PubMed Health⌕ Search

Biomedical subjects

John Eng

Publications and source records attributed to John Eng.

25 records · Page 2Linked to original sources
PubMed2003

Sample size estimation: how many individuals should be studied?

The number of individuals to include in a research study, the sample size of the study, is an important consideration in the design of many clinical studies. This article reviews the basic factors that determine an appropriate sample size and provides methods for its calculation in some simple, yet common, cases. Sample size is closely tied to statistical power, which is the ability of a study to enable detection of a statistically significant difference when there truly is one. A trade-off exists between a feasible sample size and adequate statistical power. Strategies for reducing the necessary sample size while maintaining a reasonable power will also be discussed.

Humans↗
PubMed2002

Predicting the presence of acute pulmonary embolism: a comparative analysis of the artificial neural network, logistic regression, and threshold models.

OBJECTIVE: The objective of this study was to determine whether an artificial neural network, a new data analysis method, offers increased performance over conventional logistic regression in predicting the presence of a pulmonary embolism for patients in a well-known data set. MATERIALS AND METHODS: Data from the 1064 patients who received an angiographically based diagnosis of pulmonary embolism in the Prospective Investigation of Pulmonary Embolism Diagnosis study were encoded using a previously described method. The 21 input variables represented abnormalities identified on each patient's ventilation-perfusion scan and chest radiograph. Two methods-an artificial neural network with one hidden layer and a multivariate logistic regression-were compared for accuracy in predicting the presence or absence of pulmonary embolism on subsequent pulmonary arteriography. RESULTS: No significant difference was observed between the two methods. Areas under the receiver operating characteristic curves +/- standard deviation were 0.78 +/- 0.02 for the artificial neural network model and 0.79 +/- 0.02 for the logistic regression model. Furthermore, use of these two methods resulted in no more diagnostic accuracy than did the use of a simple threshold model based only on the number of subsegmental perfusion defects, which was the dominant input variable. CONCLUSION: In the study population, the usefulness of data from ventilation-perfusion scans as predictors of the presence of a pulmonary embolism was similar for the three analytic methods, a finding that reinforces the importance of making comparisons to simpler or more established methods when performing studies involving complex analytic models, such as artificial neural networks.

Acute Disease↗
PubMedDate not supplied

Accuracy of breath-hold magnetic resonance imaging in preoperative staging of organ-confined renal cell carcinoma.

PURPOSE: To determine the accuracy of breath-hold magnetic resonance (MR) imaging for preoperative staging of patients with organ-confined (stage I) renal cell carcinoma. MATERIALS AND METHODS: Preoperative MR examinations of 43 patients (50 lesions) who underwent nephrectomy were reviewed. The MR examination consisted entirely of breath-hold sequences, and images were retrospectively evaluated by 2 blinded radiologists. Reviewers independently evaluated each case for findings that could affect the radiologic staging, particularly those that distinguish between organ-confined (stage I) and non-organ-confined (>stage II) disease. Each reviewer assigned a stage, and results were correlated with findings at surgery and pathologic examination. RESULTS: The difference between both reviewers and pathologic findings in evaluating an intact renal capsule (stage I) was statistically significant (P < 0.05) and resulted in a statistically significant difference between radiologic and pathologic staging (Wilcoxon test, P < 0.05). The kappa test demonstrated moderate agreement between radiologic and pathologic staging (82% and 80% for reviewers 1 and 2, kappa = 0.54 and 0.80, respectively) and substantial agreement (90%, kappa = 0.80) between the 2 reviewers in assigning a radiologic stage. CONCLUSION: Breath-hold MR imaging has an accuracy ranging between 80% and 82% in staging patients with organ-confined renal cell carcinoma, with substantial (90%) agreement between readers.

Adult↗
PubMedDate not supplied

Informatics in Radiology (infoRAD): radiology report entry with automatic phrase completion driven by language modeling.

Keyboard entry or correction of radiology reports by radiologists and transcriptionists remains necessary in many settings despite advances in computerized speech recognition. A report entry system that implements an automated phrase completion feature based on language modeling was developed and tested. The special text editor uses context to predict the full word or phrase being typed, updating the displayed prediction after each keystroke. At any point, pressing the tab key inserts the predicted phrase without having to type the remaining characters of the phrase. Successive words of the phrase are predicted by a trigram language model. Phrase lengths are chosen to minimize the expected number of keystrokes as predicted by the language model. Operation is highly and automatically customized to each user. The language model was trained on 36,843 general radiography reports, which were consecutively generated and contained 1.48 million words. Performance was tested on 200 randomly selected reports outside of the training set. The phrase completion technique reduced the average number of keystrokes per report from 194 to 58; the average reduction factor was 3.3 (geometric mean) (95% confidence interval, 3.2-3.5). The algorithm significantly reduced the number of keystrokes required to generate a radiography report (P <.00005).

Algorithms↗
PubMedDate not supplied

Collaboration system for radiology workstations.

Consultation between radiologists and referring physicians is part of routine medical practice. Nevertheless, a typical picture archiving and communication system contains no provision that will allow this critical interaction to occur on-line. The authors describe an image viewing system designed for real-time interactive consultation over the Internet. The system has two main components: an image viewer and a collaboration server. The image viewer connects to the collaboration server over an Internet-compatible network. Once the image viewer is connected, its display can be synchronized with that of another connected image viewer, so that radiologists can point out image findings and diagnoses in real time to remotely located physicians. The image viewer can retrieve images from any DICOM-compatible archive. In addition to standard image manipulation functions, the image viewer contains a new user interface for image annotation. Developed specifically for medical imaging, this user interface is activated by mouse actions instead of conventional on-screen controls, greatly improving the ease with which annotations can be created. The collaboration system is based on a simple yet flexible programming interface that can be readily generalized to other types of collaborative applications. The system was developed with the Java programming language because of Java's integrated support of Internet-compatible networking capabilities.

Humans↗