Relative importance of clinical and sociodemographic factors in association with post-operative in-hospital deaths in colorectal cancer patients in New South Wales: An artificial neural network approach.
artificial neural network
co-morbidities
colorectal cancer
in-hospital mortality
patient-centred strategy
post-operative care
Journal
Journal of evaluation in clinical practice
ISSN: 1365-2753
Titre abrégé: J Eval Clin Pract
Pays: England
ID NLM: 9609066
Informations de publication
Date de publication:
Oct 2020
Oct 2020
Historique:
received:
18
04
2019
revised:
28
10
2019
accepted:
30
10
2019
pubmed:
17
11
2019
medline:
29
7
2021
entrez:
17
11
2019
Statut:
ppublish
Résumé
Co-morbidities in colorectal cancer patients complicate hospital care, and their relative importance to post-operative deaths is largely unknown. This study was conducted to examine a range of clinical and sociodemographic factors in relation to post-operative in-hospital deaths in colorectal cancer patients and identify whether these contributions would vary by severity of co-morbidities. In this multicentre retrospective cohort study, we used the complete census of New South Wales inpatient data to select colorectal cancer patients admitted to public hospitals for acute surgical care, who underwent procedures on the digestive system during the period of July 2001 to June 2014. The primary outcome was in-hospital death at the end of acute care. Multilayer perceptron and back-propagation artificial neural networks (ANNs) were used to quantify the relative importance of a wide range of clinical and sociodemographic factors in relation to post-operative deaths, stratified by severity of co-morbidities based on Charlson co-morbidity index. Of 6288 colorectal cancer patients, approximately 58.3% (n = 3669) had moderate to severe co-morbidities. A total of 464 (7.4%) died in hospitals. The performance for ANN models was superior to logistic models. Co-morbid musculoskeletal and mental disorders, adverse events in health care, and socio-economic factors including rural residence and private insurance status contributed to post-operative deaths in hospitals. Identification of relative importance of factors contributing to in-hospital deaths in colorectal cancer patients using ANN may help to enhance patient-centred strategies to meet complex needs during acute surgical care and prevent post-operative in-hospital deaths.
Types de publication
Journal Article
Multicenter Study
Langues
eng
Sous-ensembles de citation
IM
Pagination
1389-1398Informations de copyright
© 2019 John Wiley & Sons, Ltd.
Références
Arnold M, Sierra M, Laversanne M, Soerjomataram I, Jemal A, Bray F. Global patterns and trends in colorectal cancer incidence and mortality. Gut. 2016;66(4):683-691.
Australian Institute of Health and Welfare 2017. Cancer in Australia. Canberra: AIHW: Cancer series no.101. Cat. no. CAN 100; 2017.
Wiegering A, Ackermann S, Riegel J, et al. Improved survival of patients with colon cancer detected by screening colonoscopy. Int J Colorectal Dis. 2016;31(5):1039-1045.
Cancer Australia. Cancer research in Australia: an overview of funding initiatives to support cancer research capacity in Australia 2006 to 2011. Cancer Australia: Surry Hills, NSW; 2015.
Janssen-Heijnen M, Maas H, Houterman S, Lemmens V, Rutten H, Coebergh J. Comorbidity in older surgical cancer patients: influence on patient care and outcome. Eur J Cancer. 2007;43(15):2179-2193.
Alves A. Postoperative mortality and morbidity in french patients undergoing colorectal surgery. Arch Surg. 2005;140(3):278. 83, discussion 284
Lemmens V, Janssen-Heijnen M, Houterman S, et al. Which comorbid conditions predict complications after surgery for colorectal cancer? World J Surg. 2006;31(1):192-199.
Beckmann K, Moore J, Wattchow D, Young G, Roder D. Short-term outcomes after surgical resection for colorectal cancer in South Australia. J Eval Clin Pract. 2016;23(2):316-324.
Usher-Smith J, Miller R, Griffin S. Predicting survival in patients with colorectal cancer. BMJ. 2017;357:j2772.
Iversen LH, Nørgaard M, Jacobsen J, Soren L, Sørensen HT. The impact of comorbidity on survival of Danish colorectal cancer patients from 1995 to 2006-a population-based cohort study. Dis Colon Rectum. 2009;52(1):71-78.
Søgaard M, Thomsen RW, Bossen KS, Sørensen HT, Nørgaard M. The impact of comorbidity on cancer survival: a review. Clin Epidemiol. 2013;5(Suppl 1):3-29.
Geraci JM, Escalante CP, Freeman JL, Goodwin JS. Comorbid disease and cancer: the need for more relevant conceptual models in health services research. J Clin Oncol Official J American Soc Clin Oncol. 2005;23(30):7399-7404.
Dormann C, Elith J, Bacher S, et al. Collinearity: a review of methods to deal with it and a simulation study evaluating their performance. Ecography. 2012;36(1):27-46.
Dreiseitl S, Ohno-Machado L. Logistic regression and artificial neural network classification models: a methodology review. J Biomed Inform. 2002;35(5-6):352-359.
Bottaci L, Drew P, Hartley J, et al. Artificial neural networks applied to outcome prediction for colorectal cancer patients in separate institutions. The Lancet. 1997;350(9076):469-472.
Hall S, Holman C, Platell C, Sheiner H, Threlfall T, Semmens J. Colorectal cancer surgical care and survival: do private health insurance, socioeconomic and locational status make a difference? ANZ J Surg. 2005;75(11):929-935.
Jackson TJ, Michel JL, Roberts RF, Jorm CM, Wakefield JG. A classification of hospital-acquired diagnoses for use with routine hospital data. Med J Aust. 2009;191(10):544-548.
Australian Bureau of Statistics (ABS). Information Paper 2039.0: an introduction to socio-economic indexes for areas (SEIFA). Canberra: ABS; 2006.
Australian Institute of Health and Welfare. Australian hospital statistics 2012-13. Health services series no. 54. Cat. no. HSE 145. Canberra: AIHW; 2014.
van Groningen J, Eddes E, Fabry H, et al. Hospital teaching status and patients' outcomes after colon cancer surgery. World J Surg. 2018;42(10):3372-3380.
Borzecki A, Christiansen C, Chew P, Loveland S, Rosen AK. Comparison of in-hospital versus 30-day mortality assessments for selected medical conditions. Med Care. 2010;48(12):1117-1121.
Ben-Tovim D, Woodman R, Harrison J, et al. Measuring and reporting mortality in hospital patients (Cat: HSE 69). Canberra: AIHW; 2009.
Olden JD, Jackson DA. Illuminating the “black box”: a randomization approach for understanding variable contributions in artificial neural networks. Ecol Model. 2002;154(1):135-150.
Olden JD, Joy MK, Death RG. An accurate comparison of methods for quantifying variable importance in artificial neural networks using simulated data. Ecol Model. 2004;178(3):389-397.
Charlson ME, Pompei P, Ales KL, et al. A new method of classifying prognostic comorbidity in longitudinal studies: development and validation, J Chronic Dis, 1987, vol. 40 5(pg. 373-383)
Quan H, Li B, Couris C, et al. Updating and validating the Charlson comorbidity index and score for risk adjustment in hospital discharge abstracts using data from 6 countries. Am J Epidemiol. 2011;173(6):676-682.
Brunelli A, Postmus PE. Preoperative functional evaluation of the surgical candidate. Second ed. 2018;265-73.e3.
De Oña J, Garrido C. Extracting the contribution of independent variables in neural network models: a new approach to handle instability. Neural Comput Applic. 2014;25(3-4):859-869.
Practical guide to deal with imbalanced classification problems in R [Internet]. Analytics Vidhya. 2019. Available at: https://www.analyticsvidhya.com/blog/2016/03/practical-guide-deal-imbalanced-classification-problems/. Accessed at: 1 March 2019.
Arnold T. Uninformative parameters and model selection using Akaike's information criterion. J Wildlife Manage. 2010;74(6):1175-1178.
Miyachi Y, Kaido T, Yao S, et al. Bone mineral density as a risk factor for patients undergoing surgery for hepatocellular carcinoma. World J Surg. 2018;43(3):920-928.
Drake M. Osteoporosis and cancer. Curr Osteoporos Rep. 2013;11(3):163-170.
Nock N, Patrick-Melin A, Cook M, Thompson C, Kirwan J, Li L. Higher bone mineral density is associated with a decreased risk of colorectal adenomas. Int J Cancer. 2010;129(4):956-964.
Safaei-Nodehi R, Esmaili J, Sharifian R, Movaseghi S, Parkhideh S. Does adjuvant chemotherapy change bone mineral density and related serum biomarkers in women with breast cancer? Caspian J Intern Med. 2017;8(2):91-98.
Assi R, Mukherji D, Haydar A, Saroufim M, Temraz S, Shamseddine A. Metastatic colorectal cancer presenting with bone marrow metastasis: a case series and review of literature. J Gastroin Oncol. 2016;7(2):284.
Li H, Hong S, Qian J, Zheng Y, Yang J, Yi Q. Cross talk between the bone and immune systems: osteoclasts function as antigen-presenting cells and activate CD4+ and CD8+ T cells. Blood. 2010;116(2):210-217.
Cardwell C, Abnet C, Veal P, Hughes C, Cantwell M, Murray L. Exposure to oral bisphosphonates and risk of cancer. Int J Cancer. 2012;131(5):E717-E725.
Pazianas M, Abrahamsen B, Eiken P, Eastell R, Russell R. Reduced colon cancer incidence and mortality in postmenopausal women treated with an oral bisphosphonate-Danish National Register Based Cohort Study. Osteoporos Int. 2012;23(11):2693-2701.
Lustberg M, Reinbolt R, Shapiro C. Bone health in adult cancer survivorship. J Clin Oncol. 2012;30(30):3665-3674.
Jehn C, Kuehnhardt D, Bartholomae A, et al. Biomarkers of depression in cancer patients. Cancer. 2006;107(11):2723-2729.
Kumari N, Dwarakanath B, Das A, Bhatt A. Role of interleukin-6 in cancer progression and therapeutic resistance. Tumor Biology. 2016;37(9):11553-11572.
Kisely S, Crowe E, Lawrence D. Cancer-related mortality in people with mental illness. JAMA Psychiat. 2013;70(2):209-217.
Nakash O, Levav I, Aguilar-Gaxiola S, et al. Comorbidity of common mental disorders with cancer and their treatment gap: findings from the World Mental Health Surveys. Psychooncology. 2013;23(1):40-51.
Hodes G, Ménard C, Russo S. Integrating Interleukin-6 into depression diagnosis and treatment. Neurobiol Stress. 2016;4:15-22.
Klevens R, Edwards J, Richards C, et al. Estimating health care-associated infections and deaths in U.S. hospitals, 2002. Public Health Rep. 2007;122(2):160-166.
Astagneau P, Rioux C, Golliot F, Brücker G. Morbidity and mortality associated with surgical site infections: results from the 1997-1999 INCISO surveillance. J Hosp Infect. 2001;48(4):267-274.
Guzman-Pruneda F, Husain S, Jones C, et al. Compliance with preoperative care measures reduces surgical site infection after colorectal operation. J Surg Oncol. 2018;119(4):497-502.
British Medical Association. Tackling healthcare associated infections through effective policy action. London: BMA; 2009.
Russo P, Cheng A, Mitchell B, Hall L. Healthcare-associated infections in Australia: tackling the ‘known unknowns’. Aust Health Rev. 2018;42(2):178.
Australian Commission on Safety and Quality in Health Care. National Safety and Quality Health Service Standards. ACSQHC, Sydney, 2011. Available at https://www.safetyandquality.gov.au/wp-content/uploads/2011/01/NSQHS-Standards-Sept2011.pdf. Accessed at: 12 Dec, 2018.
Story D. Postoperative complications in Australia and New Zealand (the REASON study). Perioperative Medicine. 2013;2(1):16.
Kneebone R, Nestel D, Chrzanowska J, et al. The perioperative specialist practitioner: developing and evaluating a new surgical role. Qual Saf Health Care. 2006;15(5):354-358.
Xu H, White R, Sastow D, Andreae M, Gaber-Baylis L, Turnbull Z. Medicaid insurance as primary payer predicts increased mortality after total hip replacement in the state inpatient databases of California, Florida and New York. J Clin Anesth. 2017;43:24-32.