Modeli za procenu rizika obolevanja od melanoma
Sažetak
Uvod/Cilj. Nedostatak efikasne terapije za kasni stadijum melanoma upućuje na značaj preventivnih mera i praćenja (testiranja) populacije pod rizikom. Izdvajanje osoba pod visokim rizikom trebalo bi da omogući ciljano ispitivanje i dalje praćenje osoba koje bi imale najviše koristi od toga. Cilj ove studije bio je da identifikuje najznačajnije faktore rizika od melanoma u našoj populaciji i napravi modele za procenu rizika. Metode. Ova anamenestička studija uključila je 697 ispitanika (341 bolesnik operisan zbog melanoma i 356 ispitanika kontrolne grupe) koji su bili pregledani i intervjuisani o faktorima rizika od melanoma. Nakon univarijantnog poređenja grupa urađena su dva prognostička modela bazirana na statistički značajnim faktorima rizika: model logističke regresije (LR) i alternativno stablo odlučivanja (ADT). Oba modela su procenjena i utvrđena je njihova tačnost u proceni rizika od obolevanja od melanoma. Procena slaganja modela sa podacima za model LR urađena je pomoću Hosmer-Lemeshow testa, dok je za ADT korišćena desetostruka unakrsna procena. Za oba modela data je procena senzitivnosti, specifičnosti, tačnosti i AUC. Rezultati. Logistička regresija ukazuje na značajnost sledećih faktora rizika za melanom: korišćenje solarijuma (OR = 4,018; 95% CI 1,724–9,366 za osobe koje ponekad koriste solarijum), solarno oštećenje kože (OR = 8,274; 95% CI 2,661–25,730 za osobe sa teškim znacima oštećenja kože), boja kose (OR = 3,222; 95% CI 1,984–5,231 za svetlo braon/plavu kosu), ukupan broj mladeža (više od 100 mladeža karakteriše OR = 3.57 95% CI 1,427-8,931), broj displastičnih mladeža (od 1 do 10 displastičnih mladeža OR je bio 2.672, 95% CI 1,572-4,540; za više od 10 displastičnih mladeža OR je bio 6.487; 5% CI 1,993–21,119), fototip kože po Fitzpatricku i kongenitalni mladeži. Crvena kosa, fototip I i veliki kongenitalni mladeži bili su prisutni samo u grupi melanoma te su zato i pokazali visoku značajnost u predviđanju rizika. Procenat ispravno klasifikovanih osoba u modelu LR bio je 74,9%, senzitivnost 71%, specifičnost 78,7% i AUC 0,805. Za stablo odlučivanja procenat ispravno klasifikovanih osoba bio je 71,9%, senzitivnost 71,9%, specifičnost 79,4% i AUC 0,808. Zaključak. Primena različitih modela za procenu rizika obolevanja od melanoma treba lekarima da pruži efikasno, jednostavno i standarizovano sredstvo za testiranje rizika. Predloženi modeli nude brzo otkrivanje osoba pod visokim rizikom, transparentan algoritam odlučivanja i identifikovanja u realnom vremenu, pogodan za kliničku praksu. Dalja poboljšanja moguća su sa porastom baze podataka o obolelima, što će omogućiti ne samo poboljšanje tačnosti predloženih modela već i primenu naprednijih algoritama mašinskog učenja.
Reference
Rigel DS. Trends in dermatology: melanoma incidence. Arch Dermatol 2010; 146(3): 318.
Hollestein LM, Akker SA, Nijsten T, Karim-Kos HE, Coebergh JW, Vries E. Trends of cutaneous melanoma in The Netherlands: increasing incidence rates among all Breslow thickness catego-ries and rising mortality rates since 1989. Ann Oncol 2012; 23(2): 524−30.
Giblin AV, Thomas JM. Incidence, mortality and survival in cu-taneous melanoma. J Plas Reconstr Aesthet Surg 2007; 60(1): 32−40.
Rigel DS, Robinson JK, Ross M, Friedman RJ, Cockerell CJ, Lim HW, et al. Cancer of the skin. 2nd ed. Philadelphia, PA: Elsevier Saunders; 2011.
Jemal A, Siegel R, Ward E, Murray T, Xu J, Smigal C, et al. Cancer statistics, 2006. CA Cancer J Clin 2006; 56(2): 106−30.
Joshua AM. Melanoma prevention: are we doing enough? A Canadian perspective. Curr Oncol 2012; 19(6): e462−7.
Chen ST, Geller AC, Tsao H. Update on the Epidemiology of Melanoma. Curr Dermatol Rep 2013; 2(1): 24−34.
Cho E, Rosner BA, Feskanich D, Colditz GA. Risk factors and individual probabilities of melanoma for whites. J Clin Oncol 2005; 23(12): 2669−75.
Xu LY, Koo J. Predictive value of phenotypic variables for skin cancer: risk assessment beyond skin typing. Int J Dermatol 2006; 45(11): 1275−83.
Walls AC, Han J, Li T, Qureshi AA. Host Risk Factors, Ultra-violet Index of Residence, and Incident Malignant Melanoma In Situ Among US Women and Men. Am J Epidemiol 2013; (In Press)
Chen J, Chi M, Chen C, Zhang XD. Obesity and melanoma: possible molecular links. J Cell Biochem 2013; 114(9): 1955−61.
Li X, Liang L, Zhang M, Song F, Nan H, Wang LE, et al. Obesi-ty-related genetic variants, human pigmentation, and risk of melanoma. Hum Genet 2013; 132(7): 793−801.
Kareus SA, Figueroa KP, Cannon-Albright LA, Pulst SM. Shared predispositions of parkinsonism and cancer: a population-based pedigree-linked study. Arch Neurol 2012; 69(12): 1572−7.
Reddy KK. Vitamin D level and basal cell carcinoma, squamous cell carcinoma, and melanoma risk. J Invest Dermatol 2013; 133(3): 589−92.
Kubica AW, Brewer JD. Melanoma in immunosuppressed pa-tients. Mayo Clin Proc 2012; 87(10): 991−1003.
Faisal RA, Lear JT. Melanoma in organ transplant recipients: incidence, outcomes and management considerations. J Skin Cancer 2012; 2012: 404615.
Engels EA, Pfeiffer RM, Fraumeni JF, Kasiske BL, Israni AK, Snyder JJ, et al. Spectrum of cancer risk among US solid organ transplant recipients. JAMA 2011; 306(17): 1891−901.
Hammer GP, Blettner M, Zeeb H. Epidemiological studies of cancer in aircrew. Radiat Prot Dosimetr 2009;136(4): 232−9.
Koomen ER, Joosse A, Herings RM, Casparie MK, Guchelaar HJ, Nijsten T. Estrogens, oral contraceptives and hormonal re-placement therapy increase the incidence of cutaneous mela-noma: a population-based case-control study. Ann Oncol 2009; 20(2): 358−64.
Gandini S, Iodice S, Koomen E, Di PA, Sera F, Caini S. Hormonal and reproductive factors in relation to melanoma in women: current review and meta-analysis. Eur J Cancer 2011; 47(17): 2607−17.
Thrift AP, Whiteman DC. Can we really predict risk of cancer. Cancer Epidemiol 2013; 37(4): 349−52.
Mar V, Wolfe R, Kelly JW. Predicting melanoma risk for the Australian population. Australas J Dermatol 2011; 52(2): 109−16.
Fortes C, Mastroeni S, Bakos L, Antonelli G, Alessandroni L, Pilla MA, et al. Identifying individuals at high risk of melanoma: a simple tool. Eur J Cancer Prev 2010; 19(5): 393−400.
Williams LH, Shors AR, Barlow WE, Solomon C, White E. Identi-fying Persons at Highest Risk of Melanoma Using Self-Assessed Risk Factors. J Clin Exp Dermatol Res 2011; 2(6): pii: 1000129.
Fargnoli MC, Piccolo D, Altobelli E, Formicone F, Chimenti S, Peris K. Constitutional and environmental risk factors for cutaneous melanoma in an Italian population. A case-control study. Me-lanoma Res 2004; 14(2): 151−7.
Ballester I, Oliver V, Bañuls J, Moragón M, Valcuende F, Botella-Estrada R, et al. . Multicenter case-control study of risk factors for cutaneous melanoma in Valencia, Spain. Actas Dermosifi-liogr 2012; 103(9): 790−7. (English, Spanish)
Bakos L, Mastroeni S, Mastroeni S, Bonamigo RR, Melchi F, Pasquini P, et al. A melanoma risk score in a Brazilian population. An Bras Dermatol 2013; 88(2): 226−32.
Fears TR, Guerry D, Pfeiffer RM, Sagebiel RW, Elder DE, Halpern A, et al. Identifying Individuals at High Risk of Melanoma: A Practical Predictor of Absolute Risk. J Clin Oncol 2006; 24(22): 3590−6.
Grimes DA, Schulz KF. Making sense of odds and odds ratios. Obstet Gynecol 2008; 111(2 Pt 1): 423−6.
Bauer A, Diepgen TL, Schmitt J. Is occupational solar ultraviolet irradiation a relevant risk factor for basal cell carcinoma? A systematic review and meta-analysis of the epidemiological lite-rature. Br J Dermatol 2011; 165(3): 612−25.
Fartasch M, Diepgen TL, Schmitt J, Drexler H. The relationship between occupational sun exposure and non-melanoma skin cancer: clinical basics, epidemiology, occupational disease evaluation, and prevention. Dtsch Arztebl Int 2012; 109(43): 715−20.
Gallagher RP, Lee TK, Bajdik CD, Borugian M. Ultraviolet radia-tion. Chronic Dis Can 2010; 29 (Suppl 1): 51−68.
Surdu S, Fitzgerald EF, Bloom MS, Boscoe FP, Carpenter DO, Haase RF, et al. Occupational exposure to ultraviolet radiation and risk of non-melanoma skin cancer in a multinational European study. PLoS One 2013; 8(4): 623−59.
Chang Y, Barrett JH, Bishop TD, Armstrong BK, Bataille V, Bergman W, et al. Sun exposure and melanoma risk at different lati-tudes: A pooled analysis of 5700 cases and 7216 controls. Int J Epidemiol 2009; 38(3): 814−30.
Boniol M, Autier P, Boyle P, Gandini S. Cutaneous melanoma at-tributable to sunbed use: systematic review and meta-analysis. BMJ 2012; 345: e4757.
Lazovich D, Vogel RI, Berwick M, Weinstock MA, Anderson KE, Warshaw EM. Indoor tanning and risk of melanoma: a case-control study in a highly exposed population. Cancer Epide-miol Biomarkers Prev 2010;1 9(6): 1557−68.
International Agency for Research on Cancer, Working Group: On ar-tificial ultraviolet (UV) light and skin cancer. The association of use of sunbeds with cutaneous malignant melanoma and other skin cancers: A systematic review. Int J Cancer 2007; 120(5): 1116−22.
Csoma Z, Erdei Z, Bartusek D, Dosa-Racz E, Dobozy A, Kemeny L, et al. The prevalence of melanocytic naevi among schoolchild-ren in South Hungary. J Eur Acad Dermatol Venereol 2008; 22(12): 1412−22.
Fehér K, Cercato MC, Prantner I, Dombi Z, Burkali B, Paller J, et al. Skin cancer risk factors among primary school children: inves-tigations in Western Hungary. Prev Med 2010; 51(3−4): 320−4.
Pesch B, Ranft U, Jakubis P, Nieuwenhuijsen MJ, Hergemöller A, Un-fried K, et al. Environmental arsenic exposure from a coal-burning power plant as a potential risk factor for nonmelano-ma skin carcinoma: results from a case-control study in the district of Prievidza, Slovakia. Am J Epidemiol 2002; 155(9): 798−809.
Gandini S, Sera F, Cattaruzza MS, Pasquini P, Abeni D, Boyle P, et al. Meta-analysis of risk factors for cutaneous melanoma: I. Common and atypical naeci. Eur J Cancer 2005; 41(1): 28−44.
Ahmed K, Emran AA, Jesmin T, Mukti RF, Rahman MZ, Ahmed F. Early detection of lung cancer risk using data mining. Asian Pac J Cancer Prev 2013; 14(1): 595−8.
Singleton KW, Hsu W, Bui AA. Comparing predictive models of glioblastoma multiforme built using multi-institutional and lo-cal data sources. AMIA Annu Symp Proc 2012; 2012: 1385−92.
Kurosaki M, Hiramatsu N, Sakamoto M, Suzuki Y, Iwasaki M, Tamori A, et al. Data mining model using simple and readily available factors could identify patients at high risk for hepato-cellular carcinoma in chronic hepatitis C. J Hepatol 2012; 56(3): 602−8.
Amini L, Azarpazhouh R, Farzadfar MT, Mousavi SA, Jazaieri F, Khorvash F, et al. Prediction and control of stroke by data min-ing. Int J Prev Med 2013; 4(Suppl 2): 245−9.
Briones N, Dinu V. Data mining of high density genomic va-riant data for prediction of Alzheimer's disease risk. BMC Med Genet 2012; 13: 7.