Department of Population Health Science and Policy, Icahn School of Medicine at Mount Sinai, One Gustav Levy Place, Box 1077, New York, NY, 10029, United States, 1 212-659-1470
Auto-generated profile, based on publicly available information
Ksenia Gorbenko
Department of Population Health Science and Policy, Icahn School of Medicine at Mount Sinai, One Gustav Levy Place, Box 1077, New York, NY, 10029, United States, 1 212-659-1470
Background: The Centers for Medicare & Medicaid Services (CMS) announced the Acute Hospital Care at Home (AHCaH) waiver program in November 2020 to help expand hospital capacity to cope with the COVID‐19 pandemic. The AHCaH waived the 24/7 on‐site nursing requirement and enabled hospitals to obtain full hospital‐level diagnosis‐related group (DRG) reimbursement for providing Hospital‐at‐Home (HaH) care. This study sought to describe AHCaH implementation processes and strategies at the national level and identify challenges and facilitators to launching or adapting a HaH to meet waiver requirements. Methods: We conducted semi‐structured interviews to explore barriers and facilitators of HaH implementation. The analysis was informed by the Exploration, Preparation, Implementation, and Sustainment (EPIS) implementation framework. Interviews were audio recorded for transcription and thematic coding. Principal Findings: We interviewed a sample of clinical leaders ( N = 18; clinical/medical directors, operational and program managers) from 14 new and pre‐existing U.S. HaH programs diverse by size, urbanicity, and geography. Participants were enthusiastic about the AHCaH waiver. Participants described barriers and facilitators at planning and implementation stages within three overarching themes influencing waiver program implementation: 1) institutional value and assets; 2) program components, such as electronic health records, vendors, pharmacy, and patient monitoring; and 3) patient enrollment, including eligibility and geographic limits. Conclusions: Implementation of AHCaH waiver is a complex process that requires building components in compliance with the requirements to extend the hospital into the home, in coordination with internal and external partners. The study identified barriers that potential adopters and proponents should consider alongside the strategies that some organizations have found useful. Clarity regarding the waiver's future may expedite HaH model dissemination and ensure longevity of this valuable model of care delivery.
People with psychosis struggle with decisions about their use of antipsychotics. They often want to reduce the dose or stop, while facing uncertainty regarding the effects these decisions will have on their treatment and recovery. They may also fear raising this issue with clinicians. The purpose of this study was to develop and test a shared decision making (SDM) tool to support patients and clinicians in making decisions about antipsychotics. A diverse editorial research team developed an Encounter Decision Aid (EDA) for patients and clinicians to use as part of the psychiatric consultation. The EDA was tested using 24 semistructured interviews with participants representing six stakeholder groups: patients with first-episode psychosis, patients with long-term psychosis, family members, psychiatrists, mental health counselors, and administrators. We used inductive and deductive coding of interview transcripts to identify points to revise within three domains: general impression and purpose of the EDA; suggested changes to the content, wording, and appearance; and usability and potential contribution to the psychiatric consultation. An EDA was developed in an iterative process that yielded evidence-based answers to five frequently asked questions about antipsychotic medications. Patients with long-term psychosis and mental health counselors suggested more changes and revisions than patients with first-episode psychosis and psychiatrists. Family members suggested more revisions to the answers about potential risks of stopping or adjusting antipsychotics than other respondents. The EDA was perceived as potentially useful and feasible in psychiatric routine care, especially if presented during the consultation.
Background: Machine learning (ML)–based clinical decision support systems (CDSS) are popular in clinical practice settings but are often criticized for being limited in usability, interpretability, and effectiveness. Evaluating the implementation of ML-based CDSS is critical to ensure CDSS is acceptable and useful to clinicians and helps them deliver high-quality health care. Malnutrition is a common and underdiagnosed condition among hospital patients, which can have serious adverse impacts. Early identification and treatment of malnutrition are important. Objective: This study aims to evaluate the implementation of an ML tool, Malnutrition Universal Screening Tool (MUST)–Plus, that predicts hospital patients at high risk for malnutrition and identify best implementation practices applicable to this and other ML-based CDSS. Methods: We conducted a qualitative postimplementation evaluation using in-depth interviews with registered dietitians (RDs) who use MUST-Plus output in their everyday work. After coding the data, we mapped emergent themes onto select domains of the nonadoption, abandonment, scale-up, spread, and sustainability (NASSS) framework. Results: We interviewed 17 of the 24 RDs approached (71%), representing 37% of those who use MUST-Plus output. Several themes emerged: (1) enhancements to the tool were made to improve accuracy and usability; (2) MUST-Plus helped identify patients that would not otherwise be seen; perceived usefulness was highest in the original site; (3) perceived accuracy varied by respondent and site; (4) RDs valued autonomy in prioritizing patients; (5) depth of tool understanding varied by hospital and level; (6) MUST-Plus was integrated into workflows and electronic health records; and (7) RDs expressed a desire to eventually have 1 automated screener. Conclusions: Our findings suggest that continuous involvement of stakeholders at new sites given staff turnover is vital to ensure buy-in. Qualitative research can help identify the potential bias of ML tools and should be widely used to ensure health equity. Ongoing collaboration among CDSS developers, data scientists, and clinical providers may help refine CDSS for optimal use and improve the acceptability of CDSS in the clinical context.
1 July 2019 in American Journal of Infection Control