The adoption of Artificial Intelligence (AI) in healthcare continues to grow in order to enhance clinical decision-making and patient outcomes. Most of the traditional machine learning models that are applied in clinical prediction activities are extensively based on statistical trends and are not necessarily interpretable or have medical contextual information. As a way of overcoming these shortcomings, this research paper suggests a Knowledge Graph-Enhanced Artificial Intelligence model of intelligent clinical decision support with the use of ICU patient data. The study uses the MIMIC3c Aggregated Dataset which is based on the MIMIC-III Clinical Database and has aggregated hospital interaction data in intensive care unit hospitalizations. The data has demographic information of patients, details of admission, clinical diagnosis, and daily interaction data, including laboratory tests, medications, imaging reports, caregivers, and clinical orders. These interaction characteristics give information about the medical care severity and the severity of patient condition. The dataset will be preprocessed in this research to process missing values, as well as, encode categorical variables and normalize numbers. This is followed by the construction of a knowledge graph representation to represent the relationship among major clinical entities, e.g. patients, diagnoses, types of admission, and treatment interactions.

This study describes a Knowledge Graph-Enhanced Artificial Intelligence system that can assist in making intelligent clinical decisions based on ICU patient data. The analysis has considered the MIMIC3C aggregated data that serves as useful information regarding patient demographics, hospital admission traits, and clinical interactions throughout the ICU hospitalizations. Through this type of data and analysis, the study was set to create a predictive system that would detect trends based on patient outcomes and assist health workers in their informed clinical decisions. The research was conducted in a systematic methodology which consisted of data preprocessing, exploratory data analysis, knowledge graph building, and machine learning model building and performance assessment. Exploratory analysis offered some valuable knowledge on patient demographics, admission patterns and length of stay at the hospital which aided in grasping the underlying structure of the data. To boost predictability of the prediction system, the knowledge graph representation was proposed to represent relationships between clinical entities (patients, diagnoses, type of admission, and interaction with treatment) and improve the interpretation of the predictive system. On the basis of the extracted features, a Support Vector Machine (SVM) model was subsequently created to classify patient outcomes. The model was tested in terms of the traditional measures such as the accuracy, precision, recall, F1-score, confusion matrix, and ROC curve analysis. The findings made it possible to conclude that the proposed model delivers high predictive results, especially accuracy and precision, which means that it is capable of analyzing the data available about patients in the ICU and can determine the possible patterns of the outcomes. Knowledge graphs usage, enhanced by the technique of artificial intelligence, is further advantageous in that it embodies the complicated clinical links and enhances the elucidation of the prediction findings. This attribute is especially significant in medical settings wherein professionals in the medical field need clear and dependable decision support applications. Despite the positive findings of the study, some issues like data limitations, imbalance in classes, and model generalization should be considered in the future work to help come up with intelligent and interpretable clinical decision support systems. These systems may help healthcare providers to detect high-risk patients, enhance planning of their treatment, and overall improve the quality of healthcare delivery with the help of the data-driven insights.

[1]. Bhatt, S., Sheth, A., Shalin, V., & Zhao, J. (2020). Knowledge graph semantic enhancement of input data for improving AI. IEEE Internet Computing, 24(2), 66-72. [2]. Sahlab, N., Kamm, S., Müller, T., Jazdi, N., & Weyrich, M. (2021, May). Knowledge graphs as enhancers of intelligent digital twins. In 2021 4th IEEE international conference on industrial cyber-physical systems (ICPS) (pp. 19-24). IEEE. [3]. Liu, W., Yin, L., Wang, C., Liu, F., & Ni, Z. (2021). Multitask healthcare management recommendation system leveraging knowledge graph. Journal of healthcare engineering, 2021(1), 1233483. [4]. Liu, Y., Ding, J., & Li, Y. (2021). Knowledge-driven site selection via urban knowledge graph. arXiv preprint arXiv:2111.00787. [5]. Zhang, Q., Lu, J., & Jin, Y. (2021). Artificial intelligence in recommender systems. Complex & intelligent systems, 7(1), 439-457. [6]. Ji, S., Pan, S., Cambria, E., Marttinen, P., & Yu, P. S. (2021). A survey on knowledge graphs: Representation, acquisition, and applications. IEEE transactions on neural networks and learning systems, 33(2), 494-514. [7]. Mezni, H., Benslimane, D., & Bellatreche, L. (2021). Context-aware service recommendation based on knowledge graph embedding. IEEE Transactions on Knowledge and Data Engineering, 34(11), 5225-5238. [8]. Zi-Yun, R., Yi, Z., Jun-Tao, L., & Wan-Hua, C. (2021). Recommendation methods and systems using knowledge graph. Acta Automatica Sinica, 47(9), 2061-2077. [9]. Lin, Y., Wang, H., Chen, J., Wang, T., Liu, Y., Ji, H., … & Natarajan, P. (2021, August). Personalized entity resolution with dynamic heterogeneous KnowledgeGraph representations. In Proceedings of The 4th Workshop on e-Commerce and NLP (pp. 38-48). [10]. Voit, M. M., & Paulheim, H. (2021). Bias in Knowledge Graphs–an Empirical Study with Movie Recommendation and Different Language Editions of DBpedia. arXiv preprint arXiv:2105.00674. [11]. Lin, X., Li, Y., Xu, Y., Guo, W., He, W., Zhang, H., … & Miao, C. (2021, December). Personalized clinical pathway recommendation via attention based pre-training. In 2021 IEEE International Conference on Bioinformatics and Biomedicine (BIBM) (pp. 980-987). IEEE. [12]. Dai, W., Sheni, S., & Hei, T. (2019, October). 3Q: A 3-Layer Semantic Analysis Model for Question Suite Reduction. In International Conference on Intelligent Science and Big Data Engineering (pp. 219-231). Cham: Springer International Publishing. [13]. Lan, Q., Wen, D., Zhang, Z., Zeng, Q., Chen, X., Popovski, P., & Huang, K. (2021). What is semantic communication? A view on conveying meaning in the era of machine intelligence. Journal of Communications and Information Networks, 6(4), 336-371. [14]. Xu, Y., Fang, M., Chen, L., Xu, G., Du, Y., & Zhang, C. (2021). Reinforcement learning with multiple relational attention for solving vehicle routing problems. IEEE transactions on cybernetics, 52(10), 11107-11120. [15]. Li, X., Wang, Y., Wang, D., Yuan, W., Peng, D., & Mei, Q. (2019). Improving rare disease classification using imperfect knowledge graph. BMC Medical Informatics and Decision Making, 19(Suppl 5), 238. [16]. Ceci, M., Hollmén, J., Todorovski, L., Vens, C., & Džeroski, S. (Eds.). (2017). Machine Learning and Knowledge Discovery in Databases: European Conference, ECML PKDD 2017, Skopje, Macedonia, September 18–22, 2017, Proceedings, Part II. Springer. [17]. Krinkin, K., Vodyaho, A., Kulikov, I., & Zhukova, N. (2021). Method of multilevel adaptive synthesis of monitoring object knowledge graphs. Applied Sciences, 11(14), 6251. [18]. Norouzi, M. (2018). Embedding Text in Hyperbolic Spaces. arXiv (Cornell University). [19]. Wen, G., Wang, K., Li, H., Huang, Y., & Zhang, S. (2021). Recommending prescription via tongue image to assist clinician. Multimedia Tools and Applications, 80(9), 14283-14304. [20]. Salatino, A. A., Thanapalasingam, T., Mannocci, A., Birukou, A., Osborne, F., & Motta, E. (2020). The computer science ontology: A comprehensive automatically-generated taxonomy of research areas. Data Intelligence, 2(3), 379-416. [21]. Tan, Y., & Shi, Y. (Eds.). (2021). Advances in Swarm Intelligence: 12th International Conference, ICSI 2021, Qingdao, China, July 17–21, 2021, Proceedings, Part I. Springer Nature. [22]. Qin, J. (2020). Research progress of news recommendation methods. arXiv preprint arXiv:2012.02360. [23]. Yang, C., Liu, Y., & Yin, C. (2021). Recent advances in intelligent source code generation: A survey on natural language based studies. Entropy, 23(9), 1174. [24]. Huang, B., Bi, Y., Wu, Z., Wang, J., & Xiao, J. (2020). Uber-gnn: A user-based embeddings recommendation based on graph neural networks. arXiv preprint arXiv:2008.02546. [25]. Brabra, H., Báez, M., Benatallah, B., Gaaloul, W., Bouguelia, S., & Zamanirad, S. (2021). Dialogue management in conversational systems: a review of approaches, challenges, and opportunities. IEEE Transactions on Cognitive and Developmental Systems, 14(3), 783-798. [26]. Sheth, A., Padhee, S., & Gyrard, A. (2019). Knowledge graphs and knowledge networks: the story in brief. IEEE Internet Computing, 23(4), 67-75. [27]. Dai, Y., Yu, H., Jiang, Y., Tang, C., Li, Y., & Sun, J. (2020). A survey on dialog management: Recent advances and challenges. arXiv preprint arXiv:2005.02233. [28]. Föhl, A. (2018). Media-enhanced cooking using a hands-free device (Doctoral dissertation, Stuttgart Media University). [29]. Bai, X., Chen, Y., Song, L., & Zhang, Y. (2021, August). Semantic representation for dialogue modeling. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) (pp. 4430-4445). [30]. Benaich, N., & Hogarth, I. (2020). State of AI report. London, UK.[Google Scholar]. [31]. Farkaš, I., Masulli, P., Otte, S., & Wermter, S. (Eds.). (2021). Artificial Neural Networks and Machine Learning–ICANN 2021: 30th International Conference on Artificial Neural Networks, Bratislava, Slovakia, September 14–17, 2021, Proceedings, Part I. Springer Nature. [32]. Wang, X., Zhang, Y., Wang, X., & Chen, J. (2019, April). A knowledge graph enhanced topic modeling approach for herb recommendation. In International conference on database systems for advanced applications (pp. 709-724). Cham: Springer International Publishing. [33]. Zong, C., Xia, F., Li, W., & Navigli, R. (2021, August). Proceedings of the 59th annual meeting of the association for computational linguistics and the 11th international joint conference on natural language processing (volume 1: Long papers). In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). [34]. Xie, X., Styles, I., Powathil, G., & Ceccarelli, M. (2018). Artificial intelligence in healthcare. [35]. Li, Z. (2021). Improving Recommender Systems via Multimodal Information. University of California, Los Angeles. [36]. Shao, W., Chen, X., Zhao, J., Xia, L., & Yin, D. (2021). User behavior understanding in real world settings. arXiv preprint arXiv:2112.02812. [37]. Jurafsky, D., Chai, J., Schluter, N., & Tetreault, J. (2020, July). Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. [38]. Espinoza-Mejía, M., Saquicela, V., & Abril-Ulloa, V. (2020, October). Ensuring traceability and orchestration in the food supply chain. In XV Multidisciplinary International Congress on Science and Technology (pp. 135-149). Cham: Springer International Publishing. [39]. Chen, J., Liu, L., Chen, R., Peng, W., & Huang, X. (2021). SecRec: A privacy-preserving method for the context-aware recommendation system. IEEE Transactions on Dependable and Secure Computing, 19(5), 3168-3182. [40]. Beebe, N. H. (2021). A Complete Bibliography of Publications in Future Internet. [41]. Wang, C., Liang, S., Jin, Y., Wang, Y., Zhu, X., & Zhang, Y. (2020, December). SemEval-2020 task 4: Commonsense validation and explanation. In Proceedings of the Fourteenth Workshop on Semantic Evaluation (pp. 307-321). [42]. Burkett, Z. D. (2017). Network-based Insights to Learned Vocalization. University of California, Los Angeles. [43]. Shao, W., Chen, X., Zhao, J., Xia, L., & Yin, D. (2021). Sequential Recommendation with Adaptive Preference Disentanglement. CoRR. [44]. Haick, H., & Tang, N. (2021). Artificial intelligence in medical sensors for clinical decisions. ACS nano, 15(3), 3557-3567. [45]. Garcia-Vidal, C., Sanjuan, G., Puerta-Alcalde, P., Moreno-García, E., & Soriano, A. (2019). Artificial intelligence to support clinical decision-making processes. EBioMedicine, 46, 27-29. [46]. Buchlak, Q. D., Esmaili, N., Leveque, J. C., Farrokhi, F., Bennett, C., Piccardi, M., & Sethi, R. K. (2020). Machine learning applications to clinical decision support in neurosurgery: an artificial intelligence augmented systematic review. Neurosurgical review, 43(5), 1235-1253. [47]. Musen, M. A., Middleton, B., & Greenes, R. A. (2021). Clinical decision-support systems. In Biomedical informatics: computer applications in health care and biomedicine (pp. 795-840). Cham: Springer International Publishing. [48]. Loftus, T. J., Tighe, P. J., Filiberto, A. C., Efron, P. A., Brakenridge, S. C., Mohr, A. M., … & Bihorac, A. (2020). Artificial intelligence and surgical decision-making. JAMA surgery, 155(2), 148-158. [49]. Tyler, N. S., Mosquera-Lopez, C. M., Wilson, L. M., Dodier, R. H., Branigan, D. L., Gabo, V. B., … & Jacobs, P. G. (2020). An artificial intelligence decision support system for the management of type 1 diabetes. Nature metabolism, 2(7), 612-619. [50]. Abdel-Basset, M., Manogaran, G., Gamal, A., & Chang, V. (2019). A novel intelligent medical decision support model based on soft computing and IoT. IEEE internet of things journal, 7(5), 4160-4170. Peiffer-Smadja, N., Rawson, T. M., Ahmad, R., Buchard, A., Georgiou, P., Lescure, F. X., … & Holmes, A. [51]. H. (2020). Machine learning for clinical decision support in infectious diseases: a narrative review of current applications. Clinical Microbiology and Infection, 26(5), 584-595. Antoniadi, A. M., Du, Y., Guendouz, Y., Wei, L., Mazo, C., Becker, B. A., & Mooney, C. (2021). Current [52]. challenges and future opportunities for XAI in machine learning-based clinical decision support systems: a systematic review. Applied Sciences, 11(11), 5088. [53]. Khanagar, S. B., Al-Ehaideb, A., Vishwanathaiah, S., Maganur, P. C., Patil, S., Naik, S., … & Sarode, S. S. (2021). Scope and performance of artificial intelligence technology in orthodontic diagnosis, treatment planning, and clinical decision-making-a systematic review. Journal of dental sciences, 16(1), 482-492. [54]. Lee, M. H., Siewiorek, D. P., Smailagic, A., Bernardino, A., & Bermúdez i Badia, S. B. (2021, May). A human-ai collaborative approach for clinical decision making on rehabilitation assessment. In Proceedings of the 2021 CHI conference on human factors in computing systems (pp. 1-14). [55]. Haleem, A., Javaid, M., & Khan, I. H. (2019). Current status and applications of Artificial Intelligence (AI) in medical field: An overview. Current Medicine Research and Practice, 9(6), 231-237. [56]. Schoonderwoerd, T. A., Jorritsma, W., Neerincx, M. A., & Van Den Bosch, K. (2021). Human-centered XAI: Developing design patterns for explanations of clinical decision support systems. International Journal of Human-Computer Studies, 154, 102684. [57]. Tack, C. (2019). Artificial intelligence and machine learning| applications in musculoskeletal physiotherapy. Musculoskeletal Science and Practice, 39, 164-169. [58]. Adlung, L., Cohen, Y., Mor, U., & Elinav, E. (2021). Machine learning in clinical decision making. Med, 2(6), 642-665. [58]. Asan, O., Bayrak, A. E., & Choudhury, A. (2020). Artificial intelligence and human trust in healthcare: focus on clinicians. Journal of medical Internet research, 22(6), e15154. [59]. Andronie, M., Lăzăroiu, G., Iatagan, M., Uță, C., Ștefănescu, R., & Cocoșatu, M. (2021). Artificial intelligence-based decision-making algorithms, internet of things sensing networks, and deep learning-assisted smart process management in cyber-physical production systems. Electronics, 10(20), 2497. [60]. Safdar, S., Zafar, S., Zafar, N., & Khan, N. F. (2018). Machine learning based decision support systems (DSS) for heart disease diagnosis: a review. Artificial Intelligence Review, 50(4), 597-623. [61]. Dataset Link: https://www.kaggle.com/datasets/drscarlat/mimic3c