Simulation in healthcare : journal of the Society for Simulation in Healthcare · 2026
Implementation of Artificial Intelligence-Powered Patient Simulation for Communication Training in a Telehealth Transitional Care Program.
СтатьяНазвание и аннотация: Перевод в очереди
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…
Ошибки и ограничения
История · было → стало
Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.
Jafri Farrukh Nadeem, Elsener Michelle, Pulido Kristelle, Kumar Anshul, Kardong-Edgren Suzie, Edwards Roger A
Аннотация
INTRODUCTION: Effective communication during care transitions is essential for patient safety and quality outcomes. Telehealth-based transitional care programs decrease 30-day readmissions and improve patient satisfaction, yet staff frequently report the need for structured communication training. Artificial intelligence (AI)-supported simulation may offer a scalable training method for health care settings with limited simulation resources. This study evaluates whether AI-powered simulation training improves communication performance during real telehealth patient encounters.
METHODS: This quality improvement initiative was conducted within a hospital-based transitions of care program (June 2025-December 2025). Sequential implementation included rubric validation (Lawshe Content Validity Index), AI platform testing, online modules, and individualized AI simulation across 3 patient pathways (inpatient, postoperative, and emergency department). Pathway-specific rubrics demonstrated excellent interrater reliability (Intraclass Correlation Coefficient = 0.91 to 0.97). Weekly communication performance was tracked using run charts and statistical process control; balancing measures included call duration and calls per hour.
RESULTS: Fifteen of 17 eligible staff completed role-specific simulation. Communication performance was assessed across 468 recorded patient calls. Total rubric scores improved: inpatient by 24% (P < 0.001), postoperative by 19% (P < 0.001), and emergency department by 37% (P < 0.001). Statistical process control analysis demonstrated special cause variation with sustained median shifts across all pathways.
CONCLUSIONS: AI-powered simulation training was associated with meaningful and sustained improvements in patient-provider communication during real-world telehealth encounters. Findings support AI simulation as a scalable, practical training method for telehealth programs.
METHODS: This quality improvement initiative was conducted within a hospital-based transitions of care program (June 2025-December 2025). Sequential implementation included rubric validation (Lawshe Content Validity Index), AI platform testing, online modules, and individualized AI simulation across 3 patient pathways (inpatient, postoperative, and emergency department). Pathway-specific rubrics demonstrated excellent interrater reliability (Intraclass Correlation Coefficient = 0.91 to 0.97). Weekly communication performance was tracked using run charts and statistical process control; balancing measures included call duration and calls per hour.
RESULTS: Fifteen of 17 eligible staff completed role-specific simulation. Communication performance was assessed across 468 recorded patient calls. Total rubric scores improved: inpatient by 24% (P < 0.001), postoperative by 19% (P < 0.001), and emergency department by 37% (P < 0.001). Statistical process control analysis demonstrated special cause variation with sustained median shifts across all pathways.
CONCLUSIONS: AI-powered simulation training was associated with meaningful and sustained improvements in patient-provider communication during real-world telehealth encounters. Findings support AI simulation as a scalable, practical training method for telehealth programs.