BACKGROUND This paper presents a systematic literature review of existing remote health monitoring systems with special reference to neonatal intensive care (NICU). Articles on NICU clinical decision support systems (CDSSs) which used cloud computing and big data analytics were surveyed. OBJECTIVE The aim of this study is to review technologies used to provide NICU CDSS. The literature review highlights the gaps within frameworks providing HAaaS paradigm for big data analytics METHODS Literature searches were performed in Google Scholar, IEEE Digital Library, JMIR Medical Informatics, JMIR Human Factors and JMIR mHealth and only English articles published on and after 2015 were included. The overall search strategy was to retrieve articles that included terms that were related to “health analytics” and “as a service” or “internet of things” / ”IoT” and “neonatal intensive care unit” / ”NICU”. Title and abstracts were reviewed to assess relevance. RESULTS In total, 17 full papers met all criteria and were selected for full review. Results showed that in most cases bedside medical devices like pulse oximeters have been used as the sensor device. Results revealed a great diversity in data acquisition techniques used however in most cases the same physiological data (heart rate, respiratory rate, blood pressure, blood oxygen saturation) was acquired. Results obtained have shown that in most cases data analytics involved data mining classification techniques, fuzzy logic-NICU decision support systems (DSS) etc where as big data analytics involving Artemis cloud data analysis have used CRISP-TDM and STDM temporal data mining technique to support clinical research studies. In most scenarios both real-time and retrospective analytics have been performed. Results reveal that most of the research study has been performed within small and medium sized urban hospitals so there is wide scope for research within rural and remote hospitals with NICU set ups. Results have shown creating a HAaaS approach where data acquisition and data analytics are not tightly coupled remains an open research area. Reviewed articles have described architecture and base technologies for neonatal health monitoring with an IoT approach. CONCLUSIONS The current work supports implementation of the expanded Artemis cloud as a commercial offering to healthcare facilities in Canada and worldwide to provide cloud computing services to critical care. However, no work till date has been completed for low resource setting environment within healthcare facilities in India which results in scope for research. It is observed that all the big data analytics frameworks which have been reviewed in this study have tight coupling of components within the framework, so there is a need for a framework with functional decoupling of components.

Critical care patients are monitored by a range of medical devices collecting high frequency data. New computing frameworks and platforms are being proposed to review and analyze the data in detail. The application of these approaches in a low resource setting is challenged by the approaches used for data acquisition. Software as a Service (SaaS) is a form of cloud computing where a cloudbased software application enables the storage, analysis and visualization of data within the cloud. A subset of SaaS is Health Analytics as a Service (HAaaS), which provides software to support health analytics in the cloud. The objective of this study is to design, implement, and demonstrate an extendable big-data compatible HAaaS framework that offers both real-time and retrospective analysis where data acquisition is not tightly coupled. A data warehousing framework is presented to facilitate analysis within a low resource setting. The framework has been instantiated in the Artemis platform within the context of the Belgaum Children Hospital (BCH) case study. Initial end-to-end testing with the Nellcor monitor (bedside monitor at BCH), which was not connected to any human, was completed. This testing confirms the functionality of the new Artemis cloud instance to receive data from test device using an alternate data acquisition approach.