A boosting inspired personalized threshold method for sepsis screening

References

• R.C. Bone, R.A. Balk, F.B. Cerra, R.P. Dellinger, A.M. Fein, W.A. Knaus, R.M. Schein, and W.J. Sibbald, Definitions for sepsis and organ failure and guidelines for the use of innovative therapies in sepsis, Chest 101 (1992), pp. 1644–1655. doi: 10.1378/chest.101.6.1644
   PubMed Web of Science ®Google Scholar
• M. Brabrand, U. Havshøj, and C.A. Graham, Validation of the qsofa score for identification of septic patients: A retrospective study, Eur. J. Intern. Med. 36 (2016), pp. e35–e36. doi: 10.1016/j.ejim.2016.09.004
   PubMed Web of Science ®Google Scholar
• A. Castellanos-Ortega, B. Suberviola, L.A. García-Astudillo, F. Ortiz, J. Llorca, and M. Delgado-Rodríguez, Late compliance with the sepsis resuscitation bundle: Impact on mortality, Shock 36 (2011), pp. 542–547. doi: 10.1097/SHK.0b013e3182360f7c
   PubMed Web of Science ®Google Scholar
• M. Collins, R.E. Schapire, and Y. Singer, Logistic regression, adaboost and bregman distances, Mach. Learn. 48 (2002), pp. 253–285. doi: 10.1023/A:1013912006537
   Web of Science ®Google Scholar
• M. Dorsett, M. Kroll, C.S. Smith, P. Asaro, S.Y. Liang, and H.P. Moy, qsofa has poor sensitivity for prehospital identification of severe sepsis and septic shock, Prehosp. Emerg. Care. 21 (2017), pp. 489–497. doi: 10.1080/10903127.2016.1274348
   PubMed Web of Science ®Google Scholar
• S.M. Fernando, A. Tran, M. Taljaard, W. Cheng, B. Rochwerg, A.J. Seely, and J.J. Perry, Prognostic accuracy of the quick sequential organ failure assessment for mortality in patients with suspected infection, Ann Intern Med 168 (2018), pp. 266–75. doi: 10.7326/M17-2820
   PubMed Web of Science ®Google Scholar
• Y. Fong, J. Fortner, R.L. Sun, M.F. Brennan, and L.H. Bumgart, Clinical score for predicting recurrence after hepatic resection for metastatic colorectal cancer, Ann. Surg. 230 (1999), p. 309. doi: 10.1097/00000658-199909000-00004
   PubMed Web of Science ®Google Scholar
• Y. Freund and R.E. Schapire, A decision-theoretic generalization of on-line learning and an application to boosting, J. Comput. Syst. Sci. 55 (1997), pp. 119–139. doi: 10.1006/jcss.1997.1504
   Web of Science ®Google Scholar
• J. Friedman, T. Hastie, and R. Tibshirani, The elements of statistical learning, Springer Series in Statistics New York, Vol. 1, 2001.
   Google Scholar
• D.F. Gaieski, J.M. Edwards, M.J. Kallan, and B.G. Carr, Benchmarking the incidence and mortality of severe sepsis in the united states, Crit. Care Med. 41 (2013), pp. 1167–1174. doi: 10.1097/CCM.0b013e31827c09f8
   PubMed Web of Science ®Google Scholar
• E.J. Giamarellos-Bourboulis, T. Tsaganos, I. Tsangaris, M. Lada, C. Routsi, D. Sinapidis, M. Koupetori, M. Bristianou, G. Adamis, K. Mandragos, and G.N. Dalekos, Validation of the new sepsis-3 definitions: Proposal for improvement in early risk identification, Clin. Microbiol. Infect. 23 (2017), pp. 104–109. doi: 10.1016/j.cmi.2016.11.003
   PubMed Web of Science ®Google Scholar
• H.M. Giannini, C. Chivers, M. Draugelis, A. Hanish, B. Fuchs, P. Donnelly, M. Lynch, L. Meadows, S.J. Parker, W.D. Schweickert, and M.E. Mikkelsen, Development and Implementation of a Machine-Learning Algorithm for Early Identification of Sepsis in a Multi-Hospital Academic Healthcare System, in D15. CriticalL Care: Do We Have a Crystal Ball? Predicting Clinical Deterioration and Outcome in Critically Ill Patients, American Thoracic Society, 2017, pp. A7015–A7015.
   Google Scholar
• F. Girosi, M. Jones, and T. Poggio, Regularization theory and neural networks architectures, Neural. Comput. 7 (1995), pp. 219–269. doi: 10.1162/neco.1995.7.2.219
   Web of Science ®Google Scholar
• E. Gyang, L. Shieh, L. Forsey, and P. Maggio, A nurse-driven screening tool for the early identification of sepsis in an intermediate care unit setting, J. Hosp. Med. 10 (2015), pp. 97–103. doi: 10.1002/jhm.2291
   PubMed Web of Science ®Google Scholar
• T. Hastie, S. Rosset, J. Zhu, and H. Zou, Multi-class adaboost, Stat. Interface. 2 (2009), pp. 349–360. doi: 10.4310/SII.2009.v2.n3.a8
   Web of Science ®Google Scholar
• K.E. Henry, D.N. Hager, P.J. Pronovost, and S. Saria, A targeted real-time early warning score (trewscore) for septic shock, Sci. Transl. Med. 7 (2015), p. 299ra122. doi: 10.1126/scitranslmed.aab3719
   PubMed Web of Science ®Google Scholar
• F. Jaimes, J. Farbiarz, D. Alvarez, and C. Martínez, Comparison between logistic regression and neural networks to predict death in patients with suspected sepsis in the emergency room, Crit Care 9 (2005), p. R150. doi: 10.1186/cc3054
   PubMed Web of Science ®Google Scholar
• A.E. Johnson, T.J. Pollard, L. Shen, H.L. Li-wei, M. Feng, M. Ghassemi, B. Moody, P. Szolovits, L.A. Celi, and R.G. Mark, Mimic-iii, a freely accessible critical care database, Sci. Data. 3 (2016), p. 160035. doi: 10.1038/sdata.2016.35
   PubMed Web of Science ®Google Scholar
• D.B. Knox, M.J. Lanspa, K.G. Kuttler, S.C. Brewer, and S.M. Brown, Phenotypic clusters within sepsis-associated multiple organ dysfunction syndrome, Intensive Care. Med. 41 (2015), pp. 814–822. doi: 10.1007/s00134-015-3764-7
   PubMed Web of Science ®Google Scholar
• D. Kojic, B.H. Siegler, F. Uhle, C. Lichtenstern, P.P. Nawroth, M.A. Weigand, S. Hofer, and T. Brenner, Are there new approaches for diagnosis, therapy guidance and outcome prediction of sepsis? World J. Exp. Med. 5 (2015), p. 50. doi: 10.5493/wjem.v5.i2.50
   PubMedGoogle Scholar
• E.D. Krebs, T.E. Hassinger, C.A. Guidry, P.S. Berry, N.R. Elwood, and R.G. Sawyer, Non-utility of sepsis scores for identifying infection in surgical intensive care unit patients, Amer. J. Surgery (2018).
   Google Scholar
• C. Kwong, A.Y. Ling, M.H. Crawford, S.X. Zhao, and N.H. Shah, A clinical score for predicting atrial fibrillation in patients with cryptogenic stroke or transient ischemic attack, Cardiology 138 (2017), pp. 133–140. doi: 10.1159/000476030
   PubMed Web of Science ®Google Scholar
• M.M. Levy, M.P. Fink, J.C. Marshall, E. Abraham, D. Angus, D. Cook, J. Cohen, S.M. Opal, J.L. Vincent, and G. Ramsay, 2001 sccm/esicm/accp/ats/sis international sepsis definitions conference, Intensive Care. Med. 29 (2003), pp. 530–538. doi: 10.1007/s00134-003-1662-x
   PubMedGoogle Scholar
• X. Liu, Classification accuracy and cut point selection, Stat. Med. 31 (2012), pp. 2676–2686. doi: 10.1002/sim.4509
   PubMed Web of Science ®Google Scholar
• S. Mani, A. Ozdas, C. Aliferis, H.A. Varol, Q. Chen, R. Carnevale, Y. Chen, J. Romano-Keeler, H. Nian, and J.H. Weitkamp, Medical decision support using machine learning for early detection of late-onset neonatal sepsis, J. Am. Med. Inform. Assoc. 21 (2014), pp. 326–336. doi: 10.1136/amiajnl-2013-001854
   PubMed Web of Science ®Google Scholar
• R. Miller and D. Siegmund, Maximally selected chi square statistics, Biometrics, 38 (1982), pp. 1011–1016. doi: 10.2307/2529881
   Web of Science ®Google Scholar
• L.J. Moore, S.L. Jones, L.A. Kreiner, B. McKinley, J.F. Sucher, S.R. Todd, K.L. Turner, A. Valdivia, and F.A. Moore, Validation of a screening tool for the early identification of sepsis, J. Trauma Acute Care Surg. 66 (2009), pp. 1539–1547. doi: 10.1097/TA.0b013e3181a3ac4b
   Google Scholar
• S. Nemati, A. Holder, F. Razmi, M.D. Stanley, G.D. Clifford, and T.G. Buchman, An interpretable machine learning model for accurate prediction of sepsis in the icu, Crit. Care Med. 46 (2018), pp. 547–553. doi: 10.1097/CCM.0000000000002936
   PubMed Web of Science ®Google Scholar
• J. Perkins Neil and F. Schisterman Enrique, The inconsistency of optimal cut-points using two roc based criteria, Am. J. Epidemiol. 163 (2006), pp. 670–675. doi: 10.1093/aje/kwj063
   PubMed Web of Science ®Google Scholar
• C.C. Polito, A. Isakov, A.H. Yancey, D.K. Wilson, B.A. Anderson, I. Bloom, G.S. Martin, and J.E. Sevransky, Prehospital recognition of severe sepsis: development and validation of a novel ems screening tool, Amer. J. Emer. Med. 33 (2015), pp. 1119–1125. doi: 10.1016/j.ajem.2015.04.024
   PubMed Web of Science ®Google Scholar
• T. Pollard and A. Johnson III, The mimic-iii clinical database (2017).
   Google Scholar
• L. Prechelt, Early stopping-but when? in Neural Networks: Tricks of the trade, Springer, 1998, pp. 55–69.
   Google Scholar
• E.P. Raith, A.A. Udy, M. Bailey, S. McGloughlin, C. MacIsaac, R. Bellomo, and D.V. Pilcher, Prognostic accuracy of the sofa score, sirs criteria, and qsofa score for in-hospital mortality among adults with suspected infection admitted to the intensive care unit, JAMA 317 (2017), pp. 290–300. doi: 10.1001/jama.2016.20328
   PubMed Web of Science ®Google Scholar
• G. Raskutti, M.J. Wainwright, and B. Yu, Early stopping and non-parametric regression: An optimal data-dependent stopping rule, J. Machine Learn. Res. 15 (2014), pp. 335–366.
   Web of Science ®Google Scholar
• E. Rezende, J.M. Silva Junior, A.M. Isola, E.V. Campos, C.P. Amendola, and S.L. Almeida, Epidemiology of severe sepsis in the emergency department and difficulties in the initial assistance, Clinics 63 (2008), pp. 457–464. doi: 10.1590/S1807-59322008000400008
   PubMed Web of Science ®Google Scholar
• C.W. Seymour, V.X. Liu, T.J. Iwashyna, F.M. Brunkhorst, T.D. Rea, A. Scherag, G. Rubenfeld, J.M. Kahn, M. Shankar-Hari, M. Singer, and C.S. Deutschman, Assessment of clinical criteria for sepsis: For the third international consensus definitions for sepsis and septic shock (sepsis-3), JAMA 315 (2016), pp. 762–774. doi: 10.1001/jama.2016.0288
   PubMed Web of Science ®Google Scholar
• D.W. Shimabukuro, C.W. Barton, M.D. Feldman, S.J. Mataraso, and R. Das, Effect of a machine learning-based severe sepsis prediction algorithm on patient survival and hospital length of stay: A randomised clinical trial, BMJ. Open Respir. Res. 4 (2017), p. e000234. doi: 10.1136/bmjresp-2017-000234
   PubMed Web of Science ®Google Scholar
• A.F. Shorr, S.T. Micek, W.L. Jackson, and M.H. Kollef, Economic implications of an evidence-based sepsis protocol: Can we improve outcomes and lower costs? Crit. Care Med. 35 (2007), pp. 1257–1262. doi: 10.1097/01.CCM.0000261886.65063.CC
   PubMed Web of Science ®Google Scholar
• M. Singer, C.S. Deutschman, C.W. Seymour, M. Shankar-Hari, D. Annane, M. Bauer, R. Bellomo, G.R. Bernard, J.D. Chiche, C.M. Coopersmith, and R.S. Hotchkiss, The third international consensus definitions for sepsis and septic shock (sepsis-3), JAMA 315 (2016), pp. 801–810. doi: 10.1001/jama.2016.0287
   PubMed Web of Science ®Google Scholar
• M. Singer, and M. Shankar-Hari, qsofa, cue confusion, Ann. Intern. Med. 168 (2018), pp. 293–295. doi: 10.7326/M17-3415
   PubMed Web of Science ®Google Scholar
• E.R. Swenson, N.D. Bastian, and H.B. Nembhard, Data analytics in health promotion: Health market segmentation and classification of total joint replacement surgery patients, Expert Syst. Appl. 60 (2016), pp. 118–129. doi: 10.1016/j.eswa.2016.05.006
   Web of Science ®Google Scholar
• D. Talmor, D. Greenberg, M.D. Howell, A. Lisbon, V. Novack, and N. Shapiro, The costs and cost-effectiveness of an integrated sepsis treatment protocol, Crit. Care Med. 36 (2008), pp. 1168–1174. doi: 10.1097/CCM.0b013e318168f649
   PubMed Web of Science ®Google Scholar
• S.W. Thiel, J.M. Rosini, W. Shannon, J.A. Doherty, S.T. Micek, and M.H. Kollef, Early prediction of septic shock in hospitalized patients, J. Hosp. Med. 5 (2010), pp. 19–25. doi: 10.1002/jhm.530
   PubMed Web of Science ®Google Scholar
• C. Tucker, Y. Han, H. Black Nembhard, W.C. Lee, M. Lewis, N. Sterling, and X. Huang, A data mining methodology for predicting early stage parkinson's disease using non-invasive, high-dimensional gait sensor data, IIE. Trans. Healthc. Syst. Eng. 5 (2015), pp. 238–254. doi: 10.1080/19488300.2015.1095256
   PubMedGoogle Scholar
• C.S. Tucker, I. Behoora, H.B. Nembhard, M. Lewis, N.W. Sterling, and X. Huang, Machine learning classification of medication adherence in patients with movement disorders using non-wearable sensors, Comput. Biol. Med. 66 (2015), pp. 120–134. doi: 10.1016/j.compbiomed.2015.08.012
   PubMed Web of Science ®Google Scholar
• S. Tusgul, P.N. Carron, B. Yersin, T. Calandra, and F. Dami, Low sensitivity of qsofa, sirs criteria and sepsis definition to identify infected patients at risk of complication in the prehospital setting and at the emergency department triage, Scand. J. Trauma. Resusc. Emerg. Med. 25 (2017), p. 108. doi: 10.1186/s13049-017-0449-y
   PubMed Web of Science ®Google Scholar
• I. Unal, Defining an optimal cut-point value in roc analysis: An alternative approach, Comput. Math. Methods. Med. 2017 (2017), pp. 1–14. doi: 10.1155/2017/3762651
   Web of Science ®Google Scholar
• N. Villegas and L.J. Moore, Sepsis screening: Current evidence and available tools, Surg. Infect. (Larchmt) 19 (2018), pp. 126–130. doi: 10.1089/sur.2017.250
   PubMed Web of Science ®Google Scholar
• J.L. Vincent, S.M. Opal, J.C. Marshall, and K.J. Tracey, Sepsis definitions: Time for change, Lancet 381 (2013), pp. 774. doi: 10.1016/S0140-6736(12)61815-7
   PubMed Web of Science ®Google Scholar
• Y. Yao, L. Rosasco, and A. Caponnetto, On early stopping in gradient descent learning, Constr. Approx. 26 (2007), pp. 289–315. doi: 10.1007/s00365-006-0663-2
   Web of Science ®Google Scholar
• W.J. Youden, Index for rating diagnostic tests, Cancer 3 (1950), pp. 32–35. doi: 10.1002/1097-0142(1950)3:1<32::AID-CNCR2820030106>3.0.CO;2-3
   PubMed Web of Science ®Google Scholar
• T. Zhang, and B. Yu, Boosting with early stopping: Convergence and consistency, Ann. Stat. 33 (2005), pp. 1538–1579. doi: 10.1214/009053605000000255
   Web of Science ®Google Scholar
• X. Zhou, Y. Ye, and G. Tang, Sepsis screening tools in the era of sepsis 3.0, Surg. Infect. (Larchmt) 19 (2018), pp. 553–553. doi: 10.1089/sur.2018.039
   PubMed Web of Science ®Google Scholar