Exploring the Association of Cancer and Depression in Electronic Health Records: Combining Encoded Diagnosis and Mining Free-Text Clinical Notes.
cancer
depression
electronic health records
natural language processing
text mining
Journal
JMIR cancer
ISSN: 2369-1999
Titre abrégé: JMIR Cancer
Pays: Canada
ID NLM: 101666844
Informations de publication
Date de publication:
11 Jul 2022
11 Jul 2022
Historique:
received:
26
04
2022
accepted:
20
06
2022
revised:
17
06
2022
entrez:
11
7
2022
pubmed:
12
7
2022
medline:
12
7
2022
Statut:
epublish
Résumé
A cancer diagnosis is a source of psychological and emotional stress, which are often maintained for sustained periods of time that may lead to depressive disorders. Depression is one of the most common psychological conditions in patients with cancer. According to the Global Cancer Observatory, breast and colorectal cancers are the most prevalent cancers in both sexes and across all age groups in Spain. This study aimed to compare the prevalence of depression in patients before and after the diagnosis of breast or colorectal cancer, as well as to assess the usefulness of the analysis of free-text clinical notes in 2 languages (Spanish or Catalan) for detecting depression in combination with encoded diagnoses. We carried out an analysis of the electronic health records from a general hospital by considering the different sources of clinical information related to depression in patients with breast and colorectal cancer. This analysis included ICD-9-CM (International Classification of Diseases, Ninth Revision, Clinical Modification) diagnosis codes and unstructured information extracted by mining free-text clinical notes via natural language processing tools based on Systematized Nomenclature of Medicine Clinical Terms that mentions symptoms and drugs used for the treatment of depression. We observed that the percentage of patients diagnosed with depressive disorders significantly increased after cancer diagnosis in the 2 types of cancer considered-breast and colorectal cancers. We managed to identify a higher number of patients with depression by mining free-text clinical notes than the group selected exclusively on ICD-9-CM codes, increasing the number of patients diagnosed with depression by 34.8% (441/1269). In addition, the number of patients with depression who received chemotherapy was higher than those who did not receive this treatment, with significant differences (P<.001). This study provides new clinical evidence of the depression-cancer comorbidity and supports the use of natural language processing for extracting and analyzing free-text clinical notes from electronic health records, contributing to the identification of additional clinical data that complements those provided by coded data to improve the management of these patients.
Sections du résumé
BACKGROUND
BACKGROUND
A cancer diagnosis is a source of psychological and emotional stress, which are often maintained for sustained periods of time that may lead to depressive disorders. Depression is one of the most common psychological conditions in patients with cancer. According to the Global Cancer Observatory, breast and colorectal cancers are the most prevalent cancers in both sexes and across all age groups in Spain.
OBJECTIVE
OBJECTIVE
This study aimed to compare the prevalence of depression in patients before and after the diagnosis of breast or colorectal cancer, as well as to assess the usefulness of the analysis of free-text clinical notes in 2 languages (Spanish or Catalan) for detecting depression in combination with encoded diagnoses.
METHODS
METHODS
We carried out an analysis of the electronic health records from a general hospital by considering the different sources of clinical information related to depression in patients with breast and colorectal cancer. This analysis included ICD-9-CM (International Classification of Diseases, Ninth Revision, Clinical Modification) diagnosis codes and unstructured information extracted by mining free-text clinical notes via natural language processing tools based on Systematized Nomenclature of Medicine Clinical Terms that mentions symptoms and drugs used for the treatment of depression.
RESULTS
RESULTS
We observed that the percentage of patients diagnosed with depressive disorders significantly increased after cancer diagnosis in the 2 types of cancer considered-breast and colorectal cancers. We managed to identify a higher number of patients with depression by mining free-text clinical notes than the group selected exclusively on ICD-9-CM codes, increasing the number of patients diagnosed with depression by 34.8% (441/1269). In addition, the number of patients with depression who received chemotherapy was higher than those who did not receive this treatment, with significant differences (P<.001).
CONCLUSIONS
CONCLUSIONS
This study provides new clinical evidence of the depression-cancer comorbidity and supports the use of natural language processing for extracting and analyzing free-text clinical notes from electronic health records, contributing to the identification of additional clinical data that complements those provided by coded data to improve the management of these patients.
Identifiants
pubmed: 35816382
pii: v8i3e39003
doi: 10.2196/39003
pmc: PMC9315897
doi:
Types de publication
Journal Article
Langues
eng
Pagination
e39003Informations de copyright
©Angela Leis, David Casadevall, Joan Albanell, Margarita Posso, Francesc Macià, Xavier Castells, Juan Manuel Ramírez-Anguita, Jordi Martínez Roldán, Laura I Furlong, Ferran Sanz, Francesco Ronzano, Miguel A Mayer. Originally published in JMIR Cancer (https://cancer.jmir.org), 11.07.2022.
Références
J R Soc Med. 2003 Dec;96(12):577-81
pubmed: 14645605
J Am Med Inform Assoc. 2019 Apr 1;26(4):364-379
pubmed: 30726935
Am J Clin Oncol. 2019 Apr;42(4):355-362
pubmed: 30844850
J Med Syst. 2018 May 31;42(7):126
pubmed: 29855732
J Am Geriatr Soc. 2018 Aug;66(8):1499-1507
pubmed: 29972595
Eur J Cancer Care (Engl). 2010 Jul;19(4):522-9
pubmed: 20030697
EJC Suppl. 2013 Sep;11(2):205-15
pubmed: 26217129
JMIR Med Inform. 2021 Aug 4;9(8):e27842
pubmed: 34346902
Psychiatry Res. 2016 Jun 30;240:343-347
pubmed: 27138829
Psychol Med. 2010 Nov;40(11):1797-810
pubmed: 20085667
BMC Cancer. 2010 Oct 20;10:569
pubmed: 20961421
Stud Health Technol Inform. 2017;235:236-240
pubmed: 28423789
J Clin Oncol. 2014 Nov 1;32(31):3540-6
pubmed: 25287821
Evid Based Ment Health. 2020 Feb;23(1):21-26
pubmed: 32046989
Breast Cancer Res Treat. 2019 Aug;176(3):519-533
pubmed: 31087199
Int J Environ Res Public Health. 2019 Jan 31;16(3):
pubmed: 30709020
Adv Exp Med Biol. 2016;939:139-166
pubmed: 27807747
J Clin Oncol. 2012 Apr 10;30(11):1187-96
pubmed: 22412144
CA Cancer J Clin. 2021 May;71(3):209-249
pubmed: 33538338
J Affect Disord. 2012 Dec 10;141(2-3):343-51
pubmed: 22727334
Eur J Cancer Care (Engl). 2019 Sep;28(5):e13129
pubmed: 31290218
BMC Med Inform Decis Mak. 2019 Jul 9;19(1):128
pubmed: 31288818
J Clin Oncol. 2008 Oct 10;26(29):4731-8
pubmed: 18695257
BMJ Open. 2014 Mar 13;4(3):e003901
pubmed: 24625637
Cancer. 2009 Nov 15;115(22):5349-61
pubmed: 19753617
JMIR Med Inform. 2019 Apr 27;7(2):e12239
pubmed: 31066697
Rev Esp Enferm Dig. 2012 Dec;104(11):572-7
pubmed: 23368648
Am J Med Genet B Neuropsychiatr Genet. 2018 Oct;177(7):601-612
pubmed: 28557243
Nat Rev Genet. 2012 May 02;13(6):395-405
pubmed: 22549152
Oncol Lett. 2015 Apr;9(4):1509-1514
pubmed: 25788991
J Gastrointest Oncol. 2017 Feb;8(1):81-88
pubmed: 28280612
Asian Pac J Cancer Prev. 2018 Jun 25;19(6):1661-1669
pubmed: 29938451
JAMA Oncol. 2016 Jun 1;2(6):797-804
pubmed: 27124593
BMJ Open. 2017 Jan 17;7(1):e012012
pubmed: 28096249