Longitudinal analysis of discussion topics in an online breast cancer community using convolutional neural networks

Zhang, Shaodian; Grave, Édouard; Sklar, Elizabeth; Elhadad, Noémie

doi:10.1016/j.jbi.2017.03.012

Cited by 54 publications

(36 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Adequate social support from closed people such as family, friend and neighbour were significantly improved quality of life of breast cancer patients (20). Support from the peers can tend to disclose more personal information, discuss more private stories, and exchange more support emotionally, meanwhile they seek help less but provide more, and shifted their interest from cancer diagnosis to cancer treatment (21). These supportive resources can be emotional, physical, informational, and companionship-related (17).…”

Section: Discussionmentioning

confidence: 99%

Breast cancer stigma among Indonesian female: a case study breast cancer patient.

S¹,

Matahari²,

Fp³

et al. 2019

Preprint

View full text Add to dashboard Cite

Background: Stigma of cancer patients was identified with death, making cancer is the most feared diseases by mankind worldwide especially cancer patients and their families. A critical evaluation of the breast cancer stigma regarding breast cancer screening behaviour is poorly understood, so we aimed to analyse the stigmatization of breast cancer patient in Indonesia for reducing morbidity and mortality of breast cancer. Methods: A qualitative study using focus group discussion and in-depth interviews with thematic analysis was conducted in this research. Results: The informants endured the pain of their breast and kept the referral letter which the medical doctor advised to medical treatment for three months later due to their embarrassment. Traditional healing using scrapping as known ‘kerokan’ and consumed some traditional drink were done by most informants to decrease the pain on their breast. Finally, most informants were diagnosed in an advanced stage when they returned to the health facilities. In addition, financial difficulties were noted as barriers of breast cancer screening in such Indonesia. Conclusions: Feeling fear and shame when diagnosed with breast cancer were identified in this study. Alternative treatment using scrapping as known ‘kerokan’ lead the first seeking help for breast cancer symptoms due to financial difficulties among patient of breast cancer. Diagnosed in an advanced stage was revealed by most of the informants after they returned back to health facilities.

show abstract

Section: Discussionmentioning

confidence: 99%

Breast cancer stigma among Indonesian female: a case study breast cancer patient.

S¹,

Matahari²,

Fp³

et al. 2019

Preprint

View full text Add to dashboard Cite

show abstract

“…However, their power is limited for discovering individuallevel health stages and health network patterns due to the privacy issues involved and data scarcity. There have been several analyses of breast cancer forum data [4], [5] and, more recently, machine learning models have been used for longitudinal analysis [6] and some binary classification tasks [7]. However, we are the first to propose a general framework that can achieve health stage sequence inference using online forum data.…”

Section: A Online Health Communities Analysismentioning

confidence: 99%

“…The communications and interactions between patients in online forums can provide valuable information about a patient's emotional well-being and behaviors related to the management of their health that conventional clinical data collected from hospital information systems and electronic health records (EHR) is unable to capture. The synergies between the information on patients' online communication and health status make possible a unique and wide range of research topics on health informatics [4]- [6] that rely on both patients' interactions in online forums as well as their health stage records.…”

Section: Introductionmentioning

confidence: 99%

DynGraph2Seq: Dynamic-Graph-to-Sequence Interpretable Learning for Health Stage Prediction in Online Health Forums

Gao

Homayoun

et al. 2019

2019 IEEE International Conference on Data Mining (ICDM)

View full text Add to dashboard Cite

Online health communities such as the online breast cancer forum enable patients (i.e., users) to interact and help each other within various subforums, which are subsections of the main forum devoted to specific health topics. The changing nature of the users' activities in different subforums can be strong indicators of their health status changes. This additional information could allow health-care organizations to respond promptly and provide additional help for the patient. However, modeling complex transitions of an individual user's activities among different subforums over time and learning how these correspond to his/her health stage are extremely challenging. In this paper, we first formulate the transition of user activities as a dynamic graph with multi-attributed nodes, then formalize the health stage inference task as a dynamic graph-to-sequence learning problem, and hence propose a novel dynamic graphto-sequence neural networks architecture (DynGraph2Seq) to address all the challenges. Our proposed DynGraph2Seq model consists of a novel dynamic graph encoder and an interpretable sequence decoder that learn the mapping between a sequence of time-evolving user activity graphs and a sequence of target health stages. We go on to propose dynamic graph hierarchical attention mechanisms to facilitate the necessary multi-level interpretability. A comprehensive experimental analysis of its use for a health stage prediction task demonstrates both the effectiveness and the interpretability of the proposed models.

show abstract

“…These vectors directly guide primitive natural language processing tasks such as part-of-speech tagging and statistical parsing as well as high-level tasks such as text classification and machine translation. Convolutional neural networks have been used in a wide array of natural language processing tasks including relation extraction [8], sentiment analysis [9], and other text classification tasks [10, 11, 12]. …”

Section: Related Workmentioning

confidence: 99%

Ordinal convolutional neural networks for predicting RDoC positive valence psychiatric symptom severity scores

Rios¹,

Kavuluru²

2017

Journal of Biomedical Informatics

View full text Add to dashboard Cite

Background The CEGS N-GRID 2016 Shared Task in Clinical Natural Language Processing (NLP) provided a set of 1000 neuropsychiatric notes to participants as part of a competition to predict psychiatric symptom severity scores. This paper summarizes our methods, results, and experiences based on our participation in the second track of the shared task. Objective Classical methods of text classification usually fall into one of three problem types: binary, multi-class, and multi-label classification. In this effort, we study ordinal regression problems with text data where misclassifications are penalized differently based on how far apart the ground truth and model predictions are on the ordinal scale. Specifically, we present our entries (methods and results) in the N-GRID shared task in predicting research domain criteria (RDoC) positive valence ordinal symptom severity scores (absent, mild, moderate, and severe) from psychiatric notes. Methods We propose a novel convolutional neural network (CNN) model designed to handle ordinal regression tasks on psychiatric notes. Broadly speaking, our model combines an ordinal loss function, a CNN, and conventional feature engineering (wide features) into a single model which is learned end-to-end. Given interpretability is an important concern with nonlinear models, we apply a recent approach called locally interpretable model-agnostic explanation (LIME) to identify important words that lead to instance specific predictions. Results Our best model entered into the shared task placed third among 24 teams and scored a macro mean absolute error (MMAE) based normalized score (100 · (1 − M M AE)) of 83.86. Since the competition, we improved our score (using basic ensembling) to 85.55, comparable with the winning shared task entry. Applying LIME to model predictions, we demonstrate the feasibility of instance specific prediction interpretation by identifying words that led to a particular decision. Conclusion In this paper, we present a method that successfully uses wide features and an ordinal loss function applied to convolutional neural networks for ordinal text classification specifically in predicting psychiatric symptom severity scores. Our approach leads to excellent performance on the N-GRID shared task and is also amenable to interpretability using existing model-agnostic approaches.

show abstract

Longitudinal analysis of discussion topics in an online breast cancer community using convolutional neural networks

Cited by 54 publications

References 31 publications

Breast cancer stigma among Indonesian female: a case study breast cancer patient.

Breast cancer stigma among Indonesian female: a case study breast cancer patient.

DynGraph2Seq: Dynamic-Graph-to-Sequence Interpretable Learning for Health Stage Prediction in Online Health Forums

Ordinal convolutional neural networks for predicting RDoC positive valence psychiatric symptom severity scores

Contact Info

Product

Resources

About