Online Deterministic Annealing for Classification and Clustering.

Inherent in virtually every iterative machine learning algorithm is the problem of hyperparameter tuning, which includes three major design parameters: 1) the complexity of the model, e.g., the number of neurons in a neural network; 2) the initial conditions, which heavily affect the behavior of the algorithm; and 3) the dissimilarity measure used to quantify its performance. We introduce an online prototype-based learning algorithm that can be viewed as a progressively growing competitive-learning neural network architecture for classification and clustering. The learning rule of the proposed approach is formulated as an online gradient-free stochastic approximation algorithm that solves a sequence of appropriately defined optimization problems, simulating an annealing process. The annealing nature of the algorithm contributes to avoiding poor local minima, offers robustness with respect to the initial conditions, and provides a means to progressively increase the complexity of the learning model, through an intuitive bifurcation phenomenon. The proposed approach is interpretable, requires minimal hyperparameter tuning, and allows online control over the performance-complexity tradeoff. Finally, we show that Bregman divergences appear naturally as a family of dissimilarity measures that play a central role in both the performance and the computational complexity of the learning algorithm.

Voice Interface Technology Adoption by Patients With Heart Failure: Pilot Comparison Study.

BACKGROUND: Heart failure (HF) is associated with high mortality rates and high costs, and self-care is crucial in the management of the condition. Telehealth can promote patients' self-care while providing frequent feedback to their health care providers about the patient's compliance and symptoms. A number of technologies have been considered in the literature to facilitate telehealth in patients with HF. An important factor in the adoption of these technologies is their ease of use. Conversational agent technologies using a voice interface can be a good option because they use speech recognition to communicate with patients. OBJECTIVE: The aim of this paper is to study the engagement of patients with HF with voice interface technology. In particular, we investigate which patient characteristics are linked to increased technology use. METHODS: We used data from two separate HF patient groups that used different telehealth technologies over a 90-day period. Each group used a different type of voice interface; however, the scripts followed by the two technologies were identical. One technology was based on Amazon's Alexa (Alexa+), and in the other technology, patients used a tablet to interact with a visually animated and voice-enabled avatar (Avatar). Patient engagement was measured as the number of days on which the patients used the technology during the study period. We used multiple linear regression to model engagement with the technology based on patients' demographic and clinical characteristics and past technology use. RESULTS: In both populations, the patients were predominantly male and Black, had an average age of 55 years, and had HF for an average of 7 years. The only patient characteristic that was statistically different (P=.008) between the two populations was the number of medications they took to manage HF, with a mean of 8.7 (SD 4.0) for Alexa+ and 5.8 (SD 3.4) for Avatar patients. The regression model on the combined population shows that older patients used the technology more frequently (an additional 1.19 days of use for each additional year of age; P=.004). The number of medications to manage HF was negatively associated with use (-5.49; P=.005), and Black patients used the technology less frequently than other patients with similar characteristics (-15.96; P=.08). CONCLUSIONS: Older patients' higher engagement with telehealth is consistent with findings from previous studies, confirming the acceptability of technology in this subset of patients with HF. However, we also found that a higher number of HF medications, which may be correlated with a higher disease burden, is negatively associated with telehealth use. Finally, the lower engagement of Black patients highlights the need for further study to identify the reasons behind this lower engagement, including the possible role of social determinants of health, and potentially create technologies that are better tailored for this population.

Modeling the Role of the Glymphatic Pathway and Cerebral Blood Vessel Properties in Alzheimer's Disease Pathogenesis.

Alzheimer's disease (AD) is the most common cause of dementia in the elderly, affecting over 10% population over the age of 65 years. Clinically, AD is described by the symptom set of short term memory loss and cognitive decline, changes in mentation and behavior, and eventually long-term memory deficit as the disease progresses. On imaging studies, significant atrophy with subsequent increase in ventricular volume have been observed. Pathology on post-mortem brain specimens demonstrates the classic findings of increased beta amyloid (Aß) deposition and the presence of neurofibrillary tangles (NFTs) within affected neurons. Neuroinflammation, dysregulation of blood-brain barrier transport and clearance, deposition of Aß in cerebral blood vessels, vascular risk factors such as atherosclerosis and diabetes, and the presence of the apolipoprotein E4 allele have all been identified as playing possible roles in AD pathogenesis. Recent research has demonstrated the importance of the glymphatic system in the clearance of Aß from the brain via the perivascular space surrounding cerebral blood vessels. Given the variety of hypotheses that have been proposed for AD pathogenesis, an interconnected, multilayer model offers a unique opportunity to combine these ideas into a single unifying model. Results of this model demonstrate the importance of vessel stiffness and heart rate in maintaining adequate clearance of Aß from the brain.

Studying the role of ApoE in Alzheimer's disease pathogenesis using a systems biology model.

Alzheimer's disease (AD) is the most common form of dementia. Even with its well-known symptoms of memory loss and well-characterized pathology of beta amyloid (Aß) plaques and neurofibrillary tangles, the disease pathogenesis and initiating factors are still not well understood. To tackle this problem, a systems biology model has been developed and used to study the varying effects of variations in the ApoE allele present, as well as the effects of short term and periodic inflammation at low to moderate levels. Simulations showed a late onset peak of Aß in the ApoE4 case that lead to localized neuron loss which could be ameliorated in part by application of short-term pro-inflammatory mediators. The model that has been developed herein represents one of the first attempts to model AD from a systems approach to study physiologically relevant parameters that may prove useful to physicians in the future.

Securing the communication of medical information using local biometric authentication and commercial wireless links.

Medical information is extremely sensitive in nature - a compromise, such as eavesdropping or tampering by a malicious third party, may result in identity theft, incorrect diagnosis and treatment, and even death. Therefore, it is important to secure the transfer of medical information from the patient to the recording system. We consider a portable, wireless device transferring medical information to a remote server. We decompose this problem into two sub-problems and propose security solutions to each of them: (1) to secure the link between the patient and the portable device, and (2) to secure the link between the portable device and the network. Thus we push the limits of the network security to the edge by authenticating the user using their biometric information; authenticating the device to the network at the physical layer; and strengthening the security of the wireless link with a key exchange mechanism. The proposed authentication methods can be used for recording the readings of medical data in a central database and for accessing medical records in various settings.