Deep Learning-Based Natural Language Processing for the Identification and Multi-Label Categorization of Social Factors of Healthcare from Unorganized Electronic Medical Records
DOI:
https://doi.org/10.56294/hl2024.585Keywords:
Social Factors, Healthcare, Deep Learning, Natural Language Processing, Multi-label categorization, Electronic Medical Records, Bidirectional Long Short-Term MemoryAbstract
Social Factors of Healthcare (SFH) are non-medical determinants that may significantly influence patient health outcomes. Nevertheless, SFH is seldom included in Unorganized Electronic Medical Records (UEMR) data, such as diagnostic codes, and is often found in uncontrolled descriptive medical notes. Consequently, discerning social factors from UEMR data has gained paramount significance. Previous research towards using Natural Language Processing (NLP) for the automated extraction of SFH from text often emphasizes a selective approach to SFH. It fails to include the current advancements in Deep Learning (DL). This study proposes Deep Learning-Based Natural Language Processing for the identification and multi-label categorization (DL-NLP-MLC) of SFH from UEMR. Information was obtained from the Medical Information Mart for Intensive Care (MIMIC-III) dataset. The database consisted of 4,124 socially connected phrases derived from 2,785 medical notes. A framework for automatic MLC for multiple SFH types has been established. The database consisted of descriptive medical notes categorized as "SFH" inside the MIMIC-III medical dataset. Four types of categorization models have been trained: Decision Tree (DT), Random Forest (RF), and Long Short-Term Memory (LSTM). The efficacy of DL-NLP-MLC has been evaluated using accuracy, precision, recall, Area Under the Curve (AUC), and F1 score. The findings indicated that, in general, LSTM surpassed the other models of categorization with AUC (98.4%) and Accuracy (94.6%) for drug abuse SFH. The suggested method of training a DL classifier on a dataset rich in structured feature hierarchies may yield a very effective classifier using UEMR. Evidence demonstrates that model performance correlates with the semantic variety used by health practitioners and the automated creation of medical statements for documenting SFH.
References
Robbiati, C., Armando, A., da Conceição, N., Putoto, G., & Cavallin, F. (2022). Association between diabetes and food insecurity in an urban setting in Angola: a case–control study. Scientific reports, 12(1), 1084.
Coughlin, S. S. (2021). Social determinants of health and cancer survivorship. Journal of environment and health sciences, 7(1), 11.
Marçal, K. (2024). Housing hardship and maternal mental health among renter households with young children. Psychiatry Research, 331, 115677.
Gadhia, S., Richards, G. C., Marriott, T., & Rose, J. (2023). Artificial intelligence and opioid use: a narrative review. BMJ Innovations, 9(2).
Magnan, S. (2021). Social determinants of health 201 for health care: Plan, do, study, act. NAM perspectives, 2021.
Truong, H. P., Luke, A. A., Hammond, G., Wadhera, R. K., Reidhead, M., & Maddox, K. E. J. (2020). Utilization of social determinants of health ICD-10 Z-codes among hospitalized patients in the United States, 2016–2017. Medical care, 58(12), 1037-1043.
Pramanik, M. I., Lau, R. Y., Azad, M. A. K., Hossain, M. S., Chowdhury, M. K. H., & Karmaker, B. K. (2020). Healthcare informatics and analytics in big data. Expert Systems with Applications, 152, 113388.
DeBarmore, B. M. (2022). Electronic Health Record Phenotyping in Cardiovascular Epidemiology (Doctoral dissertation, The University of North Carolina at Chapel Hill).
Reeves, R. M., Christensen, L., Brown, J. R., Conway, M., Levis, M., Gobbel, G. T., ... & Chapman, W. (2021). Adaptation of an NLP system to a new healthcare environment to identify social determinants of health. Journal of biomedical informatics, 120, 103851.
Hatef, E., Rouhizadeh, M., Tia, I., Lasser, E., Hill-Briggs, F., Marsteller, J., & Kharrazi, H. (2019). Assessing the availability of data on social and behavioral determinants in structured and unstructured electronic health records: a retrospective analysis of a multilevel health care system. JMIR medical informatics, 7(3), e13802.
Chen, M., Tan, X., & Padman, R. (2020). Social determinants of health in electronic health records and their impact on analysis and risk prediction: a systematic review. Journal of the American Medical Informatics Association, 27(11), 1764-1773.
Agnikula, K. S., & Balls-BerryJoyce Joy, E. (2021). Social and behavioral determinants of health in the era of artificial intelligence with electronic health records: a scoping review. Health Data Science.
Blosnich, J. R., Montgomery, A. E., Dichter, M. E., Gordon, A. J., Kavalieratos, D., Taylor, L., ... & Bossarte, R. M. (2020). Social determinants and military veterans' suicide ideation and attempt: a cross-sectional analysis of electronic health record data. Journal of general internal medicine, 35, 1759-1767.
Bettencourt-Silva, J. H., Mulligan, N., Sbodio, M., Segrave-Daly, J., Williams, R., Lopez, V., & Alzate, C. (2020). Discovering new social determinants of health concepts from unstructured data: framework and evaluation. In Digital Personalized Health and Medicine (pp. 173-177). IOS Press.
Topaz, M., Murga, L., Bar-Bachar, O., Cato, K., & Collins, S. (2019). Extracting alcohol and substance abuse status from clinical notes: The added value of nursing data. In MEDINFO 2019: Health and Well-being e-Networks for All (pp. 1056-1060). IOS Press.
Nock, M. K., Millner, A. J., Ross, E. L., Kennedy, C. J., Al-Suwaidi, M., Barak-Corren, Y., ... & Kessler, R. C. (2022). Prediction of suicide attempts using clinician assessment, patient self-report, and electronic health records. JAMA network open, 5(1), e2144373-e2144373.
Jose, T., Hays, J. T., & Warner, D. O. (2020). Improved documentation of electronic cigarette use in an electronic health record. International journal of environmental research and public health, 17(16), 5908.
https://physionet.org/content/mimiciii/1.4/
Luo, H., Cheng, F., Yu, H., & Yi, Y. (2021). SDTR: Soft decision tree regressor for tabular data. IEEE Access, 9, 55999-56011.
Correia, A., Peharz, R., & de Campos, C. P. (2020). Joints in random forests. Advances in Neural Information Processing Systems, 33, 11404-11415.
Akusok, A., Leal, L. E., Björk, K. M., & Lendasse, A. (2021). Scikit-ELM: an extreme learning machine toolbox for dynamic and scalable learning. In Proceedings of ELM2019 9 (pp. 69-78). Springer International Publishing.
Grace Dolapo, P., Onanuga Ayotola, O., Ilori Olufemi, O., & Chukwuemeka Peter, U. (2020). Library Orientation and Information Literacy Skills as Correlates of Scholarly Research of Postgraduate Students of Federal University of Agriculture, Abeokuta, Nigeria. Indian Journal of Information Sources and Services, 10(1), 40–47. https://doi.org/10.51983/ijiss.2020.10.1.479
Knežević, D., & Knežević, N. (2019). Air Pollution-Present and Future Challenges, Case Study Sanitary Landfill Brijesnica in Bijeljina. Archives for Technical Sciences, 1(20), 73–80.
Konappa, D. (2020). Access and Use of Electronic Information Resources by Faculties of RGUKT, Andra Pradesh: A Study. Indian Journal of Information Sources and Services, 10(1), 7–12. https://doi.org/10.51983/ijiss.2020.10.1.484
Radmanović, S., Nikolić, N., & Đorđević, A. (2018). Humic Acids Optical Properties of Rendzina Soils in Diverse Environmental Conditions of Serbia. Archives for Technical Sciences, 1(18), 63–70.
Debbarma, K., & Praveen, K. (2019). LIS Education in India with the Emerging Trends in Libraries: Opportunities and Challenges. Indian Journal of Information Sources and Services, 9(S1), 41–43. https://doi.org/10.51983/ijiss.2019.9.S1.567
Cvijić, R., Milošević, A., Čelebić, M., & Kovačević, Ž. (2018). Geological and Economic Assessment of the Perspective of the Mining in Ljubija Ore Region. Archives for Technical Sciences, 1(18), 1–8.
Sobha Rani, J. (2019). A Study on Marketing Strategy for Library Resources and Services with Special Reference to Sree Vidyanikethan Engineering College, Tirupati, Andhra Pradesh. Indian Journal of Information Sources and Services, 9(S1), 51–56. https://doi.org/10.51983/ijiss.2019.9.S1.564
Tunguz, V., Petrović, B., Malešević, Z., & Petronić, S. (2019). Soil and Radionuclides of Eastern Herzegovina. Archives for Technical Sciences, 1(20), 87–92.
Pal, F., & Hatua, S. R. (2019). Proficiency Building of Non-Academic Libraries in the Context of Present LIS Education in India: A Study. Indian Journal of Information Sources and Services, 9(1), 128–131. https://doi.org/10.51983/ijiss.2019.9.1.580
Karimov, A., et al. (2019). Rethinking settlements in arid environments: Case study from Uzbekistan. E3S Web of Conferences, 97, 05052. https://doi.org/10.1051/e3sconf/20199705052
Karimov, N., et al. (2024). Exploring food processing in natural science education: Practical applications and pedagogical techniques. Natural and Engineering Sciences, 9(2), 359-375. https://doi.org/10.28978/nesciences.1574453
Odilov, A., et al. (2024). Utilizing deep learning and the Internet of Things to monitor the health of aquatic ecosystems to conserve biodiversity. Natural and Engineering Sciences, 9(1), 72-83. https://doi.org/10.28978/nesciences.1491795
Balasundaram, A., Routray, S., Prabu, A. V., Krishnan, P., Malla, P. P., & Maiti, M. (2023). Internet of Things (IoT)-based smart healthcare system for efficient diagnostics of health parameters of patients in emergency care. IEEE Internet of Things Journal, 10(21), 18563-18570.
Ebenezar, U. S., Vennila, G., Balakrishnan, T. S., & Krishnan, P. (2024, June). Optimizing Healthcare Delivery through CloudBased Clinical Decision Support Systems. In 2024 OPJU International Technology Conference (OTCON) on Smart Computing for Innovation and Advancement in Industry 4.0 (pp. 1-6). IEEE.
Published
Issue
Section
License
Copyright (c) 2024 Salim Davlatov, Isroil Sharipov , Dilrabo Mamatkulova, Dilnoza Boymatova, Mavsuma Oltiboyeva, Guzel Shamsutdinova, Natalya Kitayeva (Author)
This work is licensed under a Creative Commons Attribution 4.0 International License.
The article is distributed under the Creative Commons Attribution 4.0 License. Unless otherwise stated, associated published material is distributed under the same licence.
