Search

The work considers automatic sleep stage classification, based on heart rate variability (HRV) analysis, with a focus on the distinction of wakefulness (WAKE) from sleep and rapid eye movement (REM) from non-REM (NREM) sleep. A set of 20 automatically annotated one-night polysomnographic recordings was considered, and artificial neural networks were selected for classification. For each inter-heartbeat (RR) series, beside features previously presented in literature, we introduced a set of four parameters related to signal regularity. RR series of three different lengths were considered (corresponding to 2, 6, and 10 successive epochs, 30 s each, in the same sleep stage). Two sets of only four features captured 99 % of the data variance in each classification problem, and both of them contained one of the new regularity features proposed. The accuracy of classification for REM versus NREM (68.4 %, 2 epochs; 83.8 %, 10 epochs) was higher than when distinguishing WAKE versus SLEEP (67.6 %, 2 epochs; 71.3 %, 10 epochs). Also, the reliability parameter (Cohens's Kappa) was higher (0.68 and 0.45, respectively). Sleep staging classification based on HRV was still less precise than other staging methods, employing a larger variety of signals collected during polysomnographic studies. However, cheap and unobtrusive HRV-only sleep classification proved sufficiently precise for a wide range of applications.

Introduction: Measuring breathing effort during sleep with an oesophageal pressure sensor remains technically challenging and has not become routine practice. The aim of the present work was to investigate whether increased thoracic pressure during sleep can be detected with the Emfit movement sensor. Experimental data suggest that increased respiratory efforts with the intrathoracic pressure variation induce high-frequency spikes in the Emfit signal, but this has not been systematically examined., Methods: Polysomnography, oesophageal pressure and Emfit signal were recorded in 32 patients with suspected sleep-disordered breathing. Increased respiratory effort was defined as oesophageal pressure below -8 cmH(2)O during inspiration. The epochs of normal breathing, periodic breathing patterns and sustained spiking labelled as increased respiratory resistance (IRR) were defined on the Emfit signal according to established rules., Results: Compared to normal breathing, the proportion of increased respiratory effort was higher during all periodic breathing with spiking. The highest proportion (18-23%) occurred during IRR, which is characterised by sustained spiking., Conclusion: The Emfit movement sensor is a non-invasive alternative to the oesophageal pressure sensor in the assessment of the respiratory effort during sleep. In particular, the Emfit sensor enhances detection of non-apnoeic sleep-disordered breathing, the significance of which should not be ignored.

Sleep apnoea syndrome is common in the general population and is currently underdiagnosed. The aim of the present work was to develop a new tracheal sound feature for separation of apnoea events from non-apnoea time. Ten overnight recordings from apnoea patients containing 1,107 visually scored apnoea events totalling 7 h in duration and 72 h of non-apnoea time were included in the study. The feature was designed to describe the local spectral content of the sound signal. The median, maximum and mean smoothing of different time scales were compared in the feature extraction. The feature was designed to range from 0 to 1 irrespective of tracheal sound amplitudes. This constant range could offer application of the feature without patient-specific adjustments. The overall separation of feature values during apnoea events from non-apnoea time across all patients was good, reaching 80.8%. Due to the individual differences in tracheal sound signal amplitudes, developing amplitude-independent means for screening apnoea events is beneficial.

All-night EEG recordings from 12 male apnea patients and 12 age-matched healthy control subjects were studied in the present work. The spectral mean frequency was used to provide computational sleep depth curves from two frontopolar and two central EEG channels. Our previously presented computational parameters quantifying the properties of the sleep depth curves were improved. The resulting light sleep percentage (LS%) values were higher in apnea patients than in control subjects in the right central brain position (P = 0.028), in concordance to our previous work. Moreover, apnea patients showed higher LS% values in the right frontopolar position (P = 0.008). Also, apnea patients showed a smaller anteroposterior sleep depth difference than control subjects on the right hemisphere (P = 0.002). These are interesting new findings, achieved by the present methodology. Thus, the developed computational parameters were able to quantify, at least to some degree, the disruption of sleep process caused by the recurrent apneic events.

The objective of the present work was to develop automated methods for the compressed tracheal breathing sound analysis. Overnight tracheal breathing sound was recorded from ten apnoea patients. From each patient, three different types of tracheal sound deflection pattern, each of 10 min duration, were visually scored, viewing the compressed tracheal sound curve. Among them, high deflection patterns are of special interest due to the possible correlation with apnoea-hypopnoea sequences. Three methods were developed to detect patterns with high deflection, utilizing nonlinear filtering in local characterization of tracheal sounds. Method one comprises of local signal maximum, the second method of its local range, and the third of its relative range. The three methods provided 80% sensitivity with 57, 91 and 93% specificity, respectively. Method three provided an amplitude-independent approach. The nonlinear filtering based methods developed here offer effective means for analysing tracheal sounds of sleep-disordered breathing.

Two clinical trials are currently running at the Finnish dedicated boron neutron capture therapy (BNCT) facility. Between May 1999 and December 2001, 18 patients with supratentorial glioblastoma were treated with boronophenylalanine (BPA)-based BNCT within a context of a prospective clinical trial (protocol P-01). All patients underwent prior surgery, but none had received conventional radiotherapy or cancer chemotherapy before BNCT. BPA-fructose was given as 2-h infusion at BPA-dosages ranging from 290 to 400 mg/kg prior to neutron beam irradiation, which was given as a single fraction from two fields. The average planning target volume dose ranged from 30 to 61 Gy (W), and the average normal brain dose from 3 to 6 Gy (W). The treatment was generally well tolerated, and none of the patients have died during the first months following BNCT. The estimated 1-year overall survival is 61%. In another trial (protocol P-03), three patients with recurring or progressing glioblastoma following surgery and conventional cranial radiotherapy to 50-60 Gy, were treated with BPA-based BNCT using the BPA dosage of 290 mg/kg. The average planning target dose in these patients was 25-29 Gy (W), and the average whole brain dose 2-3 Gy (W). All three patients tolerated brain reirradiation with BNCT, and none died during the first three months following BNCT. We conclude that BPA-based BNCT has been relatively well tolerated both in previously irradiated and unirradiated glioblastoma patients. Efficacy comparisons with conventional photon radiation are difficult due to patient selection and confounding factors such as other treatments given, but the results support continuation of clinical research on BPA-based BNCT.