A systematic review of speech recognition technology in health care

Abstract

BackgroundTo undertake a systematic review of existing literature relating to speech recognition technology and its application within health care.MethodsA systematic review of existing literature from 2000 was undertaken. Inclusion criteria were: all papers that referred to speech recognition (SR) in health care settings, used by health professionals (allied health, medicine, nursing, technical or support staff), with an evaluation or patient or staff outcomes. Experimental and non-experimental designs were considered.Six databases (Ebscohost including CINAHL, EMBASE, MEDLINE including the Cochrane Database of Systematic Reviews, OVID Technologies, PreMED-LINE, PsycINFO) were searched by a qualified health librarian trained in systematic review searches initially capturing 1,730 references. Fourteen studies met the inclusion criteria and were retained.ResultsThe heterogeneity of the studies made comparative analysis and synthesis of the data challenging resulting in a narrative presentation of the results. SR, although not as accurate as human transcription, does deliver reduced turnaround times for reporting and cost-effective reporting, although equivocal evidence of improved workflow processes.ConclusionsSR systems have substantial benefits and should be considered in light of the cost and selection of the SR system, training requirements, length of the transcription task, potential use of macros and templates, the presence of accented voices or experienced and in-experienced typists, and workflow patterns.

Medizinische Spracherkennung im stationären und ambulanten Einsatz – Eine systematische Übersicht

“…Einbezogen wurden ausschließlich Arbeiten, die seit dem Jahr 2000 veröffentlicht wurden. Diese Entscheidung beruht auf der Annahme, dass die Spracherkennungstechnologie ab dem Jahr 2000 einen deutlichen Schritt bezüglich ihrer Genauigkeit für die Verwendung im medizinischen Bereich aufzeigt [4]. Es wurden alle Studien eingeschlossen, in denen die Spracherkennung von medizinischem Personal, wie Ärzten in Weiterbildung, Fachärzten oder Krankenpflegern verwendet wurde.…”

“…Im Gegensatz zum traditionellen Diktat, ist bei der Verwendung der digitalen Spracherkennung keine zusätzliche Schreibkraft erforderlich, da die diktierten Wörter automatisch in Fließtext transformiert werden können. Auf diese Weise soll die Nutzung der digitalen Spracherkennung die aufgewendete Dokumentationszeit reduzieren und dabei kosteneinsparende Eigenschaften besitzen [4].…”

Learning to Detect Dysarthria from Raw Speech

“…In this work, we propose to apply such end-to-end systems to another paralinguistic task: the detection of dysarthria from speech recordings. There is a growing interest in automatically extracting information from speech for health care [8,9,10], and unlike a feature-driven approach that would require testing various combinations of fixed features, we implement a system that can directly process raw speech and learn relevant features jointly with the dysarthria classifier, such that they will be optimal for the task.…”

Asynchronous Speech Recognition Affects Physician Editing of Notes

“…6 However, broader use of ASR in the clinical setting is limited by editing time, uncaught errors, as well as administrative overhead. 9 ASR lacks the accuracy of traditional dictation, 10 requiring clinicians, rather than transcriptionists, to either spend time editing ASR transcripts or accept flawed documentation. 11 Interactive editing and dictation with ASR can provide increased speed, longer notes, and improved physician mood over typing alone.…”