OBJECTIVE: We aimed to evaluate the validity of a MARSIPAN-guidance-adapted Early Warning System (MARSI MEWS) and compare it to the National Early Warning Score (NEWS) and an adapted version of the Physical Risk in Eating Disorders Index (PREDIX), to ascertain whether current practice is comparable to best-practice standards. METHODS: We collated 3,937 observations from 36 inpatients from Addenbrookes Hospital over 2017-2018 and used three independent raters to create a "gold standard" of deteriorating cases. We ascertained performance metrics (Receiver Operating Characteristic Area Under the curve) for MARSI MEWS, NEWS and PREDIX; we also tested the proof of concept of a machine-learning-based early-warning-system (ML-EWS) using cross-validation and out-of-sample prediction of cases. RESULTS: The MARSI MEWS system showed higher ROC AUC (0.916) compared to NEWS (0.828) or PREDIX (0.865). ML-EWS (random forest) performed well at independent samples analysis (0.980) and multilevel analysis (0.922). CONCLUSION: MARSI MEWS seems most suitable for identifying critically deteriorating cases in anorexia nervosa inpatient population. We did not examine community practice in which the PREDIX arguably remains the best to ascertain deteriorating cases. Our results also provide a first proof of concept for the development of artificial-intelligence-based early warning systems in anorexia nervosa. Implications for inpatient clinical practice in eating disorders are discussed.

Cambridge and Peterborough NHS Foundation Trust Cambridge UK

Department of Kinanthropology Charles University Prague Staré Město Czechia

Department of Psychiatry University of Cambridge Cambridge UK

Zobrazit více v PubMed

Arcelus, J., Mitchell, A. J., Wales, J., & Nielsen, S. (2011). Mortality rates in patients with anorexia nervosa and other eating disorders. Archives of General Psychiatry, 68(7), 724-731. https://doi.org/10.1001/archgenpsychiatry.2011.74

Bishop, C. (2006). In M. Jordan, J. Kleinberg, & B. Schölkopf (Eds.), Pattern recognition and machine learning Information Science and Statistics (). New York, NY: Springer.

Breiman, L. (2001). Statistical modeling: The two cultures. Statistical Science, 16(3), 199-231.

De Simone, G., Scalfi, L., Galderisi, M., Celentano, A., Di Biase, G., Tammaro, P., … Contaldo, F. (1994). Cardiac abnormalities in young women with anorexia nervosa. British Heart Journal, 71, 287-292. https://doi.org/10.1136/hrt.71.3.287

Gao, H., McDonnell, A., Harrison, D. A., Moore, T., Adam, S., Daly, K., … Harvey, S. (2007). Systematic review and evaluation of physiological track and trigger warning systems for identifying at-risk patients on the ward. Intensive Care Medicine, 33(4), 667-679. https://doi.org/10.1007/s00134-007-0532-3

Gerry, S., Birks, J., Bonnici, T., Watkinson, P. J., Kirtley, S., & Collins, G. S. (2017, December 1). Early warning scores for detecting deterioration in adult hospital patients: A systematic review protocol. BMJ Open, 7, e019268. https://doi.org/10.1136/bmjopen-2017-019268

Hastie, T., Tibshirani, R., & Friedman, J. (2008). Springer series in statistics: The elements of statistical learning data mining, inference, and prediction. New York, NY: Springer.

Ioannidis, K., Lewis, G., Waterston, J., Connolly, C., Clay, F., Copping, C., … Serfontein, J. (2019, June 6). MARSIPAN-based Early Warning Signs System: A full Audit cycle in the Inpatient Eating Disorders Ward. https://doi.org/10.31219/osf.io/fgj78

Jáuregui-Garrido, B., & Jáuregui-Lobera, I. (2012). Sudden death in eating disorders. Vascular Health and Risk Management, 8, 91-98. https://doi.org/10.2147/VHRM.S28652

Jones, M. (2012). NEWSDIG: The National Early Warning Score Development and implementation group. Clinical Medicine (London, England), 12(6), 501-503. https://doi.org/10.7861/CLINMEDICINE.12-6-501

Jones, W. R., Morgan, J. F., & Arcelus, J. (2013). Managing physical risk in anorexia nervosa. Advances in Psychiatric Treatment, 19(3), 201-202. https://doi.org/10.1192/apt.bp.111.009779

Kwon, J., Lee, Y., Lee, Y., Lee, S., & Park, J. (2018). An algorithm based on deep learning for predicting in-hospital cardiac arrest. Journal of the American Heart Association, 7(13), e008678. https://doi.org/10.1161/JAHA.118.008678

MARSIPAN, The Royal Colleges of Psychiatrists, Physicians and Pathologists (2014). MARSIPAN: Management of Really Sick Patients with Anorexia Nervosa 2nd edition CR189. Retrieved from https://www.rcpsych.ac.uk/docs/default-source/improving-care/better-mh-policy/college-reports/college-report-cr189.pdf?sfvrsn=6c2e7ada_2

McCluskey, S., & Robinson, P. (2015). The MARSI MEWS Dr Sara McCluskey and Dr Paul Robinson. Evolution of the MARSI MEWS results of audit validation. Retrieved from Priory website: https://docplayer.net/53475835-The-marsi-mews-dr-sara-mccluskey-and-dr-paul-robinson-evolution-of-the-marsi-mews-results-of-audit-validation.html

Misra, M., Aggarwal, A., Miller, K. K., Almazan, C., Worley, M., Soyka, L. A., … Klibanski, A. (2004). Effects of anorexia nervosa on clinical, hematologic, biochemical, and bone density parameters in community-dwelling adolescent girls. Pediatrics, 114(6), 1574-1583. https://doi.org/10.1542/PEDS.2004-0540

Morgan, R., Williams, F., & Wright, M. (1997). An early warning scoring system for detecting developing critical illness. Clinical Intensive Care, 8, 100.

National Institute for Health and Care Excellence. (2019). Acutely ill patients in hospital overview - NICE pathways. Retrieved from https://pathways.nice.org.uk/pathways/acutely-ill-patients-in-hospital#path=view%3A/pathways/acutely-ill-patients-in-hospital/acutely-ill-patients-in-hospital-overview.xml&content=view-index

National Institute of Health and Care Excellence. (2007). Acutely ill adults in hospital: Recognising and responding to deterioration|Guidance and guidelines|NICE. Retrieved from https://www.nice.org.uk/guidance/cg50

Shamim, T., Golden, N. H., Arden, M., Filiberto, L., & Shenker, I. R. (2003). Resolution of vital sign instability: An objective measure of medical stability in anorexia nervosa. Journal of Adolescent Health, 32(1), 73-77. https://doi.org/10.1016/S1054-139X(02)00533-5

Smith, M. E. B., Chiovaro, J. C., O'Neil, M., Kansagara, D., Quiñones, A. R., Freeman, M., … Slatore, C. G. (2014, November 1). Early warning system scores for clinical deterioration in hospitalized patients: A systematic review. Annals of the American Thoracic Society, 11, 1454-1465. https://doi.org/10.1513/AnnalsATS.201403-102OC

Treasure, J. (2009). A guide to the medical risk assessment for eating disorders. Retrieved from King's College London and South London and Maudsley NHS Foundation Trust website: https://www.kcl.ac.uk/ioppn/depts/pm/research/eatingdisorders/resources/GUIDETOMEDICALRISKASSESSMENT.pdf

Umar, A., Ameh, C. A., Muriithi, F., & Mathai, M. (2019). Early warning systems in obstetrics: A systematic literature review. PLoS One, 14(5), e0217864. https://doi.org/10.1371/journal.pone.0217864

Xu, M., Tam, B., Thabane, L., & Fox-Robichaud, A. (2015). A protocol for developing early warning score models from vital signs data in hospitals using ensembles of decision trees. BMJ Open, 5(9), e008699. https://doi.org/10.1136/bmjopen-2015-008699

Zhai, H., Brady, P., Li, Q., Lingren, T., Ni, Y., Wheeler, D. S., & Solti, I. (2014). Developing and evaluating a machine learning based algorithm to predict the need of pediatric intensive care unit transfer for newly hospitalized children. Resuscitation, 85(8), 1065-1071. https://doi.org/10.1016/j.resuscitation.2014.04.009