Advertisement

Supportive Care in Cancer

, Volume 19, Issue 10, pp 1625–1635 | Cite as

Prediction of outcome in cancer patients with febrile neutropenia: a prospective validation of the Multinational Association for Supportive Care in Cancer risk index in a Chinese population and comparison with the Talcott model and artificial neural network

  • Edwin Pun Hui
  • Linda K. S. Leung
  • Terence C. W. Poon
  • Frankie Mo
  • Vicky T. C. Chan
  • Ada T. W. Ma
  • Annette Poon
  • Eugenie K. Hui
  • So-shan Mak
  • Maria Lai
  • Kenny I. K. Lei
  • Brigette B. Y. Ma
  • Tony S. K. Mok
  • Winnie Yeo
  • Benny C. Y. Zee
  • Anthony T. C. Chan
Original Article

Abstract

Purpose

We aimed to validate the Multinational Association for Supportive Care in Cancer (MASCC) risk index, and compare it with the Talcott model and artificial neural network (ANN) in predicting the outcome of febrile neutropenia in a Chinese population.

Methods

We prospectively enrolled adult cancer patients who developed febrile neutropenia after chemotherapy and risk classified them according to MASCC score and Talcott model. ANN models were constructed and temporally validated in prospectively collected cohorts.

Results

From October 2005 to February 2008, 227 consecutive patients were enrolled. Serious medical complications occurred in 22% of patients and 4% died. The positive predictive value of low risk prediction was 86% (95% CI = 81–90%) for MASCC score ≥ 21, 84% (79–89%) for Talcott model, and 85% (78–93%) for the best ANN model. The sensitivity, specificity, negative predictive value, and misclassification rate were 81%, 60%, 52%, and 24%, respectively, for MASCC score ≥ 21; and 50%, 72%, 33%, and 44%, respectively, for Talcott model; and 84%, 60%, 58%, and 22%, respectively, for ANN model. The area under the receiver-operating characteristic curve was 0.808 (95% CI = 0.717–0.899) for MASCC, 0.573 (0.455–0.691) for Talcott, and 0.737 (0.633–0.841) for ANN model. In the low risk group identified by MASCC score ≥ 21 (70% of all patients), 12.5% developed complications and 1.9% died, compared with 43.3%, and 9.0%, respectively, in the high risk group (p < 0.0001).

Conclusions

The MASCC risk index is prospectively validated in a Chinese population. It demonstrates a better overall performance than the Talcott model and is equivalent to ANN model.

Keywords

Febrile neutropenia Risk prediction model Artificial neural networks Discriminatory accuracy Receiver-operating characteristics curve 

Notes

Acknowledgment

This study was funded by the Health and Health Services Research Fund (HHSRF project No: 03040081), Food and Health Bureau, Hong Kong SAR Government. We thank the research staff at the Comprehensive Cancer Trials Unit (Jane Koh, Karin Tse, and Angel Lee) and all the patients included in this study for their contributions.

Conflict of interest

None.

References

  1. 1.
    Anaissie EJ, Vadhan-Raj S (1995) Is it time to redefine the management of febrile neutropenia in cancer patients? Am J Med 98:221–223PubMedCrossRefGoogle Scholar
  2. 2.
    Baskaran ND, Gan GG, Adeeba K (2008) Applying the Multinational Association for Supportive Care in Cancer risk scoring in predicting outcome of febrile neutropenia patients in a cohort of patients. Ann Hematol 87:563–569PubMedCrossRefGoogle Scholar
  3. 3.
    Baxt WG (1995) Application of artificial neural networks to clinical medicine. Lancet 346:1135–1138PubMedCrossRefGoogle Scholar
  4. 4.
    Bottaci L, Drew PJ, Hartley JE, Hadfield MB, Farouk R, Lee PW, Macintyre IM, Duthie GS, Monson JR (1997) Artificial neural networks applied to outcome prediction for colorectal cancer patients in separate institutions. Lancet 350:469–472PubMedCrossRefGoogle Scholar
  5. 5.
    Bryce TJ, Dewhirst MW, Floyd CE Jr, Hars V, Brizel DM (1998) Artificial neural network model of survival in patients treated with irradiation with and without concurrent chemotherapy for advanced carcinoma of the head and neck. Int J Radiat Oncol Biol Phys 41:339–345PubMedCrossRefGoogle Scholar
  6. 6.
    Cherif H, Johansson E, Bjorkholm M, Kalin M (2006) The feasibility of early hospital discharge with oral antimicrobial therapy in low risk patients with febrile neutropenia following chemotherapy for hematologic malignancies. Haematologica 91:215–222PubMedGoogle Scholar
  7. 7.
    Cheung M, Online calculator: calculate risk in febrile neutropenia (MASCC). QxMD Hematology http://www.qxmd.com/hematology/MASCC-Febrile-Neutropenia-Risk.php
  8. 8.
    Cross SS, Harrison RF, Kennedy RL (1995) Introduction to neural networks. Lancet 346:1075–1079PubMedCrossRefGoogle Scholar
  9. 9.
    Das A, Ben-Menachem T, Cooper GS, Chak A, Sivak MV Jr, Gonet JA, Wong RC (2003) Prediction of outcome in acute lower-gastrointestinal haemorrhage based on an artificial neural network: internal and external validation of a predictive model. Lancet 362:1261–1266PubMedCrossRefGoogle Scholar
  10. 10.
    Das A, Ben-Menachem T, Farooq FT, Cooper GS, Chak A, Sivak MV Jr, Wong RC (2008) Artificial neural network as a predictive instrument in patients with acute nonvariceal upper gastrointestinal hemorrhage. Gastroenterology 134:65–74PubMedCrossRefGoogle Scholar
  11. 11.
    de Bont ES, Vellenga E, Swaanenburg JC, Fidler V, Visser-van Brummen PJ, Kamps WA (1999) Plasma IL-8 and IL-6 levels can be used to define a group with low risk of septicaemia among cancer patients with fever and neutropenia. Br J Haematol 107:375–380PubMedCrossRefGoogle Scholar
  12. 12.
    de Souza Viana L, Serufo JC, da Costa Rocha MO, Costa RN, Duarte RC (2008) Performance of a modified MASCC index score for identifying low-risk febrile neutropenic cancer patients. Support Care Cancer 16:841–846PubMedCrossRefGoogle Scholar
  13. 13.
    Elting LS, Lu C, Escalante CP, Giordano SH, Trent JC, Cooksley C, Avritscher EB, Shih YC, Ensor J, Bekele BN, Gralla RJ, Talcott JA, Rolston K (2008) Outcomes and cost of outpatient or inpatient management of 712 patients with febrile neutropenia. J Clin Oncol 26:606–611PubMedCrossRefGoogle Scholar
  14. 14.
    Finberg RW, Talcott JA (1999) Fever and neutropenia—how to use a new treatment strategy. N Engl J Med 341:362–363PubMedCrossRefGoogle Scholar
  15. 15.
    Giamarellos-Bourboulis EJ, Grecka P, Poulakou G, Anargyrou K, Katsilambros N, Giamarellou H (2001) Assessment of procalcitonin as a diagnostic marker of underlying infection in patients with febrile neutropenia. Clin Infect Dis 32:1718–1725PubMedCrossRefGoogle Scholar
  16. 16.
    Jimeno A, Garcia-Velasco A, del Val O, Gonzalez-Billalabeitia E, Hernando S, Hernandez R, Sanchez-Munoz A, Lopez-Martin A, Duran I, Robles L, Cortes-Funes H, Paz-Ares L (2004) Assessment of procalcitonin as a diagnostic and prognostic marker in patients with solid tumors and febrile neutropenia. Cancer 100:2462–2469PubMedCrossRefGoogle Scholar
  17. 17.
    Kern WV (2006) Risk assessment and treatment of low-risk patients with febrile neutropenia. Clin Infect Dis 42:533–540PubMedCrossRefGoogle Scholar
  18. 18.
    Klastersky J, Paesmans M, Georgala A, Muanza F, Plehiers B, Dubreucq L, Lalami Y, Aoun M, Barette M (2006) Outpatient oral antibiotics for febrile neutropenic cancer patients using a score predictive for complications. J Clin Oncol 24:4129–4134PubMedCrossRefGoogle Scholar
  19. 19.
    Klastersky J, Paesmans M, Rubenstein EB, Boyer M, Elting L, Feld R, Gallagher J, Herrstedt J, Rapoport B, Rolston K, Talcott J (2000) The Multinational Association for Supportive Care in Cancer risk index: a multinational scoring system for identifying low-risk febrile neutropenic cancer patients. J Clin Oncol 18:3038–3051PubMedGoogle Scholar
  20. 20.
    Ma B, Yeo W, Hui P, Ho WM, Johnson PJ (2002) Acute toxicity of adjuvant doxorubicin and cyclophosphamide for early breast cancer—a retrospective review of Chinese patients and comparison with an historic Western series. Radiother Oncol 62:185–189PubMedCrossRefGoogle Scholar
  21. 21.
    Oude Nijhuis CS, Daenen SM, Vellenga E, van der Graaf WT, Gietema JA, Groen HJ, Kamps WA, de Bont ES (2002) Fever and neutropenia in cancer patients: the diagnostic role of cytokines in risk assessment strategies. Crit Rev Oncol Hematol 44:163–174PubMedCrossRefGoogle Scholar
  22. 22.
    Paesmans M, Rapoport B, Maertens J, Slabber C, Ferrant A, Wingard J, Aoun M, Dubreucq L, Plehiers B, Klastersky J (2003) Multicentric prospective validation of the mascc risk-index score for identification of febrile neutropenic cancer patients at low-risk for serious medical complications. Proc Am Soc Clin Oncol 22:556, abstr 2235Google Scholar
  23. 23.
    Poon TC, Chan AT, Zee B, Ho SK, Mok TS, Leung TW, Johnson PJ (2001) Application of classification tree and neural network algorithms to the identification of serological liver marker profiles for the diagnosis of hepatocellular carcinoma. Oncology 61:275–283PubMedCrossRefGoogle Scholar
  24. 24.
    Poon TC, Yip TT, Chan AT, Yip C, Yip V, Mok TS, Lee CC, Leung TW, Ho SK, Johnson PJ (2003) Comprehensive proteomic profiling identifies serum proteomic signatures for detection of hepatocellular carcinoma and its subtypes. Clin Chem 49:752–760PubMedCrossRefGoogle Scholar
  25. 25.
    Ramilo O, Allman W, Chung W, Mejias A, Ardura M, Glaser C, Wittkowski KM, Piqueras B, Banchereau J, Palucka AK, Chaussabel D (2007) Gene expression patterns in blood leukocytes discriminate patients with acute infections. Blood 109:2066–2077PubMedCrossRefGoogle Scholar
  26. 26.
    Sargent DJ (2001) Comparison of artificial neural networks with other statistical approaches: results from medical data sets. Cancer 91:1636–1642PubMedCrossRefGoogle Scholar
  27. 27.
    Schwarzer G, Vach W, Schumacher M (2000) On the misuses of artificial neural networks for prognostic and diagnostic classification in oncology. Stat Med 19:541–561PubMedCrossRefGoogle Scholar
  28. 28.
    Talcott JA, Finberg R, Mayer RJ, Goldman L (1988) The medical course of cancer patients with fever and neutropenia. Clinical identification of a low-risk subgroup at presentation. Arch Intern Med 148:2561–2568PubMedCrossRefGoogle Scholar
  29. 29.
    Talcott JA, Siegel RD, Finberg R, Goldman L (1992) Risk assessment in cancer patients with fever and neutropenia: a prospective, two-center validation of a prediction rule. J Clin Oncol 10:316–322PubMedGoogle Scholar
  30. 30.
    Talcott JA, Whalen A, Clark J, Rieker PP, Finberg R (1994) Home antibiotic therapy for low-risk cancer patients with fever and neutropenia: a pilot study of 30 patients based on a validated prediction rule. J Clin Oncol 12:107–114PubMedGoogle Scholar
  31. 31.
    Uys A, Rapoport BL, Anderson R (2004) Febrile neutropenia: a prospective study to validate the Multinational Association of Supportive Care of Cancer (MASCC) risk-index score. Support Care Cancer 12:555–560PubMedCrossRefGoogle Scholar
  32. 32.
    Uys A, Rapoport BL, Fickl H, Meyer PW, Anderson R (2007) Prediction of outcome in cancer patients with febrile neutropenia: comparison of the Multinational Association of Supportive Care in Cancer risk-index score with procalcitonin, C-reactive protein, serum amyloid A, and interleukins-1beta, -6, -8 and -10. Eur J Cancer Care (Engl) 16:475–483CrossRefGoogle Scholar
  33. 33.
    Uzun O, Anaissie EJ (1999) Outpatient therapy for febrile neutropenia: who, when, and how? J Antimicrob Chemother 43:317–320PubMedCrossRefGoogle Scholar
  34. 34.
    Wyatt J (1995) Nervous about artificial neural networks? Lancet 346:1175–1177PubMedCrossRefGoogle Scholar

Copyright information

© Springer-Verlag 2010

Authors and Affiliations

  • Edwin Pun Hui
    • 1
    • 2
  • Linda K. S. Leung
    • 1
  • Terence C. W. Poon
    • 2
    • 3
  • Frankie Mo
    • 1
  • Vicky T. C. Chan
    • 1
  • Ada T. W. Ma
    • 1
  • Annette Poon
    • 1
  • Eugenie K. Hui
    • 1
  • So-shan Mak
    • 1
  • Maria Lai
    • 4
  • Kenny I. K. Lei
    • 1
    • 2
  • Brigette B. Y. Ma
    • 1
    • 2
  • Tony S. K. Mok
    • 1
    • 2
  • Winnie Yeo
    • 1
    • 2
  • Benny C. Y. Zee
    • 2
    • 4
  • Anthony T. C. Chan
    • 1
    • 2
  1. 1.Department of Clinical Oncology, Prince of Wales HospitalThe Chinese University of Hong KongHong KongChina
  2. 2.State Key Laboratory in Oncology in South China, Sir YK Pao Center for Cancer, Hong Kong Cancer InstituteThe Chinese University of Hong KongHong KongChina
  3. 3.Department of Medicine and TherapeuticsThe Chinese University of Hong KongHong KongChina
  4. 4.Center for Clinical Trials, School of Public Health and Primary CareThe Chinese University of Hong KongHong KongChina

Personalised recommendations