Search

AI-enabled decision support systems have repeatedly failed in real world applications despite the underlying model operating as designed. Often this was because the system was used in an unexpected manner. Our goal is to enable better prediction of how systems will be used prior to their implementation as well as to improve existing designs, by taking human behavior into account. There are several challenges to collecting such data. Not having access to an existing prediction engine requires the simulation of such a system's behavior. This simulation must include not just the behavior of the underlying model but also the context in which the decision will be made in the real world. Additionally, collecting statistically valid samples requires that test subjects make repeated choices under slightly varied conditions. Unfortunately, in such repetitious conditions fatigue can quickly set in. Games provide us the ability to address both of these challenges by providing both systems context and narrative context. Systems context can be used to convey some or all of the information the player needs to make a decision in the game environment itself, which can help avoid the onset of fatigue. Narrative context can provide a broader environment within which the simulated system operates, adding a sense of progress, showing the effect of decisions, adding perceived social norms, and setting incentives and stakes. This broader environment can further prevent player fatigue while replicating many of the external factors that might affect choices in the real world. In this paper we describe the design of the Human-AI Decision Evaluation System (HADES), a test harness capable of interfacing with a game environment, simulating the behavior of an AI-enabled decision support system, and collecting the results of human decision making based upon such a system's predictions. Additionally, we present an analysis of data collected by HADES while interfaced with a visual novel game focused on software cyber-risk assessment.

Current process-based approaches to regulation are no longer fit for purpose

Fidelity (consistency of intervention implementation) is essential to rigorous research. Intervention fidelity maintains study internal validity, intervention reproducibility, and transparency in the research conduct. The purpose of this manuscript is to describe intervention fidelity strategies/procedures developed for a pilot study testing a new palliative care nursing intervention (FamPALcare) for families managing advanced lung disease. The procedures described herein are based on the fidelity best practices recommendations from the NIH Consortium. An evidence-based checklist guided observational ratings of the fidelity procedures used and the intervention content implemented in each intervention session. Descriptive data on how participants understood (received), enacted, or used the intervention information were summarized. The fidelity checklist observational scores found ≥ 93% of the planned intervention content was implemented, and the fidelity strategies were adhered to consistently during each intervention session. The small variation (7%) in implementation was expected and related to participants’ varying experiences, input, and/or questions. The helpfulness scale items include participants’ ability to use home care resources, to anticipate and manage end-of-life symptoms, and to use Advance Directives forms. The high ratings (M = 4.4) on the 1 to 5 (very helpful) Likert Helpfulness Scale verified participants utilized the information from the intervention. Further, there was an improvement in patients’ breathlessness scores and completion of Advance Directive forms at 3 months after baseline. It is essential to plan intervention fidelity strategies to use throughout a study and to report fidelity results.

There is a gap in current research on common factors that impact patients with advanced heart failure (HF). The purpose of this secondary data analysis was to explore associations of those factors with three empirically verified measures of HF-related clinical, physical, and mental health status. Baseline data of 198 advanced systolic HF (EF

1.1. The COVID‐19 pandemic compelled a surge of telemedicine activity to provide social distancing between health care providers and their patients, buoyed by a flurry of simultaneous federal and state telehealth policy changes to accommodate as many patients as possible. These policy adaptations included an increased number of telehealth services that could be reimbursed by Medicare, many state Medicaid plans, and even private insurers. The policy changes also relaxed Health Insurance Portability and Accountability Act (HIPAA) requirements for the technology platforms used, allowed for controlled medications to be prescribed remotely without first having an in‐person examination, and made it easier for many types of health care professionals to practice across state lines under their current home‐state licenses. These rapid policy updates were necessary, as some studies have indicated that up to an unprecedented 80% of all outpatient appointments were being conducted via telehealth during the peak periods of late March through May. Moreover, health systems, mental health centers, hospitals, and other health care organizations had to rapidly implement telehealth systems and protocols to meet the demand. As COVID‐19 induced telehealth activity enters its 10th month, a few key questions have emerged. First, what have been the effects of this unprecedented pandemic and related policy changes on telehealth volume? Also, how has policy evolved and what policy accommodations will continue post‐COVID? Will providers continue to leverage telehealth after the public health emergency ends? This short editorial opinions page provides some initial thoughts on these important questions.

Telehealth distance health care is a significant resource for young, chronically ill patient populations given their numerous medical complexities and their concomitant depression and/or suicide ideation experiences. This manuscript shares the telehealth methods used to prepare for a larger study of interventions for increasing adolescents’ and young adults’ chronic care resiliency and skills for preventing depression. The young patients in this study were prescribed lifelong home parenteral nutrition infusions, treatment for those with short gut bowel diseases. The training methods for our mental health nurse and psychologist to conduct depression and suicide ideation assessments from a distance are presented. The study implementation methods of group facilitated interventions and discussion are reviewed. The group discussions were conducted via audiovisual telehealth devices over encrypted firewall-protected connections with patients in their own homes and professionals in an office. The results of assessments of the 40 participants, 25% (n = 10) with depressive symptoms or suicide ideation, are described. Following participants’ assessments, their subsequent depression measures were all in the normal range, without any suicide ideation, across the year of the study. Patient evaluation ratings were high in the areas of being able to connect with other young patients in similar situations, using the audiovisual equipment, and learning new useful information from the interventions. The methods developed for the study ensured that the safety and well-being of participants were supported through telehealth.

The current standard in healthcare research is to maintain scientific fidelity of any intervention being tested. Fidelity is defined as the consistent delivery of interventions which ensures that all participants are provided the same information, guidance, and/or materials. Notably, the methods for ensuring fidelity of intervention delivery must also be consistent. This manuscript describes our Intervention and Technology Delivery Fidelity Checklists used to ensure consistency. These checklists were completed by trained nurse observers who rated the intervention implementation and the technology delivery. Across our clinical trials and pilot studies, the fidelity scores were tabulated and compared. Intervention information and materials were delivered by a variety of technology devices including telehealth monitors, videophones, and/or iPads. Each of the devices allow audio-visual connections between health professionals from their offices and patients/participants in their homes. Our checklists guide monitoring fidelity of technology delivery. Overall checklist ratings across our studies demonstrate consistent intervention, implementation, and technology delivery approaches. Uniquely, our fidelity checklist verifies the interventionist’s correct use of the technology devices to ensure the consistent audio-visual delivery. Our checklist methods to ensure intervention fidelity and technology delivery are essential research procedures which can be adapted for use by researchers across multiple disciplines.

The purpose of this study is to examine the effects of LGB identity on career decision-making self-efficacy. This study utilizes a mediation model that incorporates a personal (self-compassion) and an environmental (social support) factor as key model variables. Mediating effects of social support and self-compassion were found. Specifically, LGB identity was associated with social support, which in turn was linked with increased self-compassion, resulting in greater self-efficacy in career decision-making.

Background Evaluations of human immunodeficiency virus (HIV) curative interventions require reliable and efficient quantification of replication-competent latent reservoirs. The “classic” quantitative viral outgrowth assay (QVOA) has been regarded as the reference standard, although prohibitively resource and labor intensive. We compared 6 “next-generation” viral outgrowth assays, using polymerase chain reaction or ultrasensitive p24 to assess their suitability as scalable proxies for QVOA. Methods Next-generation QVOAs were compared with classic QVOA using single leukapheresis-derived samples from 5 antiretroviral therapy–suppressed HIV-infected participants and 1 HIV-uninfected control; each laboratory tested blinded batches of 3 frozen and 1 fresh sample. Markov chain Monte Carlo methods estimated extra-Poisson variation at aliquot, batch, and laboratory levels. Models also estimated the effect of testing frozen versus fresh samples. Results Next-generation QVOAs had similar estimates of variation to QVOA. Assays with ultrasensitive readout reported higher infectious units per million values than classic QVOA. Within-batch testing had 2.5-fold extra-Poisson variation (95% credible interval [CI], 2.1–3.5-fold) for next-generation assays. Between-laboratory variation increased extra-Poisson variation to 3.4-fold (95% CI, 2.6–5.4-fold). Frozen storage did not substantially alter infectious units per million values (−18%; 95% CI, −52% to 39%). Conclusions The data offer cautious support for use of next-generation QVOAs as proxies for more laborious QVOA, while providing greater sensitivities and dynamic ranges. Measurement of latent reservoirs in eradication strategies would benefit from high throughput and scalable assays., We demonstrated similar estimates of variation for classic and next-generation quantitative viral outgrowth assays (QVOAs), with enhanced sensitivity supporting the use of next-generation QVOAs as a proxy for classic QVOAs in measuring the latent human immunodeficiency virus reservoir.