Explore chapters and articles related to this topic
Use of Machine Learning in Healthcare
Published in Punit Gupta, Dinesh Kumar Saini, Rohit Verma, Healthcare Solutions Using Machine Learning and Informatics, 2023
The second application is natural language processing of medical documents. The amount of existing physical medical records in hospitals makes the documentation process slow and tedious. This calls for the development of algorithms that can usefully interpret electronic medical records (EMR) to save time and improve efficiency.
Applied Data Science
Published in Connie White Delaney, Charlotte A. Weaver, Joyce Sensmeier, Lisiane Pruinelli, Patrick Weber, Nursing and Informatics for the 21st Century – Embracing a Digital World, 3rd Edition, Book 3, 2022
Lisiane Pruinelli, Maxim Topaz
Symptom information is a key concept in nursing. Large-scale symptom research can be implemented by analyzing data collected in EHRs on millions of patients. However, most symptom information is documented in free-text clinical notes. Natural language processing can be applied to identify symptoms and enable further research and identify clinical implications.
Sentiment analysis for use within rapid implementation research
Published in Frances Rapport, Robyn Clay-Williams, Jeffrey Braithwaite, Implementation Science, 2022
Sentiment Analysis helps us to rapidly detect the positive or negative opinions in a piece of text. We can use Sentiment Analysis, a machine learning technique, considered to be a subfield of Natural Language Processing (NLP: a field at the intersection of computer science, artificial intelligence, and linguistics), to detect sentiment polarity (e.g., very positive, positive, neutral, negative, very negative opinions) within any piece of text. Text data can be drawn from transcripts, fieldnotes (Smith et al. in review), or data from microblogging websites, such as Twitter (McMullen et al. 2011). Twitter is a treasure trove of sentiment. Sentiment Analysis can rapidly convert data from unstructured Twitter data to structured text data. Examples include opinions of health interventions, such as vaccination (Zhou et al. 2015), and the delivery of outcomes such as those relating to seasonal affective disorder and obesity (Gore, Diallo, and Padilla 2015, Golder and Macy 2011, Coppersmith et al. 2015).
The fundamentals of Artificial Intelligence in medical education research: AMEE Guide No. 156
Published in Medical Teacher, 2023
Martin G. Tolsgaard, Martin V. Pusic, Stefanie S. Sebok-Syer, Brian Gin, Morten Bo Svendsen, Mark D. Syer, Ryan Brydges, Monica M. Cuddy, Christy K. Boscardin
As far as AI is concerned, text analysis and text mining are synonyms since they both look for patterns in large sets of text data (e.g. transcriptions of interviews) to extract meaning. Natural language processing (NLP), a text analysis approach, helps the machines understand and analyse textual data by simulating human language processing. However, unlike humans, NLP can analyse unlimited amounts of data in a systematic, highly efficient way. Examples of NLP studies in medical education include scoring of written exams (e.g. essays; Zhang et al. 2012), identification of factors tied to entrustment ratings in narrative feedback (Stahl et al. 2021; Solano et al. 2021), assessment of narrative feedback quality (Gin et al. 2021; Neves et al. 2021), early identification of learners in need of remediation (Tremblay et al. 2019), and the automated generation of test item distractors (Chary et al. 2019).
Qualitative and Artificial Intelligence-based Sentiment Analyses of Anti-LGBTI+ Hate Speech on Twitter in Turkey
Published in Issues in Mental Health Nursing, 2023
M. Berna Doğan, Volkan Oban, Gül Dikeç
Quantitative and qualitative analysis were used to analyze the data. First, the tweets were collected using Tweepy and were classified as positive, neutral, or negative expressions by sentiment analysis using Python natural language processing. Qualitative data analysis was then performed by two of the researchers. In the qualitative analysis of the tweets, the most frequently liked and retweeted tweets were analyzed using Colaizzi’s phenomenological interpretation method (Colaizzi, 1978), as follows: (1) Tweets were read repeatedly to understand the sentiments in the messages, (2) Expressions of anti-LGBT hate speech in the tweets were selected, (3) These significant expressions were examined, and meanings were formulated, (4) The formulated meanings were grouped into themes and sub-themes, (5) The results were integrated to generate an exhaustive description, and (6) The basic conceptual framework of the messages was defined.
Review of methods for conducting speech research with minimally verbal individuals with autism spectrum disorder
Published in Augmentative and Alternative Communication, 2023
Karen V. Chenausky, Marc Maffei, Helen Tager-Flusberg, Jordan R. Green
Despite their convenience and clinical utility, there are also some challenges associated with using natural language samples as speech, rather than language, samples. For example, children may be less likely to produce later-developing phonemes such as /ʒ/,/ʤ/, or /ʃ/ spontaneously than in imitation tasks. Furthermore, many minimally verbal children produce little to no spontaneous speech, or they may produce only unintelligible utterances so that accuracy compared to a target cannot be evaluated; therefore, word- or nonword repetition tasks are another possible data source. These tasks involve prompting the child to repeat a word (e.g., “bye” or “mommy”) or a nonword (e.g., “pipo”) after the examiner. They have the advantage of assessing a child’s ability to at least attempt phonemes, phoneme combinations, or syllable structures that do not appear in their spontaneous speech. A child’s stimulability can also be assessed during repetition tasks by providing forms of assistance such as unison production or touch cues on successive attempts.