Publications by authors named "Ali Zolnour"
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.
Article Synopsis
- The study explores the integration of automatic speech recognition (ASR) into home healthcare, specifically evaluating the transcription accuracy of four ASR systems while comparing their performance with Black and White English-speaking patients.
- The research analyzed audio recordings from 35 patients (16 Black and 19 White), focusing on 860 utterances to assess transcription accuracy using word error rate (WER) against a manual standard.
- Results indicate that while AWS General had the highest overall accuracy (39% median WER), all ASR systems struggled with transcribing speech from Black patients and exhibited notable performance disparities across different linguistic dimensions.
Background: In the United States, over 12 000 home healthcare agencies annually serve 6+ million patients, mostly aged 65+ years with chronic conditions. One in three of these patients end up visiting emergency department (ED) or being hospitalized. Existing risk identification models based on electronic health record (EHR) data have suboptimal performance in detecting these high-risk patients.
View Article and Find Full Text PDFPurpose: Between 30 and 68% of patients prematurely discontinue their antidepressant treatment, posing significant risks to patient safety and healthcare outcomes. Online healthcare forums have the potential to offer a rich and unique source of data, revealing dimensions of antidepressant discontinuation that may not be captured by conventional data sources.
Methods: We analyzed 891 patient narratives from the online healthcare forum, "askapatient.
Alzheimer's disease and related dementias (ADRD) present a looming public health crisis, affecting roughly 5 million people and 11 % of older adults in the United States. Despite nationwide efforts for timely diagnosis of patients with ADRD, >50 % of them are not diagnosed and unaware of their disease. To address this challenge, we developed ADscreen, an innovative speech-processing based ADRD screening algorithm for the protective identification of patients with ADRD.
View Article and Find Full Text PDFObjectives: Patient-clinician communication provides valuable explicit and implicit information that may indicate adverse medical conditions and outcomes. However, practical and analytical approaches for audio-recording and analyzing this data stream remain underexplored. This study aimed to 1) analyze patients' and nurses' speech in audio-recorded verbal communication, and 2) develop machine learning (ML) classifiers to effectively differentiate between patient and nurse language.
View Article and Find Full Text PDF