SEARCH · Search PubMed

Results for “Decision Trees”

Search indexed PubMed citations on genomics, clinical trials, systematic reviews and public health. Explore titles, authors and supplied subject terms, then open the PubMed record.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 91 records · Page 5Linked to original sources

PubMed1998

Learning fuzzy decision trees.

We present a recurrent neural network which learns to suggest the next move during the descent along the branches of a decision tree. More precisely, given a decision instance represented by a node in the decision tree, the network provides the degree of membership of each possible move to the fuzzy set z.Lt;good movez.Gt;. These fuzzy values constitute the core of the probability of selecting the move out of the set of the children of the current node.This results in a natural way for driving the sharp discrete-state process running along the decision tree by means of incremental methods on the continuous-valued parameters of the neural network. The bulk of the learning problem consists in stating useful links between the local decisions about the next move and the global decisions about the suitability of the final solution. The peculiarity of the learning task is that the network has to deal explicitly with the twofold charge of lighting up the best solution and generating the move sequence that leads to that solution. We tested various options for the learning procedure on the problem of disambiguating natural language sentences.

Journal Article↗

PubMed1996

Finding genes in DNA using decision trees and dynamic programming.

This study demonstrates the use of decision tree classifiers as the basis for a general gene-finding system. The system uses a dynamic programming algorithm that finds the optimal segmentation of a DNA sequence into coding and non-coding regions (exons and introns). The optimality property is dependent on a separate scoring function that takes a subsequence and assigns to it a score reflecting the probability that the sequence is an exon. In this study, the scoring functions were sets of decision trees and rules that were combined to give the probability estimate. Experimental results on a newly collected database of human DNA sequences are encouraging, and some new observations about the structure of classifiers for the gene-finding problem have emerged from this study. We also provide descriptions of a new probability chain model that produces very accurate filters to find donor and acceptor sites.

Algorithms↗

PubMed2000

The MacNeill-Lichtenberg Decision Tree: a unique method of triaging mental health problems in older medical rehabilitation patients.

OBJECTIVE: Evaluation of the utility of a "decision tree" that identifies potential mental health problems in older medical patients and guides decision making for referrals. DESIGN: Measures of utility including sensitivity, specificity, and predictive power were examined. Independent t tests and nonparametric statistics were used to evaluate group differences where appropriate. SETTING: The stroke and geriatric unit of a freestanding urban medical rehabilitation hospital. SUBJECTS: In study 1,173 older, consecutively admitted medical rehabilitation patients completed all cognitive measures. In study 2, a separate sample of 313 older adults completed the Geriatric Depression Scale during admission. MAIN OUTCOME MEASURE: The MacNeill-Lichtenberg Decision Tree (MLDT) was compared with the Mini-Mental State Exam (MMSE), the Mattis Dementia Rating Scale, and the 30-item Geriatric Depression Scale. RESULTS: Study 1: The decision tree accurately triaged 87% of mental health problems and allowed for deferral of 41% of cases, for whom further assessment was unnecessary. The MLDT was superior to the MMSE, with higher sensitivity and a lower failure rate. Study 2: The emotional status component of the MLDT was useful in triaging cases for depression evaluation. CONCLUSION: The MLDT was useful in prioritizing cases with regard to mental health problems (eg, dementia, depression) and making quick referral decisions. The MLDT is a unique instrument that not only evaluates cognitive status, but also considers psychosocial factors and emotional status in older adults.

Adult↗

PubMed2003

Decision tree and paradigms of primary breast cancer: changes elicited by preoperative therapy.

A small difference in decision-making causes a big impact on the long-term outcome in cancer treatment. Novel methods such as preoperative systemic treatment or sentinel node biopsy (SNB) may alter the decision-trees in primary breast cancer management. Recent data showed that preoperative chemotherapy drives pathological complete response (pCR) that implies long-term relapse-free, for about 25% to 30% of early breast cancer patients. In fact, preoperative systemic therapy has come to be used regardless of the tumor stage. From the point of the clinical trial, pCR can be recognized as a new endpoint, which promises to speed up new therapy development. Therefore, it is crucial to consider new paradigms including preoperative therapy in the decision-tree. There are several criticisms regarding the preoperative therapy, such as a possibility of over-treatment, however these issues might be resolved by changing the concept or procedures slightly. For instance, if SNB is conducted before the treatment, the over-treatment issue can be eliminated. In this article, we will discuss the changes in decision-tree and paradigms for primary

Antineoplastic Agents↗

PubMed2006

Management of non-complicated BPH: proposition of a renewed decision tree.

Nowadays the management of benign prostatic hypertrophia (BPH) is undergoing striking changes. The standard medical treatments are represented by three families which are the phytotherapy, the alpha-blockers and the 5-alpha-reductase inhibitors. These treatments were deemed as symptomatic and used only as monotherapy. Recent numerous studies bring new assessments on BPH: the medical treatment is able to modify the natural history of BPH especially by reducing the risk of acute urinary retention. Furthermore the association of two different therapeutic classes seems to be more efficient than the use of a monotherapy in some cases. Similarly the place of two instrumental techniques, the thermotherapy by microwaves or by radiofrequencies, previously proposed as alternatives to the surgical treatment seems to find their way rather as alternatives to the medical treatment. These different elements allow building a renewed decision tree which decisions are shared with the patient at each stage. This decision tree of the management of patients having non-complicated BPH symptoms must include initial clinical characteristics of the patient and its disease and the evolution under treatment which has not been yet considered in the international recommendations. It also considers the possibilities of associations with other therapeutic classes.

Decision Trees↗

PubMedDate not supplied

Identification of critical batch operating parameters in fed-batch recombinant E. coli fermentations using decision tree analysis.

To develop a useful fermentation process model, it is first necessary to identify which batch operating parameters are critical in determining the process outcome. To identify critical processing inputs in large databases, we have explored the use of Decision Tree Analysis with the decision metrics of Gain (i.e., Shannon Entropy changes), Gain Ratio, and a multiple hypergeometric distribution. The usefulness of this approach lies in its ability to treat "categorical" variables, which are typical of archived fermentation databases, as well as "continuous" variables. In this work, we demonstrate the use of Decision Tree Analysis for the problem of optimizing recombinant green fluorescent protein production in E. coli. A database of 85 fermentations was generated to examine the effect of 15 process input parameters on final biomass yield, maximum recombinant protein concentration, and productivity. The use of Decision Tree Analysis led to a considerable reduction in the fermentation database through the identification of the significant as well as insignificant inputs. However, different decision metrics selected different inputs and different numbers of inputs to classify the data for each output.

Algorithms↗

PubMed1988

A decision tree for early differentiation between obstructive and non-obstructive jaundice.

We present a method for early differentiation between obstructive and non-obstructive jaundice. On the basis of 14 variables (clinical data and clinical chemical tests, all available within 48 h) a simple decision tree or flow chart has been constructed. The diagnostic yield was as follows: 857 of 982 consecutive jaundiced patients (87%) in a data base and 98 of 108 patients in an independent test sample (91%) were correctly classified. Decision trees for the differentiation between benign or malignant causes within the obstructive group and between acute or chronic causes within the non-obstructive group are also presented. The resulting four-way classification was correct for 77% of the patients in the data base and for 72% of the patients in the test sample. The decision trees are compared with previous methods founded on Bayes' rule and logistic discrimination. The decision trees enable a quick and reliable classification of jaundiced patients, thus providing a valid basis for rational planning of the further diagnostic study.

Cholestasis↗

PubMedDate not supplied

Decision tree model of the treatment-seeking behaviors among Korean cancer patients.

The purpose of this study was to develop and test a decision tree model of the treatment-seeking behaviors among Korean cancer patients. The study used methodological triangulation, applying the cognitive ethnographic decision tree modeling approach. The model was developed based on qualitative data collected from in-depth interviews with 29 cancer patients. The model was tested using qualitative and quantitative data collected from interviews and a structured questionnaire involving 165 cancer patients. The predictability of the decision tree model was quantified as the proportion of participants who followed the pathway predicted by the model. Two models were developed, the first for decision making about when to visit a doctor after detecting symptoms, and the second for decision making about treatment type following the diagnosis. Decision outcomes for the first model were categorized into immediate visit and delayed visit. The first model was influenced by the perceived seriousness of symptoms, the experiences of visiting a doctor previously with similar symptoms, social-group influences on visiting a doctor, and barriers to visiting a doctor. Decision outcomes for the second model were hospital treatment only, and a mixture of hospital treatment and alternative therapies. The second model was influenced by curability, social-group influences on alternative therapies, and confidence in alternative therapies. The predictabilities of the 2 models were 90.3% and 94.5%, respectively. This study result can help nurses understand the treatment-seeking behaviors of cancer patients, and hence develop nursing intervention strategies.

Adult↗

PubMed1993

A preliminary ethnographic decision tree model of injection drug users' (IDUs) needle sharing.

This article presents a preliminary ethnographic decision tree model of the needle sharing and HIV risk decision-making processes common to injection drug users (IDUs) in Houston, Texas. Ethnographic tree decision modeling is a rigorous qualitative method used to understand and predict how and why people in certain groups do things the way they do. The model was developed from data collected from focus group and individual interviews and naturalistic observations. The research participants were White, African-American and Latino male and female IDUs. The model presents IDUs' needle-sharing routines or scripts based on several prioritized criteria. The model supports other researchers' findings that social roles play an important part in shaping IDUs' needle sharing. Yet, the model attempts to specify the different kinds of roles and relationships. The model suggests that social roles IDUs play and the status hierarchy between roles are the translation mechanisms that organize IDUs' social relationships into drug and HIV risky activities.

Acquired Immunodeficiency Syndrome↗

PubMed1997

Decision tree induction: a useful tool for assisted diagnosis and prognosis in tumor pathology.

The aim of the present work is to show that decision tree induction algorithms are a useful tool for extracting reliable information from data series, with the objective of assisting pathologists in identifying specific diagnostic and prognostic markers in various types of tumor pathologies. In terms of accuracy, we show that the decision tree technique exceeds other more sophisticated techniques, such as multilayer neural networks. Furthermore, because of the case with which decision tree results can be interpreted (logical classification rules), new methodologies can be readily developed to further assist in analyzing complex data that mix heterogeneous features. In this paper, we illustrate such capabilities in the context of different complex diagnostic and/or prognostic problems in tumor pathology relating to bladder, astrocytomas, and adipose tissues.

Adult↗

PubMed2004

Computerization of guidelines: a knowledge specification method to convert text to detailed decision tree for electronic implementation.

The initial step for the computerization of guidelines is the knowledge specification from the prose text of guidelines. We describe a method of knowledge specification based on a structured and systematic analysis of text allowing detailed specification of a decision tree. We use decision tables to validate the decision algorithm and decision trees to specify and represent this algorithm, along with elementary messages of recommendation. Edition tools are also necessary to facilitate the process of validation and workflow between expert physicians who will validate the specified knowledge and computer scientist who will encode the specified knowledge in a guide-line model. Applied to eleven different guidelines issued by an official agency, the method allows a quick and valid computerization and integration in a larger decision support system called EsPeR (Personalized Estimate of Risks). The quality of the text guidelines is however still to be developed further. The method used for computerization could help to define a framework usable at the initial step of guideline development in order to produce guidelines ready for electronic implementation.

Decision Making, Computer-Assisted↗

PubMed2001

Methods of statistical analysis of quantitative data obtained by toxicological bioassays using rodents in Japan: historical transition of the decision tree.

Massive amounts of quantitative data are being obtained by toxicity tests with time. These data sometimes include the data with a different distribution pattern or with different numbers of animals in each group. The tree-type algorithm has long been used commonly to promptly analyze the difference between the control group and dosage groups. In Japan, the decision tree has been used since 1982 with several modifications of the initial procedure. Recently, the method has been revised to have a high power. The changes have been made in two directions; one is a sophisticated method and the other is a simplified method. In this paper, the historical transition of the decision tree is described and the future of the decision tree forecasted.

Animals↗

PubMed1996

Methodological aspects of using decision trees to characterise leiomyomatous tumors.

The aim of the present work is to present the potential uses of a classification technique labeled the "decision tree" for tumor characterisation when faced with a large number of features. The decision tree technique enables multifeature logical classification rules to be produced by determining discriminatory values for each feature selected. In this report, we propose a methodology that used decision trees to compare and evaluate the information contributed by different types of features for tumor characterisation. This methodology is able to produce a set of hypotheses related to a diagnosis and or prognosis problem. For example, hypotheses can be producted (on the basis of a set of descriptive features) to explain why tumor cases belong to a given histopathological group. To illustrate our purpose, this methodology was applied to the difficult problem of leiomyomatous tumour diagnosis. The aim was to illustrate what kind of diagnostic information can be extracted from a sample data set including 23 smooth muscle tumors (14 benign leiomyomas and 9 malignant leiomyosarcomas) described by a large set of computer-assisted, microscope-generated features. Three groups of features were used relating to: (1) ploidy level determination (10 features), (2) quantitative chromatin pattern description (15 features), and (3) immunohistochemically related antigen specificities (6 features). All these features were quantified by digital cell image analysis. The results suggest that an objective distinction between leiomyomas and leiomyosarcomas can be established by means of simple logical rules depending on only a few features among which the immunohistochemically revealed antigen expression of desmin plays a preponderant part. One of the combinations of features proposed by the methodology is interesting for pathologists, because it includes two features describing the appearance of a nucleus in terms of chromatin distribution homogeneity and density, two features widely used by pathologists in tumor-grading systems.

Adolescent↗

PubMed2006

Generalized Haar DWT and transformations between decision trees and neural networks.

The core contribution of this paper is a three-fold improvement of the Haar discrete wavelet transform (DWT). It is modified to efficiently transform a multiclass- (rather than numerical-) valued function over a multidimensional (rather than low dimensional) domain, or transform a multiclass-valued decision tree into another useful representation. We prove that this multidimensional, multiclass DWT uses dynamic programming to minimize (within its framework) the number of nontrivial wavelet coefficients needed to summarize a training set or decision tree. It is a spatially localized algorithm that takes linear time in the number of training samples, after a sort. Convergence of the DWT to benchmark training sets seems to degrade with rising dimension in this test of high dimensional wavelets, which have been seen as difficult to implement. This multiclass multidimensional DWT has tightly coupled applications from learning "dyadic" decision trees directly from training data, rebalancing or converting preexisting decision trees to fixed depth boolean or threshold neural networks (in effect parallelizing the evaluation of the trees), or learning rule/exception sets represented as a new form of tree called an "E-tree", which could greatly help interpretation/visualization of a dataset.

Journal Article↗

PubMedDate not supplied

An evaluation of the decision tree approach for assessing priorities for safety testing of food additives.

In this publication we report an evaluation of the decision tree scheme of Cramer, Ford and Hall (1978) for assigning priorities for toxicity testing of chemicals. The original scheme has been modified to allow more chemical structures to be considered and to take into account recent advances in toxicology. The majority of the food additives permitted in either the UK, USA or Canada have been processed through the modified decision tree questionnaire and their classification compared with currently available chronic toxicity data. A large proportion of the additives (53/73) assigned to the lowest toxicity (I) class have a low order of chronic oral toxicity as do many of the compounds assigned to the moderate toxicity (II) class. Although the majority of the additives assigned to the highest toxicity (III) class are substantially more toxic than those in the lower toxicity classes, some relatively innocuous compounds reached this classification. In addition, a few toxic compounds were assigned to the lowest toxicity class. The reasons for these incorrect assignments are discussed. It was concluded that the decision tree approach, although less discriminating than originally suggested, remains a useful method for classifying compounds in terms of their probable toxicity and that further modifications to the tree could be made.

Accident Prevention↗

PubMed2003

A decision tree for selecting the most cost-effective waste disposal strategy in foodservice operations.

The purposes of this study were to determine costs of disposal strategies for wastes generated in foodservice operations and to develop a decision tree to determine the most cost-effective disposal strategy for foodservice operations. Four cases, including the central food processing center (CFPC) in a school district, a continuing-care retirement center (CCRC), a university dining center (UDC), and a commercial chain restaurant (CCR), were studied to determine the most cost-effective disposal strategy. Annual costs for the current and projected strategies were determined for each case. Results of waste characterization studies and stopwatch studies, interviews with foodservice directors, and water flow and electrical requirements from manufacturers' specifications were used to determine cost incurred. The annual percentage increases for labor, fees, and services were used to reflect an inflated economic condition for the ensuing 10 years of the study period. The Net Present Worth method was used to compare costs of strategies, and the multiparameter sensitivity analysis was conducted to examine the tolerance of the chosen strategy. The most cost-effective strategy differed among foodservice operations because of the composition of food and packaging wastes, the quantity of recyclable materials, the waste-hauling charges, labor costs, start-up costs, and inflation rate. For example, the use of a garbage disposal for food waste and landfills and recycling for packaging waste were the most cost-effective strategies for the CCRC. A decision tree was developed to illustrate the decision-making process that occurs when conducting cost analysis and subsequent decisions. Dietetics practitioners can use the decision tree when evaluating the results of the cost analysis.

Cost-Benefit Analysis↗

PubMed1986

When is a diagnostic test result positive? Decision tree models based on net utility and threshold.

The question "When is a diagnostic test result positive?" can be addressed by clinical decision analysis. We developed two simple decision tree models for selecting appropriate cutoff levels: a net utility model and a threshold model. These models have been incorporated in a software program for desktop computers. We believe it is important for investigators to provide raw data on test performance, for three reasons. First, these data can be used in simple decision tree models to identify "appropriate" cutoff levels. Second, they can be used to evaluate empiric cutoff levels or decision rules. Third, they can be used to evaluate optimal cutoff levels for detailed decision trees depicting specific clinical problems.

Cost-Benefit Analysis↗

PubMed2004

Evaluation of the potential allergenicity of the enzyme microbial transglutaminase using the 2001 FAO/WHO Decision Tree.

All novel proteins must be assessed for their potential allergenicity before they are introduced into the food market. One method to achieve this is the 2001 FAO/WHO Decision Tree recommended for evaluation of proteins from genetically modified organisms (GMOs). It was the aim of this study to investigate the allergenicity of microbial transglutaminase (m-TG) from Streptoverticillium mobaraense. Amino acid sequence similarity to known allergens, pepsin resistance, and detection of protein binding to specific serum immunoglobulin E (IgE) (RAST) have been evaluated as recommended by the decision tree. Allergenicity in the source material was thought unlikely, since no IgE-mediated allergy to any bacteria has been reported. m-TG is fully degraded after 5 min of pepsin treatment. A database search showed that the enzyme has no homology with known allergens, down to a match of six contiguous amino acids, which meets the requirements of the decision tree. However, there is a match at the five contiguous amino acid level to the major codfish allergen Gad c1. The potential cross reactivity between m-TG and Gad c1 was investigated in RAST using sera from 25 documented cod-allergic patients and an extract of raw codfish. No binding between patient IgE and m-TG was observed. It can be concluded that no safety concerns with regard to the allergenic potential of m-TG were identified.

Animals↗