No abstract

No abstract

Morquio syndrome is a rare disease caused by a disorder in the storage of mucopolysaccharides that affects multiple organs, including musculoskeletal, respiratory, cardiovascular, and digestive systems. Respiratory failure is one of the leading causes of mortality in Morquio patients; thus, respiratory function testing is vital to the management of the disease. An automated respiratory assessment methodology using the pneuRIP device and a machine-learning algorithm was developed. pneuRIP is a noninvasive approach that uses differences between thoracic and abdominal movements (thoracic-abdominal asynchrony) during respiration to assess respiratory status. The technique was evaluated on 17 patients with Morquio (9 females and 8 males) between the ages of 2 and 57 years. The results of the automated technique agreed with the clinical assessment in 16 out of the 17 patients. It was found that the inverse cumulative percentage representation of the time delay between the thorax and abdomen was the most critical variable for accurate evaluation. It was demonstrated that the technique could be successfully used on patients with Morquio who have difficulty breathing with 100% compliance. This technique is highly accurate, portable, noninvasive, and easy to administer, making it suitable for a variety of settings, such as outpatient clinics, at home, and emergency rooms.

No abstract

Speech delay is a childhood language problem that might resolve without intervention, but might alternatively presage continued speech and language deficits. Thus, early detection through screening might help to identify children for whom intervention is warranted. The goal of this work is to develop Automatic Speech Recognition (ASR) methods to partially automate screening for speech delay in young children. Speech data were recorded from typically developing and speech delayed children (N = 63) aged 6 to 9 years old during administration of the Goldman Fristoe Test of Articulation (GFTA). Monophone Hidden Markov Model (HMM) acoustic models were trained on speech data obtained from 207 typically developing children in the same age range. These training data consisted of a total of about 18,000 single-word utterances. The HMMs were then used to develop an utterance verification system to distinguish correct versus error productions. Several variations of the recognition strategy, feature extraction, and scoring methods were investigated. The best overall ASR result for distinguishing normal versus abnormal speech is approximately 86%. It is hypothesized that the ASR methods could approach the level of accuracy of speech therapists for this task (agreement among multiple therapists is over 95%), but a much larger database may be needed.