Automated Speech Audiometry: Can It Work Using Open-Source Pre-Trained Kaldi-NL Automatic Speech Recognition?

A practical speech audiometry tool is the digits-in-noise (DIN) test for hearing screening of populations of varying ages and hearing status. The test is usually conducted by a human supervisor (e.g., clinician), who scores the responses spoken by the listener, or online, where software scores the responses entered by the listener. The test has 24-digit triplets presented in an adaptive staircase procedure, resulting in a speech reception threshold (SRT). We propose an alternative automated DIN test setup that can evaluate spoken responses whilst conducted without a human supervisor, using the open-source automatic speech recognition toolkit, Kaldi-NL. Thirty self-reported normal-hearing Dutch adults (19-64 years) completed one DIN + Kaldi-NL test. Their spoken responses were recorded and used for evaluating the transcript of decoded responses by Kaldi-NL. Study 1 evaluated the Kaldi-NL performance through its word error rate (WER), percentage of summed decoding errors regarding only digits found in the transcript compared to the total number of digits present in the spoken responses. Average WER across participants was 5.0% (range 0-48%, SD = 8.8%), with average decoding errors in three triplets per participant. Study 2 analyzed the effect that triplets with decoding errors from Kaldi-NL had on the DIN test output (SRT), using bootstrapping simulations. Previous research indicated 0.70 dB as the typical within-subject SRT variability for normal-hearing adults. Study 2 showed that up to four triplets with decoding errors produce SRT variations within this range, suggesting that our proposed setup could be feasible for clinical applications.

Extracting regulatory active chromatin footprint from cell-free DNA.

Cell-free DNA (cfDNA) has emerged as a pivotal player in precision medicine, revolutionizing the diagnostic and therapeutic landscape. While its clinical applications have significantly increased in recent years, current cfDNA assays have limited ability to identify the active transcriptional programs that govern complex disease phenotypes and capture the heterogeneity of the disease. To address these limitations, we have developed a non-invasive platform to enrich and examine the active chromatin fragments (cfDNAac) in peripheral blood. The deconvolution of the cfDNAac signal from traditional nucleosomal chromatin fragments (cfDNAnuc) yields a catalog of features linking these circulating chromatin signals in blood to specific regulatory elements across the genome, including enhancers, promoters, and highly transcribed genes, mirroring the epigenetic data from the ENCODE project. Notably, these cfDNAac counts correlate strongly with RNA polymerase II activity and exhibit distinct expression patterns for known circadian genes. Additionally, cfDNAac signals across gene bodies and promoters show strong correlations with whole blood gene expression levels defined by GTEx. This study illustrates the utility of cfDNAac analysis for investigating epigenomics and gene expression, underscoring its potential for a wide range of clinical applications in precision medicine.

Natural Language Processing Markers for Psychosis and Other Psychiatric Disorders: Emerging Themes and Research Agenda From a Cross-Linguistic Workshop.

This workshop summary on natural language processing (NLP) markers for psychosis and other psychiatric disorders presents some of the clinical and research issues that NLP markers might address and some of the activities needed to move in that direction. We propose that the optimal development of NLP markers would occur in the context of research efforts to map out the underlying mechanisms of psychosis and other disorders. In this workshop, we identified some of the challenges to be addressed in developing and implementing NLP markers-based Clinical Decision Support Systems (CDSSs) in psychiatric practice, especially with respect to psychosis. Of note, a CDSS is meant to enhance decision-making by clinicians by providing additional relevant information primarily through software (although CDSSs are not without risks). In psychiatry, a field that relies on subjective clinical ratings that condense rich temporal behavioral information, the inclusion of computational quantitative NLP markers can plausibly lead to operationalized decision models in place of idiosyncratic ones, although ethical issues must always be paramount.

Recognizing hotspots in Brief Eclectic Psychotherapy for PTSD by text and audio mining.

Background: Identifying and addressing hotspots is a key element of imaginal exposure in Brief Eclectic Psychotherapy for PTSD (BEPP). Research shows that treatment effectiveness is associated with focusing on these hotspots and that hotspot frequency and characteristics may serve as indicators for treatment success. Objective: This study aims to develop a model to automatically recognize hotspots based on text and speech features, which might be an efficient way to track patient progress and predict treatment efficacy. Method: A multimodal supervised classification model was developed based on analog tape recordings and transcripts of imaginal exposure sessions of 10 successful and 10 non-successful treatment completers. Data mining and machine learning techniques were used to extract and select text (e.g. words and word combinations) and speech (e.g. speech rate, pauses between words) features that distinguish between 'hotspot' (N = 37) and 'non-hotspot' (N = 45) phases during exposure sessions. Results: The developed model resulted in a high training performance (mean F 1-score of 0.76) but a low testing performance (mean F 1-score = 0.52). This shows that the selected text and speech features could clearly distinguish between hotspots and non-hotspots in the current data set, but will probably not recognize hotspots from new input data very well. Conclusions: In order to improve the recognition of new hotspots, the described methodology should be applied to a larger, higher quality (digitally recorded) data set. As such this study should be seen mainly as a proof of concept, demonstrating the possible application and contribution of automatic text and audio analysis to therapy process research in PTSD and mental health research in general.

Antecedentes:La identificación y el abordaje de los puntos críticos (hotspots en inglés) es un elemento clave para exposición imaginaria en la Psicoterapia Ecléctica Breve para TEPT (BEPP por sus siglas en inglés). La investigación muestra que la efectividad del tratamiento se asocia con la focalización en estos puntos críticosy que la frecuencia y características de los puntos críticos podría servir de indicador para el éxito terapéutico.Objetivo: Este estudio tiene como objetivo desarrollar un modelo para reconocer automáticamente los puntos críticos basados en características de texto y discurso, lo que podría ser una forma eficiente de seguir los progresos del paciente y predecir la eficacia del tratamiento.Metodo: Se desarrolló un modelo de clasificación supervisada multimodal basado en grabaciones y transcripciones de cintas analógicas de sesiones de exposición imaginaria de diez de tratamiento exitosos y diez no exitosos. Se usaron técnicas de minería de datos y técnicas de aprendizaje automático para extraer y seleccionar las características de texto (ej., palabras y combinaciones de palabras) y discurso (ej., velocidad del discurso, pausas entre las palabras) que distinguen entre las fases de 'puntos críticos' (N= 37) y ' puntos no críticos' (N= 45) durante las sesiones de exposición.Resultados: El modelo desarrollado resultó en un alto rendimiento de entrenamiento (puntaje F1 promedio de 0.76) pero un bajo rendimiento de prueba (puntaje F1 promedio = 0.52). Esto muestra que las características de los textos y discursos seleccionados podrían distinguir claramente entre puntos críticos y puntos no críticos en el conjunto de datos actual, pero probablemente no reconocerá muy bien los puntos críticos de nuevos datos de entrada.Conclusiones: Para mejorar el reconocimiento de nuevos puntos críticos, la metodología descrita debería ser aplicada a un conjunto de datos más grande y de mejor alta calidad (grabado digital). Como tal, este estudio debe verse principalmente como una prueba de concepto, demostrando la posible aplicación y contribución del análisis automático de texto y audio para la investigación del proceso terapéutico en TEPT e investigación en salud mental en general.