Towards Unsupervised Subject-Independent Speech-Based Relapse Detection in Patients with Psychosis using Variational Autoencoders

Garoufis, Christos; Zlatintsi, Athanasia; Filntisis, Panagiotis P.; Efthymiou, Niki; Kalisperakis, Emmanouil; Karantinos, Thomas; Lazaridi, Marina; Smyrnis, Nikolaos; Maragos, Petros

doi:10.23919/eusipco55093.2022.9909841

Cited by 4 publications

(5 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The researchers first created spectograms from audio signals and then extracted features of them. Garoufis et al ( 59 , 60 ) utilized unsupervised learning with Convolutional Variational Autoencoders (CVAE), a type of generative model, to learn latent representations of speech data. By comparing the reconstructed speech to the original, the model identified deviations that may indicate relapse episodes.…”

Section: State-of-the Art Approaches To the Automated Analysis Of Spe...mentioning

confidence: 99%

“…By comparing the reconstructed speech to the original, the model identified deviations that may indicate relapse episodes. Their studies demonstrated the feasibility of unsupervised learning methods for detecting relapses based on speech characteristics, without requiring labeled data or subject-specific models – although it is important to note that these findings based on preliminary data from an ongoing study, therefore have been tested with limited sample sizes ( N = 5 and N = 13) ( 59 , 60 ). Fu et al ( 36 ) focused on schizophrenia and proposed an end-to-end architecture, called Sch-net for automatic detection of schizophrenia from speech.…”

Section: State-of-the Art Approaches To the Automated Analysis Of Spe...mentioning

confidence: 99%

See 1 more Smart Citation

Automated analysis of speech as a marker of sub-clinical psychotic experiences

Olah,

Spencer,

Cummins

et al. 2024

Front. Psychiatry

View full text Add to dashboard Cite

Automated speech analysis techniques, when combined with artificial intelligence and machine learning, show potential in capturing and predicting a wide range of psychosis symptoms, garnering attention from researchers. These techniques hold promise in predicting the transition to clinical psychosis from at-risk states, as well as relapse or treatment response in individuals with clinical-level psychosis. However, challenges in scientific validation hinder the translation of these techniques into practical applications. Although sub-clinical research could aid to tackle most of these challenges, there have been only few studies conducted in speech and psychosis research in non-clinical populations. This work aims to facilitate this work by summarizing automated speech analytical concepts and the intersection of this field with psychosis research. We review psychosis continuum and sub-clinical psychotic experiences, and the benefits of researching them. Then, we discuss the connection between speech and psychotic symptoms. Thirdly, we overview current and state-of-the art approaches to the automated analysis of speech both in terms of language use (text-based analysis) and vocal features (audio-based analysis). Then, we review techniques applied in subclinical population and findings in these samples. Finally, we discuss research challenges in the field, recommend future research endeavors and outline how research in subclinical populations can tackle the listed challenges.

show abstract

Section: State-of-the Art Approaches To the Automated Analysis Of Spe...mentioning

confidence: 99%

Section: State-of-the Art Approaches To the Automated Analysis Of Spe...mentioning

confidence: 99%

Automated analysis of speech as a marker of sub-clinical psychotic experiences

Olah,

Spencer,

Cummins

et al. 2024

Front. Psychiatry

View full text Add to dashboard Cite

show abstract

“…Recurrent neural networks (RNNs) can be used to process sequential data such as time‐series data from wearable devices or EHRs to predict health outcomes 26 . Generative models such as variational autoencoders (VAEs) can be used to generate synthetic data for use in personalized medicine and drug discovery 27 …”

Section: Approaches For Personalized Health Monitoringmentioning

confidence: 99%

“…26 Generative models such as variational autoencoders (VAEs) can be used to generate synthetic data for use in personalized medicine and drug discovery. 27 To fully comprehend the distinctive contributions of DL applications for individualized health monitoring, specificity is essential. CNNs, for example, are very good at interpreting time-series data from wearables, making it possible to identify irregularities in heart rate or activity levels.…”

Section: Overview Of DL Modelsmentioning

confidence: 99%

Deep learning for personalized health monitoring and prediction: A review

Damaševičius,

Jagatheesaperumal,

Kandala

et al. 2024

Computational Intelligence

View full text Add to dashboard Cite

Personalized health monitoring and prediction are indispensable in advancing healthcare delivery, particularly amidst the escalating prevalence of chronic illnesses and the aging population. Deep learning (DL) stands out as a promising avenue for crafting personalized health monitoring systems adept at forecasting health outcomes with precision and efficiency. As personal health data becomes increasingly accessible, DL‐based methodologies offer a compelling strategy for enhancing healthcare provision through accurate and timely prognostications of health conditions. This article offers a comprehensive examination of recent advancements in employing DL for personalized health monitoring and prediction. It summarizes a diverse range of DL architectures and their practical implementations across various realms, such as wearable technologies, electronic health records (EHRs), and data accumulated from social media platforms. Moreover, it elucidates the obstacles encountered and outlines future directions in leveraging DL for personalized health monitoring, thereby furnishing invaluable insights into the immense potential of DL in this domain.

show abstract

“…Recurrent neural networks (RNNs) can be used to process sequential data such as time-series data from wearable devices or electronic health records to predict health outcomes [25]. Generative models such as variational autoencoders (VAEs) can be used to generate synthetic data for use in personalized medicine and drug discovery [26].…”

Section: Overview Of Deep Learning Modelsmentioning

confidence: 99%

Deep Learning for Personalized Health Monitoring and Prediction: A Review

Damaševicˇius,

Jagatheesaperumal

et al. 2023

Preprint

View full text Add to dashboard Cite

Personalized health monitoring and prediction have become essential for improving health- care delivery, especially with the growing prevalence of chronic diseases and an aging population. Deep learning (DL) has emerged as a promising approach for developing personalized health mon- itoring systems that can predict health outcomes accurately and efficiently. With the increasing availability of personal health data, DL-based methods have emerged as a promising approach to improve healthcare delivery by providing accurate and timely predictions of health outcomes. This article provides a comprehensive review of the recent developments in the application of DL for personalized health monitoring and prediction. It summarizes various DL architectures and their applications for personalized health monitoring, including wearable devices, electronic health records, and social media data. Furthermore, the article also explores the challenges and future directions for the application of DL in personalized health monitoring. valuable insights into the potential of DL for personalized health monitoring and prediction.

show abstract

Towards Unsupervised Subject-Independent Speech-Based Relapse Detection in Patients with Psychosis using Variational Autoencoders

Cited by 4 publications

References 24 publications

Automated analysis of speech as a marker of sub-clinical psychotic experiences

Automated analysis of speech as a marker of sub-clinical psychotic experiences

Deep learning for personalized health monitoring and prediction: A review

Deep Learning for Personalized Health Monitoring and Prediction: A Review

Contact Info

Product

Resources

About