{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,13]],"date-time":"2026-11-13T23:53:05Z","timestamp":1794613985734,"version":"4.9.1"},"reference-count":36,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2021,12,1]],"date-time":"2021-12-01T00:00:00Z","timestamp":1638316800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2021,12,1]],"date-time":"2021-12-01T00:00:00Z","timestamp":1638316800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BMC Pediatr"],"published-print":{"date-parts":[[2021,12]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:sec><jats:title>Background<\/jats:title><jats:p>Neonatal mortality remains high in Tanzania at approximately 20 deaths per 1000 live births. Low birthweight, prematurity, and asphyxia are associated with neonatal mortality; however, no studies have assessed the value of combining underlying conditions and vital signs to provide clinicians with early warning of infants at risk of mortality. The aim of this study was to identify risk factors (including vital signs) associated with neonatal mortality in the neonatal intensive care unit (NICU) in Bugando Medical Centre (BMC), Mwanza, Tanzania; to identify the most accurate generalised linear model (GLM) or decision tree for predicting mortality; and to provide a tool that provides clinically relevant cut-offs for predicting mortality that is easily used by clinicians in a low-resource setting.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>In total, 165 neonates were enrolled between November 2019 and March 2020, of whom 80 (48.5%) died. We competed the performance of GLMs and decision trees by resampling the data to create training and test datasets and comparing their accuracy at correctly predicting mortality.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>GLMs always outperformed decision trees. The best fitting GLM showed that (for standardised risk factors) temperature (OR 0.61, 95% CI 0.40\u20130.90), birthweight (OR 0.33, 95% CI 0.20\u20130.52), and oxygen saturation (OR 0.66, 95% CI 0.45\u20130.94) were negatively associated with mortality, while heart rate (OR 1.59, 95% CI 1.10\u20132.35) and asphyxia (OR 3.23, 95% 1.25\u20138.91) were risk factors. To identify the tool that balances accuracy and with ease of use in a low-resource clinical setting, we compared the best fitting GLM with simpler versions, and identified the three-variable GLM with temperature, heart rate, and birth weight as the best candidate. For this tool, cut-offs were identified using receiver operator characteristic (ROC) curves with the optimal cut-off for mortality prediction corresponding to 76.3% sensitivity and 68.2% specificity. The final tool is graphical, showing cut-offs that depend on birthweight, heart rate, and temperature.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusions<\/jats:title><jats:p>Underlying conditions and vital signs can be combined into simple graphical tools that improve upon the current guidelines and are straightforward to use by clinicians in a low-resource setting.<\/jats:p><\/jats:sec>","DOI":"10.1186\/s12887-021-03012-4","type":"journal-article","created":{"date-parts":[[2021,12,1]],"date-time":"2021-12-01T07:07:42Z","timestamp":1638342462000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":17,"title":["Developing practical clinical tools for predicting neonatal mortality at a neonatal intensive care unit in Tanzania"],"prefix":"10.1186","volume":"21","author":[{"given":"Dory","family":"Kovacs","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Delfina R.","family":"Msanga","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stephen E.","family":"Mshana","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Muhammad","family":"Bilal","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Katarina","family":"Oravcova","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Louise","family":"Matthews","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2021,12,1]]},"reference":[{"key":"3012_CR1","volume-title":"Neonatology at a glance","author":"T Lissauer","year":"2020","unstructured":"Lissauer T, Fanaroff AA, Miall L, Fanaroff JM. Neonatology at a glance. 4th ed. Hoboken: Wiley-Blackwell; 2020. At a glance series","edition":"4"},{"key":"3012_CR2","volume-title":"Newborns: improving survival and well-being [internet]. WHO fact sheets","author":"World Health Organisation","year":"2019","unstructured":"World Health Organisation. Newborns: improving survival and well-being [internet]. WHO fact sheets; 2019. [cited 2020 Oct 15]. Available from: https:\/\/www.who.int\/en\/news-room\/fact-sheets\/detail\/newborns-reducing-mortality"},{"issue":"7","key":"3012_CR3","doi-asserted-by":"publisher","first-page":"e396","DOI":"10.1016\/S2214-109X(15)00059-5","volume":"3","author":"H Afnan-Holmes","year":"2015","unstructured":"Afnan-Holmes H, Magoma M, John T, Levira F, Msemo G, Armstrong CE, et al. Tanzania\u2019s countdown to 2015: an analysis of two decades of progress and gaps for reproductive, maternal, newborn, and child health, to inform priorities for post-2015. Lancet Glob Health. 2015;3(7):e396\u2013409.","journal-title":"Lancet Glob Health"},{"key":"3012_CR4","first-page":"11","volume":"1","author":"G Mbawala","year":"2014","unstructured":"Mbawala G, Fredrick F, Kamugisha E, Konje E, Hokororo A. Factors associated with mortality among premature babies admitted at Bugando medical Centre, Mwanza - Tanzania. East Afr J Public Health. 2014;1:11.","journal-title":"East Afr J Public Health"},{"issue":"1","key":"3012_CR5","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1186\/1744-8603-8-11","volume":"8","author":"G Yamey","year":"2012","unstructured":"Yamey G. What are the barriers to scaling up health interventions in low and middle income countries? A qualitative study of academic leaders in implementation science. Glob Health. 2012;8(1):11.","journal-title":"Glob Health"},{"issue":"9462","key":"3012_CR6","doi-asserted-by":"publisher","first-page":"891","DOI":"10.1016\/S0140-6736(05)71048-5","volume":"365","author":"JE Lawn","year":"2005","unstructured":"Lawn JE, Cousens S, Zupan J. 4 million neonatal deaths: when? Where? Why? Lancet. 2005;365(9462):891\u2013900.","journal-title":"Lancet"},{"key":"3012_CR7","unstructured":"UNICEF. Every child alive: the urgent need to end newborn deaths. Geneva; 2018. Available from: https:\/\/data.unicef.org\/resources\/every-child-alive-urgent-need-end-newborn-deaths\/"},{"key":"3012_CR8","volume-title":"Maternal and newborn health disparities: Tanzania [internet]","author":"UNICEF","year":"2015","unstructured":"UNICEF. Maternal and newborn health disparities: Tanzania [internet]; 2015. Available from: https:\/\/data.unicef.org\/wp-content\/uploads\/country_profiles\/United%20Republic%20of%20Tanzania\/Maternal%20and%20newborn%20health%20country%20profiles\/country%20profile_TZA.pdf"},{"issue":"2","key":"3012_CR9","doi-asserted-by":"publisher","first-page":"72","DOI":"10.2307\/30032460","volume":"10","author":"HL Kidanto","year":"2006","unstructured":"Kidanto HL, Massawe SN, Nystrom L, Lindmark G. Analysis of perinatal mortality at a teaching hospital in Dar Es Salaam, Tanzania, 1999-2003. Afr J Reprod Health. 2006;10(2):72\u201380.","journal-title":"Afr J Reprod Health"},{"key":"3012_CR10","doi-asserted-by":"publisher","first-page":"116","DOI":"10.1186\/1471-2431-12-116","volume":"12","author":"BT Mmbaga","year":"2012","unstructured":"Mmbaga BT, Lie RT, Olomi R, Mahande MJ, Kvale G, Daltveit AK. Cause-specific neonatal mortality in a neonatal care unit in northern Tanzania: a registry based cohort study. BMC Pediatr. 2012;12:116 ((Mmbaga, Olomi, Mahande) Kilimanjaro Christian Medical Centre, Kilimanjaro Christian Medical College, P.O. Box 3010, Moshi, Tanzania).","journal-title":"BMC Pediatr"},{"issue":"2","key":"3012_CR11","doi-asserted-by":"publisher","first-page":"38","DOI":"10.1097\/01.NURSE.0000410304.26165.33","volume":"42","author":"KD Duncan","year":"2012","unstructured":"Duncan KD, McMullan C, Mills BM. Early warning systems: the next level of rapid response. Nursing (Lond). 2012;42(2):38\u201344.","journal-title":"Nursing (Lond)"},{"issue":"10","key":"3012_CR12","doi-asserted-by":"publisher","DOI":"10.1136\/bmjopen-2020-039061","volume":"10","author":"EJ Mitchell","year":"2020","unstructured":"Mitchell EJ, Qureshi ZP, Were F, Daniels J, Gwako G, Osoti A, et al. Feasibility of using an early warning score for preterm or low birthweight infants in a low-resource setting: results of a mixed-methods study at a national referral hospital in Kenya. BMJ Open. 2020;10(10):e039061.","journal-title":"BMJ Open"},{"issue":"1","key":"3012_CR13","doi-asserted-by":"publisher","first-page":"112","DOI":"10.1177\/1367493516689166","volume":"21","author":"N Mortensen","year":"2017","unstructured":"Mortensen N, Augustsson JH, Ulriksen J, Hinna UT, Schm\u00f6lzer GM, Solev\u00e5g AL. Early warning- and track and trigger systems for newborn infants: a review. J Child Health Care. 2017 Mar;21(1):112\u201320.","journal-title":"J Child Health Care"},{"key":"3012_CR14","volume-title":"National Guideline for Neonatal Care and Establishment of Neonatal Care Unit","author":"Ministry of Health, Community Development, Gender, Elderly and Children","year":"2019","unstructured":"Ministry of Health, Community Development, Gender, Elderly and Children. National Guideline for Neonatal Care and Establishment of Neonatal Care Unit; 2019."},{"key":"3012_CR15","volume-title":"WHO recommendations on postnatal care of the mother and newborn [internet]","author":"World Health Organization, Department of Maternal Newborn Child and Adolescent Health","year":"2013","unstructured":"World Health Organization, Department of Maternal Newborn Child and Adolescent Health. WHO recommendations on postnatal care of the mother and newborn [internet]; 2013. [cited 2021 Jun 11]. Available from: http:\/\/www.ncbi.nlm.nih.gov\/books\/NBK190086\/"},{"key":"3012_CR16","doi-asserted-by":"publisher","first-page":"227","DOI":"10.1016\/B978-0-12-382184-3.00012-X","volume-title":"Human reproductive biology","author":"RE Jones","year":"2014","unstructured":"Jones RE, Lopez KH. The neonate and the new parents. In: Human reproductive biology: Elsevier; 2014. p. 227\u201341. [cited 2021 Jun 7]. Available from: https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/B978012382184300012X."},{"issue":"1","key":"3012_CR17","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1038\/s41746-020-0221-y","volume":"3","author":"RT Sutton","year":"2020","unstructured":"Sutton RT, Pincock D, Baumgart DC, Sadowski DC, Fedorak RN, Kroeker KI. An overview of clinical decision support systems: benefits, risks, and strategies for success. Npj Digit Med. 2020;3(1):17.","journal-title":"Npj Digit Med"},{"issue":"6","key":"3012_CR18","doi-asserted-by":"publisher","first-page":"e0251876","DOI":"10.1371\/journal.pone.0251876","volume":"16","author":"A Malhotra","year":"2021","unstructured":"Malhotra A, Rachet B, Bonaventure A, Pereira SP, Woods LM. Can we screen for pancreatic cancer? Identifying a sub-population of patients at high risk of subsequent diagnosis using machine learning techniques applied to primary care data. Real FX, editor. PLoS One. 2021;16(6):e0251876.","journal-title":"PLoS One"},{"key":"3012_CR19","doi-asserted-by":"publisher","first-page":"131","DOI":"10.12688\/wellcomeopenres.14847.1","volume":"3","author":"M Oonsivilai","year":"2018","unstructured":"Oonsivilai M, Mo Y, Luangasanatip N, Lubell Y, Miliya T, Tan P, et al. Using machine learning to guide targeted and locally-tailored empiric antibiotic prescribing in a children\u2019s hospital in Cambodia. Wellcome Open Res. 2018;3:131.","journal-title":"Wellcome Open Res"},{"issue":"5","key":"3012_CR20","doi-asserted-by":"publisher","first-page":"584","DOI":"10.1016\/j.cmi.2019.09.009","volume":"26","author":"N Peiffer-Smadja","year":"2020","unstructured":"Peiffer-Smadja N, Rawson TM, Ahmad R, Buchard A, Georgiou P, Lescure F-X, et al. Machine learning for clinical decision support in infectious diseases: a narrative review of current applications. Clin Microbiol Infect. 2020;26(5):584\u201395.","journal-title":"Clin Microbiol Infect"},{"issue":"12","key":"3012_CR21","doi-asserted-by":"publisher","first-page":"1457","DOI":"10.1017\/ice.2018.265","volume":"39","author":"JA Roth","year":"2018","unstructured":"Roth JA, Battegay M, Juchler F, Vogt JE, Widmer AF. Introduction to machine learning in digital healthcare epidemiology. Infect Control Hosp Epidemiol. 2018 Dec;39(12):1457\u201362.","journal-title":"Infect Control Hosp Epidemiol"},{"key":"3012_CR22","doi-asserted-by":"crossref","unstructured":"The WHO young infants study group. Methodology for a multicenter study of serious infections in young infants in developing countries. Pediatr Infect Dis J. 1999;18(10) Available from: https:\/\/journals.lww.com\/pidj\/Fulltext\/1999\/10001\/Methodology_for_a_multicenter_study_of_serious.3.aspx.","DOI":"10.1097\/00006454-199910001-00003"},{"key":"3012_CR23","volume-title":"Preterm birth","author":"World Health Organisation","year":"2018","unstructured":"World Health Organisation. Preterm birth; 2018. [cited 2021 Jan 25]. Available from: https:\/\/www.who.int\/news-room\/fact-sheets\/detail\/preterm-birth"},{"issue":"5","key":"3012_CR24","doi-asserted-by":"publisher","first-page":"273","DOI":"10.1093\/pch\/5.5.273","volume":"5","author":"D Leduc","year":"2000","unstructured":"Leduc D, Woods S. Community Paediatrics committee. Temperature measurement in paediatrics. Paediatr Child Health. 2000;5(5):273\u20136.","journal-title":"Paediatr Child Health"},{"key":"3012_CR25","volume-title":"Recursive partitioning and regression tree [internet]","author":"T Therneau","year":"2019","unstructured":"Therneau T, Atkinson B. Recursive partitioning and regression tree [internet]; 2019. Available from: https:\/\/CRAN.R-project.org\/package=rpart"},{"key":"3012_CR26","volume-title":"Package \u2018ROCR\u2019","author":"T Sing","year":"2020","unstructured":"Sing T. Package \u2018ROCR\u2019; 2020. (Visualizing the Performance of Scoring Classifiers). Available from: https:\/\/cran.r-project.org\/web\/packages\/ROCR\/ROCR.pdf"},{"key":"3012_CR27","unstructured":"World Health Organization. Kangaroo mother care: a practical guide. Geneva; 2003. p. 48. Available from: https:\/\/www.who.int\/publications\/i\/item\/9241590351"},{"issue":"1","key":"3012_CR28","doi-asserted-by":"publisher","first-page":"189","DOI":"10.1186\/s12884-018-1831-0","volume":"18","author":"MO Arunda","year":"2018","unstructured":"Arunda MO, Agardh A, Asamoah BO. Survival of low birthweight neonates in Uganda: analysis of progress between 1995 and 2011. BMC Pregnancy Childbirth. 2018;18(1):189.","journal-title":"BMC Pregnancy Childbirth"},{"issue":"6","key":"3012_CR29","doi-asserted-by":"publisher","first-page":"401","DOI":"10.1038\/jp.2008.233","volume":"29","author":"V Kumar","year":"2009","unstructured":"Kumar V, Shearer JC, Kumar A, Darmstadt GL. Neonatal hypothermia in low resource settings: a review. J Perinatol. 2009;29(6):401\u201312.","journal-title":"J Perinatol"},{"issue":"3","key":"3012_CR30","doi-asserted-by":"publisher","first-page":"e58924","DOI":"10.1371\/journal.pone.0058924","volume":"8","author":"P Welaga","year":"2013","unstructured":"Welaga P, Moyer CA, Aborigo R, Adongo P, Williams J, Hodgson A, et al. Why are babies dying in the first month after birth? A 7-year study of neonatal mortality in northern Ghana. Moormann AM, editor. PLoS ONE. 2013;8(3):e58924.","journal-title":"PLoS ONE"},{"key":"3012_CR31","first-page":"980","volume-title":"Oxford handbook of tropical medicine","author":"R Davidson","year":"2014","unstructured":"Davidson R, Brent A, Seale A. Oxford handbook of tropical medicine. 4th ed. Oxford, New York: Oxford University Press; 2014. p. 980. Oxford handbooks","edition":"4"},{"key":"3012_CR32","first-page":"1","volume":"101136916","author":"F Cavallin","year":"2020","unstructured":"Cavallin F, Menga A, Brasili L, Maziku D, Azzimonti G, Putoto G, et al. Factors associated with mortality among asphyxiated newborns in a low-resource setting. J Matern-Fetal Neonatal Med Off J Eur Assoc Perinat Med Fed Asia Ocean Perinat Soc Int Soc Perinat Obstet. 2020;101136916:1\u20136.","journal-title":"J Matern-Fetal Neonatal Med Off J Eur Assoc Perinat Med Fed Asia Ocean Perinat Soc Int Soc Perinat Obstet"},{"key":"3012_CR33","first-page":"1","volume-title":"The 2012 international joint conference on neural networks (IJCNN)","author":"A Floares","year":"2012","unstructured":"Floares A, Birlutiu A. Decision tree models for developing molecular classifiers for cancer diagnosis. In: The 2012 international joint conference on neural networks (IJCNN). Brisbane: IEEE; 2012. p. 1\u20137. [cited 2021 Apr 20]. Available from: http:\/\/ieeexplore.ieee.org\/document\/6252781\/."},{"issue":"1","key":"3012_CR34","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1177\/1533034615572638","volume":"15","author":"M Surucu","year":"2016","unstructured":"Surucu M, Shah KK, Mescioglu I, Roeske JC, Small W, Choi M, et al. Decision trees predicting tumor shrinkage for head and neck cancer: implications for adaptive radiotherapy. Technol Cancer Res Treat. 2016;15(1):139\u201345.","journal-title":"Technol Cancer Res Treat"},{"key":"3012_CR35","doi-asserted-by":"publisher","first-page":"104089","DOI":"10.1016\/j.compbiomed.2020.104089","volume":"128","author":"MM Ghiasi","year":"2021","unstructured":"Ghiasi MM, Zendehboudi S. Application of decision tree-based ensemble learning in the classification of breast cancer. Comput Biol Med. 2021;128:104089.","journal-title":"Comput Biol Med"},{"issue":"4 Supplement","key":"3012_CR36","first-page":"249","volume":"99","author":"LA Winkler","year":"2018","unstructured":"Winkler LA, Noon S, Babwanga T. A multi-year project implementing kangaroo mother care in rural Tanzania. Am J Trop Med Hyg. 2018;99(4 Supplement):249.","journal-title":"Am J Trop Med Hyg"}],"container-title":["BMC Pediatrics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12887-021-03012-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s12887-021-03012-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12887-021-03012-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,16]],"date-time":"2023-01-16T20:38:37Z","timestamp":1673901517000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmcpediatr.biomedcentral.com\/articles\/10.1186\/s12887-021-03012-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12]]},"references-count":36,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2021,12]]}},"alternative-id":["3012"],"URL":"https:\/\/doi.org\/10.1186\/s12887-021-03012-4","relation":{},"ISSN":["1471-2431"],"issn-type":[{"value":"1471-2431","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,12]]},"assertion":[{"value":"7 July 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 November 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 December 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Ethical approval for the study was provided by the joint CUHAS\/BMC ethical committee with certificate CREC\/318\/2018 and NatHREC with certificate number NIMRlHQ\/R.8a\/V01.IX\/3017. All methods were performed in accordance with the relevant guidelines and regulations. Written informed consent was obtained from the neonates\u2019 mothers\/guardians.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"None.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"537"}}