Detecting conversation topics in primary care office visits from transcripts of patient-provider interactions.

Published on Dec 1, 2019in Journal of the American Medical Informatics Association4.497
· DOI :10.1093/JAMIA/OCZ140
Jihyun Park6
Estimated H-index: 6
(UCI: University of California, Irvine),
Dimitrios Kotzias7
Estimated H-index: 7
(UCI: University of California, Irvine)
+ 10 AuthorsPadhraic Smyth79
Estimated H-index: 79
(UCI: University of California, Irvine)
Objective Amid electronic health records, laboratory tests, and other technology, office-based patient and provider communication is still the heart of primary medical care. Patients typically present multiple complaints, requiring physicians to decide how to balance competing demands. How this time is allocated has implications for patient satisfaction, payments, and quality of care. We investigate the effectiveness of machine learning methods for automated annotation of medical topics in patient-provider dialog transcripts.
đź“– Papers frequently viewed together
201279.32The Lancet
5 Authors (Felix Greaves, ..., Liam Donaldson)
2017Healthcom: International Conference on e-Health Networking, Applications and Services
4 Authors (Qiang Zhang)
2017BHI: Biomedical and Health Informatics
#1Ming Tai-Seale (UCSD: University of California, San Diego)H-Index: 23
#2Ellis C Dillon (Palo Alto Medical Foundation)H-Index: 8
Last. Dominick L. Frosch (Palo Alto Medical Foundation)H-Index: 46
view all 11 authors...
Despite concerns about physicians’ workload associated with electronic health records (EHRs), little attention has been paid to the relationship between physicians’ well-being and the in-basket mes...
#1Alvin Rajkomar (Google)H-Index: 12
#2Anjuli Kannan (Google)H-Index: 22
Last. Jeffrey Dean (Google)H-Index: 66
view all 7 authors...
This study assesses the feasibility of using machine learning to automatically populate a review of systems of all symptoms discussed in an encounter between a patient and a clinician.
#1Karandeep Singh (UM: University of Michigan)H-Index: 14
#2Sean R. Meyer (UM: University of Michigan)H-Index: 2
Last. John M. Westfall (Santa Clara Valley Medical Center)H-Index: 1
view all 3 authors...
Consumers have greater access to data, information, and tools to support the management of their health than ever before. While the sheer quantity of these resources has increased exponentially ove...
Sep 2, 2018 in INTERSPEECH (Conference of the International Speech Communication Association)
#2Anshuman Tripathi (Google)H-Index: 9
In this work we explored building automatic speech recognition models for transcribing doctor patient conversation. We collected a large scale dataset of clinical conversations (14,000hr), designed the task to represent the real word scenario, and explored several alignment approaches to iteratively improve data quality. We explored both CTC and LAS systems for building speech recognition models. The LAS was more resilient to noisy data and CTC required more data clean up. A detailed analysis...
#1Derek D. Caperton (UofU: University of Utah)H-Index: 4
#2David C. Atkins (UW: University of Washington)H-Index: 78
Last. Zac E. Imel (UofU: University of Utah)H-Index: 36
view all 3 authors...
: Monitoring fidelity to psychosocial treatments is critical to dissemination, process and outcome research, and internal validity in efficacy trials. However, the costs required to behavior code fidelity to treatments like motivational interviewing (MI) over many therapists and sessions quickly become intractable. Coding less of a session accelerates the process, but it is not clear how much of a session must be evaluated to capture the fidelity of the entire session. The present study used a "...
#1J. Randall Curtis (UW: University of Washington)H-Index: 108
#2Seelwan Sathitratanacheewin (UW: University of Washington)H-Index: 4
Last. James Fausto (UW: University of Washington)H-Index: 6
view all 12 authors...
Abstract Background: As our population ages and the burden of chronic illness rises, there is increasing need to implement quality metrics that measure and benchmark care of the seriously ill, including the delivery of both primary care and specialty palliative care. Such metrics can be used to drive quality improvement, value-based payment, and accountability for population-based outcomes. Methods: In this article, we examine use of the electronic health record (EHR) as a tool to assess quality...
#1Abraham Verghese (Stanford University)H-Index: 34
#2Nigam H. Shah (Stanford University)H-Index: 63
Last. Robert A. Harrington (Stanford University)H-Index: 141
view all 3 authors...
#1David T. Eton (Mayo Clinic)H-Index: 37
#2Jennifer L. Ridgeway (Mayo Clinic)H-Index: 18
Last. Roger T. Anderson (UVA: University of Virginia)H-Index: 58
view all 10 authors...
PURPOSE: Having multiple chronic conditions (MCCs) can lead to appreciable treatment and self-management burden. Healthcare provider relational quality (HPRQ) - the communicative and interpersonal skill of the provider - may mitigate treatment burden and promote self-management. The objectives of this study were to 1) identify the associations between HPRQ, treatment burden, and psychosocial outcomes in adults with MCCs, and 2) determine if certain indicators of HPRQ are more strongly associated...
#1Brian Arndt (UW: University of Wisconsin-Madison)H-Index: 7
#2John W. Beasley (UW: University of Wisconsin-Madison)H-Index: 24
Last. Valerie J. Gilchrist (UW: University of Wisconsin-Madison)H-Index: 5
view all 7 authors...
PURPOSE Primary care physicians spend nearly 2 hours on electronic health record (EHR) tasks per hour of direct patient care. Demand for non–face-to-face care, such as communication through a patient portal and administrative tasks, is increasing and contributing to burnout. The goal of this study was to assess time allocated by primary care physicians within the EHR as indicated by EHR user-event log data, both during clinic hours (defined as 8:00 am to 6:00 pm Monday through Friday) and outsid...
#1Mara van OschH-Index: 5
#2Sandra van Dulmen (Radboud University Nijmegen)H-Index: 52
Last. Jozien M. Bensing (UU: Utrecht University)H-Index: 92
view all 4 authors...
Abstract Objective To experimentally test the effects of physician's affect-oriented communication and inducing expectations on outcomes in patients with menstrual pain. Methods Using a 2Ă—2 RCT design, four videotaped simulated medical consultations were used, depicting a physician and a patient with menstrual pain. In the videos, two elements of physician's communication were manipulated: (1) affect-oriented communication (positive: warm, emphatic; versus negative: cold, formal), and (2) outcom...
Cited By11
#1Asghar Ahmadi (ACU: Australian Catholic University)
#2Michael Noetel (ACU: Australian Catholic University)H-Index: 10
Last. Nikos Ntoumanis (University of Southern Denmark)
view all 12 authors...
Many psychological treatments have been shown to be cost-effective and efficacious, as long as they are implemented faithfully. Assessing fidelity and providing feedback is expensive and time-consuming. Machine learning has been used to assess treatment fidelity, but the reliability and generalisability is unclear. We collated and critiqued all implementations of machine learning to assess the verbal behaviour of all helping professionals, with particular emphasis on treatment fidelity for thera...
Computational approaches for assessing the quality of conversation-based psychotherapy, such as Cognitive Behavioral Therapy (CBT) and Motivational Interviewing (MI), have been developed recently to support quality assurance and clinical training. However, due to the long session lengths and limited modeling resources, computational methods largely rely on frequency-based lexical features or distribution of dialogue acts. In this work, we propose a hierarchical framework to automatically evaluat...
#1Gaur ManasH-Index: 1
#2Vamsi Aribandi (Wright State University)H-Index: 3
Last. Amit ShethH-Index: 11
view all 9 authors...
Background: In clinical diagnostic interviews, mental health professionals (MHPs) implement a care practice that involves asking open questions (eg, “What do you want from your life?” “What have you tried before to bring change in your life?”) while listening empathetically to patients. During these interviews, MHPs attempted to build a trusting human-centered relationship while collecting data necessary for professional medical and psychiatric care. Often, because of the social stigma of mental...
#1Jesse Wang (URMC: University of Rochester Medical Center)
#2Marc Lavender (URMC: University of Rochester Medical Center)
Last. Henry Kautz (UR: University of Rochester)H-Index: 81
view all 5 authors...
#1Jihyun Park (UCI: University of California, Irvine)
#2Abhishek Jindal (UCI: University of California, Irvine)
Last. Padhraic Smyth (UCI: University of California, Irvine)H-Index: 79
view all 9 authors...
Abstract Objective Train machine learning models that automatically predict emotional valence of patient and physician in primary care visits. Methods Using transcripts from 353 primary care office visits with 350 patients and 84 physicians [ 1 , 2 ], we developed two machine learning models (a recurrent neural network with a hierarchical structure and a logistic regression classifier) to recognize the emotional valence (positive, negative, neutral) [ 3 ] of each utterance. We examined the agree...
#1Katie Aafjes-van Doorn (Yeshiva University)H-Index: 9
#2CĂ©line KamsteegH-Index: 3
Last. Marc AafjesH-Index: 1
view all 4 authors...
Machine learning (ML) offers robust statistical and probabilistic techniques that can help to make sense of large amounts of data. This scoping review paper aims to broadly explore the nature of re...
Nov 1, 2020 in EMNLP (Empirical Methods in Natural Language Processing)
#1Sopan Khosla (CMU: Carnegie Mellon University)H-Index: 5
#2Shikhar Vashishth (CMU: Carnegie Mellon University)H-Index: 11
Last. Carolyn Penstein Rosé (CMU: Carnegie Mellon University)H-Index: 54
view all 4 authors...
Information extraction from conversational data is particularly challenging because the task-centric nature of conversation allows for effective communication of implicit information by humans, but is challenging for machines. The challenges may differ between utterances depending on the role of the speaker within the conversation, especially when relevant expertise is distributed asymmetrically across roles. Further, the challenges may also increase over the conversation as more shared context ...
#1Adam S. Miner (Stanford University)H-Index: 12
#2Albert Haque (Stanford University)H-Index: 13
Last. Nigam H. Shah (Stanford University)H-Index: 63
view all 12 authors...
Accurate transcription of audio recordings in psychotherapy would improve therapy effectiveness, clinician training, and safety monitoring. Although automatic speech recognition software is commercially available, its accuracy in mental health settings has not been well described. It is unclear which metrics and thresholds are appropriate for different clinical use cases, which may range from population descriptions to individual safety monitoring. Here we show that automatic speech recognition ...
This website uses cookies.
We use cookies to improve your online experience. By continuing to use our website we assume you agree to the placement of these cookies.
To learn more, you can find in our Privacy Policy.