Yapay Zeka Tabanlı Türkçe Dİl İşleme, Tanı Öneri Sistemi Projesi

Year 2023, Volume: 4 Issue: 1, 8 - 18, 09.08.2023

Servet Badem , Özlem Özcan Kılıçsaymaz

https://doi.org/10.54047/bibted.1227017

Abstract

MD-Advisor, sağlık hizmetlerinde yapay zeka tabanlı bir öneri sistemi olan “tıp doktoru – danışman” ifadesinin kısaltmasıdır. Ayrıca sağlık temelli öneri sistemi, hastalara ve klinisyenlere uygun sağlık hizmeti bilgileri için önerilerde bulunan bir karar alma aracıdır. MD-Advisor projesi, doktorların hastalara teşhis koyarken izledikleri prosedürleri hızlandırmak ve olası tüm durumları kısa sürede doktora sunmak amacıyla geliştirilmiştir. Bu proje ile hastaya teşhis konulması ve sonrasında tetkik önerilmesi süreçleri çok hızlı bir şekilde tamamlanmaktadır. Böylece hasta doğrudan tedavi aşamasına geçmektedir. Hastanın mevcut sağlık durumunu gösteren hasta şikayetlerinden elde edilen verilere dayanarak; veri ön işleme, etiketleme ve derin öğrenme modelleme teknikleri kullanılmaktadır. Teşhis önerisi için etiket olarak kullanılan teşhis kodları, Tekrarlayan Sinir Ağları modelinden çıktı olarak elde edildi. Çalışma sonucunda uygulanan tekrarlayan sinir ağları (RNN) modeli yaklaşımı ile hastanın şikayetlerine yönelik tanı önerisi başarılı bir şekilde tahmin edilmiştir.

Keywords

AI-based Recommendation System, Machine Learning, Deep Learning, Turkish Natural Language Processing, LSTM(Long Short Term Memory), Recurrent Neural Network (RNN), Healthcare Recommendation System

Supporting Institution

ACIBADEM TEKNOLOJİ

Project Number

ATE-21-MDA

A Natural Language Processing-Based Turkish Diagnosis Recommendation System

Abstract

MD-Advisor is the abbreviation of “medical doctor – advisor” which is an artificial intelligence-based recommendation system in healthcare. Moreover, the health-based recommender system is a decision-making tool that makes recommendations for appropriate healthcare information to patients and clinicians. MD-Advisor project was developed in order to speed up the procedures that doctors follow when diagnosing patients and to present all possible conditions to the doctor in a short time. With this project, the processes of diagnosing the patient and then recommending the examination are completed very quickly. Thus, the patient is directly transferred to the treatment phase. Based on the data obtained from patient complaints which indicates the current health status of the patient; data preprocessing, labeling and deep learning modeling techniques are used. The diagnostic codes used as labels for the diagnosis recommendation were obtained as output from the Recurrent Neural Networks model. As a result of the study, the diagnosis proposal for the patient's complaints was successfully predicted with the applied recurrent neural networks (RNN) model approach.

Keywords

AI-based Recommendation System, Machine Learning, Deep Learning, Turkish Natural Language Processing, LSTM(Long Short Term Memory), Recurrent Neural Network (RNN), Healthcare Recommendation System

Project Number

ATE-21-MDA

References

• Adelkhah, R., Shamsfard, M., & Naderian, N. (2019). The ontology of natural language processing. 5th International Conference on Web Research (ICWR), 128-133.
• Kaur, R., Ginige, J.A., & Obst, O. (2021). A systematic literature review of automated ICD coding and classification systems using discharge summaries. ArXiv, 2107. 10652.
• Ma, F., Chitta, R., Zhou, J., You, Q., Sun, T., & Gao, J. (2017). Dipole: diagnosis prediction in healthcare via attention-based bidirectional recurrent neural networks. Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.
• Melo, M., Gusso, G.D.F., Levites, M., Massad, E., Lotufo, P.A., Zeidman, P., . . . Price, C.J. (2017). How doctors diagnose diseases and prescribe treatments: an fMRI study of diagnostic salience. Scientific Reports, 7(1), 1304.
• Plisson, J., Lavrač, N., & Mladenic, D. (2004). A rule based approach to word lemmatization.
• Ruder, S. (2016). An overview of gradient descent optimization algorithms. ArXiv, 1609.04747.
• Stark, B., Knahl, C., Aydin, M., & Elish, K. (2019). A Literature Review on Medicine Recommender Systems. International Journal of Advanced Computer Science and Applications, 10(8).
• Wiesner, M., & Pfeifer, D. (2014). Health Recommender Systems: Concepts, Requirements, Technical Basics, and Challenges. International Journal of Environmental Research and Public Health, 11(3), 2580–2607.
• Brownlee, J. (2022). Your first deep learning project in python with keras step-by-step. Machine Learning Mastery. Retrieved from https://machinelearningmastery.com/tutorial-first-neural-network-python-keras/.
• Brownlee, J. (2021). How to choose an activation function for deep learning. Machine Learning Mastery. Retrieved from https://machinelearningmastery.com/choose-an-activation-function-for-deep-learning/.
• Brownlee, J. (2019). A gentle introduction to cross-entropy for machine learning. Machine Learning Mastery. Retrieved from https://machinelearningmastery.com/cross-entropy-for-machine-learning/.
• Brownlee, J. (2017). How to visualize a deep learning neural network model in keras. Machine Learning Mastery. Retrieved from https://machinelearningmastery.com/visualize-deep-learning-neural-network-model-keras/.
• Brownlee, J. (2017). Gentle introduction to the adam optimization algorithm for deep learning. Machine Learning Mastery. Retrieved from https://machinelearningmastery.com/adam-optimization-algorithm-for-deep-learning/.
• Brownlee, J. (2016). 5 step life-cycle for neural network models in keras. Machine Learning Mastery. Retrieved from https://machinelearningmastery.com/5-step-life-cycle-neural-network-models-keras/.
• Brownlee, J. (2016). Multi-class classification tutorial with the keras deep learning library. Machine Learning Mastery. Retrieved from https://machinelearningmastery.com/multi-class-classification-tutorial-keras-deep-learning-library/.
• Jain, V. (2019). Everything you need to know about “activation functions” in deep learning models. Towards Data Science. Retrieved from https://towardsdatascience.com/everything-you-need-to-know-about-activation-functions-in-deep-learning-models-84ba9f82c253.
• URL-1: https://www.dictionary.com/browse/diagnosis [Access Date: January 2023]
• URL-2:https://www.healthit.gov/faq/what-electronic-health-record-ehr [Access Date: January 2023]
• URL-3: Anonymous, (2020). How Does the Gradient Descent Algorithm Work in Machine Learning? https://github.com/visionatseecs/keras-starter/blob/main/keras_intro_mlp.ipynb [Access Date: January 2023]
• URL-4: https://www.analyticsvidhya.com/blog/2020/10/how-does-the-gradient-descent-algorithm-work-in-machine-learning/ [Access Date: January 2023]
• URL-5: https://tutorialspoint.com/deep_learning_with_keras/deep_learning_with_keras_tutorial.pdf [Access Date: January 2023]
• URL-6:https://deepai.org/machine-learning-glossary-and-terms/softmax-layer [Access Date: January 2023]
• URL-7: https://deepnotes.io/softmax-crossentropy [Access Date: January 2023]
• URL-8: Li, S. (2018). Named Entity Recognition with NLTK and SpaCy. https://towardsdatascience.com/named-entity-recognition-with-nltk-and-spacy-8c4a7d88e7da [Access Date: January 2023]
• URL-9: Menzli, A. (2022). Tokenization in NLP: Types, Challenges, Examples, Tools. https://neptune.ai/blog/tokenization-in-nlp [Access Date: January 2023]
• URL-10: Arnx, A., (2019, Jan 13). First neural network for beginners explained (with code). https://towardsdatascience.com/first-neural-network-for-beginners-explained-with-code-4cfd37e06eaf [Access Date: January 2023]
• URL-11: Nielsen, M., (2019). Neural Networks and Deep Learning. Neural Networks and Deep Learning, http://neuralnetworksanddeeplearning.com [Access Date: January 2023]
• URL-12: Trehan, D. (2022). Gradient Descent Explained. https://towardsdatascience.com/gradient-descent-explained-9b953fc0d2c [Access Date: January 2023]
• URL-13: Srivastava, K., (2021, Jan 21). Classification – Let’s understand the basics. https://towardsdatascience.com/classification-lets-understand-the-basics-78baa6fbff48 [Access Date: January 2023]
• URL-14: Roman, V., (2019). Supervised Learning: Basics of Classification and Main Algorithms. Towards Data Science. https://towardsdatascience.com/supervised-learning-basics-of-classification-and-main-algorithms-c16b06806cd3 [Access Date: January 2023]
• URL-15: Saxena, S. (2021). Binary Cross-Entropy/Log Loss for Binary Classification. https://www.analyticsvidhya.com/blog/2021/03/binary-cross-entropy-log-loss-for-binary-classification/ [Access Date: January 2023]
• URL-16: Godoy, D. (2018). Understanding Binary Cross-Entropy / Log Loss: A Visual Explanation. https://towardsdatascience.com/understanding-binary-cross-entropy-log-loss-a-visual-explanation-a3ac6025181a [Access Date: January 2023]
• URL-17: Sharma, A., (2017). Understanding Activation Functions in Neural Networks. The Theory of Everything. https://medium.com/the-theory-of-everything/understanding-activation-functions-in-neural-networks-9491262884e0 [Access Date: January 2023]
• URL-18: Sharma, P. (2020). Keras Optimizers Explained with Examples for Beginners. https://machinelearningknowledge.ai/keras-optimizers-explained-with-examples-for-beginners/ [Access Date: January 2023]
• URL-19: Gomez, R.,(2018). Understanding Categorical Cross-Entropy Loss, Binary Cross-Entropy Loss, Softmax Loss, Logistic Loss, Focal Loss, and all those confusing names. https://gombru.github.io/2018/05/23/cross_entropy_loss/ [Access Date: January 2023]
• URL-20: Wambui, R. (2022). Cross-Entropy Loss and Its Applications in Deep Learning. https://neptune.ai/blog/cross-entropy-loss-and-its-applications-in-deep-learning [Access Date: January 2023]