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.

MGMT promoter hypermethylation and K-RAS, PTEN and TP53 mutations in tamoxifen-exposed and non-exposed endometrial cancer cases.

BACKGROUND: Tamoxifen has anti-oestrogenic and anti-tumour activity in the breast, but is oestrogenic and carcinogenic in the endometrium. It can induce experimental tumours by both hormonal and DNA-damaging mechanisms, but its carcinogenic mode of action in human endometrium remains unclear. METHODS: We investigated whether an epigenetic mechanism, involving promoter hypermethylation of the gene for the DNA repair enzyme MGMT (O6-methylguanine DNA methyltransferase), was associated with K-RAS, TP53 and PTEN mutations in endometrial tumours from women treated with tamoxifen (TAM, n=30) or unexposed to the drug (EC, n=38). RESULTS: There were significant (P<0.05) differences in tumour grade between the TAM and EC groups, with more favourable morphology in the latter. K-RAS mutations, predominantly G>A, occurred in small numbers in both groups. TP53 mutations were of mainly A>G, C>T and indel modifications in both groups, but more frequent in TAM cases. PTEN mutations dominated in EC tumours and were of the type that has large impact on protein function, such as indel or nonsense mutations. These observations alongside the mutational spectrum in PTEN suggest that the malignancies arise from different backgrounds, hence pointing to an effect of tamoxifen. Both groups displayed MGMT promoter hypermethylation. This coincided with mutations more frequently in the TAM (78%) than in the EC (50%) group, even though there were significantly (P<0.05) fewer mutations and methylations in TAM cases. CONCLUSIONS: Although the difference in coincidence did not reach significance with the current sample size, the findings suggest that epigenetic processes may play a role in the way tamoxifen induces endometrial cancer.

Infrared spectroscopy with multivariate analysis to interrogate endometrial tissue: a novel and objective diagnostic approach.

BACKGROUND: Endometrial cancer is the most common gynaecological malignancy in the United Kingdom. Diagnosis currently involves subjective expert interpretation of highly processed tissue, primarily using microscopy. Previous work has shown that infrared (IR) spectroscopy can be used to distinguish between benign and malignant cells in a variety of tissue types. METHODS: Tissue was obtained from 76 patients undergoing hysterectomy, 36 had endometrial cancer. Slivers of endometrial tissue (tumour and tumour-adjacent tissue if present) were dissected and placed in fixative solution. Before analysis, tissues were thinly sliced, washed, mounted on low-E slides and desiccated; 10 IR spectra were obtained per slice by attenuated total reflection Fourier-transform IR (ATR-FTIR) spectroscopy. Derived data was subjected to principal component analysis followed by linear discriminant analysis. Post-spectroscopy analyses, tissue sections were haematoxylin and eosin-stained to provide histological verification. RESULTS: Using this approach, it is possible to distinguish benign from malignant endometrial tissue, and various subtypes of both. Cluster vector plots of benign (verified post-spectroscopy to be free of identifiable pathology) vs malignant tissue indicate the importance of the lipid and secondary protein structure (Amide I and Amide II) regions of the spectrum. CONCLUSION: These findings point towards the possibility of a simple objective test for endometrial cancer using ATR-FTIR spectroscopy. This would facilitate earlier diagnosis and so reduce the morbidity and mortality associated with this disease.

The syndrome of nonejection click-late systolic murmur and mitral valve prolapse. A case report and review of the subject.

The syndrome of nonejection click-late systolic murmur and mitral valve prolapse is reviewed. A patient with this syndrome is reported. Physical findings, important diagnostic studies, and possible complications are discussed.

Termination of atrial flutter and atrial tachycardia with rapid atrial stimulation.

The results in this series of fifty-seven patients confirms the safety and reliability of rapid atrial stimulation to terminate atrial flutter and atrial tachycardia. Transthoracic wires implanted at thoracotomy or transvenously placed atrial electrodes can be used for the confident intracardiac electrocardiographic diagnosis of tachyarrhythmias and for atrial stimulation. Our experience represents the second largest reported series of patients to undergo cardioversion by this method. In all but five of fifty-seven patients either the atrial tachyarrhythmia was converted to normal sinus rhythm or the flutter-tachycardia was terminated with resultant atrial fibrillation. In forty-three patients sinus rhythm was eventually re-established after atrial stimulation. Various aspects of rapid atrial stimulation, including it's preference over precordial shock, have been discussed. We feel particular consideration should be given cardioversion by rapid atrial stimulation in patients with possible digitalis toxicity and in all patients who have atrial flutter, atrial tachycardia, or junctional tachycardia after open heart surgery.