Speech recognition can help evaluate shared decision making and predict medication adherence in primary care setting
<h4>Objective</h4> Asthma is a common chronic illness affecting 19 million US adults. Inhaled corticosteroids are a safe and effective treatment for asthma, yet, medication adherence among patients remains poor. Shared decision-making, a patient activation strategy, can improve patient a...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Public Library of Science (PLoS)
2022-01-01
|
Series: | PLoS ONE |
Online Access: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9352008/?tool=EBI |
_version_ | 1811315163644559360 |
---|---|
author | Maxim Topaz Maryam Zolnoori Allison A. Norful Alexis Perrier Zoran Kostic Maureen George |
author_facet | Maxim Topaz Maryam Zolnoori Allison A. Norful Alexis Perrier Zoran Kostic Maureen George |
author_sort | Maxim Topaz |
collection | DOAJ |
description | <h4>Objective</h4> Asthma is a common chronic illness affecting 19 million US adults. Inhaled corticosteroids are a safe and effective treatment for asthma, yet, medication adherence among patients remains poor. Shared decision-making, a patient activation strategy, can improve patient adherence to inhaled corticosteroids. This study aimed to explore whether audio-recorded patient-primary care provider encounters can be used to: 1. Evaluate the level of patient-perceived shared decision-making during the encounter, and 2. Predict levels of patient’s inhaled corticosteroid adherence. <h4>Materials and methods</h4> Shared decision-making and inhaled corticosteroid adherence were assessed using the SDM Questionnaire-9 and the Medication Adherence Report Scale for Asthma (MARS-A). Speech-to-text algorithms were used to automatically transcribe 80 audio-recorded encounters between primary care providers and asthmatic patients. Machine learning algorithms (Naive Bayes, Support Vector Machines, Decision Tree) were applied to achieve the study’s predictive goals. <h4>Results</h4> The accuracy of automated speech-to-text transcription was relatively high (ROUGE F-score = .9). Machine learning algorithms achieved good predictive performance for shared decision-making (the highest F-score = .88 for the Naive Bayes) and inhaled corticosteroid adherence (the highest F-score = .87 for the Support Vector Machines). <h4>Discussion</h4> This was the first study that trained machine learning algorithms on a dataset of audio-recorded patient-primary care provider encounters to successfully evaluate the quality of SDM and predict patient inhaled corticosteroid adherence. <h4>Conclusion</h4> Machine learning approaches can help primary care providers identify patients at risk for poor medication adherence and evaluate the quality of care by measuring levels of shared decision-making. Further work should explore the replicability of our results in larger samples and additional health domains. |
first_indexed | 2024-04-13T11:25:16Z |
format | Article |
id | doaj.art-6eada98ee6b9497483d70f5d459a2528 |
institution | Directory Open Access Journal |
issn | 1932-6203 |
language | English |
last_indexed | 2024-04-13T11:25:16Z |
publishDate | 2022-01-01 |
publisher | Public Library of Science (PLoS) |
record_format | Article |
series | PLoS ONE |
spelling | doaj.art-6eada98ee6b9497483d70f5d459a25282022-12-22T02:48:42ZengPublic Library of Science (PLoS)PLoS ONE1932-62032022-01-01178Speech recognition can help evaluate shared decision making and predict medication adherence in primary care settingMaxim TopazMaryam ZolnooriAllison A. NorfulAlexis PerrierZoran KosticMaureen George<h4>Objective</h4> Asthma is a common chronic illness affecting 19 million US adults. Inhaled corticosteroids are a safe and effective treatment for asthma, yet, medication adherence among patients remains poor. Shared decision-making, a patient activation strategy, can improve patient adherence to inhaled corticosteroids. This study aimed to explore whether audio-recorded patient-primary care provider encounters can be used to: 1. Evaluate the level of patient-perceived shared decision-making during the encounter, and 2. Predict levels of patient’s inhaled corticosteroid adherence. <h4>Materials and methods</h4> Shared decision-making and inhaled corticosteroid adherence were assessed using the SDM Questionnaire-9 and the Medication Adherence Report Scale for Asthma (MARS-A). Speech-to-text algorithms were used to automatically transcribe 80 audio-recorded encounters between primary care providers and asthmatic patients. Machine learning algorithms (Naive Bayes, Support Vector Machines, Decision Tree) were applied to achieve the study’s predictive goals. <h4>Results</h4> The accuracy of automated speech-to-text transcription was relatively high (ROUGE F-score = .9). Machine learning algorithms achieved good predictive performance for shared decision-making (the highest F-score = .88 for the Naive Bayes) and inhaled corticosteroid adherence (the highest F-score = .87 for the Support Vector Machines). <h4>Discussion</h4> This was the first study that trained machine learning algorithms on a dataset of audio-recorded patient-primary care provider encounters to successfully evaluate the quality of SDM and predict patient inhaled corticosteroid adherence. <h4>Conclusion</h4> Machine learning approaches can help primary care providers identify patients at risk for poor medication adherence and evaluate the quality of care by measuring levels of shared decision-making. Further work should explore the replicability of our results in larger samples and additional health domains.https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9352008/?tool=EBI |
spellingShingle | Maxim Topaz Maryam Zolnoori Allison A. Norful Alexis Perrier Zoran Kostic Maureen George Speech recognition can help evaluate shared decision making and predict medication adherence in primary care setting PLoS ONE |
title | Speech recognition can help evaluate shared decision making and predict medication adherence in primary care setting |
title_full | Speech recognition can help evaluate shared decision making and predict medication adherence in primary care setting |
title_fullStr | Speech recognition can help evaluate shared decision making and predict medication adherence in primary care setting |
title_full_unstemmed | Speech recognition can help evaluate shared decision making and predict medication adherence in primary care setting |
title_short | Speech recognition can help evaluate shared decision making and predict medication adherence in primary care setting |
title_sort | speech recognition can help evaluate shared decision making and predict medication adherence in primary care setting |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9352008/?tool=EBI |
work_keys_str_mv | AT maximtopaz speechrecognitioncanhelpevaluateshareddecisionmakingandpredictmedicationadherenceinprimarycaresetting AT maryamzolnoori speechrecognitioncanhelpevaluateshareddecisionmakingandpredictmedicationadherenceinprimarycaresetting AT allisonanorful speechrecognitioncanhelpevaluateshareddecisionmakingandpredictmedicationadherenceinprimarycaresetting AT alexisperrier speechrecognitioncanhelpevaluateshareddecisionmakingandpredictmedicationadherenceinprimarycaresetting AT zorankostic speechrecognitioncanhelpevaluateshareddecisionmakingandpredictmedicationadherenceinprimarycaresetting AT maureengeorge speechrecognitioncanhelpevaluateshareddecisionmakingandpredictmedicationadherenceinprimarycaresetting |