculino , Feminino , Adolescente , Adulto Jovem , Estatura , Postura , Modelos Lineares , Antropometria , Probabilidade , Kosovo
12.
Stud Health Technol Inform ; 261: 217-222, 2019.
Artigo em Inglês | MEDLINE | ID: mdl-31156119

RESUMO

Many guidelines for prevention and treatment still locate persons in risk classes (e.g. low, moderate, high) on the basis of thresholds placed on a continuous metric for a single criterion (e.g. risk of developing x). These 'traffic light' signals can lead to inferior decisions through their mono-criterial focus and lack of preference-sensitivity to the multiple criteria relevant to the person. It is arguably unethical to communicate to someone that they are at low, moderate, or high risk of x solely on the basis of the unpublished and often unknown preferences of the group that has set the classification thresholds. Any prior classification and labelling will interfere with the individual's balanced processing of information on the performance of all treatment options on their multiple relevant criteria - including treatment side effects and burdens as well as main benefit - and jeopardise meeting the requirements for fully informed and preference-based consent to any subsequent action. Personalised decision support tools based on Multi-Criteria Decision Analysis can help fulfil these objectives, with apomediative (at home) e-decision support especially appealing because of its empowering and resource-saving potential. The individual's absolute risk score is required in these tools since any threshold-based risk classification will interfere with the coherence of the analysis across the multiple criteria.


Assuntos
Tomada de Decisões , Técnicas de Apoio para a Decisão , Sistemas Especialistas , Recursos em Saúde , Probabilidade
13.
Environ Monit Assess ; 191(Suppl 1): 322, 2019 Jun 20.
Artigo em Inglês | MEDLINE | ID: mdl-31222469

RESUMO

In 2011, the US Environmental Protection Agency and its partners conducted the first National Wetland Condition Assessment at the continental-scale of the conterminous United States. A probability design for site selection was used to allow an unbiased assessment of wetland condition. We developed a vegetation multimetric index (VMMI) as a parsimonious biological indicator of ecological condition applicable to diverse wetland types at national and regional scales. Vegetation data (species presence and cover) were collected from 1138 sites that represented seven broad estuarine intertidal and inland wetland types. Using field collected data and plant species trait information, we developed 405 candidate metrics with potential for distinguishing least disturbed (reference) from most disturbed sites. Thirty-five of the metrics passed range, repeatability, and responsiveness screens and were considered as potential component metrics for the VMMI. A permutation approach was used to calculate thousands of randomly constructed potential national-scale VMMIs with 4, 6, 8, or 10 metrics. The best performing VMMI was identified based on limited redundancy among constituent metrics, sensitivity, repeatability, and precision. This final VMMI had four broadly applicable metrics (floristic quality index, relative importance of native species, richness of disturbance-tolerant species, and relative cover of native monocots). VMMI values and weights from the survey design for probability sites (n = 967) were used to estimate wetland area in good, fair, and poor condition, nationally and for each of 10 ecoregion by wetland type reporting groups. Strengths and limitations of the national VMMI for describing ecological condition are highlighted.


Assuntos
Monitoramento Ambiental/métodos , Plantas/classificação , Áreas Alagadas , Coleta de Dados , Ecologia , Biomarcadores Ambientais , Probabilidade , Estados Unidos , United States Environmental Protection Agency
14.
Environ Monit Assess ; 191(7): 441, 2019 Jun 16.
Artigo em Inglês | MEDLINE | ID: mdl-31203453

RESUMO

An effective detection algorithm, supervising an online water system, is expected to monitor changes in water quality due to any contamination. However, contemporary event detection methods are often criticized for their high false detection rates as well as for their low true detection rates. This study proposes two new event detection methods for contamination that use multi-objective optimization by investigating the correlation between multiple types of conventional water quality sensors. While the first method incorporates non-dominated sorting genetic algorithm II (NSGA-II) with the Pearson correlation Euclidean distance (PE) method in order to maximize the probability of detection (PD) and to minimize the false alarm rate (FAR), the second method introduces fuzzy logic in order to establish a degree of correlations ranking that replaces the correlation relationship indicator threshold. Optimization is performed by using NSGA-II in the second method. The results of this study show that the incorporation of fuzzy logic with NSGA-II in event detection method have produced better results in event detection. The results also show that both methods detect all true events without producing any false alarm rates. Moreover, an uncertainty analysis on input sensor signals is performed to test the robustness of the fuzzy logic-based event detection method by employing the widely used Monte Carlo simulation (MCS) technique. Four different scenarios of uncertainty are analyzed, in particular, and the findings suggest that the proposed method is very effective in minimizing false alarm rates and maximizing true events detection, and hence, it can be regarded as one of the novel approaches to demonstrate its application in the development of an event detection algorithm.


Assuntos
Monitoramento Ambiental/métodos , Modelos Teóricos , Poluentes Químicos da Água/análise , Qualidade da Água/normas , Abastecimento de Água/normas , Algoritmos , Lógica Fuzzy , Método de Monte Carlo , Probabilidade , Incerteza
15.
BMC Bioinformatics ; 20(1): 330, 2019 Jun 13.
Artigo em Inglês | MEDLINE | ID: mdl-31196129

RESUMO

BACKGROUND: Ontology has attracted substantial attention from both academia and industry. Handling uncertainty reasoning is important in researching ontology. For example, when a patient is suffering from cirrhosis, the appearance of abdominal vein varices is four times more likely than the presence of bitter taste. Such medical knowledge is crucial for decision-making in various medical applications but is missing from existing medical ontologies. In this paper, we aim to discover medical knowledge probabilities from electronic medical record (EMR) texts to enrich ontologies. First, we build an ontology by identifying meaningful entity mentions from EMRs. Then, we propose a symptom-dependency-aware naïve Bayes classifier (SDNB) that is based on the assumption that there is a level of dependency among symptoms. To ensure the accuracy of the diagnostic classification, we incorporate the probability of a disease into the ontology via innovative approaches. RESULTS: We conduct a series of experiments to evaluate whether the proposed method can discover meaningful and accurate probabilities for medical knowledge. Based on over 30,000 deidentified medical records, we explore 336 abdominal diseases and 81 related symptoms. Among these 336 gastrointestinal diseases, the probabilities of 31 diseases are obtained via our method. These 31 probabilities of diseases and 189 conditional probabilities between diseases and the symptoms are added into the generated ontology. CONCLUSION: In this paper, we propose a medical knowledge probability discovery method that is based on the analysis and extraction of EMR text data for enriching a medical ontology with probability information. The experimental results demonstrate that the proposed method can effectively identify accurate medical knowledge probability information from EMR data. In addition, the proposed method can efficiently and accurately calculate the probability of a patient suffering from a specified disease, thereby demonstrating the advantage of combining an ontology and a symptom-dependency-aware naïve Bayes classifier.


Assuntos
Algoritmos , Teorema de Bayes , Técnicas e Procedimentos Diagnósticos , Registros Eletrônicos de Saúde , Bases de Conhecimento , Área Sob a Curva , Doença , Humanos , Probabilidade , Curva ROC
16.
Accid Anal Prev ; 129: 136-147, 2019 Aug.
Artigo em Inglês | MEDLINE | ID: mdl-31150920

RESUMO

Safety-in-numbers denotes the tendency for the number of accidents to increase less than in proportion to traffic volume. This paper updates a meta-analysis of estimates of safety-in-numbers published in 2017 (Elvik and Bjørnskau, Safety Science, 92, 274-282). Nearly all studies find safety-in-numbers, but the numerical estimates vary considerably. As virtually all studies are cross-sectional, it is not possible to determine if safety-in-numbers represents a causal relationship. Meta-regression analysis was performed to identify factors which may explain the large heterogeneity of estimates of safety-in-numbers. It was found that safety-in-numbers tends to be stronger for pedestrians than for cyclists, and stronger at the macro-level (e.g. citywide) than at the micro-level (e.g. in junctions). Recent studies find a stronger tendency towards safety-in-numbers than older studies.


Assuntos
Acidentes de Trânsito/estatística & dados numéricos , Condução de Veículo/estatística & dados numéricos , Ciclismo/estatística & dados numéricos , Pedestres/estatística & dados numéricos , Estudos Transversais , Humanos , Modelos Estatísticos , Probabilidade , Análise de Regressão , Medição de Risco , Segurança
17.
Accid Anal Prev ; 129: 156-169, 2019 Aug.
Artigo em Inglês | MEDLINE | ID: mdl-31150922

RESUMO

Risky lane-changing (LC) behavior of vehicles on the road has negative effects on traffic safety. This study presents a research framework for key feature selection and risk prediction of car's LC behavior on the highway based on vehicles' trajectory dataset. To the best of our knowledge, this is the first study that focuses on key feature selection and risk prediction for LC behavior on the highway. From the vehicles' trajectory dataset, we extract car's candidate features and apply fault tree analysis and k-Means clustering algorithm to determine the LC risk level based on the performance indicator of Crash Potential Index (CPI). Random Forest (RF) classifier is applied to select key features from car's candidate features and predict LC risk level. This study also proposes a method to evaluate the resampling methods to resample the LC risk dataset in terms of fitness performance and prediction performance. The cars' trajectory data collected from the Next Generation Simulation (NGSIM) dataset is used for framework development and verification. The sensitivity analysis of CPI indicates that the following cars in the original lane and target lane are respectively the safest and riskiest cars of the surrounding cars in an LC event. The results of resampling method evaluation show that SMOTETomek, which is less likely to be overfitting and has high prediction performance, is well suited for resampling the LC risk dataset on which RF classifier is trained. The results of key feature selection imply that the individual behaviors of the LC car and its surrounding cars in the original lane, the interactions between the LC car and its surrounding cars, and the interactions between the surrounding cars in the target lane (especially the interaction of the cars' accelerations) are of importance to the LC risk.


Assuntos
Acidentes de Trânsito/estatística & dados numéricos , Automóveis/estatística & dados numéricos , Algoritmos , Condução de Veículo/estatística & dados numéricos , Humanos , Probabilidade , Medição de Risco , Segurança
18.
BMC Bioinformatics ; 20(Suppl 12): 315, 2019 Jun 20.
Artigo em Inglês | MEDLINE | ID: mdl-31216983

RESUMO

BACKGROUND: The hybrid stochastic simulation algorithm, proposed by Haseltine and Rawlings (HR), is a combination of differential equations for traditional deterministic models and Gillespie's algorithm (SSA) for stochastic models. The HR hybrid method can significantly improve the efficiency of stochastic simulations for multiscale biochemical networks. Previous studies on the accuracy analysis for a linear chain reaction system showed that the HR hybrid method is accurate if the scale difference between fast and slow reactions is above a certain threshold, regardless of population scales. However, the population of some reactant species might be driven negative if they are involved in both deterministic and stochastic systems. RESULTS: This work investigates the negativity problem of the HR hybrid method, analyzes and tests it with several models including a linear chain system, a nonlinear reaction system, and a realistic biological cell cycle system. As a benchmark, the second slow reaction firing time is used to measure the effect of negative populations on the accuracy of the HR hybrid method. Our analysis demonstrates that usually the error caused by negative populations is negligible compared with approximation errors of the HR hybrid method itself, and sometimes negativity phenomena may even improve the accuracy. But for systems where negative species are involved in nonlinear reactions or some species are highly sensitive to negative species, the system stability will be influenced and may lead to system failure when using the HR hybrid method. In those circumstances, three remedies are studied for the negativity problem. CONCLUSION: The results of different models and examples suggest that the Zero-Reaction rule is a good remedy for nonlinear and sensitive systems considering its efficiency and simplicity.


Assuntos
Algoritmos , Simulação por Computador , Caulobacter/citologia , Ciclo Celular , Modelos Teóricos , Dinâmica não Linear , Probabilidade , Processos Estocásticos
19.
BMC Bioinformatics ; 20(Suppl 12): 321, 2019 Jun 20.
Artigo em Inglês | MEDLINE | ID: mdl-31216989

RESUMO

BACKGROUND: Missing values frequently arise in modern biomedical studies due to various reasons, including missing tests or complex profiling technologies for different omics measurements. Missing values can complicate the application of clustering algorithms, whose goals are to group points based on some similarity criterion. A common practice for dealing with missing values in the context of clustering is to first impute the missing values, and then apply the clustering algorithm on the completed data. RESULTS: We consider missing values in the context of optimal clustering, which finds an optimal clustering operator with reference to an underlying random labeled point process (RLPP). We show how the missing-value problem fits neatly into the overall framework of optimal clustering by incorporating the missing value mechanism into the random labeled point process and then marginalizing out the missing-value process. In particular, we demonstrate the proposed framework for the Gaussian model with arbitrary covariance structures. Comprehensive experimental studies on both synthetic and real-world RNA-seq data show the superior performance of the proposed optimal clustering with missing values when compared to various clustering approaches. CONCLUSION: Optimal clustering with missing values obviates the need for imputation-based pre-processing of the data, while at the same time possessing smaller clustering errors.


Assuntos
Algoritmos , Neoplasias da Mama/genética , Análise por Conglomerados , Simulação por Computador , Feminino , Perfilação da Expressão Gênica , Humanos , Modelos Teóricos , Distribuição Normal , Probabilidade
20.
Zhonghua Liu Xing Bing Xue Za Zhi ; 40(6): 707-712, 2019 Jun 10.
Artigo em Chinês | MEDLINE | ID: mdl-31238624

RESUMO

Objective: This project aimed to explore the effectiveness of estimating individual treatment effect on real data, among the heterogeneous population, with Causal Forests (CF) method, to find out the characteristics of heterogeneous population. Methods: We designed and conducted four computer simulation schemes to verify the effect of estimating on individual treatment, using the CF under four different environments of the treatment effects. Real data was then analyzed for the catheterization on right heart. Results: Results from the simulation process showed that the values on individual treatment effect that were estimated by causal forests were consistent with the population effect as well as in line with the expected distribution under the setting of four different effect values. Results of real data analysis showed that values of individual treatment effect among most patients appeared positive, so the use of RHC could cause an increase of the '180-day mortality rate' in the sampled population. Patients with lower predicted probability of 2-mo survival and albumin were more likely to have a lower risk of death after using the RHC. Conclusion: CF method could be effectively used to estimate the individual treatment effect and helping the individuals to make decision on the receipt of treatment.


Assuntos
Causalidade , Simulação por Computador , Florestas , Interpretação Estatística de Dados , Humanos , Probabilidade
SELEÇÃO DE REFERÊNCIAS
DETALHE DA PESQUISA