Malnutrition and its contributing factors for older people living in residential aged care facilities: Insights from natural language processing of aged care records
Restricted accessResearch articleFirst published online November, 2023
Malnutrition and its contributing factors for older people living in residential aged care facilities: Insights from natural language processing of aged care records
Malnutrition is a serious health risk facing older people living in residential aged care facilities. Aged care staff record observations and concerns about older people in electronic health records (EHR), including free-text progress notes. These insights are yet to be unleashed.
OBJECTIVE:
This study explored the risk factors for malnutrition in structured and unstructured electronic health data.
METHODS:
Data of weight loss and malnutrition were extracted from the de-identified EHR records of a large aged care organization in Australia. A literature review was conducted to identify causative factors for malnutrition. Natural language processing (NLP) techniques were applied to progress notes to extract these causative factors. The NLP performance was evaluated by the parameters of sensitivity, specificity and F1-Score.
RESULTS:
The NLP methods were highly accurate in extracting the key data, values for 46 causative variables, from the free-text client progress notes. Thirty three percent (1,469 out of 4,405) of the clients were malnourished. The structured, tabulated data only recorded 48% of these malnourished clients, far less than that (82%) identified from the progress notes, suggesting the importance of using NLP technology to uncover the information from nursing notes to fully understand the health status of the vulnerable older people in residential aged care.
CONCLUSION:
This study identified 33% of older people suffered from malnutrition, lower than those reported in the similar setting in previous studies. Our study demonstrates that NLP technology is important for uncovering the key information about health risks for older people in residential aged care. Future research can apply NLP to predict other health risks for older people in this setting.
AgarwalEFergusonMBanksMBauerJCapraSIsenringE. Malnutrition coding shortfalls in Australian and New Zealand hospitals. Nutr Diet.2015; 72(1): 69-73. doi: 10.1111/1747-0080.12116.
2.
Dietitians Association Australia. [https://dietitiansaustralia.org.au/] Malnutrition in older Australians 2019 [updated 2022; cited 2022 March 10]. Available from: https://agedcare.royalcommission.gov.au/system/files/2020-06/DAA.0001.0001.0079.pdf.
3.
EdingtonJBoormanJDurrantERPerkinsAGiffinCVJamesR, et al. Prevalence of malnutrition on admission to four hospitals in England. Clin Nutr.2000; 19(3): 191-5. doi: 10.1054/clnu.1999.0121.
4.
CorreiaMITDWaitzbergDL. The impact of malnutrition on morbidity, mortality, length of hospital stay and costs evaluated through a multivariate model analysis. Clin Nutr.2003; 22(3): 235-9. doi: 10.1016/S0261-5614(02)00215-7.
5.
StrattonRJKingCLStroudMAJacksonAAEliaM. ‘Malnutrition Universal Screening Tool’ predicts mortality and length of hospital stay in acutely ill elderly. Br J Nutr.2006; 95(2): 325-30. doi: 10.1079/bjn20051622.
6.
DoumitJNasserR. Nutrients intake in elderly residing in Lebanese nursing homes. Nutrition and Food Science.2017; 47(2): 217-28. doi: 10.1108/NFS-06-2016-0070.
7.
GaskillDBlackLJIsenringEAHassallSSandersFBauerJD. Malnutrition prevalence and nutrition issues in residential aged care facilities. Australas J Ageing.2008; 27(4): 189-94. doi: 10.1111/j.1741-6612.2008.00324.x.
8.
MeijersJMMHalfensRJGvan Bokhorst-de van der SchuerenMAEDassenTScholsJMGA. Malnutrition in Dutch health care: Prevalence, prevention, treatment, and quality indicators. Nutrition.2009; 25(5): 512-9. doi: 10.1016/j.nut.2008.11.004.
9.
ParsonsELStrattonRJCawoodALSmithTREliaM. Oral nutritional supplements in a randomised trial are more effective than dietary advice at improving quality of life in malnourished care home residents. Clin Nutr.2017; 36(1): 134-42. doi: 10.1016/j.clnu.2016.01.002.
10.
SahinSTasarPTSimsekHÇicekZEskiizmirliHAykarFS, et al. Prevalence of anemia and malnutrition and their association in elderly nursing home residents. Aging Clin Exp Res.2016; 28(5): 857-62. doi: 10.1007/s40520-015-0490-5.
11.
SuominenMMuurinenSRoutasaloPSoiniHSuur-UskiIPeiponenA, et al. Malnutrition and associated factors among aged residents in all nursing homes in Helsinki. Eur J Clin Nutr.2005; 59(4): 578-83. doi: 10.1038/sj.ejcn.1602111.
12.
KellettJKyleGItsiopoulosCNauntonMBaconR. Malnutrition prevalence in aged care residents. Top Clin Nutr.2015; 30(3): 276-80. doi: 10.1097/tin.0000000000000042.
13.
BanksMAshSBauerJGaskillD. Prevalence of malnutrition in adults in Queensland public hospitals and residential aged care facilities. Nutrition and Dietetics.2007; 64(3): 172-8. doi: 10.1111/j.1747-0080.2007.00179.x.
14.
AmarantosEMartinezADwyerJ. Nutrition and quality of life in older adults. The Journals of Gerontology: Series A. 2001; 56(suppl_2): 54-64. doi: 10.1093/gerona/56.suppl_2.54.
15.
DentEHoogendijkEOVisvanathanRWrightORL. Malnutrition screening and assessment in hospitalised older people: A review. J Nutr Health Aging.2019; 23(5): 431-41. doi: 10.1007/s12603-019-1176-z.
16.
KellettJKyleGItsiopoulosCNauntonM. Nutrition screening practices amongst australian Residential Aged Care Facilities. J Nutr Health Aging.2016; 20(10): 1040-4. doi: 10.1007/s12603-015-0693-7.
17.
AhmedTHaboubiN. Assessment and management of nutrition in older people and its importance to health. Clin Interv Aging.2010; 5: 207-16. doi: 10.2147/cia.s9664.
18.
AgarwalEMillerMYaxleyAIsenringE. Malnutrition in the elderly: A narrative review. Maturitas.2013; 76(4): 296-302. doi: 10.1016/j.maturitas.2013.07.013.
19.
CroganNLCorbettCFShortRA. The minimum data set: Predicting malnutrition in newly admitted nursing home residents. Clin Nurs Res.2002; 11(3): 341-53.
20.
PaulyLStehlePVolkertD. Nutritional situation of elderly nursing home residents. Z Gerontol Geriatr.2007; 40(1): 3-12. doi: 10.1007/s00391-007-0430-x.
21.
O’KeeffeMKellyMO’HerlihyEO’ToolePWKearneyPMTimmonsS, et al. Potentially modifiable determinants of malnutrition in older adults: A systematic review. Clin Nutr.2019; 38(6): 2477-98. doi: 10.1016/j.clnu.2018.12.007.
22.
StangeIPoeschlKStehlePVolkertD. Screening for malnutrition in nursing home residents: Comparison of different risk markers and their association to functional impairment. J Nutr Health Aging.2013; 17(4). doi: 10.1007/s12603-013-0021-z.
23.
BeckAM. Weight loss, mortality and associated potentially modifiable nutritional risk factors among nursing home residents – A Danish follow-up study. J Nutr Health Aging.2015; 19(1): 96-101. doi: 10.1007/s12603-015-0439-6.
24.
BanksMBauerJGravesNAshS. Malnutrition and pressure ulcer risk in adults in Australian health care facilities. Nutrition.2010; 26(9): 896-901. doi: 10.1016/j.nut.2009.09.024.
25.
FlintKMatthews-RenschKFlawsDMudgeAYoungA. Mealtime care and dietary intake in older psychiatric hospital inpatient: A multiple case study. J Adv Nurs.2021; 77(3): 1490-500. doi: 10.1111/jan.14728.
26.
GoostHVidakovicEDeborreCRandauTWirtzDCBurgerC, et al. Malnutrition in geriatric trauma patients: Screening methods in comparison. Technol Health Care.2016; 24(2): 225-39. doi: 10.3233/THC1112.
27.
ChenTDredzeMWeinerJPHernandezLKimuraJKharraziH. Extraction of geriatric syndromes from electronic health record clinical notes: Assessment of statistical natural language processing methods. JMIR Med Inform.2019; 7(1): e13039. doi: 10.2196/13039.
28.
KharraziHAnzaldiLJHernandezLDavisonABoydCMLeffB, et al. The value of unstructured electronic health record data in geriatric syndrome case identification. J Am Geriatr Soc.2018; 66(8): 1499-507. doi: 10.1111/jgs.15411.
29.
LiaoKPAnanthakrishnanANKumarVXiaZCaganAGainerVS, et al. Methods to develop an electronic medical record phenotype algorithm to compare the risk of coronary artery disease across 3 chronic disease cohorts. PLoS One.2015; 10(8): e0136651. doi: 10.1371/journal.pone.0136651.
30.
LindKRabanMBrettLJorgensenMGeorgiouAWestbrookJ. Measuring the prevalence of 60 health conditions in older Australians in residential aged care with electronic health records: A retrospective dynamic cohort study. Popul Health Metr.2020; 18(1): 1-9. doi: 10.1186/s12963-020-00234-z.
31.
MurdochTBDetskyAS. The inevitable application of big data to health care. JAMA.2013; 309(13): 1351-2. doi: 10.1001/jama.2013.393.
32.
VivantiALeeHCPalmerM. Capitalising on opportunities: Malnutrition coding in hospital before and after the introduction of electronic health records with an embedded malnutrition screening tool. Clin Nutr ESPEN.2021; 41: 193-7. doi: 10.1016/j.clnesp.2020.11.012.
33.
HegdeHShimpiNGlurichIAcharyaA. Tobacco use status from clinical notes using Natural Language Processing and rule based algorithm. Technol Health Care.2018; 26(3): 445-56. doi: 10.3233/THC-171127.
34.
SheikhalishahiSMiottoRDudleyJTLavelliARinaldiFOsmaniV. Natural language processing of clinical notes on chronic diseases: Systematic review. JMIR Med Inform.2019; 7(2): e12239. doi: 10.2196/12239.
35.
MikolovTChenKCorradoGDeanJ. Efficient estimation of word representations in vector space. arXiv:13013781. 2013: 1-12. doi: 10.48550/arXiv.1301.3781.
36.
BodenreiderO. The Unified Medical Language System (UMLS): Integrating biomedical terminology. Nucleic Acids Res.2004; 32(Issue suppl_1): 267-70. doi: 10.1093/nar/gkh061.
37.
ZhouXWangYSohnSTherneauTMLiuHKnopmanDS. Automatic extraction and assessment of lifestyle exposures for Alzheimer’s disease using natural language processing. Int J Med Inform.2019; 130(August): 103943-. doi: 10.1016/j.ijmedinf.2019.08.003.
38.
MichalopoulosGQaziHWongAButtZChenH. Automatic extraction of risk factors for dialysis patients from clinical notes using natural language processing techniques. Digital Personalized Health and Medicine.2020; 270: 53-7. doi: 10.3233/SHTI200121.
39.
JonnalagaddaSRDel FiolGMedlinRWeirCFiszmanMMostafaJ, et al. Automatically extracting sentences from medline citations to support clinicians’ information needs. J Am Med Inform Assoc.2013; 20(5): 995-1000. doi: 10.1136/amiajnl-2012-001347.
40.
MiottoRLiLKiddBADudleyJT. Deep patient: An unsupervised representation to predict the future of patients from the electronic health records. Sci Rep.2016; 6(May): 1-10. doi: 10.1038/srep26094.
41.
NeumannMKingDBeltagyIAmmarW, editors.ScispaCy: Fast and robust models for biomedical natural language processing. Proceedings of the 18th BioNLP Workshop and Shared Task; 2019. Italy: Association for Computational Linguistics. doi: 10.18653/v1/w19-5034.
42.
Department of Health Australian Government. [https://www.health.gov.au/] Unplanned Weight Loss Quick Reference Guide – National Aged Care Mandatory Quality Indicator Program: Department of Health; [updated 2020; cited 2022 March 10]. Available from: https://www.health.gov.au/sites/default/files/documents/2020/09/unplanned-weight-loss-quick-reference-guide-national-aged-care-mandatory-quality-indicator-program_0.pdf.
43.
WangNBjörvellCHaileyDYuP. Development of the quality of australian nursing documentation in aged care (QANDAC) instrument to assess paper-based and electronic resident records. Australas J Ageing.2014; 33(4): E18-E24. doi: 10.1111/ajag.12072.
44.
Al-DooriSKSTaspinarYSKokluM. Distracted Driving Detection with Machine Learning Methods by CNN Based Feature Extraction. International Journal of Applied Mathematics Electronics and Computers.2021; 9(4): 116-21. doi: 10.18100/ijamec.1035749.
45.
Aged Care Royal Commission. [https://agedcare.royalcommission.gov.au/] Final Report: Care, Dignity and Respect 2021 [updated 2021; cited 2022 March 10]. Available from: https://agedcare.royalcommission.gov.au/sites/default/files/2021-03/final-report-volume-1.pdf.
46.
ShaoYMohantyAFAhmedAWeirCRBrayBEShahRU, et al. Identification and use of frailty indicators from text to examine associations with clinical outcomes among patients with heart failure. AMIA Annual Symposium proceedings AMIA Symposium.2017; 2016: 1110-8.
47.
ShaoYZengQTChenKKShutes-DavidAThielkeSMTsuangDW. Detection of probable dementia cases in undiagnosed patients using structured and unstructured electronic health records. BMC Med Inform Decis Mak.2019; 19(1): 1-11. doi: 10.1186/s12911-019-0846-4.
48.
AnzaldiLJDavisonABoydCMLeffBKharraziH. Comparing clinician descriptions of frailty and geriatric syndromes using electronic health records: A retrospective cohort study. BMC Geriatr.2017; 17(1): 1-7. doi: 10.1186/s12877-017-0645-7.
49.
VolkertDBeckAMCederholmTCruz-JentoftAGoisserSHooperL, et al. ESPEN guideline on clinical nutrition and hydration in geriatrics. Clin Nutr.2019; 38(1): 10-47. doi: 10.1016/j.clnu.2018.05.024.
50.
CroganNLAlvineCPasvogelA. Improving nutrition care for nursing home residents using the INRx process. J Nutr Elder.2006; 25(3-4): 89-103. doi: 10.1300/j052v25n03_07.
51.
CorcoranCMurphyCCulliganEPWaltonJSleatorRD. Malnutrition in the elderly. Sci Prog.2019; 102(2): 171-80. doi: 10.1177/0036850419854290.
52.
KubrakCJensenL. Malnutrition in acute care patients: A narrative review. Int J Nurs Stud.2007; 44(6): 1036-54. doi: 10.1016/j.ijnurstu.2006.07.015.
53.
Van der Pols-VijlbriefRWijnhovenHAHSchaapLATerweeCBVisserM. Determinants of protein-energy malnutrition in community-dwelling older adults: A systematic review of observational studies. Ageing Res Rev.2014; 18: 112-31. doi: 10.1016/j.arr.2014.09.001.
54.
AfzalNMallipeddiVPSohnSLiuHChaudhryRScottCG, et al. Natural language processing of clinical notes for identification of critical limb ischemia. Int J Med Inform.2018; 111: 83-9. doi: 10.1016/j.ijmedinf.2017.12.024.
