Natural language processing has been increasingly used in palliative care research over the last 5 years for its versatility and accuracy.
Aim:
To evaluate and characterize natural language processing use in palliative care research, including the most commonly used natural language processing software and computational methods, data sources, trends in natural language processing use over time, and palliative care topics addressed.
Design:
A scoping review using the framework by Arksey and O’Malley and the updated recommendations proposed by Levac et al. was conducted.
Sources:
PubMed, Web of Science, Embase, Scopus, and IEEE Xplore databases were searched for palliative care studies that utilized natural language processing tools. Data on study characteristics and natural language processing instruments used were collected and relevant palliative care topics were identified.
Results:
197 relevant references were identified. Of these, 82 were included after full-text review. Studies were published in 48 different journals from 2007 to 2022. The average sample size was 21,541 (median 435). Thirty-two different natural language processing software and 33 machine-learning methods were identified. Nine main sources for data processing and 15 main palliative care topics across the included studies were identified. The most frequent topic was mortality and prognosis prediction. We also identified a trend where natural language processing was frequently used in analyzing clinical serious illness conversations extracted from audio recordings.
Conclusions:
We found 82 papers on palliative care using natural language processing methods for a wide-range of topics and sources of data that could expand the use of this methodology. We encourage researchers to consider incorporating this cutting-edge research methodology in future studies to improve published palliative care data.
NowellLSNorrisJMWhiteDE, et al. Thematic analysis: striving to meet the trustworthiness criteria. Int J Qual Methods2017; 16: 1609406917733847.
2.
CollinsCA.‘There’s this big fear around palliative care because it’s connected to death and dying’: a qualitative exploration of the perspectives of undergraduate students on the role of the speech and language therapist in palliative care. Palliat Med2022; 36: 171–180.
3.
ByrneD.A worked example of Braun and Clarke’s approach to reflexive thematic analysis. Qual Quant2022; 56: 1391–1412.
4.
PastranaTDe LimaLPettusK, et al. The impact of COVID-19 on palliative care workers across the world: a qualitative analysis of responses to open-ended questions. Palliat Support Care2021; 19: 187–192.
5.
SarmetMCavalcantideOliveiraERNCirne FrancoH, et al. The current state of neuropalliative care in Brazil: trends in representation and advocacy. J Palliat Med2022; 25: 343–344.
6.
van den Broek-AltenburgEGramlingRGothardK, et al. Using natural language processing to explore heterogeneity in moral terminology in palliative care consultations. BMC Palliat Care2021; 20: 23.
7.
MorinLOnwuteaka-PhilipsenBD.The promise of big data for palliative and end-of-life care research. Palliat Med2021; 35: 1638–1640.
8.
NwosuACCollinsBMasonS.Big data analysis to improve care for people living with serious illness: the potential to use new emerging technology in palliative care. Palliat Med2018; 32: 164–166.
9.
SapetaPCentenoCBelarA, et al. Adaptation and continuous learning: integrative review of coping strategies of palliative care professionals. Palliat Med2022; 36: 15–29.
10.
YimW-WYetisgenMHarrisWP, et al. Natural language processing in oncology: a review. JAMA Oncol2016; 2: 797–804.
11.
DunnJ.Natural language processing for corpus linguistics. Cambridge: Cambridge University Press, 2022.
12.
KusalSPatilSKotechaK, et al. AI based emotion detection for textual big data: techniques and contribution. Big Data Cogn Comput2021; 5: 43. DOI: 10.3390/bdcc5030043
13.
ChowandaASutoyoRTanachutiwatS.Exploring text-based emotions recognition machine learning techniques on social media conversation. Procedia Comput Sci2021; 179: 821–828.
14.
AlswaidanNMenaiMEB. A survey of state-of-the-art approaches for emotion recognition in text. Knowl Inf Syst2020; 62: 2937–2987.
15.
ArkseyHO’MalleyL.Scoping studies: towards a methodological framework. Int J Soc Res Methodol2005; 8: 19–32.
16.
LevacDColquhounHO’BrienKK.Scoping studies: advancing the methodology. Implement Sci2010; 5: 69.
17.
AromatarisEZM. JBI manual for evidence synthesis. Adelaide: JBI, 2020.
18.
TriccoACLillieEZarinW, et al. PRISMA extension for scoping reviews (PRISMA-ScR): checklist and explanation. Ann Intern Med2018; 169: 467–473.
19.
RietjensJABramerWMGeijtemanEC, et al. Development and validation of search filters to find articles on palliative care in bibliographic databases. Palliat Med2019; 33: 470–474.
20.
BaccoLRussoFAmbrosioL, et al. Natural language processing in low back pain and spine diseases: a systematic review. Front Surg2022; 9: 957085.
21.
AndoMMoritaTO’ConnorSJ.Primary concerns of advanced cancer patients identified through the structured life review process: a qualitative study using a text mining technique. Palliat Support Care2007; 5: 265–271.
22.
AndoMTsudaAMoritaT.Life review interviews on the spiritual well-being of terminally ill cancer patients. Support Care Cancer2007; 15: 225–231.
23.
BakerKDunwoodieEJonesRG, et al. Process mining routinely collected electronic health records to define real-life clinical pathways during chemotherapy. Int J Med Inform2017; 103: 32–41.
24.
BarrettNWeber-JahnkeJHThaiV.Engineering natural language processing solutions for structured information from clinical text: extracting sentinel events from palliative care consult letters. Stud Health Technol Inform2013; 192: 594–598.
25.
BrizziKZupancSNUdelsmanBV, et al. Natural language processing to assess palliative care and end-of-life process measures in patients with breast cancer with leptomeningeal disease. Am J Hosp Palliat Care2020; 37: 371–376.
26.
ChanAChienIMoseleyE, et al. Deep learning algorithms to identify documentation of serious illness conversations during intensive care unit admissions. Palliat Med2019; 33: 187–196.
27.
ChiSGuoAHeardK, et al. Development and structure of an accurate machine learning algorithm to predict inpatient mortality and hospice outcomes in the coronavirus disease 2019 era. Med Care2022; 60: 381–386.
28.
ClarfeldLAGramlingRRizzoDM, et al. A general model of conversational dynamics and an example application in serious illness communication. PLoS One2021; 16: e0253124.
29.
DavoudiATissotHDoucetteA, et al. Using natural language processing to classify serious illness communication with oncology patients. AMIA Annu Symp Proc2022; 2022: 168–177.
30.
DiMartinoLMianoTWessellK, et al. Identification of uncontrolled symptoms in cancer patients using natural language processing. J Pain Symptom Manag2022; 63: 610–617.
31.
DixonJKnappM.Whose job? The staffing of advance care planning support in twelve international healthcare organizations: a qualitative interview study. BMC Palliat Care2018; 17: 78.
32.
DurieuxBNGramlingCJManukyanV, et al. Identifying connectional silence in palliative care consultations: a tandem machine-learning and human coding method. J Palliat Med2018; 21: 1755–1760.
33.
ElhazmiAAl-OmariASallamH, et al. Machine learning decision tree algorithm role for predicting mortality in critically ill adult COVID-19 patients admitted to the ICU. J Infect Public Health2022; 15: 826–834.
34.
ErnecoffNCWessellKLHansonLC, et al. Electronic health record phenotypes for identifying patients with late-stage disease: a method for research and clinical application. J Gen Intern Med2019; 34: 2818–2823.
35.
ForsythAWBarzilayRHughesKS, et al. Machine learning methods to extract documentation of breast cancer symptoms from electronic health records. J Pain Symptom Manag2018; 55: 1492–1499.
36.
GanguliRFranklinJYuX, et al. Machine learning models to prognose 30-day mortality in postoperative disseminated cancer patients. Surg Oncol2022; 44: 101810.
37.
GeorgeNMoseleyEEberR, et al. Deep learning to predict long-term mortality in patients requiring 7 days of mechanical ventilation. PLoS One2021; 16: e0253443.
38.
GramlingCJDurieuxBNClarfeldLA, et al. Epidemiology of connectional silence in specialist serious illness conversations. Patient Educ Couns2022; 105: 2005–2011.
39.
GramlingRJavedADurieuxBN, et al. Conversational stories & self organizing maps: innovations for the scalable study of uncertainty in healthcare communication. Patient Educ Couns2021; 104: 2616–2621.
40.
GrayTFKwokADoKM, et al. Associations between family member involvement and outcomes of patients admitted to the intensive care unit: retrospective cohort study. JMIR Med Inform2022; 10: e33921.
41.
AasenEMCrawfordPDahlBM.Discursive construction of the patient in online clinical cancer pathways information. J Adv Nurs2020; 76: 3113–3122.
42.
GreerJAMoyBEl-JawahriA, et al. Randomized trial of a palliative care intervention to improve end-of-life care discussions in patients with metastatic breast cancer. J Natl Compr Cancer Netw2022; 20: 136–143.
43.
HeintzelmanNHTaylorRJSimonsenL, et al. Longitudinal analysis of pain in patients with metastatic prostate cancer using natural language processing of medical record text. J Am Med Inform Assoc2013; 20: 898–905.
44.
HuCAChenC-MFangY-C, et al. Using a machine learning approach to predict mortality in critically ill influenza patients: a cross-sectional retrospective multicentre study in Taiwan. BMJ Open2020; 10: e033898.
45.
JayNNuemiGGadreauM, et al. A data mining approach for grouping and analyzing trajectories of care using claim data: the example of breast cancer. BMC Med Inform Decis Mak2013; 13: 130.
46.
JohnsonJLodhiMKCheemaU, et al. Outcomes for end-of-life patients with anticipatory grieving: insights from practice with standardized nursing terminologies within an interoperable internet-based electronic health record. J Hosp Palliat Nurs2017; 19: 223–231.
47.
JohnsonPCMarkovitzNHGrayTF, et al. Association of social support with overall survival and healthcare utilization in patients with aggressive hematologic malignancies. J Natl Compr Canc Netw2021; 1–7.
48.
KehlKLXuWLepistoE, et al. Natural language processing to ascertain cancer outcomes from medical oncologist notes. JCO Clin Cancer Inform2020; 4: 680–690.
49.
KernHCoraniGHuberD, et al. Impact on place of death in cancer patients: a causal exploration in southern Switzerland. BMC Palliat Care2020; 19: 160.
50.
LaiosAKatsenouATanYS, et al. Feature selection is critical for 2-year prognosis in advanced stage high grade serous ovarian cancer by using machine learning. Cancer Control2021; 28: 1–12.
51.
LakinJRZupancSNLindvallC, et al. Study protocol for video images about decisions to improve ethical outcomes with palliative care educators (VIDEO-PCE): a pragmatic stepped wedge cluster randomised trial of older patients admitted to the hospital. BMJ Open2022; 12: e065236.
52.
AgaronnikNDEl-JawahriALindvallC, et al. Exploring the process of cancer care for patients with pre-existing mobility disability. J Oncol Pract2021; 17: e53–e61.
53.
LauISKraljevicZAl-AgilM, et al. Natural language word embeddings as a glimpse into healthcare language and associated mortality surrounding end of life. BMJ Health Care Inform2021; 28: e100464.
54.
LeeKCUdelsmanBVStreidJ, et al. Natural language processing accurately measures adherence to best practice guidelines for palliative care in Trauma. J Pain Symptom Manag2020; 59: 225–232.e2.
55.
LeeRYBrumbackLCLoberWB, et al. Identifying goals of care conversations in the electronic health record using natural language processing and machine learning. J Pain Symptom Manag2021; 61: 136–142.e2.
56.
LefèvreCEconomosGTricouC, et al. Art therapy and social function in palliative care patients: a mixed-method pilot study. BMJ Support Palliat Care2022; 12: e75–e82.
57.
LinY-JChenR-JTangJ-H, et al. Machine-learning monitoring system for predicting mortality among patients with noncancer end-stage liver disease: retrospective study. JMIR Med Inform2020; 8: e24305.
58.
LindvallCDengC-YMoseleyE, et al. Natural language processing to identify advance care planning documentation in a multisite pragmatic clinical trial. J Pain Symptom Manag2022; 63: e29–e36.
59.
LindvallCLilleyEJZupancSN, et al. Natural language processing to assess end-of-life quality indicators in cancer patients receiving palliative surgery. J Palliat Med2019; 22: 183–187.
60.
López-TorrecillaJGonzález SanchisDGranero CabañeroD, et al. Pattern of care in radiotherapy at a University Hospital in Spain: the RENORT project. Clin Transl Oncol2021; 23: 1657–1665.
61.
LuciniFRKrewulakKDFiestKM, et al. Natural language processing to measure the frequency and mode of communication between healthcare professionals and family members of critically ill patients. J Am Med Inform Assoc2021; 28: 541–548.
62.
LuoXGandhiPStoreyS, et al. A computational framework to analyze the associations between symptoms and cancer patient attributes post chemotherapy using EHR Data. IEEE J Biomed Health Inform2021; 25: 4098–4109.
63.
AgaronnikNDLindvallCEl-JawahriA, et al. Challenges of developing a natural language processing method with electronic health records to identify persons with chronic mobility disability. Arch Phys Med Rehabil2020; 101: 1739–1746.
64.
MacieiraTGRYaoYKeenanGM.Use of machine learning to transform complex standardized nursing care plan data into meaningful research variables: a palliative care exemplar. J Am Med Inform Assoc2021; 28: 2695–2701.
65.
ManukyanVDurieuxBNGramlingCJ, et al. Automated detection of conversational pauses from audio recordings of serious illness conversations in natural hospital settings. J Palliat Med2018; 21: 1724–1728. DOI: 10.1089/jpm.2018.0269
66.
ManzCRChenJLiuM, et al. Validation of a machine learning algorithm to predict 180-day mortality for outpatients with cancer. JAMA Oncol2020; 6: 1723–1730.
67.
MasukawaKAoyamaMYokotaS, et al. Machine learning models to detect social distress, spiritual pain, and severe physical psychological symptoms in terminally ill patients with cancer from unstructured text data in electronic medical records. Palliat Med2022; 36: 1207–1216.
68.
MurphreeDHWilsonPMAsaiSW, et al. Improving the delivery of palliative care through predictive modeling and healthcare informatics. J Am Med Inform Assoc2021; 28: 1065–1073.
69.
O’HanlonCE.What kills us and what moves us: a comparative discourse analysis of heart disease and breast cancer. Digit Health2019; 5: 2055207619844865.
70.
OuchiKLo BelloJMoseleyE, et al. Long-term prognosis of older adults who survive emergency mechanical ventilation. J Pain Symptom Manag2020; 60: 1019–1026.
71.
PoortHZupancSNLeiterRE, et al. Documentation of palliative and end-of-life care process measures among young adults who died of cancer: a natural language processing approach. J Adolesc Young Adult Oncol2020; 9: 100–104.
72.
RossLDanforthCMEppsteinMJ, et al. Story arcs in serious illness: natural language processing features of palliative care conversations. Patient Educ Couns2020; 103: 826–832.
73.
SaeedSAbdullahAJhanjhiNZ.Analysis of the lung cancer patient’s for data mining tool. Int J Comput Sci Netw Secur2019; 19: 90–105.
74.
AgarwalRDomenicoHJBallaSR, et al. Palliative care exposure relative to predicted risk of six-month mortality in hospitalized adults. J Pain Symptom Manag2022; 63: 645–653.
75.
SandhamMHHedgecockEASiegertRJ, et al. Intelligent palliative care based on patient-reported outcome measures. J Pain Symptom Manag2022; 63: 747–757.
76.
SantarpiaABrabantEDudoitE.The narrative effects of classical music in palliative care. Psycho-Oncol2017; 11: 243–251.
77.
SantosHGDZampieriFGNormilio-SilvaK, et al. Machine learning to predict 30-day quality-adjusted survival in critically ill patients with cancer. J Crit Care2020; 55: 73–78.
78.
SealeCRausKBruinsmaS, et al. The language of sedation in end-of-life care: the ethical reasoning of care providers in three countries. Health2015; 19: 339–354.
79.
SongJTopazMLandauAY, et al. Using natural language processing to identify acute care patients who lack advance directives, decisional capacity, and surrogate decision makers. PLoS One2022; 17: e0270220.
80.
SteinerJMMorseCLeeRY, et al. Sensitivity and specificity of a machine learning algorithm to identify goals-of-care documentation for adults with congenital heart disease at the end of life. J Pain Symptom Manag2020; 60: e33–e36.
81.
SuLZhangZZhengF, et al. Five novel clinical phenotypes for critically ill patients with mechanical ventilation in intensive care units: a retrospective and multi database study. Respir Res2020; 21: 325.
82.
SungS-FChenC-HPanR-C, et al. Natural language processing enhances prediction of functional outcome after acute ischemic stroke. J Am Heart Assoc2021; 10: e023486.
83.
TaggartMChapmanWWSteinbergBA, et al. Comparison of 2 natural language processing methods for identification of bleeding among critically ill patients. JAMA Netw open2018; 1: e183451.
84.
UdelsmanBVMoseleyETSudoreRL, et al. Deep natural language processing identifies variation in care preference documentation. J Pain Symptom Manag2020; 59: 1186–1194.e3.
85.
AlmasalhaFXuDKeenanGM, et al. Data mining nursing care plans of end-of-life patients: a study to improve healthcare decision making. Int J Nurs Knowl2013; 24: 15–24.
86.
UdelsmanBChienIOuchiK, et al. Needle in a haystack: natural language processing to identify serious illness. J Palliat Med2019; 22: 179–182.
87.
UdelsmanBVLeeKCLilleyEJ, et al. Variation in serious illness communication among surgical patients receiving palliative care. J Palliat Med2020; 23: 411–414.
88.
UdelsmanBVLilleyEJQadanM, et al. Deficits in the palliative care process measures in patients with advanced pancreatic cancer undergoing operative and invasive nonoperative palliative procedures. Ann Surg Oncol2019; 26: 4204–4212.
89.
UyedaAMCurtisJREngelbergRA, et al. Mixed-methods evaluation of three natural language processing modeling approaches for measuring documented goals-of-care discussions in the electronic health record. J Pain Symptom Manag2022; 63: e713–e723.
90.
WangLLakinJRileyC, et al. Disease trajectories and end-of-life care for dementias: latent topic modeling and trend analysis using clinical notes. AMIA Annu Symp Proc2018; 2018: 1056–1065.
91.
YangCYuRJiH, et al. Application of data mining in the provision of in-home medical care for patients with advanced cancer. Transl Cancer Res2021; 10: 3013–3019.
92.
YangXZhangJChenS, et al. Utilizing electronic health record data to understand comorbidity burden among people living with HIV: a machine learning approach. AIDS2021; 35: S39–S51.
93.
YeJYaoLShenJ, et al. Predicting mortality in critically ill patients with diabetes using machine learning and clinical notes. BMC Med Inform Decis Mak2020; 20: 295.
94.
YoonSBroadwellPAlcantaraC, et al. Analyzing topics and sentiments from Twitter to gain insights to refine interventions for family caregivers of persons with Alzheimer’s disease and related dementias (ADRD) during COVID-19 pandemic. Stud Health Technol Inform2022; 289: 170–173.
95.
Zhang-SalomonsJSalomonsG.Determine the therapeutic role of radiotherapy in administrative data: a data mining approach. BMC Med Res Methodol2015; 15: 11.
96.
AndoMMoritaTAkechiT.Factors in the short-term life review that affect spiritual well-being in terminally ill cancer patients. J Hosp Palliat Nurs2010; 12: 305–311.
97.
ZhangHLiYMcConnellW.Predicting potential palliative care beneficiaries for health plans: a generalized machine learning pipeline. J Biomed Inform2021; 123: 103922.
98.
ZhaoYZhangHHuoJ, et al. Mining Twitter to assess the determinants of health behavior towards palliative care in the United States. AMIA Jt Summits Transl Sci Proc2020; 2020: 730–739.
99.
AndoMMoritaTMiyashitaM, et al. Factors that influence the efficacy of bereavement life review therapy for spiritual well-being: a qualitative analysis. Support Care Cancer2011; 19: 309–314 DOI: 10.1007/s00520-010-1006-7
100.
AgaronnikNDKwokASchoenfeldAJ, et al. Natural language processing for automated surveillance of intraoperative neuromonitoring in spine surgery. J Clin Neurosci2022; 97: 121–126.
101.
ChienI.Natural language processing for precision clinical diagnostics and treatment. Thesis, Massachusetts Institute of Technology, Cambridge, MA, 2018.
102.
ParkJJindalAKuoP, et al. Automated rating of patient and physician emotion in primary care visits. Patient Educ Couns2021; 104: 2098–2105.
103.
RanardBLWernerRMAntanaviciusT, et al. Yelp reviews of hospital care can supplement and inform traditional surveys of the patient experience of care. Health Aff2016; 35: 697–705.
Supplementary Material
Please find the following supplemental material available below.
For Open Access articles published under a Creative Commons License, all supplemental material carries the same license as the article it is associated with.
For non-Open Access articles published, all supplemental material carries a non-exclusive license, and permission requests for re-use of supplemental material or any part of supplemental material shall be sent directly to the copyright owner as specified in the copyright notice associated with the article.
