1
RUNNING HEAD: MODULE TWO SHORT PAPER
Southern New Hampshire University
HIM-350 Communications and Technologies
Module Two Short Paper
Instructor Shante Willis
January 19, 2025
2
RUNNING HEAD: MODULE TWO SHORT PAPER
Data warehouses, electronic health records (EHR), and health information systems (HIS)
are three technologies used in health information exchange (HIE). Data warehouses are
substantial libraries of information gathered from multiple places throughout a healthcare
institution. They guide managerial choices. EHRs allow doctors to organize patient care
accurately. Patients can access their health information and converse with the doctor who treats
them. They improve the care patients receive, improve diagnostics, and practice cost-cutting and
efficiency (Univ of San Diego, 2025). Health information systems collect data, store and manage
the data, and transfer the patient's medical record. They may help to enhance patient outcomes,
provide information for research, and have an impact on making decisions and policymaking.
When extracting data from a data warehouse using the hybrid model, you use a
combination of cloud-based and on-site tools to access data from multiple sources within the data
warehouse using an ETL (Extract, Transform, Load) process in which suitable data changes take
place in the cloud and on-site depending on the data and where it's stored. You must determine
where information is located and utilize the most effective extraction method, whether cloud-
based or a typical in-house data search (Poppy, 2025).
To extract data from an EHR using a hybrid model, you would use natural language
processing (NLP) techniques to gather information from unorganized text sections and structured
query methods to access well-defined data fields within the EHR. This allows you to obtain a
comprehensive data set by utilizing structured and unstructured data within the medical record;
typically, this involves preliminary processing the text, using developed NLP models to find
essential entities and relationships, and then combining the results of the extracted data with the
organized information for evaluation (Fu, 2022).
3
RUNNING HEAD: MODULE TWO SHORT PAPER
To extract data from the health information system, you would use combined structured
data extraction procedures with unstructured data extraction methods to obtain details from
different areas of the system. The combined data is then stored and examined in a centrally
located information warehouse (McCarthy, 2014).
Analyzing the data to improve patient outcomes using predictive analytics allows the
provider to identify patients at high risk for certain diseases. This allows the provider to take
preventative measures to help the patient before conditions worsen. This also helps doctors find
the best treatment options based on their medical history (Park University, n.d.). Another way to
improve patient outcomes is by using descriptive analytics. Descriptive analytics helps to
uncover trends by analyzing historical data. It breaks down the information into patterns. This
helps the doctor to make smarter decisions to help patient outcomes. This also helps to break
down patient wait times for treatments, which treatments had the most positive outcomes
(Matellio, 2024).
4
RUNNING HEAD: MODULE TWO SHORT PAPER
References
10 technologies that are Changing Health Care. University of San Diego Online Degrees. (2025,
January 14). https://onlinedegrees.sandiego.edu/8-technologies-changing-
healthcare/#:~:text=A%20more%20technical%20explanation%20is,of%20a%20patient’s
%20medical%20history .
Data Analytics in healthcare: Transforming patient care delivery. Park University. (n.d.).
https://www.park.edu/blog/data-analytics-in-healthcare-transforming-patient-care-
delivery/#:~:text=Improved%20Patient%20Outcomes&text=By%20analyzing%20patient
%20data%2C%20healthcare,diagnoses%20and%20personalized%20treatment%20plans.
Descriptive analytics in healthcare - the game-changer you need right now. Matellio Inc. (2024,
October 22). https://www.matellio.com/blog/descriptive-analytics-in-healthcare/
Fu, S., Thorsteinsdottir, B., Zhang, X., Lopes, G. S., Pagali, S. R., LeBrasseur, N. K., Wen, A.,
Liu, H., Rocca, W. A., Olson, J. E., St Sauver, J., & Sohn, S. (2022, March 7). A hybrid
model to identify fall occurrence from electronic health records. International Journal of
Medical Informatics.
https://www.sciencedirect.com/science/article/abs/pii/S1386505622000508#:~:text=They
%20reported%20deep%20learning%20models,and%20performed%20detailed%20error
%20analysis.
McCarthy, D. B., Propp, K., Cohen, A., Sabharwal, R., Schachter, A. A., & Rein, A. L. (2014,
May 5). Learning from Health Information Exchange Technical Architecture and
implementation in seven beacon communities. EGEMS (Washington, DC).
https://pmc.ncbi.nlm.nih.gov/articles/PMC4371446/#:~:text=We%20found%20two%20general%
20forms,by%20multiple%20health%20care%20providers.
5
RUNNING HEAD: MODULE TWO SHORT PAPER
Poppy, D. (2025, January 16). Understanding ETL: Extract, transform, load. dbt Labs.
https://www.getdbt.com/blog/extract-transform-load
