Medical Speech Recognition: Reaching Parity with Humans

Edwards, Erik; Salloum, Wael; Finley, Greg; Fone, James; Cardiff, Greg; Miller, Mark A.; Suendermann-Oeft, David

doi:10.1007/978-3-319-66429-3_51

Cited by 27 publications

(14 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…More recently, a neural network based speech recognition system has been built for the medical domain using relatively small medical speech data (270 hours) and has been benchmarked against medical transcriptionists [3]. Speech recognition systems have been evaluated on a clinical question answering task and it has been shown that domain adaptation with a language model improves the accuracy in interpreting spoken clinical questions significantly [4].…”

Section: Introductionmentioning

confidence: 99%

Speech Recognition for Medical Conversations

et al. 2018

View full text Add to dashboard Cite

In this paper we document our experiences with developing speech recognition for medical transcription -a system that automatically transcribes doctor-patient conversations. Towards this goal, we built a system along two different methodological lines -a Connectionist Temporal Classification (CTC) phoneme based model and a Listen Attend and Spell (LAS) grapheme based model. To train these models we used a corpus of anonymized conversations representing approximately 14,000 hours of speech. Because of noisy transcripts and alignments in the corpus, a significant amount of effort was invested in data cleaning issues. We describe a two-stage strategy we followed for segmenting the data. The data cleanup and development of a matched language model was essential to the success of the CTC based models. The LAS based models, however were found to be resilient to alignment and transcript noise and did not require the use of language models. CTC models were able to achieve a word error rate of 20.1%, and the LAS models were able to achieve 18.3%. Our analysis shows that both models perform well on important medical utterances and therefore can be practical for transcribing medical conversations.

show abstract

Section: Introductionmentioning

confidence: 99%

Speech Recognition for Medical Conversations

et al. 2018

View full text Add to dashboard Cite

show abstract

“…46 Another study developed a deep neural network model for medical voice recognition trained on over 270 hours of speech data and compared the performance to professional medical transcriptionists. 47 The model had a 15.4% error rate when applied to a "realistic clinical use case" and performed equally as well as humans. 47 The 2 studies discussed here illustrate the ability of ML to recognize real conversations between patients and providers.…”

Section: Clinical Assistancementioning

confidence: 94%

“…47 The model had a 15.4% error rate when applied to a "realistic clinical use case" and performed equally as well as humans. 47 The 2 studies discussed here illustrate the ability of ML to recognize real conversations between patients and providers. With further refinement, this software could be hugely beneficial for clinical and office work, creating less need for providers to manually input notes.…”

Section: Clinical Assistancementioning

confidence: 94%

Applications of Machine Learning Using Electronic Medical Records in Spine Surgery

et al. 2019

View full text Add to dashboard Cite

Developments in machine learning in recent years have precipitated a surge in research on the applications of artificial intelligence within medicine. Machine learning algorithms are beginning to impact medicine broadly, and the field of spine surgery is no exception. Electronic medical records are a key source of medical data that can be leveraged for the creation of clinically valuable machine learning algorithms. This review examines the current state of machine learning using electronic medical records as it applies to spine surgery. Studies across the electronic medical record data domains of imaging, text, and structured data are reviewed. Discussed applications include clinical prognostication, preoperative planning, diagnostics, and dynamic clinical assistance, among others. The limitations and future challenges for machine learning research using electronic medical records are also discussed.

show abstract

“…To date, research effort has focused on solving foundational problems in the development of a digital scribe, including ASR of medical conversations, 10,11 automatically populating the review of symptoms discussed in a medical encounter, 12 extracting symptoms from medical conversations, 13,14 and generating medical reports from dictations. 15,16 While these developments are promising, several challenges hinder the implementation of a fully functioning digital scribe and its evaluation in a clinical environment.…”

Section: Introductionmentioning

confidence: 99%

Challenges of developing a digital scribe to reduce clinical documentation burden

et al. 2019

View full text Add to dashboard Cite

Clinicians spend a large amount of time on clinical documentation of patient encounters, often impacting quality of care and clinician satisfaction, and causing physician burnout. Advances in artificial intelligence (AI) and machine learning (ML) open the possibility of automating clinical documentation with digital scribes, using speech recognition to eliminate manual documentation by clinicians or medical scribes. However, developing a digital scribe is fraught with problems due to the complex nature of clinical environments and clinical conversations. This paper identifies and discusses major challenges associated with developing automated speech-based documentation in clinical settings: recording high-quality audio, converting audio to transcripts using speech recognition, inducing topic structure from conversation data, extracting medical concepts, generating clinically meaningful summaries of conversations, and obtaining clinical data for AI and ML algorithms.npj Digital Medicine (2019) 2:114 ; https://doi.

show abstract

Medical Speech Recognition: Reaching Parity with Humans

Cited by 27 publications

References 45 publications

Speech Recognition for Medical Conversations

Speech Recognition for Medical Conversations

Applications of Machine Learning Using Electronic Medical Records in Spine Surgery

Challenges of developing a digital scribe to reduce clinical documentation burden

Contact Info

Product

Resources

About