Computational Intelligence and Healthcare Informatics. Группа авторов

algorithms, scientists have been able to identify molecules that activate a particular protein which is relevant to symptoms of Alzheimer’s disease and schizophrenia; this could lead to early development of drugs for the treatment of these as yet incurable diseases [26].

      1.5.6 Cost Reduction

      With the availability of medical data, the healthcare provider gets all the background information of his patient helping him to make decisions with less errors, resulting in lower costs for the patient and the healthcare system. Analysis of data from a particular patient population helps in deciding disease management strategies improving preventive care, thereby minimizing costs.

      1.5.7 Population Health

      Big data availability leads to optimal use of the available resources for the entire community. It provides insights as to which patient population is especially vulnerable to a particular illness, so that measures can be taken to lessen the impact of a disease whether communicable or non-communicable by scaling up the facilities needed for its management so that the impact of the disease can be contained.

      1.5.8 Telemedicine

      Doctors recommend telemedicine to patients for personalized treatment solutions to prevent readmissions, and data analytics can then be used to make assessments and predictions of the course and associated management adjustments.

      1.5.9 Equipment Maintenance

      With connectivity between healthcare infrastructures for seamless real-time operations, its maintenance to prevent breakdowns becomes the backbone of the entire system.

      1.5.10 Improved Operational Efficiency

      The big data helps us understand the admission, diagnosis, and records of utilization of resources, helping to understand the efficiency and productivity of the hospital facilities.

      1.5.11 Outbreak Prediction

      With the availability of data like temperature and rainfall, reported cases reasonable predictions can be made about the outbreak of vector borne diseases like malaria and encephalitis, saving lives.

1.6 Challenges for Big Data

      The volumes of data generated from diverse sources need to be sorted into a cohesive format and then be constantly updated so that it can be shared between healthcare service providers addressing the relevant security concerns, which is the biggest challenge. Insights gained from big data help us in understanding the pooled data better, thereby helping in improving the outcomes and benefitting insurance providers by reducing fraud and false claims.

      The healthcare industry needs skilled data analysts who can sift out relevant data, analyze it, and communicate it to the relevant decision makers.

1.7 Conclusion

This chapter provides an overview regarding better healthcare services with the help of ML and big data technology. It presents big data approaches to gather valuable medical records and further the application of ML algorithm. The implementation of ML tool in medicine shows more accurate result with less processing time. Big data will surely help in collecting and maintaining EHR (electronic health records) for better decision-making in future. This paper provides a systematic review to the researchers about better options in the field of healthcare using ML and big data (Figure 1.5). This paper has identified several application areas in healthcare services using ML and big data which can further improve the unresolved challenges. The traditional healthcare services will be greatly transformed by such technologies. ML will help in improving the relationship between the locals and service provider by providing better service in less time. It will help in keeping an eye on critical patients in real time and help them diagnose the disease and recommend further treatment.

Figure 1.5 Applications of big data in healthcare.

References

      1. James, M., Michael, C., Brad, B., Jacques, B., Big Data: The Next Frontier for Innovation, Competition, and Productivity, McKinsey Global Institute, New York, NY, 2011.

      2. Al-Jarrah, O.Y., Yoo, P.D., Muhaidat, S., Karagiannidis, G.K., Taha, K., Efficient machine learning for big data: A review. Big Data Res., 2, 3, 87–93, Sep. 2015.

      3. Beyer, M.A. and Laney, D., The importance of ‘big data’: A definition, Gartner Research, Stamford, CT, USA, Tech. Rep. G00235055, 2012.

      4. Xing, L., Krupinski, E.A., Cai, J., Artificial intelligence will soon change the landscape of medical physics research and practice. Med. Phys., 45, 5, 1791–1793, 2018.

      5. Deo, R.C., Machine Learning in Medicine. Circulation, 132, 20, 1920–1930, 2015.

      6. Kannel, W.B., Doyle, J.T., McNamara, P.M., Quickenton, P., Gordon, T., Precursors of sudden coronary death. Factors related to the incidence of sudden death. Circulation, 51, 606–613, 1975, [PubMed] [Google Scholar].

      7. Lip, G.Y.H., Nieuwlaat, R., Pisters, R., Lane, D.A., Crijns, H.J.G.M., Refining clinical risk stratification for predicting stroke and thromboembolism in atrial fibrillation using a novel risk factor-based approach: the euro heart survey on atrial fibrillation. Chest, 137, 263–272, 2010, [PubMed] [Google Scholar].

      8. O’Mahony, C., Jichi, F., Pavlou, M., Monserrat, L., Anastasakis, A., Rapezzi, C., Biagini, E., Gimeno, J.R., Limongelli, G., McKenna, W.J., Omar, R.Z., Elliott, P.M., A novel clinical risk prediction model for sudden cardiac death in hypertrophic cardiomyopathy (HCM risk-SCD). Eur. Heart J., 35, 2010–2020, 2014, [PubMed] [Google Scholar].

      9. National Research Council (US), Committee on A Framework for Developing a New Taxonomy of Disease, in: Toward Precision Medicine: Building a Knowledge Network for Biomedical Research and a New Taxonomy of Disease, National Academies Press (US), Washington (DC), 2011, [PubMed] [Google Scholar].

      10. Woodruff, P.G., Modrek, B., Choy, D.F., Jia, G., Abbas, A.R., Ellwanger, A., Koth, L.L., Arron, J.R., Fahy, J.V., T-helper type 2-driven inflammation defines major subphenotypes of asthma. Am. J. Respir. Crit. Care Med., 180, 388–395, 2009, [PMC free article] [PubMed] [Google Scholar].

      11. Corren, J., Lemanske, R.F., Hanania, N.A., Korenblat, P.E., Parsey, M.V., Arron, J.R., Harris, J.M., Scheerens, H., Wu, L.C., Su, Z., Mosesova, S., Eisner, M.D., Bohen, S.P., Matthews, J.G., Lebrikizumab treatment in adults with asthma. N. Engl. J. Med., 365, 1088–1098, 2011, [PubMed] [Google Scholar].

      12. Laine, S. and Aila, T., Temporal ensembling for semi-supervised learning, in: International Conference on Learning Representations, 2017.

13. Cheplygina, V., d. Bruijne, M., Pluim, J.P.W., Not-so-supervised: a survey of semi-supervised, multi-instance, and transfer learning in medical image analysis. Medical Image Analysis, 54, 280–296, 2019.

      14. Bai, W., Oktay, O., Sinclair, M., Suzuki, H., Rajchl, M., Tarroni, G., Glocker, B., King, A., Matthews, P.M., Rueckert, D., Semisupervised learning for network-based cardiac mr image segmentation, in: Medical Image Computing and Comput.-Assisted Intervention, pp. 253–260, Springer, Heidelberg, 2017.

      15. Zhang, Y., Yang, L., Chen, J., Fredericksen, M., Hughes, D.P., Chen, D.Z., Deep adversarial networks for biomedical image