Multi-modality Hierarchical Recall based on GBDTs for Bipolar Disorder Classification

Xing, Xiaofen; Cai, Bolun; Zhao, Yinhu; Li, Shuzhen; Fan, Weiquan

doi:10.1145/3266302.3266311

Cited by 18 publications

(26 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is unlikely that performance will generalize as reported if studies did not evaluate performance on a representative held‐out test set (which are most studies in this review) and instead used some form of cross‐validation (which is the case in most reviewed studies), which is likely overfitting (see Figures and ). This limited generalizability and overfitting are observed for instance in the drop in performance from development to test set in submissions to the AVEC challenges . For results that used held‐out test sets, which are more likely to generalize if they are representative, scores range from close to chance to higher scores including Afshan et al (F1‐score = 0.95) which most likely benefited from having a large sample size (N depressed = 735, N controls = 953) and all participants being the same sex (female).…”

Section: Discussionmentioning

confidence: 99%

Automated assessment of psychiatric disorders using speech: A systematic review

Low

Bentley

Ghosh

2020

Laryngoscope Investig Oto

316

268

View full text Add to dashboard Cite

Objective There are many barriers to accessing mental health assessments including cost and stigma. Even when individuals receive professional care, assessments are intermittent and may be limited partly due to the episodic nature of psychiatric symptoms. Therefore, machine‐learning technology using speech samples obtained in the clinic or remotely could one day be a biomarker to improve diagnosis and treatment. To date, reviews have only focused on using acoustic features from speech to detect depression and schizophrenia. Here, we present the first systematic review of studies using speech for automated assessments across a broader range of psychiatric disorders. Methods We followed the Preferred Reporting Items for Systematic Reviews and Meta‐Analysis (PRISMA) guidelines. We included studies from the last 10 years using speech to identify the presence or severity of disorders within the Diagnostic and Statistical Manual of Mental Disorders (DSM‐5). For each study, we describe sample size, clinical evaluation method, speech‐eliciting tasks, machine learning methodology, performance, and other relevant findings. Results 1395 studies were screened of which 127 studies met the inclusion criteria. The majority of studies were on depression, schizophrenia, and bipolar disorder, and the remaining on post‐traumatic stress disorder, anxiety disorders, and eating disorders. 63% of studies built machine learning predictive models, and the remaining 37% performed null‐hypothesis testing only. We provide an online database with our search results and synthesize how acoustic features appear in each disorder. Conclusion Speech processing technology could aid mental health assessments, but there are many obstacles to overcome, especially the need for comprehensive transdiagnostic and longitudinal studies. Given the diverse types of data sets, feature extraction, computational methodologies, and evaluation criteria, we provide guidelines for both acquiring data and building machine learning models with a focus on testing hypotheses, open science, reproducibility, and generalizability. Level of Evidence 3a

show abstract

Section: Discussionmentioning

confidence: 99%

Automated assessment of psychiatric disorders using speech: A systematic review

Low

Bentley

Ghosh

2020

Laryngoscope Investig Oto

316

268

View full text Add to dashboard Cite

show abstract

“…Iit is unlikely that performance will generalize as reported if studies did not evaluate performance on a representative held-out test set (which are most studies in this review) and instead used some form of cross-validation (which is the case in most reviewed studies), which is likely overfitting (see Figure 1 and Figure 5). This limited generalizability and overfitting are observed for instance in the drop in performance from development to test set in submissions to the AVEC challenges 8,9,60,63 . For results that used held-out test sets, which are more likely to generalize if they are representative, scores range from close to chance to higher scores including Afshan and colleagues (2018) 64 (F1-score = 0.95) which most likely benefited from having a large sample size (N depressed = 735, N controls = 953) and all participants being the same sex (female).…”

Section: Discussionmentioning

confidence: 99%

Automated Assessment of Psychiatric Disorders Using Speech: A Systematic Review

Low¹,

Bentley²,

Ghosh³

2019

Preprint

View full text Add to dashboard Cite

Objective: There are many barriers to accessing mental health assessments including cost and stigma. Even when individuals receive professional care, assessments are intermittent and may be limited partly due to the episodic nature of psychiatric symptoms. Therefore, machine learning technology using speech samples obtained in the clinic or remotely could one day be a biomarker to improve diagnosis and treatment. To date, reviews have only focused on using acoustic features from speech to detect depression and schizophrenia. Here we present the first systematic review of studies using speech for automated assessments across a broader range of psychiatric disorders.Methods: We followed the Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA) guidelines. We included studies from the last 10 years using speech to identify the presence or severity of disorders within the Diagnostic and Statistical Manual of Mental Disorders (DSM–5). For each disorder we describe sample size, clinical evaluation method, speech-eliciting tasks, machine learning methodology, performance, and other relevant findings. Results: 1395 studies were screened of which 127 studies met the inclusion criteria. The majority of studies were on depression, schizophrenia, and bipolar disorder, and the remaining on post-traumatic stress disorder, anxiety disorders, and eating disorders. 63% of studies built machine learning predictive models, and the remaining 37% performed null-hypothesis testing only. We provide an online database with our search results and synthesize how acoustic features appear in each disorder.Conclusion: Speech processing technology could aid mental health assessments, but there are many obstacles to overcome, especially the need for comprehensive transdiagnostic and longitudinal studies. Given the diverse types of datasets, feature extraction, computational methodologies, and evaluation criteria, we provide guidelines for both acquiring data and building machine learning models with a focus on testing hypotheses, open science, reproducibility, and generalizability.

show abstract

“…SVMs (A) [26] 55.0 50.0 GEWELMs (A) [30] 55.0 48.2 Multistream (A+V) [35] 78.3 40.7 IncepLSTM (A+V) [12] 65.1 -Hierarchical recall model(A+V) [33] 86.8 57.4 Multi-instance learning (A only) 61.6 57.4…”

Section: Uar[%] Dev T Estmentioning

confidence: 99%

“…The best result obtained by our proposed method is highly competitive with those obtained by state-of-the-art methods (Table 4). Except for [35] which also segmented the speech files, these methods fed features obtained from the full audio/video records into SVMs [26], Greedy Ensembles of Weighted Extreme Learning Machines (GEWELMs) [30], Inception LSTM (IncepLSTM) [12], or a hierarchical recall decision tree model [33]. Our multi-instance learning method performs better than all other audio-based methods, and better than, or comparable with, the methods using both speech and visual information.…”

Section: Uar[%] Dev T Estmentioning

confidence: 99%

“…This approach consisted of an Inception Net [31] combined with an LSTM-RNN designed to learn multi-resolution features from a Mel Frequency Cepstral Coefficients (MFCCs) feature space. Interestingly, other than the AVEC 2018 baseline system [26], this approach did not outperform the more conventional machine learning systems presented in the challenge [30,33].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Multi-instance Learning for Bipolar Disorder Diagnosis using Weakly Labelled Speech Data

Ren

Cummins

Kong

et al. 2019

Proceedings of the 9th International Conference on Digital Public Health

View full text Add to dashboard Cite

While deep learning is undoubtedly the predominant learning technique across speech processing, it is still not widely used in healthbased applications. The corpora available for health-style recognition problems are often small, both concerning the total amount of data available and the number of individuals present. The Bipolar Disorder corpus, used in the 2018 Audio/Visual Emotion Challenge, contains only 218 audio samples from 46 individuals. Herein, we present a multi-instance learning framework aimed at constructing more reliable deep learning-based models in such conditions. First, we segment the speech files into multiple chunks. However, the problem is that each of the individual chunks is weakly labelled, as they are annotated with the label of the corresponding speech file, but may not be indicative of that label. We then train the deep learning-based (ensemble) multi-instance learning model, aiming at solving such a weakly labelled problem. The presented results demonstrate that this approach can improve the accuracy of feedforward, recurrent, and convolutional neural nets on the 3-class mania classification tasks undertaken on the Bipolar Disorder corpus. CCS CONCEPTS • Computing methodologies → Supervised learning by classification; • Applied computing → Health care information systems; Health informatics.

show abstract

Multi-modality Hierarchical Recall based on GBDTs for Bipolar Disorder Classification

Cited by 18 publications

References 19 publications

Automated assessment of psychiatric disorders using speech: A systematic review

Automated assessment of psychiatric disorders using speech: A systematic review

Automated Assessment of Psychiatric Disorders Using Speech: A Systematic Review

Multi-instance Learning for Bipolar Disorder Diagnosis using Weakly Labelled Speech Data

Contact Info

Product

Resources

About