Dataset Information

Factors to improve distress and fatigue in Cancer survivorship; further understanding through text analysis of interviews by machine learning.

ABSTRACT:

Background

From patient-reported surveys and individual interviews by health care providers, we attempted to identify the significant factors related to the improvement of distress and fatigue for cancer survivors by text analysis with machine learning techniques, as the secondary analysis using the single institute data from the Korean Cancer Survivorship Center Pilot Project.

Methods

Surveys and in-depth interviews from 322 cancer survivors were analyzed to identify their needs and concerns. Among the keywords in the surveys, including EQ-VAS, distress, fatigue, pain, insomnia, anxiety, and depression, distress and fatigue were focused. The interview transcripts were analyzed via Korean-based text analysis with machine learning techniques, based on the keywords used in the survey. Words were generated as vectors and similarity scores were calculated by the distance related to the text's keywords and frequency. The keywords and selected high-ranked ten words for each keyword based on the similarity were then taken to draw a network map.

Results

Most participants were otherwise healthy females younger than 50 years suffering breast cancer who completed treatment less than 6 months ago. As the 1-month follow-up survey's results, the improved patients were 56.5 and 58.4% in distress and fatigue scores, respectively. For the improvement of distress, dyspepsia (p = 0.006) and initial scores of distress, fatigue, anxiety, and depression (p < 0.001, < 0.001, 0.043, and 0.013, respectively) were significantly related. For the improvement of fatigue, economic state (p = 0.021), needs for rehabilitation (p = 0.035), initial score of fatigue (p < 0.001), any intervention (p = 0.017), and participation in family care program (p = 0.022) were significant. For the text analysis, Stress and Fatigue were placed at the center of the keyword network map, and words were intricately connected. From the regression anlysis combined survey scores and the quantitative variables from the text analysis, participation in family care programs and mention of family-related words were associated with the fatigue improvement (p = 0.033).

Conclusion

Common symptoms and practical issues were related to distress and fatigue in the survey. Through text analysis, however, we realized that the specific issues and their relationship such as family problem were more complicated. Although further research needs to explore the hidden problem in cancer patients, this study was meaningful to use personalized approach such as interviews.

SUBMITTER: Yang K

PROVIDER: S-EPMC8237475 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:Early identification and intervention are imperative for suicide prevention. However, at-risk people often neither seek help nor take professional assessment. A tool to automatically assess their risk levels in natural settings can increase the opportunity for early intervention.The aim of this study was to explore whether computerized language analysis methods can be utilized to assess one's suicide risk and emotional distress in Chinese social media.A Web-based survey of Chinese social media (ie, Weibo) users was conducted to measure their suicide risk factors including suicide probability, Weibo suicide communication (WSC), depression, anxiety, and stress levels. Participants' Weibo posts published in the public domain were also downloaded with their consent. The Weibo posts were parsed and fitted into Simplified Chinese-Linguistic Inquiry and Word Count (SC-LIWC) categories. The associations between SC-LIWC features and the 5 suicide risk factors were examined by logistic regression. Furthermore, the support vector machine (SVM) model was applied based on the language features to automatically classify whether a Weibo user exhibited any of the 5 risk factors.A total of 974 Weibo users participated in the survey. Those with high suicide probability were marked by a higher usage of pronoun (odds ratio, OR=1.18, P=.001), prepend words (OR=1.49, P=.02), multifunction words (OR=1.12, P=.04), a lower usage of verb (OR=0.78, P<.001), and a greater total word count (OR=1.007, P=.008). Second-person plural was positively associated with severe depression (OR=8.36, P=.01) and stress (OR=11, P=.005), whereas work-related words were negatively associated with WSC (OR=0.71, P=.008), severe depression (OR=0.56, P=.005), and anxiety (OR=0.77, P=.02). Inconsistently, third-person plural was found to be negatively associated with WSC (OR=0.02, P=.047) but positively with severe stress (OR=41.3, P=.04). Achievement-related words were positively associated with depression (OR=1.68, P=.003), whereas health- (OR=2.36, P=.004) and death-related (OR=2.60, P=.01) words positively associated with stress. The machine classifiers did not achieve satisfying performance in the full sample set but could classify high suicide probability (area under the curve, AUC=0.61, P=.04) and severe anxiety (AUC=0.75, P<.001) among those who have exhibited WSC.SC-LIWC is useful to examine language markers of suicide risk and emotional distress in Chinese social media and can identify characteristics different from previous findings in the English literature. Some findings are leading to new hypotheses for future verification. Machine classifiers based on SC-LIWC features are promising but still require further optimization for application in real life.

Project description:BACKGROUND:Clinical narratives represent the main form of communication within health care, providing a personalized account of patient history and assessments, and offering rich information for clinical decision making. Natural language processing (NLP) has repeatedly demonstrated its feasibility to unlock evidence buried in clinical narratives. Machine learning can facilitate rapid development of NLP tools by leveraging large amounts of text data. OBJECTIVE:The main aim of this study was to provide systematic evidence on the properties of text data used to train machine learning approaches to clinical NLP. We also investigated the types of NLP tasks that have been supported by machine learning and how they can be applied in clinical practice. METHODS:Our methodology was based on the guidelines for performing systematic reviews. In August 2018, we used PubMed, a multifaceted interface, to perform a literature search against MEDLINE. We identified 110 relevant studies and extracted information about text data used to support machine learning, NLP tasks supported, and their clinical applications. The data properties considered included their size, provenance, collection methods, annotation, and any relevant statistics. RESULTS:The majority of datasets used to train machine learning models included only hundreds or thousands of documents. Only 10 studies used tens of thousands of documents, with a handful of studies utilizing more. Relatively small datasets were utilized for training even when much larger datasets were available. The main reason for such poor data utilization is the annotation bottleneck faced by supervised machine learning algorithms. Active learning was explored to iteratively sample a subset of data for manual annotation as a strategy for minimizing the annotation effort while maximizing the predictive performance of the model. Supervised learning was successfully used where clinical codes integrated with free-text notes into electronic health records were utilized as class labels. Similarly, distant supervision was used to utilize an existing knowledge base to automatically annotate raw text. Where manual annotation was unavoidable, crowdsourcing was explored, but it remains unsuitable because of the sensitive nature of data considered. Besides the small volume, training data were typically sourced from a small number of institutions, thus offering no hard evidence about the transferability of machine learning models. The majority of studies focused on text classification. Most commonly, the classification results were used to support phenotyping, prognosis, care improvement, resource management, and surveillance. CONCLUSIONS:We identified the data annotation bottleneck as one of the key obstacles to machine learning approaches in clinical NLP. Active learning and distant supervision were explored as a way of saving the annotation efforts. Future research in this field would benefit from alternatives such as data augmentation and transfer learning, or unsupervised learning, which do not require data annotation.