Designing explainable and personalized AI systems to provide support to older adults aging in place requires an understanding of their motivations and expectations for the explanations. This poster presents our ongoing work in exploring explanation preferences within AI systems for older adults aging in place with their carepartners. We do so by leveraging the speculative and iterative benefits of the Research through Design (RtD) approach in HCI, and explore variations in explanation requirements for different users by understanding their needs, goals and motivations for the different sources of information within the home. We illustrate an example for employing a Research through Design inquiry for the design of AI applications, adopting speculative methods to probe into future possibilities of Explainable AI (XAI) using a human-centered design framework. Through a Speed Dating study and a Co-Design activity, we investigate different explanation types and scenarios and argue for a shift in the algorithmic focus of Explainable AI research toward user-centered requirements, positioning explanation as a collaborative process between AI systems and users.

As the permeability of AI systems in interpersonal domains like the home expands, their technical capabilities of generating explanations are required to be aligned with user expectations for transparency and reasoning. This paper presents insights from our ongoing work in understanding the effectiveness of explanations in Conversational AI systems for older adults aging in place and their family caregivers. We argue that in collaborative and multi-user environments like the home, AI systems will make recommendations based on a host of information sources to generate explanations. These sources may be more or less salient based on user mental models of the system and the specific task. We highlight the need for cross technological collaboration between AI systems and other available sources of information in the home to generate multiple explanations for a single user query. Through example scenarios in a caregiving home setting, this paper provides an initial framework for categorizing these sources and informing a potential design space for AI explanations surrounding everyday tasks in the home.

Artificial intelligence (AI) is poised to transform health care across medical specialties. Although the application of AI to neuroanesthesiology is just emerging, it will undoubtedly affect neuroanesthesiologists in foreseeable and unforeseeable ways, with potential roles in preoperative patient assessment, airway assessment, predicting intraoperative complications, and monitoring and interpreting vital signs. It will advance the diagnosis and treatment of neurological diseases due to improved risk identification, data integration, early diagnosis, image analysis, and pharmacological and surgical robotic assistance. Beyond direct medical care, AI could also automate many routine administrative tasks in health care, assist with teaching and training, and profoundly impact neuroscience research. This article introduces AI and its various approaches from a neuroanesthesiology perspective. A basic understanding of the computational underpinnings, advantages, limitations, and ethical implications is necessary for using AI tools in clinical practice and research. The update summarizes recent reports of AI applications relevant to neuroanesthesiology. Providing a holistic view of AI applications, this review shows how AI could usher in a new era in the specialty, significantly improving patient care and advancing neuroanesthesiology research.

While consumer digital calendars are widely used for appointment reminders, they do not fulfill all of the compensatory functions that are supported by calendars designed for cognitive rehabilitation therapies (CRTs). To inform the development of digital compensatory solutions, we employed a Distributed Cognition framework to elucidate how older adults with mild cognitive impairment (MCI) and their care partners manage calendaring details when supported by a traditional rehabilitation calendar. Participants mapped out their calendaring cognitive systems, composed of people and artifacts, completed a chart detailing how they track specific types of information, and shared calendaring strategies with each other. We used a Distributed Cognition framing to articulate information flows and breakdowns in participants’ calendaring systems, and we identified groups of participants with similar breakdowns in their calendaring systems. We close by suggesting design recommendations for digital calendaring approaches to support dyads of older adults with MCI and their care partners.

While commercial conversational agents (CA) (i.e. Google assistant, Siri, Alexa) are widely used, these systems have limitations in error-handling, flexibility, personalization and overall dialogue management that are amplified in care coordination settings. In this paper, we synthesize and articulate these limitations through quantitative and qualitative analysis of 56 older adults interacting with a commercial CA deployed in their home for a 10 week period. We look at the CA as a compensatory technology in an older adult's care network. We argue that the CA limitations are rooted in the rigid cue-and-response style of task-oriented interactions common in CAs. We then propose a redesign for CA conversation flow to favor flexibility and personalization that is nonetheless viable within the limitations of current AI and machine learning technologies. We explore design tradeoffs to better support the usability needs of older adults compared to current design optimizations driven by efficiency and privacy goals.

As Conversational AI systems evolve, their user base widens to encompass individuals with varying cognitive abilities, including older adults facing cognitive challenges like Mild Cognitive Impairment (MCI). Current systems, like smart speakers, struggle to provide effective explanations for their decisions or responses. This paper argues that the expectations and requirements for AI explanations for older adults with MCI differ significantly from conventional Explainable AI (XAI) research goals. Drawing from our ongoing research involving older adults with MCI and their interactions with the Google Home Hub, we highlight breakdowns in conversational flow when older adults seek explanations. Based on our experience, we conclude with recommendations for HCI researchers to adopt a more human-centered approach as we move towards developing the next generation of AI systems.

Improving medication management for older adults with Mild Cognitive Impairment (MCI) requires designing systems that support functional independence and provide compensatory strategies as their abilities change. Traditional medication management interventions emphasize forming new habits alongside the traditional path of learning to use new technologies. In this study, we navigate designing for older adults with gradual cognitive decline by creating a conversational “check-in” system for routine medication management. We present the design of MATCHA - Medication Action To Check-In for Health Application, informed by exploratory focus groups and design sessions conducted with older adults with MCI and their caregivers, alongside our evaluation based on a two-phased deployment period of 20 weeks. Our results indicate that a conversational “check-in” medication management assistant increased system acceptance while also potentially decreasing the likelihood of accidental over-medication, a common concern for older adults dealing with MCI.

Conversational agents (CAs) such as Google Home or Alexa offer empowering opportunities for dyads composed of older adults with mild cognitive impairment (MCI) and their care partners. CAs support coordination and planning between the two, and can amplify the support that the care partner needs to provide. In this study, we observed how ten such dyads interacted with a Google Home over 10 weeks. We logged and analyzed 3,878 total interactions, interviewed the dyads to better understand their experiences, and also surveyed their individual preferences and priorities for automated assistance in the home. We found that CAs empowered both the people who had MCI, and their care partners. We observed that the utility of the CA in the day-to-day lives of users largely depended on how much the care partner scaffolded promising functionality, setting it up and contextualizing it for specific needs and desires.

Single-valued neutrosophic sets (SVNSs) have been used in scientific problems but not in sociological analysis. This chapter provides a modern-day real-world application of Neutrosophy in sentiment analysis of the #MeToo movement. Sentiment analysis categorizes people's opinions as positive or negative, and the neutral part is generally ignored even in fuzzy sentiment analysis. To capture the prevailing indeterminate feelings, Neutrosophy is used. Over 400,000 tweets of the #MeToo movement were separately represented with positive, indeterminate, negative memberships as an SVNS, which gives an accurate evaluation of the tweets. Clustering of these tuples into three major clusters using a K-means algorithm displays indeterminate as the largest cluster. To increase the accuracy in predicting the indeterminate polarity, the data was further classified into eight classes. Training data was used to model k-nearest neighbor and support vector machine classifiers. A comparative analysis between the classifiers was done.

Introduction: Blood group antigens are hereditarily determined and play a vital role in transfusion safety, understanding genetics and inheritance pattern and disease susceptibility.ABO and Rh system is the most common and widely used world-wide.The objective of the present study was to determine the distribution of blood groups (ABO and Rh) subtypes A1, A2, A1B & A2B and Bombay blood group in the local population of Sikkim.Methods: A total of 262 blood samples were collected over a period of two months from voluntary blood donors, which included hospital staff, visitors and patients and local inhabitants of Sikkim.Determination of various blood groups namely |ABO, Rh, A1, A2, A1B, A2B and Bombay blood group were performed.Results: Out of the total sample the most common blood group was O blood group comprising 34.73% followed by B group (28.24%),A (22.91%) and AB (14.12%).98.4% of the total samples were Rh positive.When blood group A and AB were further sub-typed the distribution of A1 antigen was 98.3% and A1B was 89.7% respectively among A and AB blood groups.Among the 91 blood group O samples only 1 was reactive to H antigen. Conclusion: The distribution of Blood group O was highest in these region closely followed by B, A and AB.Almost all the samples showed positivity for Rh.The distribution of A2 and A2B were very low and Bombay blood group was very rare in this part of the country, however further study is required on a larger scale as this study was done in a hospital set up for a very short period of time