Zare Ali, Mahmoodi Mahmood, Mohammad Kazem, Zeraati Hojjat, Hosseini Mostafa, Naieni Kourosh Holakouie
Department of Epidemiology and Biostatistics, Tehran University of Medical Sciences, Tehran, Iran E-mail :
Asian Pac J Cancer Prev. 2014;15(9):4109-15. doi: 10.7314/apjcp.2014.15.9.4109.
Accurate assessment of disease progression requires proper understanding of natural disease process which is often hidden and unobservable. For this purpose, disease status should be clearly detected. But in most diseases it is not possible to detect such status. This study, therefore, aims to present a model which both investigates the unobservable disease process and considers the error probability in diagnosis of disease states.
Data from 330 patients with gastric cancer undergoing surgery at the Iran Cancer Institute from 1995 to 1999 were analyzed. Moreover, to estimate and assess the effect of demographic, diagnostic and clinical factors as well as medical and post-surgical variables on transition rates and the probability of misdiagnosis of relapse, a hidden Markov multi-state model was employed.
Classification errors of patients in alive state without a relapse (e21) and with a relapse (e12) were 0.22 (95% CI: 0.04-0.63) and 0.02 (95% CI: 0.00-0.09), respectively. Only variables of age and number of renewed treatments affected misdiagnosis of relapse. In addition, patient age and distant metastasis were among factors affecting the occurrence of relapse (state1→state2) while the number of renewed treatments and the type and extent of surgery had a significant effect on death hazard without relapse (state2→state3) and death hazard with relapse (state2→state3).
A hidden Markov multi-state model provides the possibility of estimating classification error between different states of disease. Moreover, based on this model, factors affecting the probability of this error can be identified and researchers can be helped with understanding the mechanisms of classification error.
准确评估疾病进展需要正确理解通常隐藏且不可观察的自然疾病过程。为此，应清晰检测疾病状态。但在大多数疾病中，检测这种状态是不可能的。因此，本研究旨在提出一种模型，该模型既能研究不可观察的疾病过程，又能考虑疾病状态诊断中的错误概率。
分析了1995年至1999年在伊朗癌症研究所接受手术的330例胃癌患者的数据。此外，为了估计和评估人口统计学、诊断和临床因素以及医学和术后变量对转移率和复发误诊概率的影响，采用了隐马尔可夫多状态模型。
无复发存活状态（e21）和复发状态（e12）患者的分类错误分别为0.22（95%CI：0.04 - 0.63）和0.02（95%CI：0.00 - 0.09）。只有年龄和重新治疗次数的变量影响复发的误诊。此外，患者年龄和远处转移是影响复发发生（状态1→状态2）的因素，而重新治疗次数以及手术类型和范围对无复发死亡风险（状态2→状态3）和有复发死亡风险（状态2→状态3）有显著影响。
隐马尔可夫多状态模型提供了估计疾病不同状态之间分类错误的可能性。此外，基于该模型，可以识别影响这种错误概率的因素，并有助于研究人员理解分类错误的机制。
