عنوان

Patients Harm Classification and Prediction Through Natural Language Processing in a Cancer Medical Center

شماره

TL53729

زبان متن نوشتاري يا گفتاري و مانند آن

انگلیسی

عنوان اصلي

Patients Harm Classification and Prediction Through Natural Language Processing in a Cancer Medical Center

نام عام مواد

[Thesis]

نام نخستين پديدآور

Salazar Reyna, Roberto Jesus

نام ساير پديدآوران

Khasawneh, Mohammad T.

نام ناشر، پخش کننده و غيره

State University of New York at Binghamton

تاریخ نشرو بخش و غیره

2020

متن يادداشت

106 p.

جزئيات پايان نامه و نوع درجه آن

M.Eng.

کسي که مدرک را اعطا کرده

State University of New York at Binghamton

امتياز متن

2020

متن يادداشت

This research addresses the problem of predicting adverse events and patient harm in cancer medical centers. Unintentional harm on patients has negative consequences for multiple parties, including patients and their families, healthcare providers, hospitals, and healthcare organizations. Therefore, identifying in advance patients that are at higher risk of suffering an adverse event is necessary to prevent harm, avoid unnecessary costs and provide safer care services. This can be achieved by employing natural language processing and machine learning algorithms to predict harm on patients based on structured and unstructured medical data. Most previous research works that addressed this problem have built and evaluated a single machine learning model using a single source of medical text. For this purpose, this research builds, evaluates and compares the performance of multiple machine learning models using three different sources of medical text (admission notes, final nursing assessment, and discharge notes) to determine the most reliable source to predict harm. Over 27,000 records were used to build the classification models. The experimental results suggested the final nursing assessment as the best source of medical text to predict harm. The best prediction model implemented 10 folds cross-validation, TF-IDF bag of words, chi-square feature selection, ADASYN over sampling technique, and a random forest classifier. This model outperformed the others by achieving 85% accuracy, 95% precision, 75% recall and 85% F1-scores. Results suggests that predicting adverse event and harm is possible through the use of natural language processing and machine learning algorithms.

اصطلاح موضوعی

Artificial intelligence

اصطلاح موضوعی

Computer engineering

اصطلاح موضوعی

Health care management

اصطلاح موضوعی

Health sciences

اصطلاح موضوعی

Industrial engineering

اصطلاح موضوعی

Medical ethics

اصطلاح موضوعی

Technical communication

مستند نام اشخاص تاييد نشده

Salazar Reyna, Roberto Jesus

مستند نام اشخاص تاييد نشده

Khasawneh, Mohammad T.

مستند نام تنالگان تاييد نشده

State University of New York at Binghamton

نام الکترونيکي

فرمت انتشار

p

نوع ماده

[Thesis]

کد کاربرگه

276903

سطح دسترسي

a

تكميل شده

Y