Speech patterns are modulated by the emotional and neurophysiological state of the speaker. There exists a growing body of work that computationally examines this modulation in patients suffering from depression, autism, and post-traumatic stress disorder. However, the majority of the work in this area focuses on the analysis of structured speech collected in controlled environments. Here we expand on the existing literature by examining bipolar disorder (BP). BP is characterized by mood transitions, varying from a healthy euthymic state to states characterized by mania or depression. The speech patterns associated with these mood states provide a unique opportunity to study the modulations characteristic of mood variation. We describe methodology to collect unstructured speech continuously and unobtrusively via the recording of day-to-day cellular phone conversations. Our pilot investigation suggests that manic and depressive mood states can be recognized from this speech data, providing new insight into the feasibility of unobtrusive, unstructured, and continuous speech-based wellness monitoring for individuals with BP.

No abstract

No abstract

The accurate and early detection of epileptic seizures in continuous electroencephalographic (EEG) data has a growing role in the management of patients with epilepsy. Early detection allows for therapy to be delivered at the start of seizures and for caregivers to be notified promptly about potentially debilitating events. The challenge to detecting epileptic seizures, however, is that seizure morphologies exhibit considerable inter-patient and intrapatient variability. While recent work has looked at addressing the issue of variations across different patients (inter-patient variability) and described patient-specific methodologies for seizure detection, there are no examples of systems that can simultaneously address the challenges of inter-patient and intra-patient variations in seizure morphology. In our study, we address this complete goal and describe a multi-task learning approach that trains a classifier to perform well across many kinds of seizures rather than potentially overfitting to the most common seizure types. Our approach increases the generalizability of seizure detection systems and improves the tradeoff between latency and sensitivity versus false positive rates. When compared against the standard approach on the CHB-MIT multi-channel scalp EEG data, our proposed method improved discrimination between seizure and non-seizure EEG for almost 83 % of the patients while reducing false positives on nearly 70 % of the patients studied.

No abstract