Improving Cause-of-Death Classification from Verbal Autopsy Reports

Manaka, Thokozile; Zyl, Terence L. van; Kar, D.

doi:10.1007/978-3-031-22321-1_4

Cited by 3 publications

(2 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…On more recent works that incorporate context and character information, [25] achieved recall scores of 0.6990 while [40] gave 0.6000. Taking into account the improvement added by character information on improving CoD classification, [19] added features from multiple domains and reported a score of 0.8755. These findings suggest that our proposed transfer learning methodology can adapt to VA datasets across a variety of demographics as the works compared against used VA datasets collected in other developing countries including Ghana, India and Tanzania.…”

Section: Resultsmentioning

confidence: 99%

“…Multi-source domain adaptation, where more than one source domain and one target domain is available for training has been shown to improve causeof-death (COD) classification from verbal autopsy (VA) reports [19]. Here the authors showed that using a combination of the English and the biomedical domains for learning representations of the VA corpus via character-level embeddings for the English domain and word-level embeddings for the biomedical domain achieved better performances than when embeddings from these two domains were used separately.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Multi-Step Transfer Learning in Natural Language Processing in the Health Domain

Manaka

Zyl

Kar

et al. 2023

Preprint

View full text Add to dashboard Cite

As a result of the restricted access to data in healthcare facilities due to patient privacy and confidentiality policies, the application of general natural language processing (NLP) techniques has advanced relatively slowly in the health domain. Additionally, because clinical data is unique to various institutions and laboratories, there aren't enough standards and standards for data annotation. In places without robust death registration systems, the cause of death (COD) is determined through a verbal autopsy (VA) report. A non-clinician field agent completes a VA report using a set of predefined questions as a guidance in order to identify the symptoms of a COD. The narrative text of the VA report is used as a case study to examine the difficulties of applying NLP techniques to the health care domain.Motivated by multi-step learning where a final learning task is realized via a sequence of intermediate learning tasks, this paper presents a framework to leverage knowledge across the two domain adaptation settings of feature extraction and fine-tuning to improve VA narrative representations for COD classification task in the health domain. We use the Bidirectional Encoder Representations from Transformers (BERT) and Embeddings from Language Models (ELMo) models pretrained on the general English and health domains to extract features from the VA narratives. Our results demonstrate increased performance when the two embeddings from the English and health domains—learned through the domain adaptation tasks of feature extraction and fine-tuning are combined. The advantage of using character embeddings in conjunction with word embeddings is also apparent.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Multi-Step Transfer Learning in Natural Language Processing in the Health Domain

Manaka

Zyl

Kar

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

Sentiment analysis of linguistic cues to assist medical image classification

Kaur,

Malhi,

Pannu

2023

Multimed Tools Appl

View full text Add to dashboard Cite

Multi-step Transfer Learning in Natural Language Processing for the Health Domain

Manaka,

Zyl,

Kar

et al. 2024

Neural Process Lett

Self Cite

View full text Add to dashboard Cite

The restricted access to data in healthcare facilities due to patient privacy and confidentiality policies has led to the application of general natural language processing (NLP) techniques advancing relatively slowly in the health domain. Additionally, because clinical data is unique to various institutions and laboratories, there are not enough standards and conventions for data annotation. In places without robust death registration systems, the cause of death (COD) is determined through a verbal autopsy (VA) report. A non-clinician field agent completes a VA report using a set of standardized questions as guide to identify the symptoms of a COD. The narrative text of the VA report is used as a case study to examine the difficulties of applying NLP techniques to the healthcare domain. This paper presents a framework that leverages knowledge across multiple domains via two domain adaptation techniques: feature extraction and fine-tuning. These techniques aim to improve VA text representations for COD classification tasks in the health domain. The framework is motivated by multi-step learning, where a final learning task is realized via a sequence of intermediate learning tasks. The framework builds upon the strengths of the Bidirectional Encoder Representations from Transformers (BERT) and Embeddings from Language Models (ELMo) models pretrained on the general English and biomedical domains. These models are employed to extract features from the VA narratives. Our results demonstrate improved performance when initializing the learning of BERT embeddings with ELMo embeddings. The benefit of incorporating character-level information for learning word embeddings in the English domain, coupled with word-level information for learning word embeddings in the biomedical domain, is also evident.

show abstract

Improving Cause-of-Death Classification from Verbal Autopsy Reports

Cited by 3 publications

References 22 publications

Multi-Step Transfer Learning in Natural Language Processing in the Health Domain

Multi-Step Transfer Learning in Natural Language Processing in the Health Domain

Sentiment analysis of linguistic cues to assist medical image classification

Multi-step Transfer Learning in Natural Language Processing for the Health Domain

Contact Info

Product

Resources

About