Big Data Analytics and Machine Intelligence in Biomedical and Health Informatics. Группа авторов

the Internet of Things has helped the elderly stay in control of their health conditions 24/7 and has changed their lives. Most importantly, it affects people’s lives, including those who are single, as well as their families. If a patient is discharged from the hospital or goes home, an alert is issued to their family and concerned healthcare providers so they can be located and admitted in case they require attention.

      Fitness bands and other wirelessly connected devices like BP cuffs, blood pressure, as well as glucose sensors allow patients to monitor their condition and keep up with their personal health better-being via apps on their phones or other devices. These devices are designed to count calories, keep track of physical activity, measure your blood pressure, and perform several other functions; they can be adjusted to remember everything.

      1.5.8 Improved Supply Chain Management

Patients will not receive the proper care, if the supply of medical institutions is weakened or destroyed. In addition, hospitals’ financing will also become unstable, as well as other aspects of their operations, such as treatment and long-term care. Next area of exploration is in the realm of big data in healthcare which involves the value of analytics to keep the supply chain efficient and fluent from beginning to end.

      By using analytics tools to track supply chain metrics and making data driven decisions, they can save the hospitals $10 million a year. Descriptive and Predictive Analytics methods may assist in both formulating pricing and curbing the range of possible variations in product, as well as optimizing the ordering procedures. By expanding in the long term, this way, institutions are able to handle numerous snags and glitches that could lead to long wait times or failure for the patient population, while still helping to ensure their survival.

      1.5.9 Developing New Therapies and Innovations

      More importantly, the last example is a call to action in healthcare analytics is to reach beyond our current limitations in healthcare to make the world a better place. It has the ability to help research and development of new therapies and medicinal treatments through powerful data analysis of health records. Using a combination of historical, real-time, and predictive metrics with a more unified visualization of data. Using healthcare processes and visual analytics techniques, these healthcare experts can provide an enhanced vision of emerging strengths and weaknesses before running any more complex experiments.

      Furthermore, the new genetic and biomedical technologies can allow us to discover new drug therapies and assist in responding to medical emergencies as they arise, which is how the data can make these expansive big data analyses essential. These three aspects of data analytics have the ability to unclog, innovate, streamline, and protect lives. Confidence and clarity are both given to someone when they know the route ahead of time, before the journey begins.

1.6 Challenges in Big Data Analytics

Some difficult issues should be considered when collecting large amounts of data. The cost of experimental measurements is a factor in obtaining high throughput ‘omics’ data. Prior to integrating these heterogeneous data and employing data mining methods, it is necessary to consider the heterogeneity of the data sources, the noise in the experimental ‘omics’ data, and the variety of experimental techniques, environmental conditions, and biological nature. On these heterogeneous biomedical data sets, various data mining techniques can be applied, including anomaly detection, clustering, classification, association rules, as well as summarization and visualization of those large data sets.

      These flaws may result in the unreliability of individual data points, such as missing values or outliers. Despite these limitations of ‘omics’ data, EHRs data are heavily influenced by the staff who entered the patient’s data, which can result in the entry of missing values or incorrect data due to human error, misunderstanding, or incorrect interpretation of the original data [20]. Integrating data from disparate databases and standardizing laboratory protocols and values continue to be difficult issues [21].

      The high dimensionality of the ‘omics’ data means that it contains many more dimensions or features than the number of samples, whereas the EHRs data, which contains information about individuals/patients, makes data mining techniques more difficult to apply.

      The following stage is data pre-processing, which typically entails dealing with noisy data, outliers, missing values, as well as data transformation and normalization. This data pre-processing enables the application of statistical techniques and data mining methods, thereby improving the quality and outcomes of big data analytics and potentially resulting in the discovery of novel knowledge. This novel knowledge obtained through the integration of ‘omics’ and EHRs data should result in enhanced healthcare delivery to patients as well as advanced decision-making by healthcare policymakers.

1.7 Big Data Privacy and Security

In the survey paper [22] Archenaa et al. clearly mentioned that two critical issues in the healthcare and medical analytics sphere in regard to big data are the privacy of patients and the protection of personal data and information. While each country views this information as having a rightful claim to medical data, medical data are indeed very private and confidential, and no information is really safe [23]. A solution to these difficulties, which means the software should be used advanced and able to obfuscate identity data, needs to use effective encryption algorithms and, alternatively, anonymize itation. In order to achieve all of these goals, software should offer enhanced security and strict access controls that give the end users/clients the appropriate levels of protection, it must also have excellent governance controls that make sure user privacy and control is maintained.

1.8 Conclusion

      The use of big data analytics in medicine and healthcare is incredibly powerful, productive, interesting, and diverse. It integrates heterogeneous data like medical records, experimental, electronic health, and social data in order to explore the relations among the different characteristics and traces of data points like diagnoses and medication dosages, along with information such as public chatter to derive conclusions about outcomes. More diverse data needs to be combined into big data analysis, such as biosciences, sensor informatics, medical informatics, bioinformatics, and health computational biomedicine to get the truth out of its information.

1.9 Future Work

      As a future endeavor, the characteristics of big data provide an excellent foundation for developing applications that can handle big data in medicine and healthcare using promising software platforms. One such platform is Apache Hadoop Map Reduce, an open-source distributed data processing platform that makes use of massive parallel processing (MPP). These applications should enable data mining techniques to be applied to these heterogeneous and complex data in order to uncover hidden patterns and novel knowledge. Recent advancements in processor technology, newer types of memories, and network architecture will reduce the time required to transfer data from storage to the processor in a distributed environment.

References

      1. Manogaran, G., Lopez, D., Thota, C., Abbas, K.M., Pyne, S., Sundarasekar, R., Big data analytics in healthcare internet of things, in: Innovative healthcare systems for the 21st century, pp. 263–284, Springer International Publishing, 2017.

      2. Lander, E.S., Linton, L.M., Birren, B., Nusbaum, C., Zody, M.C., Baldwin, J., Devon, K., Dewar, K., Doyle, M., FitzHugh, W. et al., Initial sequencing and analysis of the human genome, Nature, 409, 6822, 2001.

3. Caulfield, T., Evans, J., McGuire, A., McCabe, C., Bubela, T., Cook-Deegan, R., Fishman, J., Hogarth, S., Miller, F.A., Ravitsky, V. et al., Reflections on the cost of “low-cost” whole genome sequencing: framing the health policy debate. PloS Biol., 11, 11, e1001699, 2013.

      4. Hood, L. and Friend, S.H., Predictive, personalized, preventive,