A New Paradigm to Analyze Data Completeness of Patient Data

Nasir, Ayan; Gurupur, Varadraj P.; Liu, Xinliang

doi:10.4338/aci-2016-04-ra-0063

Cited by 16 publications

(25 citation statements)

References 25 publications

(24 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…where r is number of rows 1 ≤ z ≤ number of columns (c) 1 (1) Distribution fitting is not the only necessary step required in data engineering, but rather, one of two steps. The second critical step in finding a best fit distribution is testing the proposed model.…”

Section: A Distribution Fittingmentioning

confidence: 99%

“…Whether the data need exists for research, hospital demographics, or even for the patients themselves, the need for completeness of each entry in a medical records system increases. In the past Nasir et al [1], have introduced the idea of using an algorithmic approach towards solving this problem. However, given the advances in artificial intelligence and machine learning there is a critical need for a more advanced approach that can be effectively used to predict data incompleteness in electronic health records.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Machine Learning Analysis for Data Incompleteness (MADI): Analyzing the Data Completeness of Patient Records Using a Random Variable Approach to Predict the Incompleteness of Electronic Health Records

Gurupur

Shelleh

2021

IEEE Access

View full text Add to dashboard Cite

The purpose of this article is to propose a methodology involving various methods that can be used to predict the data incompleteness of a dataset. Here the investigators have presented data incompleteness as both a continuous and discrete random variables and transfer entropy for the purpose of advancing the science associated with the analysis of data incompleteness of electronic health records. The underlying methodology has been coined as "Machine Learning Analysis for Data Incompleteness" (MADI) with the intention of developing a possible solution to data incompleteness in electronic health records. MADI advances the analysis of data incompleteness with the use of Kolomogorov Smirnov goodness of fit, mielke distribution, and beta distributions for a holistic analysis. Alongside the methodology presented, the investigators explored stochastic gradient descent, generalized additive models, and support vector machines for comparison. Overall, the investigators have presented a complete set of methods and algorithms to help predict data incompleteness in a medical setting and provided suggestions for practical applications into the prediction of data incompleteness.

show abstract

Section: A Distribution Fittingmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Machine Learning Analysis for Data Incompleteness (MADI): Analyzing the Data Completeness of Patient Records Using a Random Variable Approach to Predict the Incompleteness of Electronic Health Records

Gurupur

Shelleh

2021

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Completeness, accuracy, and timeliness of clinical data have been suggested as fundamental data quality measures for operational purposes. 7 , 8 Past studies have investigated data quality issues such as completeness and timeliness for physiologic signals, although not within ICU settings. 9 , 10 Completeness refers to the presence of values in data fields 7 , 8 , 11 and the availability of information for all relevant individuals.…”

Section: Introductionmentioning

confidence: 99%

An exploratory data quality analysis of time series physiologic signals using a large-scale intensive care unit database

Afshar

Chen

et al. 2021

JAMIA Open

View full text Add to dashboard Cite

Physiological data, such as heart rate and blood pressure, are critical to clinical decision-making in the intensive care unit (ICU). Vital signs data, which are available from electronic health records, can be used to diagnose and predict important clinical outcomes; While there have been some reports on the data quality of nurse-verified vital sign data, little has been reported on the data quality of higher frequency time-series vital signs acquired in ICUs, that would enable such predictive modeling. In this study, we assessed the data quality issues, defined as the completeness, accuracy, and timeliness, of minute-by-minute time series vital signs data within the MIMIC-III data set, captured from 16009 patient-ICU stays and corresponding to 9410 unique adult patients. We measured data quality of four time-series vital signs data streams in the MIMIC-III data set: heart rate (HR), respiratory rate (RR), blood oxygen saturation (SpO2), and arterial blood pressure (ABP). Approximately, 30% of patient-ICU stays did not have at least 1 min of data during the time-frame of the ICU stay for HR, RR, and SpO2. The percentage of patient-ICU stays that did not have at least 1 min of ABP data was ∼56%. We observed ∼80% coverage of the total duration of the ICU stay for HR, RR, and SpO2. Finally, only 12.5%%, 9.9%, 7.5%, and 4.4% of ICU lengths of stay had ≥ 99% data available for HR, RR, SpO2, and ABP, respectively, that would meet the three data quality requirements we looked into in this study. Our findings on data completeness, accuracy, and timeliness have important implications for data scientists and informatics researchers who use time series vital signs data to develop predictive models of ICU outcomes.

show abstract

“…The Data Completeness Analysis Package (DCAP) is used on patient data from the Healthcare Cost and Utilization Project (HCUP). 9…”

Section: Introductionmentioning

confidence: 99%

“…The research discussed previously (especially projects concerning patient data analysis) contributed in developing the DCAP research project. 9 That research developed both the software needed to analyze the data and a framework through which to understand results. DCAP examines native patient data with a master map indicating Importance Weights (IWs—indicates the relative importance of a specific data field’s completeness versus other data fields on a scale from 0 to 100).…”

Section: Introductionmentioning

confidence: 99%

Disparities in patient record completeness with respect to the health care utilization project

Nasir¹,

Liu²,

Gurupur

et al. 2017

Health Informatics J

Self Cite

View full text Add to dashboard Cite

Patient data completeness is an important characteristic in maintaining accurate health records and providing the highest standard of care. Furthermore, finding discrepancies in care based on different subpopulation parameters is important to identify areas of underlying systemic issues in order to address concerns and alleviate those discrepancies. In this project, the investigators use the Data Completeness Analysis Package to find trends in patient record completeness using Healthcare Cost and Utilization Project's State Inpatient Database for the state of Florida, specifically focusing on finding discrepancies among subpopulations along the variables of age, race, and gender. The results from testing Data Completeness Analysis Package with State Inpatient Database show a variety of patterns that provides insights to the health care delivery in Florida.

show abstract

A New Paradigm to Analyze Data Completeness of Patient Data

Cited by 16 publications

References 25 publications

Machine Learning Analysis for Data Incompleteness (MADI): Analyzing the Data Completeness of Patient Records Using a Random Variable Approach to Predict the Incompleteness of Electronic Health Records

Machine Learning Analysis for Data Incompleteness (MADI): Analyzing the Data Completeness of Patient Records Using a Random Variable Approach to Predict the Incompleteness of Electronic Health Records

An exploratory data quality analysis of time series physiologic signals using a large-scale intensive care unit database

Disparities in patient record completeness with respect to the health care utilization project

Contact Info

Product

Resources

About