Automated abstraction of myocardial perfusion imaging reports using natural language processing
© 2020. American Society of Nuclear Cardiology..
BACKGROUND: Findings and interpretations of myocardial perfusion imaging (MPI) studies are documented in free-text MPI reports. MPI results are essential for research, but manual review is prohibitively time consuming. This study aimed to develop and validate an automated method to abstract MPI reports.
METHODS: We developed a natural language processing (NLP) algorithm to abstract MPI reports. Randomly selected reports were double-blindly reviewed by two cardiologists to validate the NLP algorithm. Secondary analyses were performed to describe patient outcomes based on abstracted-MPI results on 16,957 MPI tests from adult patients evaluated for suspected ACS.
RESULTS: The NLP algorithm achieved high sensitivity (96.7%) and specificity (98.9%) on the MPI categorical results and had a similar degree of agreement compared to the physician reviewers. Patients with abnormal MPI results had higher rates of 30-day acute myocardial infarction or death compared to patients with normal results. We identified issues related to the quality of the reports that not only affect communication with referring physicians but also challenges for automated abstraction.
CONCLUSION: NLP is an accurate and efficient strategy to abstract results from the free-text MPI reports. Our findings will facilitate future research to understand the benefits of MPI studies but requires validation in other settings.
Errataetall: |
CommentIn: J Nucl Cardiol. 2022 Jun;29(3):1188-1190. - PMID 33474697 |
---|---|
Medienart: |
E-Artikel |
Erscheinungsjahr: |
2022 |
---|---|
Erschienen: |
2022 |
Enthalten in: |
Zur Gesamtaufnahme - volume:29 |
---|---|
Enthalten in: |
Journal of nuclear cardiology : official publication of the American Society of Nuclear Cardiology - 29(2022), 3 vom: 05. Juni, Seite 1178-1187 |
Sprache: |
Englisch |
---|
Beteiligte Personen: |
Zheng, Chengyi [VerfasserIn] |
---|
Links: |
---|
Themen: |
Data abstraction |
---|
Anmerkungen: |
Date Completed 06.06.2022 Date Revised 30.01.2024 published: Print-Electronic CommentIn: J Nucl Cardiol. 2022 Jun;29(3):1188-1190. - PMID 33474697 Citation Status MEDLINE |
---|
doi: |
10.1007/s12350-020-02401-z |
---|
funding: |
|
---|---|
Förderinstitution / Projekttitel: |
|
PPN (Katalog-ID): |
NLM317232932 |
---|
LEADER | 01000caa a22002652 4500 | ||
---|---|---|---|
001 | NLM317232932 | ||
003 | DE-627 | ||
005 | 20240130231930.0 | ||
007 | cr uuu---uuuuu | ||
008 | 231225s2022 xx |||||o 00| ||eng c | ||
024 | 7 | |a 10.1007/s12350-020-02401-z |2 doi | |
028 | 5 | 2 | |a pubmed24n1275.xml |
035 | |a (DE-627)NLM317232932 | ||
035 | |a (NLM)33155169 | ||
040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
041 | |a eng | ||
100 | 1 | |a Zheng, Chengyi |e verfasserin |4 aut | |
245 | 1 | 0 | |a Automated abstraction of myocardial perfusion imaging reports using natural language processing |
264 | 1 | |c 2022 | |
336 | |a Text |b txt |2 rdacontent | ||
337 | |a ƒaComputermedien |b c |2 rdamedia | ||
338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
500 | |a Date Completed 06.06.2022 | ||
500 | |a Date Revised 30.01.2024 | ||
500 | |a published: Print-Electronic | ||
500 | |a CommentIn: J Nucl Cardiol. 2022 Jun;29(3):1188-1190. - PMID 33474697 | ||
500 | |a Citation Status MEDLINE | ||
520 | |a © 2020. American Society of Nuclear Cardiology. | ||
520 | |a BACKGROUND: Findings and interpretations of myocardial perfusion imaging (MPI) studies are documented in free-text MPI reports. MPI results are essential for research, but manual review is prohibitively time consuming. This study aimed to develop and validate an automated method to abstract MPI reports | ||
520 | |a METHODS: We developed a natural language processing (NLP) algorithm to abstract MPI reports. Randomly selected reports were double-blindly reviewed by two cardiologists to validate the NLP algorithm. Secondary analyses were performed to describe patient outcomes based on abstracted-MPI results on 16,957 MPI tests from adult patients evaluated for suspected ACS | ||
520 | |a RESULTS: The NLP algorithm achieved high sensitivity (96.7%) and specificity (98.9%) on the MPI categorical results and had a similar degree of agreement compared to the physician reviewers. Patients with abnormal MPI results had higher rates of 30-day acute myocardial infarction or death compared to patients with normal results. We identified issues related to the quality of the reports that not only affect communication with referring physicians but also challenges for automated abstraction | ||
520 | |a CONCLUSION: NLP is an accurate and efficient strategy to abstract results from the free-text MPI reports. Our findings will facilitate future research to understand the benefits of MPI studies but requires validation in other settings | ||
650 | 4 | |a Journal Article | |
650 | 4 | |a Research Support, N.I.H., Extramural | |
650 | 4 | |a Myocardial perfusion imaging | |
650 | 4 | |a data abstraction | |
650 | 4 | |a ischemia | |
650 | 4 | |a natural language processing | |
650 | 4 | |a noninvasive stress test | |
650 | 4 | |a nuclear cardiology | |
700 | 1 | |a Sun, Benjamin C |e verfasserin |4 aut | |
700 | 1 | |a Wu, Yi-Lin |e verfasserin |4 aut | |
700 | 1 | |a Ferencik, Maros |e verfasserin |4 aut | |
700 | 1 | |a Lee, Ming-Sum |e verfasserin |4 aut | |
700 | 1 | |a Redberg, Rita F |e verfasserin |4 aut | |
700 | 1 | |a Kawatkar, Aniket A |e verfasserin |4 aut | |
700 | 1 | |a Musigdilok, Visanee V |e verfasserin |4 aut | |
700 | 1 | |a Sharp, Adam L |e verfasserin |4 aut | |
773 | 0 | 8 | |i Enthalten in |t Journal of nuclear cardiology : official publication of the American Society of Nuclear Cardiology |d 1994 |g 29(2022), 3 vom: 05. Juni, Seite 1178-1187 |w (DE-627)NLM087703971 |x 1532-6551 |7 nnns |
773 | 1 | 8 | |g volume:29 |g year:2022 |g number:3 |g day:05 |g month:06 |g pages:1178-1187 |
856 | 4 | 0 | |u http://dx.doi.org/10.1007/s12350-020-02401-z |3 Volltext |
912 | |a GBV_USEFLAG_A | ||
912 | |a GBV_NLM | ||
951 | |a AR | ||
952 | |d 29 |j 2022 |e 3 |b 05 |c 06 |h 1178-1187 |