Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “Software Validation”

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 703 records · Page 39Linked to original sources
PubMed2003

A rapid speech synthesizing software on a PDA for Japanese with speech impairments.

We developed a Japanese-language, rapid synthesizing software application for use on a personal digital assistant. It has an unrestricted vocabulary and can synthesize words and sentences within 3 s. Eight hundred common sentences and words are preregistered. By touching the first character at the head of a preregistered sentence or word from an on-screen Kana (Japanese alphabet) chart, the user can select the sentence or word to be spoken. Characters on the Kana chart can also be input sequentially. Two Japanese subjects with speech impairments rated the device highly for its portability and quick response. Whereas communication previously had to be done by writing or sign language, it was easy for listeners with or without specialized training in communication with persons with speech impairments to understand the output from this device, making conversation easier which, in turn, improved the quality of life and social activity of these persons with speech impairments.

Asian People↗
PubMed2004

Adaptive software for head-operated computer controls.

Head-operated computer controls provide an alternative means of computer access for people with disabilities who are unable to use a standard mouse. However, a person's disability may limit his or her neck movements as well as upper extremity movements. Software was developed which automatically adjusts the interface sensitivity to the needs of a particular user. This adaptive software was evaluated in two stages. First, 16 novice head-control users with spinal-cord injury or multiple sclerosis used head controls with and without the adaptive software. The adaptive software was associated with increased speed in standardized icon selection exercises (p < 0.05). A small increase in accuracy was also observed. In addition, five current head-control users evaluated the software in a real-world setting. One of these five subjects perceived an improvement in comparison to his current head-control system.

Activities of Daily Living↗
PubMed2005

Performance evaluation of local descriptors.

In this paper, we compare the performance of descriptors computed for local interest regions, as, for example, extracted by the Harris-Affine detector. Many different descriptors have been proposed in the literature. It is unclear which descriptors are more appropriate and how their performance depends on the interest region detector. The descriptors should be distinctive and at the same time robust to changes in viewing conditions as well as to errors of the detector. Our evaluation uses as criterion recall with respect to precision and is carried out for different image transformations. We compare shape context, steerable filters, PCA-SIFT, differential invariants, spin images, SIFT, complex filters, moment invariants, and cross-correlation for different types of interest regions. We also propose an extension of the SIFT descriptor and show that it outperforms the original method. Furthermore, we observe that the ranking of the descriptors is mostly independent of the interest region detector and that the SIFT-based descriptors perform best. Moments and steerable filters show the best performance among the low dimensional descriptors.

Algorithms↗
PubMed2005

An empirical comparison of combinations of evolutionary algorithms and neural networks for classification problems.

There are numerous combinations of neural networks (NNs) and evolutionary algorithms (EAs) used in classification problems. EAs have been used to train the networks, design their architecture, and select feature subsets. However, most of these combinations have been tested on only a few data sets and many comparisons are done inappropriately measuring the performance on training data or without using proper statistical tests to support the conclusions. This paper presents an empirical evaluation of eight combinations of EAs and NNs on 15 public-domain and artificial data sets. Our objective is to identify the methods that consistently produce accurate classifiers that generalize well. In most cases, the combinations of EAs and NNs perform equally well on the data sets we tried and were not more accurate than hand-designed neural networks trained with simple backpropagation.

Algorithms↗
PubMed2005

An empirical comparison of nine pattern classifiers.

There are many learning algorithms available in the field of pattern classification and people are still discovering new algorithms that they hope will work better. Any new learning algorithm, beside its theoretical foundation, needs to be justified in many aspects including accuracy and efficiency when applied to real life problems. In this paper, we report the empirical comparison of a recent algorithm RM, its new extensions and three classical classifiers in different aspects including classification accuracy, computational time and storage requirement. The comparison is performed in a standardized way and we believe that this would give a good insight into the algorithm RM and its extension. The experiments also show that nominal attributes do have an impact on the performance of those compared learning algorithms.

Algorithms↗
PubMed2006

Evolutionary neural networks for anomaly detection based on the behavior of a program.

The process of learning the behavior of a given program by using machine-learning techniques (based on system-call audit data) is effective to detect intrusions. Rule learning, neural networks, statistics, and hidden Markov models (HMMs) are some of the kinds of representative methods for intrusion detection. Among them, neural networks are known for good performance in learning system-call sequences. In order to apply this knowledge to real-world problems successfully, it is important to determine the structures and weights of these call sequences. However, finding the appropriate structures requires very long time periods because there are no suitable analytical solutions. In this paper, a novel intrusion-detection technique based on evolutionary neural networks (ENNs) is proposed. One advantage of using ENNs is that it takes less time to obtain superior neural networks than when using conventional approaches. This is because they discover the structures and weights of the neural networks simultaneously. Experimental results with the 1999 Defense Advanced Research Projects Agency (DARPA) Intrusion Detection Evaluation (IDEVAL) data confirm that ENNs are promising tools for intrusion detection.

Algorithms↗
PubMedDate not supplied

Design and evaluation of tiled parallel coordinate visualization of multichannel EEG data.

The field of visualization assists data interpretation in many areas, but does not manage all types of data equally well. This holds, in particular, for time-varying multichannel EEG data. No existing method can successfully visualize simultaneous information from all channels in use at all time steps. To address this problem, a new visualization method is presented based on the parallel coordinate method and making use of a tiled organization. This tiled organization employs a two-dimensional row-column representation, rather than a one-dimensional arrangement in columns as used for classical parallel coordinates. The usefulness of the new method, referred to as tiled parallel coordinates (TPC), is demonstrated by a particular type of EEG data. It can be applied to an arbitrary number of time steps, handling the maximum number of channels currently in use. An extensive user evaluation shows that, for a typical EEG assessment task, data evaluation by the TPC method is faster than by an existing clinical EEG visualization method, without loss of information. The generality of the TPC method makes it widely applicable to other time-varying multivariate data types.

Computer Graphics↗
PubMed2004

Sensitivity and selectivity in protein structure comparison.

Seven protein structure comparison methods and two sequence comparison programs were evaluated on their ability to detect either protein homologs or domains with the same topology (fold) as defined by the CATH structure database. The structure alignment programs Dali, Structal, Combinatorial Extension (CE), VAST, and Matras were tested along with SGM and PRIDE, which calculate a structural distance between two domains without aligning them. We also tested two sequence alignment programs, SSEARCH and PSI-BLAST. Depending upon the level of selectivity and error model, structure alignment programs can detect roughly twice as many homologous domains in CATH as sequence alignment programs. Dali finds the most homologs, 321-533 of 1120 possible true positives (28.7%-45.7%), at an error rate of 0.1 errors per query (EPQ), whereas PSI-BLAST finds 365 true positives (32.6%), regardless of the error model. At an EPQ of 1.0, Dali finds 42%-70% of possible homologs, whereas Matras finds 49%-57%; PSI-BLAST finds 36.9%. However, Dali achieves >84% coverage before the first error for half of the families tested. Dali and PSI-BLAST find 9.2% and 5.2%, respectively, of the 7056 possible topology pairs at an EPQ of 0.1 and 19.5, and 5.9% at an EPQ of 1.0. Most statistical significance estimates reported by the structural alignment programs overestimate the significance of an alignment by orders of magnitude when compared with the actual distribution of errors. These results help quantify the statistical distinction between analogous and homologous structures, and provide a benchmark for structure comparison statistics.

Computational Biology↗
PubMed2005

The use of personal digital assistants by nurse practitioner students and faculty.

PURPOSE: To describe the prevalence and patterns of use of personal digital assistants (PDAs) by nurse practitioner (NP) students and faculty, examine relationships between patterns of use of PDAs and demographic characteristics of NP students and faculty, and describe patterns of use of PDAs that support evidence-based practice (clinical scholarship). DATA SOURCES: Responses to a 20-item questionnaire administered via electronic or postal mail from 227 NP students and faculty. CONCLUSIONS: A majority (67%) of the participants used PDAs. Use was higher among men (82%) than women (64%) (p < .05). On average, respondents who used a PDA (N = 153) had been using it just over a year (M = 13 months). Respondents reported using a PDA most days of the week (M = 5 days). The top three medical software programs identified by respondents as the most useful in clinical practice were ePocrates Rx (82%), Griffith's 5-Minute Clinical Consult (26%), and MedCalc (22%). Most participants (96%) related that PDA use supported clinical decision making. IMPLICATIONS FOR PRACTICE: Personal digital assistants may facilitate the application of evidence-based knowledge to practice. However, until there is evidence that PDA software is valid and reliable, clinicians should continue to use a multitude of references to assure the quality and safety of care provided.

Adult↗
PubMed1994

Automating ward evaluations: a tentative first step.

Auditing nursing practice is a time-consuming, error-prone task. Feedback to individuals is highly desirable but usually is not offered. This is particularly difficult in large-scale studies. In this study of 654 wards a new method was attempted. Structured questionnaires were analysed by a computer program and feedback reports generated automatically. Informal evaluations by the initial recipients are positive and the method seems worthy of future development.

Hospital Units↗
PubMed2005

Assessing the accuracy of a computerized decision support system for digoxin dosing in primary care: an observational study.

BACKGROUND: This study was carried out as part of a European Union funded project (PharmDIS-e+), to develop and evaluate software aimed at assisting physicians with drug dosing. A drug that causes particular problems with drug dosing in primary care is digoxin because of its narrow therapeutic range and low therapeutic index. OBJECTIVES: To determine (i) accuracy of the PharmDIS-e+ software for predicting serum digoxin levels in patients who are taking this drug regularly; (ii) whether there are statistically significant differences between predicted digoxin levels and those measured by a laboratory and (iii) whether there are differences between doses prescribed by general practitioners and those suggested by the program. METHODS: We needed 45 patients to have 95% Power to reject the null hypothesis that the mean serum digoxin concentration was within 10% of the mean predicted digoxin concentration. Patients were recruited from two general practices and had been taking digoxin for at least 4 months. Exclusion criteria were dementia, low adherence to digoxin and use of other medications known to interact to a clinically important extent with digoxin. RESULTS: Forty-five patients were recruited. There was a correlation of 0.65 between measured and predicted digoxin concentrations (P < 0.001). The mean difference was 0.12 microg/L (SD 0.26; 95% CI 0.04, 0.19, P = 0.005). Forty-seven per cent of the patients were prescribed the same dose as recommended by the software, 44% were prescribed a higher dose and 9% a lower dose than recommended. CONCLUSION: PharmDIS-e+ software was able to predict serum digoxin levels with acceptable accuracy in most patients.

Aged↗
PubMed1997

High-resolution HLA-DRB typing using denaturing gradient gel electrophoresis and direct sequencing.

High-resolution HLA-DRB typing is required for bone marrow transplantation between unrelated donors and recipients and also for identification of novel HLA-DRB alleles. Here we describe a method for the unambiguous identification of HLA-DRB alleles using the polymerase chain reaction (PCR), denaturing gradient gel electrophoresis (DGGE) and direct sequencing. The highly variable second exon of all HLA-DRB1, -DRB3, -DRB4, -DRB5, -DRB6 and -DRB7 alleles was amplified using a single pair of generic DRB-specific primers and alleles were separated by DGGE. DNA was then reamplified from plugs removed from the gel and the sequences of these alleles were determined using fluorescent-based sequencing and allele-assignment software. The validity of this typing procedure was confirmed by identification of HLA-DRB alleles for 17 individuals previously characterized by PCR-SSP and/or cloning and sequencing techniques. We identified 34 different HLA-DRB alleles in these 17 unrelated individuals. Importantly, our analysis revealed HLA-DRB1 alleles which had not been identified using the PCR-SSP typing technique. Additionally, alleles from the HLA-DRB3, -DRB4 and -DRB5 loci were identified. Whereas traditional HLA-DRB typing methods provide limited information or require the use of multiple oligonucleotide primers or probes, our technique provides a reliable, specific and relatively rapid way of identifying all HLA-DRB alleles for high-resolution tissue typing.

Alleles↗
PubMed1994

An information manager for the Assessment Protocol for Excellence in Public Health.

The Assessment Protocol for Excellence in Public Health (APEXPH) is a method for comprehensive public health planning that can be implemented by state and local health departments. Many local health departments have limited resources for the data analysis and synthesis needed for APEXPH. To facilitate the implementation of APEXPH in Michigan, we used the Centers for Disease Control and Prevention (CDC) Epi Info software package to develop an APEXPH information manager (CDC-AIM) for use by the 50 local health departments in that state. This report describes our methods for formatting, compressing, and presenting data. Examples of tables are provided for demographics by age and sex, numbers of deaths, years of potential life lost, crude mortality rates, and perinatal indicators such as low birthweight. Areas where additional work is needed to further improve CDC-AIM are discussed. Our experience in Michigan suggests that CDC-AIM potentially is an extremely helpful tool to assist state and local health departments in working with their communities to establish public health program plans based on mortality, morbidity, and risk-factor data.

Comprehensive Health Care↗
PubMed1994

Structural determinants of developmental toxicity.

Developmental toxicity, an area of public concern, suffers from the lack of accessible, reliable, peer-reviewed compilations of data and substantial gaps in testing. These deficits frequently make it necessary for regulatory agencies to use other toxicological end points to regulate developmental toxicants. We have utilized a database of chemicals identified as developmental toxicants in rats, mice, rabbits, and humans and an expert system which learns the association between molecular structure and biological response (Computer Automated Structure Evaluation; CASE) to explore structure-activity relationships in developmental toxicity. Developmental toxicity was defined as death, growth retardation, or structural or functional malformations. In analyzing the data CASE selects its own molecular descriptors from a learning set of active and inactive molecules. Using randomly constructed learner and tester sets, the concordance of the predictions with the actual data was between 77 and 82%. CASE identified 13 major structural fragments associated with developmental toxicity in mice, 15 in rats, 9 in rabbits, and 7 in humans. These analyses indicate that there is indeed a structural basis for developmental toxicity which may be used to predict the developmental hazard of untested or inadequately tested chemicals.

Animals↗
PubMed1990

Clinical evaluation of an automatic sensitivity adjustment feature in a dual chamber pacemaker.

The clinical evaluation of a new automatic sensitivity adjustment feature in the Cosmos II, Model #284-05 is described. This feature, designed to maintain a 2:1 safety margin for sensing intrinsic signals, was activated by way of special programmer software in ten patients at two centers. While the feature worked satisfactorily in some cases, it did not perform as expected, and undersensing in both chambers was observed. This may have been due to biasing the adjustment toward maximum rather than minimum electrograms. This study suggested that electrograms may vary by more than 100% which underscores the importance of this feature, and reinforces the need for continued development.

Algorithms↗
PubMed1990

Activation times for "emergency back-up" programs.

A bench study was performed on 34 different pulse generators to evaluate the time necessary to actuate an "emergency back-up" (EBU) program. Pacemakers were programmed to loss of capture before the EBU was activated. Two pauses were measured that included the total pause from captured beat to captured beat and the time from the first pacing artifact showing loss of capture to the first captured beat resulting from EBU activation. Special features for threshold testing such as temporary pacing, auto threshold, Vario, and an alternating pulse ventricular threshold test were also evaluated. Activation times of the EBU ranged from 1.8 to 11.1 seconds with total pauses of 2.7 to 13.2 seconds, respectively. There were considerable variations in EBU times even within a single manufacturers' pulse generators. The special features for threshold testing resulted in pauses measuring 0.6 to 3.0 seconds with total pauses of 1.2 to 4.0 seconds, respectively, and in all cases were faster than using the EBU. Utilization of the EBU to regain capture during threshold testing in pacemaker dependent patients may result in prolonged pauses and syncope or near syncopal episodes.

Electrocardiography↗
PubMed1998

Prevalence of supraventricular arrhythmias from the automated analysis of data stored in the DDD pacemakers of 617 patients: the AIDA study. The AIDA Multicenter Study Group. Automatic Interpretation for Diagnosis Assistance.

The confirmation of the occurrence of supraventricular arrhythmias (SVAs) is possible only if a surface electrocardiogram (ECG) is recorded during an episode, or if SVAs occur during 24 h ambulatory monitoring (Holter). The automatic interpretation of memory functions in DDD pacemakers may be useful in this diagnostic task over longer periods of follow up. This hypothesis was tested in 384 men and 233 women (mean age = 70 +/- 11 years) who had received Chorus 6034/6035, 6234 or 7034 pacemakers (ELA Medical, Montrouge, France) with fall-back function in case of sustained SVAs. The Automatic Interpretation for Diagnostic Assistance (AIDA) algorithm included in these pacemakers was compared with 24 h Holters recorded simultaneously (D1) and with the clinical history of symptoms consistent with SVAs up to 28 days of follow up (D28). Indications for pacing were atrioventricular block (AVB) in 269 patients, sinus node dysfunction (SND) in 248, and AVB + SND in 100. SVAs were documented before implant in 199 patients (32%). Among the 617 patients included at D1, 76 (12.4%) developed at least one SVA episode, lasting between 1 min and 24 hours, simultaneously recorded on Holter and by AIDA with a 93.8% sensitivity and 94.2% specificity. Data from 354 patients were available for analysis at D28. AIDA diagnosed SVAs in 179 patients (50.6%), 104 of whom (65%) had remained asymptomatic and 117 of whom (65%) had had no SVA documented before implant. Among the 354 patients, AIDA diagnosed SVAs in 76 (21%) asymptomatic patients who had no known SVA before implant. The prevalence of SVA in our AVB population was higher than reported in previous studies: 89 patients (56.3%) with AVB had SVAs versus 90 patients (45.9%) with other diagnoses (p = 0.55). Furthermore atrial pacing was associated with fewer SVAs. These first clinical results of the AIDA study demonstrate that the memory functions of Chorus pacemakers and the AIDA software are reliable to analyze the prevalence of SVA at 1 month of follow-up. From a clinical point of view, AIDA is a valuable tool to evaluate the efficacy of antiarrhythmic therapy, particularly as it pertains to the prevention of stroke due to atrial fibrillation.

Aged↗
PubMed1996

A treadmill test of sprint running.

Anaerobic power is characterized by a high degree of specificity regarding both the recruited muscles as well as the recruitment pattern. The popular Wingate Anaerobic Test (WAnT) is a cycling test that does not satisfy the need for a running-specific anaerobic test. We describe such a test, using a novel type of a commercially available treadmill (BRL 1800, Gymrol, France). The ergometer is equipped with a torque motor to neutralize the frictional resistance of the treadmill belt, and a hip-belt harness connected to a horizontal rod. Force applied to the harness is monitored by a strain gauge mounted on the rod, while vertical movement is monitored by a potentiometer at the posterior fixed end of the rod. These, in conjunction with the treadmill belt speed, enable the computation of horizontal and vertical power as well as the combined total output. Power is calculated both as 'peak' power (highest 2.5 s segment) and 'mean' power (20 s duration). Preliminary results of young athletes were generally consistent with the expected age-related changes in anaerobic power. Values obtained on the anaerobic treadmill were always higher than the corresponding WAnT values previously obtained in comparable age groups. The higher values were probably due to the larger muscle mass involved and the shorter peak and mean power durations (2.5 and 20 s versus 5 and 30 s in the WAnT, respectively). This test should enable not only running-specific anaerobic power monitoring but also the characterization of the relationship between the horizontal and vertical components of that power.

Adolescent↗