Video walkthrough

Methodological issues of the electronic health records’ use in the context of epidemiological investigations, in light of missing data: a review of the recent literature

Curious 3:12 CC AI

paperi.ai
0:00 / 0:00

Thomas Tsiampalis, Demosthenes B. Panagiotakos

Medical records can help prevent disease and improve treatment—even when parts of a patient’s story are missing. But the way those blank spaces are handled can quietly change the conclusion doctors and researchers reach.

Abstract

Background Electronic health records (EHRs) are widely accepted to enhance the health care quality, patient monitoring, and early prevention of various diseases, even when there is incomplete or missing information in them. Aim The present review sought to investigate the impact of EHR implementation on healthcare quality and medical decision in the context of epidemiological investigations, considering missing or incomplete data. Methods Google scholar, Medline (via PubMed) and Scopus databases were searched for studies investigating the impact of EHR implementation on healthcare quality and medical decision, as well as for studies investigating the way of dealing with missing data, and their impact on medical decision and the development process of prediction models. Electronic searches were carried out up to 2022. Results EHRs were shown that they constitute an increasingly important tool for both physicians, decision makers and patients, which can improve national healthcare systems both for the convenience of patients and doctors, while they improve the quality of health care as well as they can also be used in order to save money. As far as the missing data handling techniques is concerned, several investigators have already tried to propose the best possible methodology, yet there is no wide consensus and acceptance in the scientific community, while there are also crucial gaps which should be addressed. Conclusions Through the present thorough investigation, the importance of the EHRs’ implementation in clinical practice was established, while at the same time the gap of knowledge regarding the missing data handling techniques was also pointed out.

Transcript

Medical records can help prevent disease and improve treatment—even when parts of a patient’s story are missing. But the way those blank spaces are handled can quietly change the conclusion doctors and researchers reach. Electronic health records are widely accepted to enhance health care quality, patient monitoring, and the early prevention of various diseases, even when information in them is incomplete or missing.

That makes them valuable not only for treating illness, but also for noticing risks earlier and following patients over time. The review investigates how using electronic health records affects health care quality and medical decisions when information is missing or incomplete.

The central question is simple: how much can a medical conclusion be trusted when the record does not contain the whole story? The review presents the challenges of using electronic health records for population health investigations when information is missing. It also discusses the common ways researchers handle missing information so they can reach valid conclusions.

The reviewed studies use many different approaches to manage missing information. Some keep only records with complete information, while others fill gaps using averages or more advanced approaches for certain kinds of measurements.

One approach keeps only records with complete information, while another uses stratified mean imputation; more advanced methods can interpolate some longitudinal measurements. Few studies used informative observations, where the fact that a measurement is present can itself carry meaning about a value that is missing.

One method using deep learning reduced errors caused by filling in missing values under different situations, compared with four other techniques, and could help physicians and researchers use patient records for better management. The review finds that electronic health records are an increasingly important tool for health professionals and decision makers.

They can improve health care systems for patients and doctors by helping prevent and treat both long-term and other diseases. But the review cannot measure how well electronic health records perform in clinical practice because there is no well-established measure for doing so.

It therefore cannot quantitatively assess whether they save money when they guide medical decisions. The review highlights the importance of using electronic health records in clinical practice, while also pointing out a gap in knowledge about handling missing information.

For patients and doctors, electronic health records are increasingly important tools that can make health systems more convenient, improve health-care quality, and possibly save money. At the same time, the review highlights a continuing gap in knowledge about techniques for handling missing data in clinical practice.

Electronic health records can improve care, prevention, convenience, and costs, but this review finds no widely accepted way to deal with missing information. Better handling is needed before incomplete records can reliably guide decisions.

A derivative work by Paperi · AI-generated script, voice and captions · pages and figures unaltered

Made with Paperi.

Drop in a research PDF — get a narrated video walkthrough like this one, with highlights that follow the narration. Free to start.

Try it with your paper →

More papers

Hybrid Threshold Denoising Framework Using Singular Value Decomposition for Side-Channel Analysis Preprocessing 3:54

Hybrid Threshold Denoising Framework Using Singular Value Decomposition for Side-Channel Analysis Preprocessing

A device can reveal its encryption key without saying a word. Tiny electrical traces carry clues about the secret, but noise can bury them before anyone can read them.

A high-efficiency elementary network of interchangeable superconducting qubit devices 3:33

A high-efficiency elementary network of interchangeable superconducting qubit devices

What if a quantum computer did not have to be built as one giant, delicate object? This experiment shows that separate quantum devices can be connected by a cable, unplugged, and still exchange information with about one percent loss.

Resting-state occipito-frontal alpha connectome is linked to differential word learning ability in adult learners 3:14

Resting-state occipito-frontal alpha connectome is linked to differential word learning ability in adult learners

Why can one adult learn a new word almost effortlessly while another struggles? This study suggests the answer may partly lie in how two distant parts of the resting brain keep time together.

All 2 papers in Computer Science →