Unstructured Medical Text Classification using Linguistic Analysis: A Supervised Deep Learning Approach

Al-Doulat, Ahmad; Obaidat, Islam; Lee, Minwoo

doi:10.1109/aiccsa47632.2019.9035282

Cited by 4 publications

(3 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The development of SBD is probably the same [27] . For the SBD task, researchers mainly investigate new features and models that effectively discriminate between boundaries or non-boundaries [28,29] . Researchers have adopted Decision Trees (DTs), MLP, HMM, Maximum Entropy (ME), and CRF to study SBD [30,31] .…”

Section: Related Workmentioning

confidence: 99%

“…Experimental results of Tibetan on SBD (L), SBD (B), and SBD (R) models. ) 96 29. 93.21 96.10 94.63 96.89 94.32 96.67 95.48 97.07 94.56 96.94 95.74 97.09 94.61 96.98 95.78 Bi-LSTM (L) 96.37 93.82 95.61 94.71 96.63 94.78 96.28 95.53 97.12 94.39 97.32 95.83 97.11 94.61 97.04 95.81 GRU (L) 93.88 88.67 94.01 91.26 95.18 90.73 95.60 93.10 95.22 92.47 93.56 93.01 95.01 91.53 94.03 92.76 Bi-GRU (L) 95.71 92.65 94.92 93.77 94.76 90.47 94.55 92.47 87.36 81.04 82.00 81.52 93.21 86.74 94.48 90.45 ) 70.39 64.15 29.28 40.21 71.47 67.15 31.52 42.91 71.71 65.45 35.60 46.12 72.00 68.46 32.72 44.28 Bi-LSTM (R) 70.47 66.03 27.05 38.38 71.40 65.96 32.83 43.84 71.69 64.98 36.27 46.55 71.91 67.53 33.51 44.79 GRU (R) 70.45 65.20 28.08 39.25 70.66 71.20 23.01 34.78 68.82 63.11 19.99 30.37 68.74 76.68 11.58 20.12 Bi-GRU (R) 70.17 61.41 33.01 42.94 70.31 76.19 18.43 29.68 69.84 72.60 18.14 29.03 69.72 76.07 15.97 26.40 MLP (R) 68.91 81.34 11.11 19.55 67.90 61.14 15.32 24.51 68.30 66.04 13.95 23.03 68.21 65.49 13.73 22.69…”

mentioning

confidence: 99%

See 1 more Smart Citation

A Tibetan Sentence Boundary Disambiguation Model Considering the Components on Information on Both Sides of Shad

Gao

et al. 2023

Tsinghua Sci. Technol.

View full text Add to dashboard Cite

Sentence Boundary Disambiguation (SBD) is a preprocessing step for natural language processing.Segmenting text into sentences is essential for Deep Learning (DL) and pretraining language models. Tibetan punctuation marks may involve ambiguity about the sentences' beginnings and endings. Hence, the ambiguous punctuation marks must be distinguished, and the sentence structure must be correctly encoded in language models. This study proposed a component-level Tibetan SBD approach based on the DL model. The models can reduce the error amplification caused by word segmentation and part-of-speech tagging. Although most SBD methods have only considered text on the left side of punctuation marks, this study considers the text on both sides. In this study, 465 669 Tibetan sentences are adopted, and a Bidirectional Long Short-Term Memory (Bi-LSTM) model is used to perform SBD. The experimental results show that the F1-score of the Bi-LSTM model reached 96%, the most efficient among the six models. Experiments are performed on low-resource languages such as Turkish and Romanian, and high-resource languages such as English and German, to verify the models' generalization.

show abstract

Section: Related Workmentioning

confidence: 99%

mentioning

confidence: 99%

A Tibetan Sentence Boundary Disambiguation Model Considering the Components on Information on Both Sides of Shad

Gao

et al. 2023

Tsinghua Sci. Technol.

View full text Add to dashboard Cite

show abstract

“…), which simplifies access to content and reduces the time for retrieving information. NLP algorithms has shown promising results in clinical text classification such as classification of online medical articles(Al-Doulat et al, 2019), and smoking status classification and proximal femur (hip) fracture classification from the clinical notes and radiology reports(Wang et al, 2019).…”

mentioning

confidence: 99%

Applications of Artificial Intelligence and Voice Assistant in Healthcare

Ahanin¹,

Sade²,

Tat³

2022

IJARBSS

View full text Add to dashboard Cite

The modern smart technology such as Artificial Intelligence (AI) is merging with humans' physical lives and is going to change the way we live, work, and interact. AI in the healthcare sector is gaining attention from researchers, health professionals, and life sciences companies. The new technology advancement has brought various opportunities in electronic health (e-health) that allows healthcare to be accessible regardless of distance using information and communication technologies (ICTs) such as use of blood pressure telemonitoring service and voice assistants. Voice Assistant (VA) as an emerging technology in healthcare helps to reduce expenses, build loyalty, drive revenue, and it is especially beneficial amidst COVID-19 outbreak as healthcare will need to move towards more touchfree technologies post-pandemic. In this paper, we summarize the latest developments of applications of AI and VA in healthcare, and some basic knowledge regarding the techniques, the current state of this technology in healthcare, and possible developments in future, which potentially can transform many aspects of patient care.

show abstract

A Technique to Find Out Low Frequency Rare Words in Medical Cancer Text Document Classification

Patel

Shah²,

Shah

2022

Advances in Data Computing, Communication and Security

View full text Add to dashboard Cite

Unstructured Medical Text Classification using Linguistic Analysis: A Supervised Deep Learning Approach

Cited by 4 publications

References 31 publications

A Tibetan Sentence Boundary Disambiguation Model Considering the Components on Information on Both Sides of Shad

A Tibetan Sentence Boundary Disambiguation Model Considering the Components on Information on Both Sides of Shad

Applications of Artificial Intelligence and Voice Assistant in Healthcare

A Technique to Find Out Low Frequency Rare Words in Medical Cancer Text Document Classification

Contact Info

Product

Resources

About