Trends and Opportunities in Health Analytics as a Service and Implications for Use in Low Resource Settings: A Literature Review Abstract (Preprint)
Bibliographic record
Abstract
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.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Direct model labels (unvalidated)
Per-model category and study-design labels from the labeling rounds. They are machine output, unvalidated, and the disagreement between models ships as data. No study design here is MEDLINE-validated yet.
| Model arm | Categories | Study design | Confidence |
|---|---|---|---|
| gemma | no category Domain: not available · Genre: Review About the Canadian research system: no · About a Canadian topic: no | Systematic review | low |
| gpt | no category Domain: not available · Genre: Review About the Canadian research system: no · About a Canadian topic: no | Other design | high |
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.010 | 0.043 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.003 |
| Bibliometrics | 0.019 | 0.022 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.006 | 0.005 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.005 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedLabeled directly by 2 models reading the full record.
The models disagree on parts of this classification; every voice is preserved in the section at the end of the page.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".