Development and validation of a point-of-care nursing mobile tool to guide the diagnosis of malnutrition in hospitalized adult patients: a multicenter, prospective cohort study

Abstract

Malnutrition is a prevalent and severe issue in hospitalized patients with chronic diseases. However, malnutrition screening is often overlooked or inaccurate due to lack of awareness and experience among health care providers. This study aimed to develop and validate a novel digital smartphone-based self-administered tool that uses facial features, especially the ocular area, as indicators of malnutrition in inpatient patients with chronic diseases. Facial photographs and malnutrition screening scales were collected from 619 patients in four different hospitals. A machine learning model based on back propagation neural network was trained, validated, and tested using these data. The model showed a significant correlation (p < 0.05) and a high accuracy (area under the curve 0.834–0.927) in different patient groups. The point-of-care mobile tool can be used to screen malnutrition with good accuracy and accessibility, showing its potential for screening malnutrition in patients with chronic diseases.

Keywords

artificial intelligence / e-health / facial recognition / malnutrition / mobile multimedia technologies / nutritional screening

References

1	T Ji, Y Li, P Liu, Y Zhang, Y Song, L Ma. Validation of GLIM criteria on malnutrition in older Chinese inpatients. Front Nutr. 2022;9:969666. doi:
2	HJ Andreyev, AR Norman, J Oates, D Cunningham. Why do patients with weight loss have a worse outcome when undergoing chemotherapy for gastrointestinal malignancies? Eur J Cancer. 1998;34(4):503-509. doi:
3	Y Tamura, T Omura, K Toyoshima, A Araki. Nutrition management in older adults with diabetes: a review on the importance of shifting prevention strategies from metabolic syndrome to frailty. Nutrients. 2020;12(11):3367. doi:
4	J Arends, V Baracos, H Bertz, et al. ESPEN expert group recommendations for action against cancer-related malnutrition. Clin Nutr. 2017;36(5):1187-1196. doi:
5	MVL Saintrain, R Sandrin, CB Bezerra, AOP Lima, MA Nobre, DRA Braga. Nutritional assessment of older adults with diabetes mellitus. Diabetes Res Clin Pract. 2019;155:107819. doi:
6	P Schuetz, D Seres, DN Lobo, F Gomes, N Kaegi-Braun, Z Stanga. Management of disease-related malnutrition for patients being treated in hospital. Lancet. 2021;398(10314):1927-1938. doi:
7	J Bauer, S Capra, M Ferguson. Use of the scored Patient-Generated Subjective Global Assessment (PG-SGA) as a nutrition assessment tool in patients with cancer. Eur J Clin Nutr. 2002;56(8):779-785. doi:
8	LM De Groot, G Lee, A Ackerie, BS van der Meij. Malnutrition screening and assessment in the cancer care ambulatory setting: mortality predictability and validity of the Patient-Generated Subjective Global Assessment Short form (PG-SGA SF) and the GLIM criteria. Nutrients. 2020;12(8):2287. doi:
9	L Zhu, P Spachos, Annotation efficiency in multimodal emotion recognition with deep learning. GLOBECOM 2022 - 2022 IEEE Global Communications Conference. 2022:560-565.
10	X Zhang, M Tang, Q Zhang, et al. The GLIM criteria as an effective tool for nutrition assessment and survival prediction in older adult cancer patients. Clin Nutr. 2021;40(3):1224-1232. doi:
11	KA Poulia, S Klek, I Doundoulakis, et al. The two most popular malnutrition screening tools in the light of the new ESPEN consensus definition of the diagnostic criteria for malnutrition. Clin Nutr. 2017;36(4):1130-1135. doi:
12	C Serón-Arbeloa, L Labarta-Monzón, J Puzo-Foncillas, et al. Malnutrition screening and assessment. Nutrients. 2022;14(12):2392. doi:
13	K Schindler, E Pernicka, A Laviano, et al. How nutritional risk is assessed and managed in European hospitals: a survey of 21,007 patients findings from the 2007–2008 cross-sectional nutritionDay survey. Clin Nutr. 2010;29(5):552-559. doi:
14	V Coetzee, J Chen, DI Perrett, ID Stephen. Deciphering faces: quantifiable visual cues to weight. Perception. 2010;39(1):51-61. doi:
15	PJ Cornbleet, MC Shea. Comparison of product moment and rank correlation coefficients in the assessment of laboratory method-comparison data. Clin Chem. 1978;24(6):857-861.
16	ML Barr, G Guo, SE Colby, MD Olfert. Detecting body mass index from a facial photograph in lifestyle intervention. Technologies. 2018;6(3):83. doi:
17	C Mayer, S Windhager, K Schaefer, P Mitteroecker. BMI and WHR are reflected in female facial shape and texture: a geometric morphometric image analysis. PLoS One. 2017;12(1):e0169336. doi:
18	M Jiang, Y Shang, G Guo. On visual BMI analysis from facial images. Image Vision Comput. 2019;89:183-196. doi:
19	T Altameem, A Altameem. Facial expression recognition using human machine interaction and multi-modal visualization analysis for healthcare applications. Article. Image Vision Comput. 2020;103:104044. doi:
20	Z Long, S Huang, J Zhang, et al. A digital smartphone-based self-administered tool (R+ Dietitian) for nutritional risk screening and dietary assessment in hospitalized patients with cancer: evaluation and diagnostic accuracy study. JMIR Form Res. 2022;6(10):e40316. doi:
21	X Chen, X Liu, W Ji, et al. The PG-SGA outperforms the NRS 2002 for nutritional risk screening in cancer patients: a retrospective study from China. Front Nutr. 2023;10:1272420. doi:
22	OV Demler, MJ Pencina. Misuse of DeLong test to compare AUCs for nested models. Stat Med. 2012;31(23):2577-2587. doi:
23	MS Pepe, J Fan, Z Feng, T Gerds, J Hilden. The Net Reclassification Index (NRI): a misleading measure of prediction improvement even with independent test data sets. Stat Biosci. 2015;7(2):282-295. doi:
24	KF Kerr, RL McClelland, ER Brown, T Lumley. Evaluating the incremental value of new biomarkers with integrated discrimination improvement. Am J Epidemiol. 2011;174(3):364-374. doi:
25	M Fischer, A JeVenn, P Hipskind. Evaluation of muscle and fat loss as diagnostic criteria for malnutrition. Nutr Clin Pract. 2015;30(2):239-248. doi:
26	W Tay, R Quek, B Kaur, J Lim, CJ Henry. Use of facial morphology to determine nutritional status in older adults: opportunities and challenges. JMIR Public Health Surveill. 2022;8(7):e33478. doi:
27	IH Kao, C-Y Chan. Comparison of eye and face features on drowsiness analysis. Article. Sensors. 2022;22(17):6529. doi:
28	CY Cheung, AR Ran, S Wang, et al. A deep learning model for detection of Alzheimer's disease based on retinal photographs: a retrospective, multicentre case-control study. Lancet Digit Health. 2022;4(11):e806-e815. doi:
29	AR Henderson. The bootstrap: a technique for data-driven statistics. Using computer-intensive analyses to explore experimental data. Clin Chim Acta. 2005;359(1-2):1-26. doi:
30	EH Thijssen, A Strom, et al. Plasma phosphorylated tau 217 and phosphorylated tau 181 as biomarkers in Alzheimer's disease and frontotemporal lobar degeneration: a retrospective diagnostic performance study. Lancet Neurol. 2021;20(9):739-752. doi:
31	A Essén, AD Stern, CB Haase, et al. Health app policy: international comparison of nine countries' approaches. NPJ Digit Med. 2022;5(1):31. doi:
32	J Qiang, D Wu, H Du, H Zhu, S Chen, H Pan. Review on facial-recognition-based applications in disease diagnosis. Review. Bioengineering-Basel. 2022;9(7):273. doi:
33	L Frey, C Menon, M Elgendi. Blood pressure measurement using only a smartphone. NPJ Digit Med. 2022;5(1):86. doi:
34	M Shukla, R Pandey, D Jain, JYF Lau. Poor emotional responsiveness in clinical hypertension: reduced accuracy in the labelling and matching of emotional faces amongst individuals with hypertension and prehypertension. Psychol Health. 2018;33(6):765-782. doi:
35	K Hoti, PT Chivers, JD Hughes. Assessing procedural pain in infants: a feasibility study evaluating a point-of-care mobile solution based on automated facial analysis. Lancet Digit Health. 2021;3(10):e623-e634. doi:
36	L Pu, MW Coppieters, J Byrnes, et al. Feasibility study protocol of the PainChek app to assess the efficacy of a social robot intervention for people with dementia. J Adv Nurs. 2022;78(2):587-594. doi:
37	B Qin, Q Quan, J Wu, L Liang, D Li. Diagnostic performance of artificial intelligence to detect genetic diseases with facial phenotypes A protocol for systematic review and meta analysis. Review. Medicine (Baltimore). 2020;99(27):20989. doi:
38	A Marwaha, D Chitayat, MS Meyn, R Mendoza-Londono, L Chad. The point-of-care use of a facial phenotyping tool in the genetics clinic: enhancing diagnosis and education with machine learning. Am J Med Genet A. 2021;185(4):1151-1158. doi:
39	K Yang, D Oh, JM Noh, et al. Feasibility of an interactive health coaching mobile app to prevent malnutrition and muscle loss in esophageal cancer patients receiving neoadjuvant concurrent chemoradiotherapy: prospective pilot study. J Med Internet Res. 2021;23(8):e28695. doi:
40	N Seyyedi, B Rahimi, HR Farrokh Eslamlou, T Timpka, H Lotfnezhad Afshar. Mobile phone applications to overcome malnutrition among preschoolers: a systematic review. BMC Med Inform Decis Mak. 2019;19(1):83. doi:
41	M Heemann, R Kim, S Vollmer, SV Subramanian. Assessment of undernutrition among children in 55 low- and middle-income countries using dietary and anthropometric measures. JAMA Netw Open. 2021;4(8):e2120627. doi:
42	ZA Bhutta, JA Berkley, RHJ Bandsma, M Kerac, I Trehan, A Briend. Severe childhood malnutrition. Nat Rev Dis Primers. 2017;3:17067. doi:
43	SAO Adeyeye, TJ Ashaolu, OT Bolaji, TA Abegunde, AO Omoyajowo. Africa and the Nexus of poverty, malnutrition and diseases. Crit Rev Food Sci Nutr. 2023;63(5):641-656. doi:
44	AJ Ruiz, G Buitrago, N Rodríguez, et al. Clinical and economic outcomes associated with malnutrition in hospitalized patients. Clin Nutr. 2019;38(3):1310-1316. doi:
45	Q Zhang, C He, W Qin, et al. Eliminate the hardware: mobile terminals-oriented food recognition and weight estimation system. Front Nutr. 2022;9:965801. doi:
46	Z Zhang, Z Wan, Y Zhu, L Zhang, L Zhang, H Wan. Prevalence of malnutrition comparing NRS2002, MUST, and PG-SGA with the GLIM criteria in adults with cancer: a multi-center study. Nutrition. 2021;83:111072. doi:
47	M Muscaritoli, J Arends, P Bachmann, et al. ESPEN practical guideline: clinical nutrition in cancer. Clin Nutr. 2021;40(5):2898-2913. doi:
48	M Tian, H Fu, J Du. Application value of NRS2002 and PG-SGA in nutritional assessment for patients with cervical cancer surgery. Am J Transl Res. 2021;13(6):7186-7192.