Biomedical subjects

Terrence Sejnowski

Publications and source records attributed to Terrence Sejnowski.

5 recordsLinked to original sources

PubMed2004

Using unsupervised learning with variational bayesian mixture of factor analysis to identify patterns of glaucomatous visual field defects.

PURPOSE: To determine whether an unsupervised machine learning classifier can identify patterns of visual field loss in standard visual fields consistent with typical patterns learned by decades of human experience. METHODS: Standard perimetry thresholds for 52 locations plus age from one eye of each of 156 patients with glaucomatous optic neuropathy (GON) and 189 eyes of healthy subjects were clustered with an unsupervised machine classifier, variational Bayesian mixture of factor analysis (vbMFA). RESULTS: The vbMFA formed five distinct clusters. Cluster 5 held 186 of 189 fields from normal eyes plus 46 from eyes with GON. These fields were then judged within normal limits by several traditional methods. Each of the other four clusters could be described by the pattern of loss found within it. Cluster 1 (71 GON + 3 normal optic discs) included early, localized defects. A purely diffuse component was rare. Cluster 2 (26 GON) exhibited primarily deep superior hemifield defects, and cluster 3 (10 GON) held deep inferior hemifield defects only or in combination with lesser superior field defects. Cluster 4 (6 GON) showed deep defects in both hemifields. In other words, visual fields within a given cluster had similar patterns of loss that differed from the predominant pattern found in other clusters. The classifier separated the data based solely on the patterns of loss within the fields, without being guided by the diagnosis, placing 98.4% of the healthy eyes within the same cluster and spreading 70.5% of the eyes with GON across the other four clusters, in good agreement with a glaucoma expert and pattern standard deviation. CONCLUSIONS: Without training-based diagnosis (unsupervised learning), the vbMFA identified four important patterns of field loss in eyes with GON in a manner consistent with years of clinical experience.

Algorithms↗

PubMed2003

The computational self.

Your brain is never at rest. Shifting patterns of activity course through your brain at night as you review the events of the day and plan the next day before falling asleep. Rumination is a reflection of the Self that is not directly driven by sensory stimuli. When we record from single neurons in the brain, we discover that even in the absence of sensory stimulation, neurons are continuously active. This is called maintained, or spontaneous, activity, and although it is well documented, it has not been as well studied. Most experiments are designed to look for signals that are elicited by sensory stimuli above the background, without mentioning whether the background has changed too, as it often does. New methods have been developed recently that allow us to study the brain's spontaneous activity and to explore how it might provide clues to the origin and nature of the Self.

Animals↗

PubMed2002

Cortical hyperpolarization-activated depolarizing current takes part in the generation of focal paroxysmal activities.

During paroxysmal neocortical oscillations, sudden depolarization leading to the next cycle occurs when the majority of cortical neurons are hyperpolarized. Both the Ca(2+)-dependent K(+) currents (I(K(Ca))) and disfacilitation play critical roles in the generation of hyperpolarizing potentials. In vivo experiments and computational models are used here to investigate whether the hyperpolarization-activated depolarizing current (I(h)) in cortical neurons also contributes to the generation of paroxysmal onsets. Hyperpolarizing current pulses revealed a depolarizing sag in approximately 20% of cortical neurons. Intracellular recordings from glial cells indirectly indicated an increase in extracellular potassium concentration ([K(+)](o)) during paroxysmal activities, leading to a positive shift in the reversal potential of K(+)-mediated currents, including I(h). In the paroxysmal neocortex, approximately 20% of neurons show repolarizing potentials originating from hyperpolarizations associated with depth-electroencephalogram positive waves of spike-wave complexes. The onset of these repolarizing potentials corresponds to maximal [K(+)](o) as estimated from dual simultaneous impalements from neurons and glial cells. Computational models showed how, after the increased [K(+)](o), the interplay between I(h), I(K(Ca)), and a persistent Na(+) current, I(Na(P)), could organize paroxysmal oscillations at a frequency of 2-3 Hz.

Animals↗

PubMed2002

Comparing machine learning classifiers for diagnosing glaucoma from standard automated perimetry.

PURPOSE: To determine which machine learning classifier learns best to interpret standard automated perimetry (SAP) and to compare the best of the machine classifiers with the global indices of STATPAC 2 and with experts in glaucoma. METHODS: Multilayer perceptrons (MLP), support vector machines (SVM), mixture of Gaussian (MoG), and mixture of generalized Gaussian (MGG) classifiers were trained and tested by cross validation on the numerical plot of absolute sensitivity plus age of 189 normal eyes and 156 glaucomatous eyes, designated as such by the appearance of the optic nerve. The authors compared performance of these classifiers with the global indices of STATPAC, using the area under the ROC curve. Two human experts were judged against the machine classifiers and the global indices by plotting their sensitivity-specificity pairs. RESULTS: MoG had the greatest area under the ROC curve of the machine classifiers. Pattern SD (PSD) and corrected PSD (CPSD) had the largest areas under the curve of the global indices. MoG had significantly greater ROC area than PSD and CPSD. Human experts were not better at classifying visual fields than the machine classifiers or the global indices. CONCLUSIONS: MoG, using the entire visual field and age for input, interpreted SAP better than the global indices of STATPAC. Machine classifiers may augment the global indices of STATPAC.

Diagnosis, Computer-Assisted↗

PubMed2002

Using machine learning classifiers to identify glaucomatous change earlier in standard visual fields.

PURPOSE: To compare the ability of several machine learning classifiers to predict development of abnormal fields at follow-up in ocular hypertensive (OHT) eyes that had normal visual fields in baseline examination. METHODS: The visual fields of 114 eyes of 114 patients with OHT with four or more visual field tests with standard automated perimetry over three or more years and for whom stereophotographs were available were assessed. The mean (+/-SD) number of visual field tests was 7.89 +/- 3.04. The mean number of years covered (+/-SD) was 5.92 +/- 2.34 (range, 2.81-11.77). Fields were classified as normal or abnormal based on Statpac-like methods (Humphrey Instruments, Dublin, CA) and by several machine learning classifiers. The machine learning classifiers were two types of support vector machine (SVM), a mixture of Gaussian (MoG) classifier, a constrained MoG, and a mixture of generalized Gaussian (MGG). Specificity was set to 96% for all classifiers, using data from 94 normal eyes evaluated longitudinally. Specificity cutoffs required confirmation of abnormality. RESULTS: Thirty-two percent (36/114) of the eyes converted to abnormal fields during follow-up based on the Statpac-like methods. All 36 were identified by at least one machine classifier. In nearly all cases, the machine learning classifiers predicted the confirmed abnormality, on average, 3.92 +/- 0.55 years earlier than traditional Statpac-like methods. CONCLUSIONS: Machine learning classifiers can learn complex patterns and trends in data and adapt to create a decision surface without the constraints imposed by statistical classifiers. This adaptation allowed the machine learning classifiers to identify abnormality in visual field converts much earlier than the traditional methods.

Algorithms↗