PubMed Health⌕ Search

Biomedical subjects

M Frize

Publications and source records attributed to M Frize.

15 recordsLinked to original sources
PubMed2001

Clinical decision support systems for intensive care units: using artificial neural networks.

The paper provides an overview of applications of artificial neural networks (ANNs) to various medical problems, with a particular focus on the intensive care unit environment (ICU). Several technical approaches were tested to see whether they improve the ANN performance in estimating medical outcomes and resource utilization in adult ICUs. These experiments include: (1) use of the weight-elimination cost function; (2) use of 'high' and 'low' nodes for input variables; (3) verifying the effect of the total number of input variables on the results; (4) testing the impact of the value of the constant predictor on the performance of the ANNs. The developments presented intend to help medical and nursing personnel to assess patient status, assist in making a diagnosis, and facilitate the selection of a course of therapy.

APACHE↗
PubMed2001

Influence of missing values on artificial neural network performance.

The problem of databases containing missing values is a common one in the medical environment. Researchers must find a way to incorporate the incomplete data into the data set to use those cases in their experiments. Artificial neural networks (ANNs) cannot interpret missing values, and when a database is highly skewed, ANNs have difficulty identifying the factors leading to a rare outcome. This study investigates the impact on ANN performance when predicting neonatal mortality of increasing the number of cases with missing values in the data sets. Although previous work using the Canadian Neonatal Intensive Care Unit (NICU) Network s database showed that the ANN could not correctly classify any patients who died when the missing values were replaced with normal or mean values, this problem did not arise as expected in this study. Instead, the ANN consistently performed better than the constant predictor (which classifies all cases as belonging to the outcome with the highest training set a priori probability) with a 0.6-1.3% improvement over the constant predictor. The sensitivity of the models ranged from 14.5-20.3% and the specificity ranged from 99.2- 99.7%. These results indicate that nearly 1 in 5 babies who will eventually die are correctly classified by the ANN, and very few babies were incorrectly identified as patients who will die. These findings are important for patient care, counselling of parents and resource allocation.

Decision Support Systems, Clinical↗
PubMed2000

Clinical decision-support systems for intensive care units using case-based reasoning.

The artificial intelligence approach used in this work focusses on case-based reasoning techniques for the estimation of medical outcomes and resource utilization. The systems were designed with a view to help medical and nursing personnel to assess patient status, assist in making a diagnosis, and facilitate the selection of a course of therapy. The initial prototype provided information on the closest-matching patient cases to the newest patient admission in an adult intensive care unit (ICU). The system was subsequently re-designed for use in a neonatal ICU. The results of a short clinical pilot evaluation performed in both adult and neonatal units are reported and have led to substantial improvement of the prototype. Future work will include longer-term clinical trials for both adult and neonatal ICUs, once all the software changes have been made to both prototypes in response to the comments of the users made during the preliminary evaluations. To date, the results are very encouraging and physician interest in the potential clinical usefulness of these two systems remains high, and particularly so in the new testing environment in Ottawa.

Adult↗
PubMed2000

Decision-support and intelligent tutoring systems in medical education.

One of the challenges in medical education is to teach the decision-making process. This learning process varies according to the experience of the student and can be supported by various tools. In this paper we present several approaches that can strengthen this mechanism, from decision-support tools, such as scoring systems, Bayesian models, neural networks, to cognitive models that can reproduce how the students progressively build their knowledge into memory and foster pedagogic methods.

Artificial Intelligence↗
PubMed2000

Selective sampling to overcome skewed a priori probabilities with neural networks.

Highly skewed a priori probabilities present challenges for researchers developing medical decision aids due to a lack of information on the rare outcome of interest. This paper attempts to overcome this obstacle by artificially increasing the mortality rate of the training sets. A weight pruning technique called weight-elimination is also applied to this coronary artery bypass grafting (CABG) database to assess its impact on the artificial neural network's (ANN) performance. The results showed that increasing the mortality rate improved the sensitivity rates at the cost of the other performance measures, and the weight-elimination cost function improved the sensitivity rate without seriously affecting the other performance measures.

Algorithms↗
PubMed1998

New advances and validation of knowledge management tools for critical care using classifier techniques.

An earlier version (2.0) of the case-based reasoning (CBR) tool, called IDEAS for ICU's, allowed users to compare the ten closest matching cases to the newest patient admission, using a large database of intensive care patient records, and physician-selected matching-weights [1,2]. The new version incorporates matching-weights, which have been determined quantitatively. A faster CBR matching engine has also been incorporated into the new CBR. In a second approach, a back-propagation, feed-forward artificial neural network estimated two classes of the outcome "duration of artificial ventilation" for a subset of the database used for the CBR work. Weight-elimination was successfully applied to reduce the number of input variables and speed-up the estimation of outcomes. New experiments examined the impact of using a different number of input variables on the performance of the ANN, measured by correct classification rates (CCR) and the Average Squared Error (ASE).

Critical Care↗
PubMed1995

Computer-assisted decision support systems for patient management in an intensive care unit.

The application of the intelligent monitoring techniques of case-based reasoning and neural network analysis to physician decision making concerning patient care in an Intensive Car Unit (ICU) is described. Case-based reasoning offers a model for quickly matching--using a predetermined hierarchical structure--a single patient's parameters (text or numeric) to similar parameters contained in a clinical database. The output produces a group of patients which may be set to match exactly on certain characteristics and may also be set to match "as closely as possible" on a gradient of patient properties. Clinicians may thus use the system to find the group of the closest matching cases to their current patient. Aspects of the ICU history of the selected group may then be displayed graphically (e.g., mortality, length of stay, hours of ventilation, procedures utilized, and complications encountered). Neural network analysis is a pattern recognition technique which uses a training set of patient data (text or numeric) to seek mathematical relationships between various subsets of patient parameters. The discovered relationships from the training set are then applied to estimate the outcomes (e.g., mortality, length of stay, hours of ventilation) of new patients. The effects of these intelligent monitoring techniques are scheduled to be tested in a field trial held in a regional referral center ICU.

Algorithms↗
PubMed1991

Clinical engineering in today's hospital: perspectives of the administrator and the clinical engineer.

In 1987-88, the first of two surveys conducted questioned the administrator's viewpoint on choice of reporting authority for plant operations and clinical engineering departments as well as the job satisfaction and prestige associated with these responsibilities. The second tested the response of clinical engineers on similar issues as well as the effect of certain organizational factors on their degree of functional involvement in the equipment-management process. In the first survey, two-thirds of the administrators chose a structure that, as shown in the second survey, leads to a higher degree of involvement and satisfaction for clinical engineers. Other organizational factors that have an effect are: the type of hospital (teaching and nonteaching), the presence of qualified university-degree engineers, and ensuring that the clinical engineering role within the health care institution is recognized and supported. Teaching hospitals are found to provide a better climate than nonteaching ones for the support of the research and education activities. Clinical engineering departments, whose role has been recognized and supported by their institution, are more substantially involved in all aspects of the equipment-management process than those who are still seeking this recognition. Finally, departments where university-degree engineers have been hired again show more involvement and commitment to the quality and efficiency of their operation.

Attitude of Health Personnel↗
PubMed1991

Oxytocin augmentation of labor and perinatal outcome in nulliparas.

Recent pharmacologic observations in vivo suggest the use of a lower starting dose (0.5-0.1 mU/minute) of oxytocin and a longer interval between dose augmentations (30-60 minutes) than previously advocated. In this study, a high-dose oxytocin protocol was used to augment nonprogressive labor in normal nulliparous women. The rate of oxytocin infusion started at 6 mU/minute and was increased by 6 mU/minute every 15 minutes to a maximum dose of 40 mU/minute. Charts were reviewed of 1080 nulliparous women for whom the principles of active management of labor were followed and delivery occurred between March 1, 1986 and December 31, 1988. Four hundred fifty-six who required oxytocin augmentation in labor were compared with 624 who did not receive oxytocin. There were no statistically significant differences in birth asphyxia or perinatal morbidity.

Female↗