Search results for: L. Hederman

Authors: S. Impey, D. Berry, S. Furtado, M. Galvin, L. Grogan, O. Hardiman, L. Hederman, M. Heverin, V. Wade, L. Douris, D. O'Sullivan, G. Stephens

Abstract:

Healthcare is a knowledge-rich environment. This knowledge, while valuable, is not always accessible outside the borders of individual clinics. This research aims to address part of this problem (at a study site) by constructing a maximal data set (knowledge artefact) for motor neurone disease (MND). This data set is proposed as an initial knowledge base for a concurrent project to develop an MND patient data platform. It represents the domain knowledge at the study site for the duration of the research (12 months). A knowledge elicitation method was also developed from the lessons learned during this process - the WICKED method. WICKED is an anagram of the words: eliciting and confirming data, information, knowledge, wisdom. But it is also a reference to the concept of wicked problems, which are complex and challenging, as is eliciting expert knowledge. The method was evaluated at a second site, and benefits and limitations were noted. Benefits include that the method provided a systematic way to manage data, information, knowledge and wisdom (DIKW) from various sources, including healthcare specialists and existing data sets. Limitations surrounded the time required and how the data set produced only represents DIKW known during the research period. Future work is underway to address these limitations.

Keywords: Healthcare, knowledge acquisition, maximal data sets, action design science.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 543

Authors: Shahad Nagoor, Lucy Hederman, Kevin Koidl, Annalina Caputo

Abstract:

Doctors’ notes reflect their impressions, attitudes, clinical sense, and opinions about patients’ conditions and progress, and other information that is essential for doctors’ daily clinical decisions. Despite their value, clinical notes are insufficiently researched within the language processing community. Automatically extracting information from unstructured text data is known to be a difficult task as opposed to dealing with structured information such as physiological vital signs, images and laboratory results. The aim of this research is to investigate how Natural Language Processing (NLP) techniques and machine learning techniques applied to clinician notes can assist in doctors’ decision making in Intensive Care Unit (ICU) for coronavirus disease 2019 (COVID-19) patients. The hypothesis is that clinical outcomes like survival or mortality can be useful to influence the judgement of clinical sentiment in ICU clinical notes. This paper presents two contributions: first, we introduce COVID_ICU_BERT, a fine-tuned version of a clinical transformer model that can reliably predict clinical sentiment for notes of COVID patients in ICU. We train the model on clinical notes for COVID-19 patients, ones not previously seen by Bio_ClinicalBERT or Bio_Discharge_Summary_BERT. The model which was based on Bio_ClinicalBERT achieves higher predictive accuracy than the one based on Bio_Discharge_Summary_BERT (Acc 93.33%, AUC 0.98, and Precision 0.96). Second, we perform data augmentation using clinical contextual word embedding that is based on a pre-trained clinical model to balance the samples in each class in the data (survived vs. deceased patients). Data augmentation improves the accuracy of prediction slightly (Acc 96.67%, AUC 0.98, and Precision 0.92).

Keywords: BERT fine-tuning, clinical sentiment, COVID-19, data augmentation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 276