INTRODUCTION: Children with Down Syndrome (DS) are at high risk of sleep disordered breathing (SDB). We aimed to examine the burden of SDB in infants with DS referred to tertiary sleep center. METHODS: Infants (≤12 months old) with DS who underwent consecutive polysomnography (PSG) at a single academic sleep center over a 6-year period were included. obstructive sleep apnea (OSA) (obstructive apnea hypopnea index [oAHI]>1/hr), central sleep apnea (central apnea index > 5/h) and the presence of hypoventilation (% time spent with CO2  > 50 mmHg either by end-tidal or transcutaneous> 25% of total sleep time) and hypoxemia (time spent with O2 saturation <88% >5 min) were ascertained. RESULTS: A total of 40 infants were included (Mean age 6.6 months, male 66%). PSGs consisted of diagnostic (n = 13) and split night (n = 27, 68%) studies. All met criteria for OSA with mean oAHI 34.6/h (32.3). Central sleep apnea was present in 11 (27.5%) of infants. A total of 11 (27.5%) had hypoxemia. Hypoventilation was present in 10 (25%) infants. CONCLUSION: This study highlights the high prevalence of SDB in infants with DS referred to a sleep center, and supports early PSG assessment in this patient population.

Background

Accurately assessing pain for those who cannot make self-report of pain, such as minimally responsive or severely brain-injured patients, is challenging. In this paper, we attempted to address this challenge by answering the following questions: (1) if the pain has dependency structures in electronic signals and if so, (2) how to apply this pattern in predicting the state of pain. To this end, we have been investigating and comparing the performance of several machine learning techniques.

Methods

We first adopted different strategies, in which the collected original n-dimensional numerical data were converted into binary data. Pain states are represented in binary format and bound with above binary features to construct (n + 1) -dimensional data. We then modeled the joint distribution over all variables in this data using the Restricted Boltzmann Machine (RBM).

Results

Seventy-eight pain data items were collected. Four individuals with the number of recorded labels larger than 1000 were used in the experiment. Number of avaliable data items for the four patients varied from 22 to 28. Discriminant RBM achieved better accuracy in all four experiments.

Conclusion

The experimental results show that RBM models the distribution of our binary pain data well. We showed that discriminant RBM can be used in a classification task, and the initial result is advantageous over other classifiers such as support vector machine (SVM) using PCA representation and the LDA discriminant method.