Search PubMed⌕ Search

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.

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

At least 19 recordsLinked to original sources
PubMedDate not supplied

Methods of decision analysis: protocols, decision trees, and algorithms in medicine.

Algorithms, decision trees, and protocols are defined and explained since they constitute an accepted part of clinical decision analysis and application to clinical care. Algorithms are particularly useful for common clinical problems where uncertainties are unlikely. Decision trees are helpful when--as usually occurs in difficult clinical decisions--there are problems in probability. Clinical protocols, which, at best, are based on algorithms and decision trees, provide instruction of how to best treat a patient given the strict definitions of the clinical problem. These techniques are, in essence, merely graphic representations of a logical scientific approach to clinical problems. Criticisms of these techniques center on their rigidity and the automatic unthinking cookbook medicine they might sponsor. It is concluded that if these techniques are wisely designed and, even more importantly, wisely administered with an understanding flexibility, they can lead to both economy and patient benefit.

Algorithms↗
PubMed1989

[Construction of a decision tree for preoperative diagnosis in urinary incontinence].

In order to analyse the decisions used in non-urodynamic preoperative diagnosis of female urinary incontinence we constructed a decision tree, consisting of decision nodes and probability nodes. Each branch of the decision tree leads to an end point (terminal node), to which an utility must be assigned. We describe the different steps in the construction of the decision tree: 1. listing of all possible decisions (questionnaire, clinical stress test, both, no preoperative tests), 2. assignment of probabilities to the different events (e.g. cure, failure, operation in the absence of genuine stress incontinence), and 3. assignment of utility factors to the end points. We used previously published probabilities from our clinic, utility was assigned arbitrarily using a score from -10 to +90. The decision tress allows not only the calculation of the strategy with the highest expected utility, but also threshold analysis, sensitivity analysis and cost-benefit analysis. We feel that decision trees are valuable tools for analysing how medical decisions are reached and are particularly useful in teaching situations.

Adult↗
PubMedDate not supplied

Automated critiquing of medical decision trees.

The authors developed a decision tree-critiquing program (called BUNYAN) that identifies potential modeling errors in medical decision trees. The program's critiques are based on the structure of a decision problem, obtained from an abstract description specifying only the basic semantic categories of the model's components. A taxonomy of node and branch types supplies the primitive building blocks for representing decision trees. Bunyan detects potential problems in a model by matching general pattern expressions that refer to these primitives. A small set of general principles justifies critiquing rules that detect four categories of potential structural problems: impossible strategies, dominated strategies, unaccountable violations of symmetry, and omission of apparently reasonable strategies. Although critiquing based on structure alone has clear limitations, principled structural analysis constitutes the core of a methodology for reasoning about decision models.

Decision Trees↗
PubMed1991

Application of portfolio theory in decision tree analysis.

A general application of portfolio analysis for herd decision tree analysis is described. In the herd environment, this methodology offers a means of employing population-based decision strategies that can help the producer control economic variation in expected return from a given set of decision options. An economic decision tree model regarding the use of prostaglandin in dairy cows with undetected estrus was used to determine the expected return of the decisions to use prostaglandin and breed on a timed basis, use prostaglandin and then breed on sign of estrus, or breed on signs of estrus. The risk attributes of these decision alternatives were calculated from the decision tree, and portfolio theory was used to find the efficient decision combinations (portfolios with the highest return for a given variance). The resulting combinations of decisions could be used to control return variation.

Animals↗
PubMedDate not supplied

Use of a decision tree to improve accuracy of diagnosis.

Thirty triads of nurses matched for educational background, length of experience, and previous performance were studied to determine if use of a decision tree would improve diagnostic accuracy. One experimental and two control groups were given a written case study and asked to list all possible diagnoses that could cause the change in behavior exhibited by the patient. Experimental group nurses were given a set of decision trees to enable them to use the information systematically to determine if characteristics of each condition were present. Significant improvement in diagnostic accuracy was shown by nurses who used the decision trees.

Decision Making↗
PubMedDate not supplied

A thrombolytic decision tree.

We constructed a decision analysis model based on data in the medical literature to estimate the possible outcomes of thrombolytic therapy in patients 50 to 80 years old with possible myocardial infarction. We used the model to test the most likely effects of treatment (determined by averaging the values in reports of large studies) and the worst effects reported so far. The program begins by asking the patient's age, the hours from the onset of pain, and the probability of acute myocardial infarction. It then provides an opportunity to perform sensitivity analyses by changing the values for these variables and for the probability of death in the absence of thrombolytic therapy, as well as for the probability of major stroke and hemorrhage. The counterintuitive findings observed with this program are that the benefits of thrombolytic therapy increase with age and that young patients derive surprisingly little benefit from it.

Age Factors↗
PubMed1989

Decision-tree analysis of treatment alternatives for left displaced abomasum.

This study evaluates treatment alternatives for left displaced abomasum (LDA) in dairy cattle. The technique of decision-tree analysis was used to evaluate 3 treatment possibilities. A computerized spreadsheet decision tree was used for the evaluation. Results of this investigation suggested that surgical treatment had the highest expected monetary value. Closed surgical techniques had expected monetary values close to the surgical techniques. Rolling the cow had the lowest expected monetary value, but the expected monetary value for rolling was higher than the expected monetary value for selling. If an LDA recurs after treatment, surgical and closed surgical treatments are preferred over rolling. From this study, we can conclude that surgical and closed surgical treatment alternatives are preferred if expected monetary values are considered. Rolling is preferred over selling the cow. However, if an LDA recurs, selling the cow is preferred over rolling.

Abomasum↗
PubMed1992

Well differentiated follicular neoplasms of the thyroid: reproducibility and validity of a 'decision tree' classification based on nucleolar and karyometric features.

This study was conducted on fine-needle aspirates of well differentiated follicular neoplasms of the thyroid. A 'decision tree' classification based on the percentage of nucleolated nuclei, percentage of nuclei with two or more nucleoli and mean major nuclear diameter was adopted. We observed that the reproducibility and the validity of the follicular adenoma vs follicular carcinoma discrimination are greater than in the subjective evaluation. Moreover, similar classification results were obtained when measurements were performed either with a fully automated image analysis system or with semiautomatic or manual instrumentation. As for reproducibility of the inter-instrument comparisons, the k statistic values ranged from 0.85 to 1.00 (mean value 0.90, that is, an 'almost perfect' degree of agreement); in the subjective evaluations, the inter-observer comparisons showed values ranging from 0.20 to 0.56 (mean value 0.37, that is, 'fair'). In the decision tree classification, feature value thresholds were selected in order to have specificity of 100% and the predictive value of a positive result (carcinoma) of 100%; accuracy was 87% (range 86-89%), sensitivity 74% (71-79%), the predictive value of a negative result (adenoma) 79% (78-82%). In the subjective evaluation the values were as follows: accuracy 67% (64-71%), sensitivity 57% (50-64%), specificity 77% (71-79%), predictive value of a negative result (adenoma) 64% (61-69%), predictive value of a positive result (carcinoma) 71% (67-75%). The conclusion is that, by using a routine microscope equipped with a micrometer, the preoperative diagnosis of follicular carcinoma from smears can be formulated with a high degree of certainty.

Adenocarcinoma↗
PubMed1992

Decision tree for the management of substance-abusing psychiatric patients.

This paper describes a short-term approach developed at a time of numerous drug-related incidents occurring at a large VA Hospital to help staff manage psychiatric patients abusing alcohol or drugs during hospitalization. This was accomplished through the development of a decision tree designed to improve the clinical problem-solving process by identifying key decision points. Prior to this, staff responded emotionally either by prematurely discharging patients or by not recognizing the problem at all. Decision Trees have widespread applicability for resolving complex clinical problems.

Adult↗
PubMed1990

A decision tree for the treatment of caries in posterior teeth.

Because of a better understanding of the caries process, a decrease in the prevalence of caries, and the rapid development of dental materials, a renewed approach to the treatment of dental caries in the posterior region is possible. A decision tree for the treatment of caries in posterior teeth, taking into account some of the most recent tooth substance-saving treatment options, is presented. These possibilities gradually evolve from nondestructive to conventional cavity preparations. In addition, the "preventive Class II restoration" is introduced. The application of this conservative attitude toward invasive techniques offers great advantages for both the patient and the dentist. Unfortunately, this approach is time-consuming. Long-term clinical evaluation of the application of the proposed decision tree on a wide scale is needed to confirm its potential benefits or to modify and improve treatment options.

Bicuspid↗
PubMed1989

[Forecasting strategies of hepatitis B vaccination based on decision tree model].

The strategies of hepatitis B vaccination was studied based on the decision tree model. The results showed that the young, especially newborn should be given the highest priority for vaccination and the best strategy to the neonate is vaccination without screening for HBsAg to their mothers. The results also showed that the population groups who can take positive benefits (BCR greater than 1) after being vaccinated can be enlarged if decreasing the costs of the vaccination and tests for hepatitis B virus markers, and increasing the protect rates and years of vaccination. It told us that we should not only pay attention to the study for the more effective and cheaper vaccine, but manage scientifically and use reasonably as well.

Adolescent↗
PubMed1989

Determining optimal screening policies using decision trees and spreadsheets.

The determination of the proportion of population to be screened, so that overall costs are minimized, is treated. A decision tree approach is used, based on knowing the probabilities and costs of all possible outcomes. This involves specifying models that estimate the prevalences in the screened and non-screened groups for various screening levels. The generalized implementation on a microcomputer spreadsheet that is presented permits sensitivity and optimality to be explored for different parameter conditions. A numerical example illustrates the results.

Costs and Cost Analysis↗