Informative missingness: What can we learn from patterns in missing laboratory data in the electronic health record?

被引：4

作者：

Tan, Amelia L. M. ^{[1
]}

Getzen, Emily J. ^{[2
]}

Hutch, Meghan R. ^{[3
]}

Strasser, Zachary H. ^{[4
]}

Gutierrez-Sacristan, Alba ^{[1
]}

Le, Trang T. ^{[2
]}

Dagliati, Arianna ^{[5
]}

Morris, Michele ^{[6
]}

Hanauer, David A. ^{[7
]}

Moal, Bertrand ^{[8
]}

Bonzel, Clara -Lea ^{[1
]}

Yuan, William ^{[1
]}

Chiudinelli, Lorenzo ^{[9
]}

Das, Priam ^{[1
]}

Zhang, Harrison G. ^{[1
]}

Aronow, Bruce J. ^{[10
]}

Avillach, Paul ^{[1
]}

Brat, Gabriel. A. ^{[1
]}

Cai, Tianxi ^{[1
]}

Hong, Chuan ^{[1
,11
]}

La Cava, William G. ^{[1
,12
]}

Loh, He Hooi Will ^{[13
]}

Luo, Yuan ^{[3
]}

Murphy, Shawn N. ^{[4
]}

Hgiam, Kee Yuan ^{[13
]}

Omenn, Gilbert S. ^{[6
]}

Patel, Lav P. ^{[14
]}

Samayamuthu, Malarkodi Jebathilagam ^{[6
]}

Shriver, Emily R. ^{[15
]}

Abad, Zahra Shakeri Hossein ^{[1
]}

Tan, Byorn W. L. ^{[13
]}

Visweswaran, Shyam ^{[6
]}

Wang, Xuan ^{[1
]}

Weber, Griffin M. ^{[1
]}

Xia, Zongqi ^{[6
]}

Verdy, Bertrand ^{[8
]}

Long, Qi ^{[2
]}

Mowery, Danielle L. ^{[2
]}

Holmes, John H. ^{[2
]}

机构：

[1] Harvard Med Sch, Cambridge, MA 02138 USA

[2] Univ Penn, Perelman Sch Med, Philadelphia, PA 19104 USA

[3] Northwestern Univ, Chicago, IL USA

[4] Massachusetts Gen Hosp, Boston, MA USA

[5] Univ Pavia, Pavia, Italy

[6] Univ Pittsburgh, Pittsburgh, PA USA

[7] Univ Michigan, Ann Arbor, MI USA

[8] Bordeaux Univ Hosp, Talence, France

[9] ASST Papa Giovanni XXIII, Bergamo, Italy

[10] Univ Cincinnati, Cincinnati Childrens Hosp Med Ctr, Cincinnati, OH USA

[11] Duke Univ, Durham, NC USA

[12] Boston Childrens Hosp, Boston, MA USA

[13] Natl Univ Hlth Syst, Singapore, Singapore

[14] Univ Kansas, Med Ctr, Lawrence, KS 66045 USA

[15] Univ Penn Hlth Syst, Philadelphia, PA USA

来源：

JOURNAL OF BIOMEDICAL INFORMATICS | 2023年 / 139卷

基金：

美国国家卫生研究院;

关键词：

Missing data; Electronic health records; COVID-19; Laboratory tests; Multi -site health data; METAANALYSIS; ASSOCIATION; GENOTYPE;

D O I：

10.1016/j.jbi.2023.104306

中图分类号：

TP39 [计算机的应用];

学科分类号：

081203 ; 0835 ;

摘要：

Background: In electronic health records, patterns of missing laboratory test results could capture patients' course of disease as well as reflect clinician's concerns or worries for possible conditions. These patterns are often understudied and overlooked. This study aims to identify informative patterns of missingness among laboratory data collected across 15 healthcare system sites in three countries for COVID-19 inpatients. Methods: We collected and analyzed demographic, diagnosis, and laboratory data for 69,939 patients with positive COVID-19 PCR tests across three countries from 1 January 2020 through 30 September 2021. We analyzed missing laboratory measurements across sites, missingness stratification by demographic variables, temporal trends of missingness, correlations between labs based on missingness indicators over time, and clus-tering of groups of labs based on their missingness/ordering pattern. Results: With these analyses, we identified mapping issues faced in seven out of 15 sites. We also identified nuances in data collection and variable definition for the various sites. Temporal trend analyses may support the use of laboratory test result missingness patterns in identifying severe COVID-19 patients. Lastly, using miss-ingness patterns, we determined relationships between various labs that reflect clinical behaviors. Conclusion: In this work, we use computational approaches to relate missingness patterns to hospital treatment capacity and highlight the heterogeneity of looking at COVID-19 over time and at multiple sites, where there might be different phases, policies, etc. Changes in missingness could suggest a change in a patient's condition, and patterns of missingness among laboratory measurements could potentially identify clinical outcomes. This allows sites to consider missing data as informative to analyses and help researchers identify which sites are better poised to study particular questions.

引用

页数：12

共 50 条

[41] WHAT CAN WE LEARN FROM ART
DIFFEY, TJ
AUSTRALASIAN JOURNAL OF PHILOSOPHY, 1995, 73 (02) : 204 - 211
[42] WHAT CAN WE LEARN FROM THE PAST
DEBREE, S
CHEMISTRY & INDUSTRY, 1995, (23) : 965 - 967
[43] WHAT CAN WE LEARN FROM THE OCTOPUS?
Tramacere, F.
Beccai, L.
Mazzolai, B.
BIOLOGICAL AND BIOMIMETIC ADHESIVES: CHALLENGES AND OPPORTUNITIES, 2013, : 89 - 102
[44] What We Can Learn From the Analects
Ling, Li
CONTEMPORARY CHINESE THOUGHT, 2009, 41 (02) : 91 - 103
[45] What we can learn from Geckos
Kroner, Elmar
Arzt, Eduard
NACHRICHTEN AUS DER CHEMIE, 2009, 57 (02) : 137 - 139
[46] What can we learn from spin?
Baillie, O. Villalobos
JOURNAL OF PHYSICS G-NUCLEAR AND PARTICLE PHYSICS, 2008, 35 (04)
[47] WHAT WE CAN LEARN FROM JAPAN
GOLDSTON, E
FORTUNE, 1971, 84 (04) : 137 - &
[48] WHAT CAN WE LEARN FROM PEMEX
CULLEN, J
CHEMICAL ENGINEER-LONDON, 1985, (418): : 21 - 22
[49] WHAT CAN WE LEARN FROM THE BORSTALS
GOODMAN, PW
ROCKY MOUNTAIN SOCIAL SCIENCE JOURNAL, 1965, 2 (01): : 207 - 207
[50] WHAT CAN WE LEARN FROM SWEDEN
NORDIN, BEC
BRITISH MEDICAL JOURNAL, 1974, 3 (5928): : 458 - 459

← 1 2 3 4 5 →