Moving toward AI-assisted decision-making: Observation on clinicians’ management of multimedia patient information in synchronous and asynchronous telehealth contexts

Abstract

Background. Artificial intelligence (AI) intends to support clinicians’ patient diagnosis decisions by processing and identifying insights from multimedia patient information. Objective. We explored clinicians’ current decision-making patterns using multimedia patient information (MPI) provided by AI algorithms and identified areas where AI can support clinicians in diagnostic decision-making. Design. We recruited 87 advanced practice nursing (APN) students who had experience making diagnostic decisions using AI algorithms under various care contexts, including telehealth and other healthcare modalities. The participants described their diagnostic decision-making experiences using videos, images, and audio-based MPI. Results. Clinicians processed multimedia patient information differentially such that their focus, selection, and utilization of MPI influence diagnosis and satisfaction levels. Conclusions and implications. To streamline collaboration between AI and clinicians across healthcare contexts, AI should understand clinicians’ patterns of MPI processing under various care environments and provide them with interpretable analytic results for them. Furthermore, clinicians must be trained with the interface and contents of AI technology and analytic assistance.

How clinicians make decisions for patient management plans in telehealth

“…Compared with traditional face-to-face clinical settings, studies reported that clinicians found telehealth convenient, fast (Hah & Goldin, 2022) and engaging (Barken et al, 2017). However, the inconvenience of not being able to perform physical assessment led clinicians to ask for more information and a detailed medical history via the mode of telehealth (Hah & Goldin, 2022), pay more attention to the tone of the voice (Haimi et al, 2018;Wouters et al, 2020) and check parents' health literacy if children were patients (Haimi et al, 2018(Haimi et al, , 2020. Clinicians were also concerned that a lack of accurate risk assessment could lead to misdiagnosis.…”

“…Two studies explored video consultation (Hah & Goldin, 2022;Haimi et al, 2018). Hah and Goldin (2022) found that in asynchronous TA B L E 2 Inclusion and exclusion criteria.…”

“…Telehealth can be further divided into synchronous and asynchronous modalities. Synchronous models entail live communication in a virtual setting, whereas asynchronous models often include delayed processing of patient information, such as text, images, audio or video (Hah & Goldin, 2022).…”

Transforming Clinical Information Systems: Empowering Healthcare through Telemedicine, Data Science, and Artificial Intelligence Applications

“…If you are interested in this, you should read the paper. And last but not least, we have a paper from Hah and Goldin [26] in our selection. It is on AI-assisted decision-making in healthcare.…”

Dermatología e inteligencia artificial: oportunidades, temores y un futuro colaborativo

“…Otro componente, que se convierte en una oportunidad, está relacionado con el ajuste de los tratamientos personalizados a partir del análisis que la IA permite realizar de los datos de un paciente: historial médico, resultados de pruebas y exámenes, entre otros, para predecir posibles respuestas a diferentes tratamientos. En esta misma perspectiva, el fortalecimiento de la telemedicina puede ser una estrategia de atención especializada al alcance de poblaciones vulnerables y distantes de los centros especializados de diagnóstico (10) .…”