Search

A neuro-fuzzy classifier (NFC) of sleep-wake states and stages has been developed for healthy infants of ages 6 mo and onward. The NFC takes five input patterns previously identified on 20-s epochs from polysomnographic recordings and assigns them to one out of five possible classes: Wakefulness, REM-Sleep, Non-REM Sleep Stage 1, Stage 2, and Stage 3-4. The definite criterion for a sleep state or stage to be established is duration of at least 1 rein. The data set consisted of a total of 14 continuous recordings of naturally occurring naps (average duration: 143 [+ or -] 39 min), corresponding to a total of 6021 epochs. They were divided in a training, a validation and a test set with 7, 2, and 5 recordings, respectively. During supervised training, the system determined the fuzzy concepts associated to the inputs and the rules required for performing the classification, extracting knowledge from the training set, and pruning nonrelevant rules. Results on an independent test set achieved 83.9 [+ or -] 0.4% of expert agreement. The fuzzy rules obtained from the training examples without a priori information showed a high level of coincidence with the crisp rules stated by the experts, which are based on internationally accepted criteria. These results show that the NFC can be a valuable tool for implementing an automated sleep-wake classification system. Index Terms--ANFIS, fuzzy rule extraction, knowledge discovery, neural nets and expert systems, rule pruning, sleep classification.

A rule-based system was designed to control the mean arterial pressure (MAP) and the cardiac output (CO) of a patient with congestive heart failure (CHF), using two vasoactive drugs: sodium nitroprusside (SNP) and dopamine (DPM). The controller has three different modes, that engage according to the hemodynamic state. The critical conditions control mode (CCC) determines the initial infusion rates, and continues active if the MAP or the CO fall outside of the defined criticality thresholds: an upper and a lower boundary for the MAP and a lower boundary for the CO. Inside the boundaries the control is performed by noncritical conditions control modes (NCC's), which are fuzzy logic controllers. If the CO is within normal range and the MAP is close to the goal range, then the MAP is driven using only SNP, in a single-input--single-output mode (NCC-SISO). Otherwise the NCC multiple-input--multiple-output is active (NCC-MIMO). The goal values for the controlled variables are defined as a band of 5 mmHg for the MAP and 5 mL/kg/min for the CO, but there is little concern for this application if the CO is too high (i.e., in practical terms the CO only needs to achieve a necessary minimum rate). The NCC-MIMO includes a gain adaptation algorithm to cope with the wide variety in sensitivities to SNP. Supervisory capabilities to ensure adequate drug delivery complete the controller scheme. After extensive testing and tuning on a CHF-hemodynamics nonlinear model, the control system was applied in dog experiments, which led to further enhancements. The results show an adequate control, presenting a fast response to setpoint changes with an acceptable overshoot. Index Terms--Congestive heart failure, fuzzy logic, hemodynamic management, multiple mode control, vasoactive drug infusions.

Sleep spindles (SSs) are characteristic electroencephalographic (EEG) waveforms of sleep stages N2 and N3. One of the main problems associated with SS detection is the high number of false positives. In this paper we propose a new periodogram based on correntropy to detect SSs and enhance their characterization. Correntropy is a generalized correlation, under the information theoretic learning framework. A non-negative matrix factorization decomposition of correntropy allows us to obtain a new periodogram, which shows an improved resolution capability compared to the conventional power spectrum density. Preliminary results show that the proposed method obtained a sensitivity rate of 0.868 with a false positive rate of 0.121.

A methodology to detect sleep apnea/hypopnea events in the respiratory signals of polysomnographic recordings is presented. It applies empirical mode decomposition (EMD), Hilbert-Huang transform (HHT), fuzzy logic and signal preprocessing techniques for feature extraction, expert criteria and context analysis. EMD, HHT and fuzzy logic are used for artifact detection and preliminary detection of respiration signal zones with significant variations in the amplitude of the signal; feature extraction, expert criteria and context analysis are used to characterize and validate the respiratory events. An annotated database of 30 all-night polysomnographic recordings, acquired from 30 healthy ten-year-old children, was divided in a training set of 15 recordings (485 sleep apnea/hypopnea events), a validation set of five recordings (109 sleep apnea/hypopnea events), and a testing set of ten recordings (281 sleep apnea/hypopnea events). The overall detection performance on the testing data set was 89.7% sensitivity and 16.3% false-positive rate. The next step is to include discrimination among apneas, hypopneas and respiratory pauses.

We present an automated multiple-step tool to identify Rapid Eye Movements (REMs) in the polysomnogram, based on modeling expert criteria. It begins by identifying the polysomnogram segments compatible with REMs presence. On these segments, high-energy REMs are identified. Then, vicinity zones around those REMs are defined, and lesser-energy REMs are sought in these vicinities. This strategy has the advantage that it can detect lesser-energy REMs without increasing much the false positive detections. Signal processing, feature extraction, and fuzzy logic tools are used to achieve the goal. The tool was trained and validated on a database consisting of 20 all-night polysomnogram recordings (160 hr) of healthy ten-year-old children. Preliminary results on the validation set show 85.5% sensitivity and a false positive rate of 16.2%. Our tool works on complete polysomnogram recordings, without the need of preprocessing, prior knowledge of the hypnogram, or noise-free segments selection.

An automated system for sleep spindles detection within EEG background activity, combining two different approaches, is presented. The first approach applies detection criteria on the sigma-band filtered EEG signal, including fuzzy thresholds. The second approach mimics an expert's procedure. A sleep spindle detection is validated if both approaches agree. The method was applied on a testing set, consisting of continuous sleep recordings of two patients, totaling 1132 epochs (pages). A total of 803 sleep spindles events were marked by the experts. Results showed an 87.7% agreement between the detection system and the medical experts.