A user evaluation of speech/phrase recognition software in critically ill patients: a DECIDE-AI feasibility study

OBJECTIVES

Evaluating effectiveness of speech/phrase recognition software in critically ill patients with speech impairments.

DESIGN

Prospective study.

SETTING

Tertiary hospital critical care unit in the northwest of England.

PARTICIPANTS

14 patients with tracheostomies, 3 female and 11 male.

MAIN OUTCOME MEASURES

Evaluation of dynamic time warping (DTW) and deep neural networks (DNN) methods in a speech/phrase recognition application. Using speech/phrase recognition app for voice impaired (SRAVI), patients attempted mouthing various supported phrases with recordings evaluated by both DNN and DTW processing methods. Then, a trio of potential recognition phrases was displayed on the screen, ranked from first to third in order of likelihood.

RESULTS

A total of 616 patient recordings were taken with 516 phrase identifiable recordings. The overall results revealed a total recognition accuracy across all three ranks of 86% using the DNN method. The rank 1 recognition accuracy of the DNN method was 75%. The DTW method had a total recognition accuracy of 74%, with a rank 1 accuracy of 48%.

CONCLUSION

This feasibility evaluation of a novel speech/phrase recognition app using SRAVI demonstrated a good correlation between spoken phrases and app recognition. This suggests that speech/phrase recognition technology could be a therapeutic option to bridge the gap in communication in critically ill patients.

WHAT IS ALREADY KNOWN ABOUT THIS TOPIC

Communication can be attempted using visual charts, eye gaze boards, alphabet boards, speech/phrase reading, gestures and speaking valves in critically ill patients with speech impairments.

WHAT THIS STUDY ADDS

Deep neural networks and dynamic time warping methods can be used to analyse lip movements and identify intended phrases.

HOW THIS STUDY MIGHT AFFECT RESEARCH, PRACTICE AND POLICY

Our study shows that speech/phrase recognition software has a role to play in bridging the communication gap in speech impairment.

Rational screening of biomineralisation peptides for colour-selected one-pot gold nanoparticle syntheses

Biomineralisation peptides that facilitate the one-pot synthesis of gold nanoparticles (AuNPs) with selected optical properties, were screened using a coherent peptide-spotted array consisting of a AuNP binding peptide library. As the biomineralised AuNPs were captured on each peptide spot, analysis of the images provided information on their collective optical properties.

Failure to induce reactive hypoglycaemia by drinking a starch-based alcohol beverage (sorghum beer)

Alcohol is a well-recognised cause of fasting hypoglycaemia but may also provoked reactive hypoglycaemia when drunk together with a carbohydratee mixer. In this study the ability of sorghum beer (an 'in-built' alcohol-starch beverage widely enjoyed in Southern Africa) to induce reactive hypoglycaemia was compared with "gin and tonic' in eight non-obese health African men. After an overnight fast, each subject drank, in random sequence on their different occasions, 2 litres of sorghum beer (carbohydrat content approximately 5% and alcohol concentration 2.24 g/dl-2.8% v/v), the same volume of a control solution providing a similar carbohydrate load, or a gin and standard tonic water mixture. No evidence of reactive hypoglycaemia was apparent during the 5 hours after the beginning of the sorghum beer tolerance tests, despite a mean peak blood alcohol level reaching 80 mg/dl. both the peak and total plasma insulin responses were significantly reduced (p less than or equal to 0.05) when compared to the brisk responses elicited by the carbohydrate solution alone and the gin and tonic drinks, with consequent hypoglycaemia. These data suggest that African home-brews are not potent causes of reactive hypoglycaemia, although they may be implicated in the development of ethanol-induced hypoglycaemia in the fasting state.