A Term Extraction Approach to Survey Analysis in Health Care

15233

Authors

nan

Abstract

AbstractThe voice of the customer has for a long time been a key focus of businesses in all domains. It has received a lot of attention from the research community in Natural Language Processing (NLP) resulting in many approaches to analyzing customers feedback ((aspect-based) sentiment analysis, topic modeling, etc.). In the health domain, public and private bodies are increasingly prioritizing patient engagement for assessing the quality of the service given at each stage of the care. Patient and customer satisfaction analysis relate in many ways. In the domain of health particularly, a more precise and insightful analysis is needed to help practitioners locate potential issues and plan actions accordingly. We introduce here an approach to patient experience with the analysis of free text questions from the 2017 Irish National Inpatient Survey campaign using term extraction as a means to highlight important and insightful subject matters raised by patients. We evaluate the results by mapping them to a manually constructed framework following the Activity, Resource, Context (ARC) methodology (Ordenes, 2014) and specific to the health care environment, and compare our results against manual annotations done on the full 2017 dataset based on those categories.

Keywords

nan

Full Content

Proceedings of the 12th Conference on Language Resources and Evaluation (LREC 2020), pages 2069–2077 Marseille, 11–16 May 2020 c⃝ European Language Resources Association (ELRA), licensed under CC-BY-NC 2069 A Term Extraction Approach to Survey Analysis in Health Care C´ecile Robin, Mona Isazad Mashinchi, Fatemeh Ahmadi Zeleti, Adegboyega Ojo, Paul Buitelaar Insight Centre for Data Analytics, NUI Galway Galway, Ireland {cecile.robin, mona.isazad, fatemeh.ahmadizeleti, adegboyega.ojo, paul.buitelaar }@insight-centre.org Abstract The voice of the customer has for a long time been a key focus of businesses in all domains. It has received a lot of attention from the research community in Natural Language Processing (NLP) resulting in many approaches to analysing customers feedback ((aspect- based) sentiment analysis, topic modeling, etc.). In the health domain, public and private bodies are increasingly prioritising patient engagement for assessing the quality of the service given at each stage of the care. Patient and customer satisfaction analysis relate in many ways. In the domain of health particularly, a more precise and insightful analysis is needed to help practitioners locate potential issues and plan actions accordingly. We introduce here an approach to patient experience with the analysis of free text questions from the 2017 Irish National Inpatient Survey campaign using term extraction as a means to highlight important and insightful subject matters raised by patients. We evaluate the results by mapping them to a manually constructed framework following the Activity, Resource, Context (ARC) methodology (Ordenes et al., 2014) and specific to the health care environment, and compare our results against manual annotations done on the full 2017 dataset based on those categories. Keywords: health care, patient experience, term extraction, natural language processing, ARC framework, patient engagement, evalua- tion methodology 1. Introduction Patient engagement became recently a focus in Ireland with the creation three years ago of the National Care Experi- ence Programme1 in partnership between the Health Infor- mation and Quality Authority (HIQA), the Health Service Executive (HSE) and the Department of Health. The pro- gramme is responsible for the National Inpatient Experi- ence Survey (NIES) conducted for the first time in 2017 in 39 public hospitals from six hospital groups, and is now in its third edition. The first edition of the survey collected feedback of patients who spent at least 24 hours in a pub- lic hospital during the month of May 2017, and retrieved 13,000 responses. The questions were mainly of multiple choice type, except three open-ended questions at the end asking responders to provide more details on the positive or negative experiences they had, as well as suggestions for improvement. The survey was designed to assess patients’ experience during their stay and to identify particular areas in need of improvement. The aim for health care organi- zations is to be able to act on patient feedback, and create solutions for better service in terms of quality and safety within hospital care. An analysis of the close-ended survey questions was previ- ously carried out, and a project with the Insight Centre for Data Analytics2 (Galway, Ireland) was …

Content truncated to 500 words

Labeled Text

AbstractThe voice of the customer has for a long time been a key focus of businesses in all domains. It has received a lot of attention from the research community in Natural Language Processing (NLP) resulting in many approaches to analyzing customers feedback ((aspect-based) sentiment analysis, topic modeling, etc.). In the health domain, public and private bodies are increasingly prioritizing patient engagement for assessing the quality of the service given at each stage of the care. Patient and customer satisfaction analysis relate in many ways. In the domain of health particularly, a more precise and insightful analysis is needed to help practitioners locate potential issues and plan actions accordingly. We introduce here an approach to patient experience with the analysis of free text questions from the 2017 Irish National Inpatient Survey campaign using term extraction as a means to highlight important and insightful subject matters raised by patients. We evaluate the results by mapping them to a manually constructed framework following the Activity, Resource, Context (ARC) methodology (Ordenes, 2014) and specific to the health care environment, and compare our results against manual annotations done on the full 2017 dataset based on those categories.

Publication Details

Paper ID:
15233
Year:
2020
Publication:
TIPSTER
Publication Type:
conf
DOI:
nan