Big data and digital health solutions show promise for improving sleep health and respiratory care. Telemonitoring can provide insights into sleep apnea trajectories over time. Machine learning applied to large clinical datasets may help predict patient outcomes more accurately. Digital compliance monitoring and proactive telehealth support have potential to increase adherence to treatments like CPAP and inhaled medications. However, biases in data collection and overreliance on correlations without causal understanding need addressing. Overall, integrating digital tools while maintaining clinical expertise offers opportunities to advance medicine.
6. Big Data
Big data is data sets that are so voluminous and
complex that traditional data processing
application software are inadequate to deal with
them.
The term “big data” refers not only to large data sets, but also to the
frameworks, techniques, and tools used to analyze it.
It can be collected through any data-generating process such as
social media, public utility infrastructure, and search engines.
Big data may be either semi-structured, structured, or unstructured.
7. The Five V‘s of Big Data: 4 + value
https://www.mosaiq.com; http://onlinembapage.com/data-analytics-mba/; http://www.phonecruncher.com; resmed.com
8. Big Data
Pros
Insights (e.g., phenotyping,
precision medicine)
Safety (long-term, real time;
interactions)
Trends, trajectories
Monitoring
Cons
Inherent biases in how all
data are collected and
interpreted.
Objections to the idea that
data mining can replace
hypothesis driven theory by
content experts.
The observation that the
larger the data set the more
likely that spurious
correlations that are not
useful will be identified
Bottles et al; PEJ JULY•AUGUST/2014
14. Quo vadis?
A new research paper, published Jan. 24 with 34 co-authors and not peer-
reviewed, claims better accuracy than existing software at predicting
outcomes like whether a patient will die in the hospital, be discharged and
readmitted, and their final diagnosis. To conduct the study, Google obtained
de-identified data of 216,221 adults, with more than 46 billion data points
between them. The data span 11 combined years at two hospitals,
University of California San Francisco Medical Center (from 2012-2016)
and University of Chicago Medicine (2009-2016).
15. Digital health - Sleep
Source: sleepcycle.com, apple.com, fitbit.com, sleepscore.com
16. Digital health - Sleep
„self-managment program“
Source: sleepio.com