Scribd
Upload
58 views

Description of Proposed Research

This document discusses using manual chart review (MCR) for clinical research and quality improvement efforts. While MCR provides detailed patient data, it is time-consuming. The document proposes using machine learning on electronic health record data to automate and accelerate the MCR process for identifying postoperative complications. Automating MCR through electronic records could improve healthcare by providing faster access to higher quality data. However, barriers like technical complexity, infrastructure issues, and user resistance must be addressed for successful implementation.

Uploaded by

Harlene Joyce Rey
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
58 views

Description of Proposed Research

This document discusses using manual chart review (MCR) for clinical research and quality improvement efforts. While MCR provides detailed patient data, it is time-consuming. The document proposes using machine learning on electronic health record data to automate and accelerate the MCR process for identifying postoperative complications. Automating MCR through electronic records could improve healthcare by providing faster access to higher quality data. However, barriers like technical complexity, infrastructure issues, and user resistance must be addressed for successful implementation.

Uploaded by

Harlene Joyce Rey
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 2

Description of Proposed Research

Conducting research and quality improvement using manual chart review


(MCR) remains widely used in traditional observational clinical studies aimed at
assessing detailed information on patients to understand disease course or
outcomes and is also a primary modality used for quality improvement,
epidemiologic assessments, and for graduate and ongoing professional education
and assessment. Though MCR provides high-quality data for further secondary
purposes including research, it is very time-consuming and labor-consuming to
conduct and may be a bottle-neck step in the research discovery process. “The
patient record is the principal repository for information concerning a patient’s
health care. It affects everyone associated with providing, receiving, or
reimbursing health care services. Despite the many technological advances in
health care over the past few decades, the typical patient record of today is
remarkably similar to the patient record of 50 years ago. This failure of patient
records to evolve is now creating additional stress within the U.S health care
system, as the information needs of practitioners, patients, administrators, third-
party payers, researchers and policymakers often go unmet.”, as stated by
Ellywood 1988.
For the improvement of MCR, some people have explored the feasibility of
computerizing its process for automatically and much easier way of collecting
necessary data elements in quality improvement program, but these efforts have
mainly been based on unstructured data such as physician narratives and nursing
notes. In one example, relevant keywords and phrases were extracted from free
text documents for adverse event detection. In another case, statistical and rule-
based extractors were developed to automatically abstract data elements such as
procedure type and demographic information from clinical notes.

This project aims to get and know the needed medical data as fast as
possible with the help of the advance technologies that our world has today.
Included in this analysis are the main postoperative complications of three
subtypes of SSI (superficial, deep, and organ space), pneumonia, UTI, sepsis, and
septic shock. We hypothesized that EHR data would include significant indicators
and signals of postoperative complications and that sophisticated machine learning
methods might be able to extract these signals, accelerating the MCR process of
these adverse events. Automated patient records can improve health care delivery
by providing medical personnel with better access, faster data retrieval, higher
quality data, and more versatility in data display. It can also support decision
making and quality assurance activities and provide clinical reminders to assist in
patient care. It can also enhance the outcomes of research programs by
electronically capturing clinical information for evaluation and it can increase
hospital efficiency by reducing cost and improving staff productivity. However,
according to the case study of Ryan A. Ebardo, there are some barriers that can
affect the implementation of Automated Medical charting namely; complexity,
weak infrastructure, poor interface design, user resistance, unskilled IT staff,
privacy regulation compliance, and medical school orientation. Hence, the
management will require appropriate orientation on the
importance of technology to support their strategic initiatives and increased
resource allocation to medical staff orientation on the benefits of EMR
solutions and better compensation to its IT staff.

References:
Accelerating Chart Review Using Automated Methods on Electronic Health Record Data
for Postoperative Complications, 2017
https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5333220/
The Computer-Based Patient Record: An Essential Technology for Health Care, Revised
Edition 1997
https://www.nap.edu/read/5306/chapter/5
Barriers to the Adoption of Electronic Medical Records in
Select Philippine Hospitals: A Case Study Approach, Ryan A. Ebardo
https://www.researchgate.net/publication/334754948_Barriers_to_the_Adoption_of_Elec
tronic_Medical_Records_in_Select_Philippine_Hospitals_A_Case_Study_Approach

You might also like