Limits...
Cloud-based Electronic Health Records for Real-time, Region-specific Influenza Surveillance.

Santillana M, Nguyen AT, Louie T, Zink A, Gray J, Sung I, Brownstein JS - Sci Rep (2016)

Bottom Line: Accurate real-time monitoring systems of influenza outbreaks help public health officials make informed decisions that may help save lives.We show that information extracted from cloud-based electronic health records databases, in combination with machine learning techniques and historical epidemiological information, have the potential to accurately and reliably provide near real-time regional estimates of flu outbreaks in the United States.

View Article: PubMed Central - PubMed

Affiliation: Computational Health Informatics Program, Boston Children's Hospital, Boston, MA, USA.

ABSTRACT
Accurate real-time monitoring systems of influenza outbreaks help public health officials make informed decisions that may help save lives. We show that information extracted from cloud-based electronic health records databases, in combination with machine learning techniques and historical epidemiological information, have the potential to accurately and reliably provide near real-time regional estimates of flu outbreaks in the United States.

No MeSH data available.


Related in: MedlinePlus

The errors associated with the linear regression and AR(2) autoregressive model baselines, and ARES are displayed as a function of time for each of the 10 US regions defined by the HHS.
© Copyright Policy - open-access
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4863169&req=5

f3: The errors associated with the linear regression and AR(2) autoregressive model baselines, and ARES are displayed as a function of time for each of the 10 US regions defined by the HHS.

Mentions: Our first out-of-sample real-time estimate of ILI was produced for the week of 1/8/2012. Time series of real-time (out-of-sample) estimates using ARES, the AR(2) model, and the linear model, were generated up to and including the week of June 28, 2015. Figure 1 shows the national level real-time estimates produced by ARES and the target CDC ILI signal. Estimates produced by the two baseline models described in the previous section are included for comparison purposes as well as their respective errors when compared to the CDC ILI. Figures 2 and 3 show the same results but at a regional resolution for each of the 10 regions defined by the Health and Human Services (HHS).


Cloud-based Electronic Health Records for Real-time, Region-specific Influenza Surveillance.

Santillana M, Nguyen AT, Louie T, Zink A, Gray J, Sung I, Brownstein JS - Sci Rep (2016)

The errors associated with the linear regression and AR(2) autoregressive model baselines, and ARES are displayed as a function of time for each of the 10 US regions defined by the HHS.
© Copyright Policy - open-access
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4863169&req=5

f3: The errors associated with the linear regression and AR(2) autoregressive model baselines, and ARES are displayed as a function of time for each of the 10 US regions defined by the HHS.
Mentions: Our first out-of-sample real-time estimate of ILI was produced for the week of 1/8/2012. Time series of real-time (out-of-sample) estimates using ARES, the AR(2) model, and the linear model, were generated up to and including the week of June 28, 2015. Figure 1 shows the national level real-time estimates produced by ARES and the target CDC ILI signal. Estimates produced by the two baseline models described in the previous section are included for comparison purposes as well as their respective errors when compared to the CDC ILI. Figures 2 and 3 show the same results but at a regional resolution for each of the 10 regions defined by the Health and Human Services (HHS).

Bottom Line: Accurate real-time monitoring systems of influenza outbreaks help public health officials make informed decisions that may help save lives.We show that information extracted from cloud-based electronic health records databases, in combination with machine learning techniques and historical epidemiological information, have the potential to accurately and reliably provide near real-time regional estimates of flu outbreaks in the United States.

View Article: PubMed Central - PubMed

Affiliation: Computational Health Informatics Program, Boston Children's Hospital, Boston, MA, USA.

ABSTRACT
Accurate real-time monitoring systems of influenza outbreaks help public health officials make informed decisions that may help save lives. We show that information extracted from cloud-based electronic health records databases, in combination with machine learning techniques and historical epidemiological information, have the potential to accurately and reliably provide near real-time regional estimates of flu outbreaks in the United States.

No MeSH data available.


Related in: MedlinePlus