Biomedical subjects

M Revow

Publications and source records attributed to M Revow.

5 recordsLinked to original sources

PubMed2000

Honest assessments of automatic learning algorithm performance.

OBJECTIVE: To compare methods of evaluating probabilistic predictors in systems that learn from examples. STUDY DESIGN: The performance of four automatic learning algorithms, representing current machine learning technology, were assessed using four methodologies in the task of separating normal squamous intermediate cervical cells from all other segmented objects in digital images. Two of the methodologies were carefully constructed to model sources of variation associated with the choice of training and test sets. These assessments were statistically compared with assessments using both standard and a modified version of cross-validation. RESULTS: The investigation illustrates the tradeoffs involved in obtaining statistical rigor as compared with the cost of collecting data. While cross-validation makes frugal use of data, it can produce misleading assessments of algorithm performance in terms of both bias and variance. The modified version produces more reliable assessments but in some cases may also be misleading. CONCLUSION: We suggest that users of learning algorithms should exercise judicious care in evaluating learning algorithm performance in order to avoid unnecessary bias and large variance in their assessments.

Algorithms↗

PubMed1998

A comparison of statistical learning methods on the Gusto database.

We apply a battery of modern, adaptive non-linear learning methods to a large real database of cardiac patient data. We use each method to predict 30 day mortality from a large number of potential risk factors, and we compare their performances. We find that none of the methods could outperform a relatively simple logistic regression model previously developed for this problem.

Databases as Topic↗

PubMed1989

Expiratory airflow patterns and gas exchange in the newborn infant: results of model simulations.

A mathematical model simulating the newborn human infant's respiratory system was used to study the effects on gas exchange of varying expiratory airflow pattern and end expiratory lung volume (FRC). Inspiratory flow was modelled as a square wave and was constant for all simulations as were inspiratory and expiratory times. Expiratory airflow was also modelled as a square wave and was varied between 21 and 75 ml/sec with FRC held constant at either 30.2 or 21.2 ml/kg for each simulation. At a given FRC, expiratory airflow pattern had only a trivial effect on blood gases in the steady state. Comparing the extreme cases, fast expiration (75 ml/sec) at low FRC (21.1 ml/kg) with slow expiration (21 ml/sec) at high FRC (30.2 ml/kg), arterial PO2 was 3.8 mm Hg higher and arterial PCO2 1.0 mm Hg lower under the latter conditions. However, when short apneas were imposed, blood gases deteriorated less precipitously following the slow expiration at high FRC. We conclude that expiratory airflow retardation and the resultant elevation in end expiratory lung volume do not greatly enhance gas exchange in the healthy full term infant. However, mechanisms which slow expiratory airflow do provide a buffer for gas exchange during the short apneas often observed in infants.

Apnea↗

PubMed1989

A model of the maturation of respiratory control in the newborn infant.

A model of automatic neonatal respiratory control has been constructed as an aid in the investigation of a possible maturation in respiratory control loops during the newborn period. The primary objective was to provide a framework for investigating this hypothesis without the need for external stimuli or invasive measurements. Spontaneous sighs provide a physiological disturbance to the respiratory system by transiently altering the levels of the blood gases. The dynamic ventilatory response following such a disturbance was modeled. A change from a highly damped to less damped pattern was found when model parameter values were varied to mimic maturation in the neonatal period. A perturbation model analysis demonstrated the dynamic ventilatory response is most sensitive to factors affecting the gain of the peripheral chemoreflex loop. It is concluded that the model provides valuable insight into the hypothesis that the peripheral chemoreflex matures during the neonatal period and provides a viable method for testing this in the human infant.

Humans↗

PubMed1987

Evaluation of respiratory inductive plethysmography in infants weighing less than 1,500 grams.

Calibration of the respiratory inductive plethysmograph (RIP) was performed in premature infants weighing less than 1,500 g. In only 25% of the studies was an acceptable calibration achieved, as assessed by statistical comparison of simultaneously measured pneumotachygraph and RIP tidal volumes. In 6 infants, dead space loading or air injection was performed in an attempt to alter abdominal and rib cage volume contributions and thereby improve the calibration. Neither of these maneuvers resulted in an improvement of the accuracy of the RIP calibration coefficient. We conclude that, when calibrated by the least squares technique, the reliability of inductive plethysmography in measuring tidal volume in small infants is low. This is presumably because they have very small tidal volumes and highly compliant rib cages.

Female↗