ABSTRACT
BACKGROUND: Health anxiety has many damaging effects on patients with chronic illness. Physicians are often unable to alleviate concerns related to living with a disease that has an impact on daily life, and unregulated websites can overrepresent extreme anxiety-inducing outcomes. Educational clinician video interventions have shown some success as an acute anxiolytic in health settings. However, little research has evaluated if peer-based video interventions would be a feasible alternative or improvement. OBJECTIVE: This pilot study assesses the efficacy of anxiety reduction for patients with Crohn disease (CD) and those with ulcerative colitis (UC) by showing patient testimonial videos during hospital visits. It investigates the degree to which patient testimonials can affect state anxiety, and whether patients are comfortable enough with the technology to share their stories. METHODS: Patients with CD (n=51) and those with UC (n=49) were shown testimonial videos of patients with CD during their physician consultations at Kitasato University Kitasato Institute Hospital in Japan. The video testimonials were collected from Dipex Japan, the Japan branch of an international organization specializing in understanding patient experiences. Patients completed a Visual Analogue Scale for Anxiety before and after viewing the videos, a Hospital Anxiety and Depression Scale (HADS) survey before the videos, and satisfaction surveys. Patients receiving infusion therapy participated in the study while receiving treatment to minimize hospital workflow disruption. RESULTS: Anxiety reduction, on the Visual Analog Scale for Anxiety, was significant in the entire cohort both when viewed as an ordinal variable (P=.003, t98=1086.5) and as a continuous variable (P=.01, t94=-2.54, 90% CI -3.47 to -0.72). Eighty percent (n=15) of patients with high HADS Anxiety (HADS-A) scores and 71% (n=24) of patients with high starting state anxiety experienced reduced anxiety after watching testimonials. Patients with high state anxiety but low HADS-A scores experienced anxiety reduction (69%, n=16). Forty-two percent (n=100) of patients responded that they would share their stories for future users. When patients with UC received testimonials from patients with CD, 71% (n=49) of patients reported that they were relevant despite differences in condition. CONCLUSIONS: Our pilot results suggest that patient testimonial videos can reduce illness-related state anxiety for patients with CD and those with UC, especially in those with higher baseline state anxiety. The success of this study in reducing anxiety and achieving patient involvement suggests that video interventions for reducing anxiety might be a low-cost intervention that could scale to any number of hospitals, suggesting that technology can help scale up efforts to record and share patient testimonials. Future work can establish whether patient testimonials can be helpful in other contexts, such as before major surgeries or when a family member receives a difficult diagnosis.
ABSTRACT
The COVID-19 pandemic has highlighted the global need for reliable models of disease spread. We propose an AI-augmented forecast modeling framework that provides daily predictions of the expected number of confirmed COVID-19 deaths, cases, and hospitalizations during the following 4 weeks. We present an international, prospective evaluation of our models' performance across all states and counties in the USA and prefectures in Japan. Nationally, incident mean absolute percentage error (MAPE) for predicting COVID-19 associated deaths during prospective deployment remained consistently <8% (US) and <29% (Japan), while cumulative MAPE remained <2% (US) and <10% (Japan). We show that our models perform well even during periods of considerable change in population behavior, and are robust to demographic differences across different geographic locations. We further demonstrate that our framework provides meaningful explanatory insights with the models accurately adapting to local and national policy interventions. Our framework enables counterfactual simulations, which indicate continuing Non-Pharmaceutical Interventions alongside vaccinations is essential for faster recovery from the pandemic, delaying the application of interventions has a detrimental effect, and allow exploration of the consequences of different vaccination strategies. The COVID-19 pandemic remains a global emergency. In the face of substantial challenges ahead, the approach presented here has the potential to inform critical decisions.
