PMID- 38433189
OWN - NLM
STAT- MEDLINE
DCOM- 20240305
LR  - 20240306
IS  - 1472-6947 (Electronic)
IS  - 1472-6947 (Linking)
VI  - 22
IP  - Suppl 2
DP  - 2024 Mar 3
TI  - Natural language processing to identify lupus nephritis phenotype in electronic 
      health records.
PG  - 348
LID - 10.1186/s12911-024-02420-7 [doi]
LID - 348
AB  - BACKGROUND: Systemic lupus erythematosus (SLE) is a rare autoimmune disorder 
      characterized by an unpredictable course of flares and remission with diverse 
      manifestations. Lupus nephritis, one of the major disease manifestations of SLE 
      for organ damage and mortality, is a key component of lupus classification 
      criteria. Accurately identifying lupus nephritis in electronic health records 
      (EHRs) would therefore benefit large cohort observational studies and clinical 
      trials where characterization of the patient population is critical for 
      recruitment, study design, and analysis. Lupus nephritis can be recognized 
      through procedure codes and structured data, such as laboratory tests. However, 
      other critical information documenting lupus nephritis, such as histologic 
      reports from kidney biopsies and prior medical history narratives, require 
      sophisticated text processing to mine information from pathology reports and 
      clinical notes. In this study, we developed algorithms to identify lupus 
      nephritis with and without natural language processing (NLP) using EHR data from 
      the Northwestern Medicine Enterprise Data Warehouse (NMEDW). METHODS: We 
      developed five algorithms: a rule-based algorithm using only structured data 
      (baseline algorithm) and four algorithms using different NLP models. The first 
      NLP model applied simple regular expression for keywords search combined with 
      structured data. The other three NLP models were based on regularized logistic 
      regression and used different sets of features including positive mention of 
      concept unique identifiers (CUIs), number of appearances of CUIs, and a mixture 
      of three components (i.e. a curated list of CUIs, regular expression concepts, 
      structured data) respectively. The baseline algorithm and the best performing NLP 
      algorithm were externally validated on a dataset from Vanderbilt University 
      Medical Center (VUMC). RESULTS: Our best performing NLP model incorporated 
      features from both structured data, regular expression concepts, and mapped 
      concept unique identifiers (CUIs) and showed improved F measure in both the NMEDW 
      (0.41 vs 0.79) and VUMC (0.52 vs 0.93) datasets compared to the baseline lupus 
      nephritis algorithm. CONCLUSION: Our NLP MetaMap mixed model improved the 
      F-measure greatly compared to the structured data only algorithm in both internal 
      and external validation datasets. The NLP algorithms can serve as powerful tools 
      to accurately identify lupus nephritis phenotype in EHR for clinical research and 
      better targeted therapies.
CI  - (c) 2024. The Author(s).
FAU - Deng, Yu
AU  - Deng Y
AD  - Center for Health Information Partnerships, Feinberg School of Medicine, 
      Northwestern University, Chicago, USA.
FAU - Pacheco, Jennifer A
AU  - Pacheco JA
AD  - Center for Genetic Medicine, Feinberg School of Medicine, Northwestern 
      University, Chicago, USA.
FAU - Ghosh, Anika
AU  - Ghosh A
AD  - Center for Health Information Partnerships, Feinberg School of Medicine, 
      Northwestern University, Chicago, USA.
FAU - Chung, Anh
AU  - Chung A
AD  - Center for Health Information Partnerships, Feinberg School of Medicine, 
      Northwestern University, Chicago, USA.
AD  - Department of Medicine/Rheumatology, Feinberg School of Medicine, Northwestern 
      University, Chicago, USA.
FAU - Mao, Chengsheng
AU  - Mao C
AD  - Center for Health Information Partnerships, Feinberg School of Medicine, 
      Northwestern University, Chicago, USA.
FAU - Smith, Joshua C
AU  - Smith JC
AD  - Department of Biomedical Informatics, Vanderbilt University Medical Center, 
      Nashville, USA.
FAU - Zhao, Juan
AU  - Zhao J
AD  - Department of Biomedical Informatics, Vanderbilt University Medical Center, 
      Nashville, USA.
FAU - Wei, Wei-Qi
AU  - Wei WQ
AD  - Department of Biomedical Informatics, Vanderbilt University Medical Center, 
      Nashville, USA.
FAU - Barnado, April
AU  - Barnado A
AD  - Department of Medicine, Vanderbilt University Medical Center, Nashville, USA.
FAU - Dorn, Chad
AU  - Dorn C
AD  - Department of Biomedical Informatics, Vanderbilt University Medical Center, 
      Nashville, USA.
FAU - Weng, Chunhua
AU  - Weng C
AD  - Department of Biomedical Informatics, Columbia University, New York City, USA.
FAU - Liu, Cong
AU  - Liu C
AD  - Department of Biomedical Informatics, Columbia University, New York City, USA.
FAU - Cordon, Adam
AU  - Cordon A
AD  - Center for Genetic Medicine, Feinberg School of Medicine, Northwestern 
      University, Chicago, USA.
FAU - Yu, Jingzhi
AU  - Yu J
AD  - Center for Health Information Partnerships, Feinberg School of Medicine, 
      Northwestern University, Chicago, USA.
FAU - Tedla, Yacob
AU  - Tedla Y
AD  - Center for Health Information Partnerships, Feinberg School of Medicine, 
      Northwestern University, Chicago, USA.
FAU - Kho, Abel
AU  - Kho A
AD  - Center for Health Information Partnerships, Feinberg School of Medicine, 
      Northwestern University, Chicago, USA.
FAU - Ramsey-Goldman, Rosalind
AU  - Ramsey-Goldman R
AD  - Department of Medicine/Rheumatology, Feinberg School of Medicine, Northwestern 
      University, Chicago, USA.
FAU - Walunas, Theresa
AU  - Walunas T
AD  - Center for Health Information Partnerships, Feinberg School of Medicine, 
      Northwestern University, Chicago, USA. t-walunas@northwestern.edu.
FAU - Luo, Yuan
AU  - Luo Y
AUID- ORCID: 0000-0003-0195-7456
AD  - Center for Health Information Partnerships, Feinberg School of Medicine, 
      Northwestern University, Chicago, USA. yuan.luo@northwestern.edu.
LA  - eng
GR  - U01HG008680/HG/NHGRI NIH HHS/United States
GR  - U01HG008673/HG/NHGRI NIH HHS/United States
GR  - U01HG008672/HG/NHGRI NIH HHS/United States
GR  - 5R21AR072262/AR/NIAMS NIH HHS/United States
GR  - 1K08 AR072757-01/AR/NIAMS NIH HHS/United States
GR  - R61 AR076824/AR/NIAMS NIH HHS/United States
GR  - U01 HG008680/HG/NHGRI NIH HHS/United States
PT  - Journal Article
DEP - 20240303
PL  - England
TA  - BMC Med Inform Decis Mak
JT  - BMC medical informatics and decision making
JID - 101088682
SB  - IM
MH  - Humans
MH  - *Lupus Nephritis/diagnosis
MH  - Electronic Health Records
MH  - Natural Language Processing
MH  - *Lupus Erythematosus, Systemic
MH  - Phenotype
MH  - Rare Diseases
PMC - PMC10910523
OTO - NOTNLM
OT  - Computational phenotyping
OT  - Electronic health records
OT  - Lupus nephritis
OT  - Natural language processing
COIS- The authors declare that they have no competing interests.
EDAT- 2024/03/04 00:43
MHDA- 2024/03/05 06:44
PMCR- 2024/03/03
CRDT- 2024/03/03 23:13
PHST- 2021/04/09 00:00 [received]
PHST- 2024/01/09 00:00 [accepted]
PHST- 2024/03/05 06:44 [medline]
PHST- 2024/03/04 00:43 [pubmed]
PHST- 2024/03/03 23:13 [entrez]
PHST- 2024/03/03 00:00 [pmc-release]
AID - 10.1186/s12911-024-02420-7 [pii]
AID - 2420 [pii]
AID - 10.1186/s12911-024-02420-7 [doi]
PST - epublish
SO  - BMC Med Inform Decis Mak. 2024 Mar 3;22(Suppl 2):348. doi: 
      10.1186/s12911-024-02420-7.