Publications by authors named "Ian Spens"
Article Synopsis
- Mild cognitive impairment and early-stage dementia are often underdiagnosed, leading to increased healthcare costs; this study aims to address this gap by using patient-nurse conversations recorded in home healthcare settings to develop an AI tool for early detection of cognitive decline.
- The research involved analyzing audio from conversations of 47 patients, identifying key linguistic features related to cognitive decline, and comparing the effectiveness of a speech processing algorithm to traditional electronic health record data.
- Results showed that the combined approach of using verbal communication and EHR data significantly outperformed either method alone, highlighting that certain speech patterns can predict cognitive decline, thus potentially improving patient care and reducing emergency healthcare visits.
Objectives: As artificial intelligence evolves, integrating speech processing into home healthcare (HHC) workflows is increasingly feasible. Audio-recorded communications enhance risk identification models, with automatic speech recognition (ASR) systems as a key component. This study evaluates the transcription accuracy and equity of 4 ASR systems-Amazon Web Services (AWS) General, AWS Medical, Whisper, and Wave2Vec-in transcribing patient-nurse communication in US HHC, focusing on their ability in accurate transcription of speech from Black and White English-speaking patients.
View Article and Find Full Text PDF