One of the most challenging fields where Artificial Intelligence (AI) can be applied is lung cancer research, specifically non-small cell lung cancer (NSCLC). In particular, overall survival (OS) is a vital indicator of patient status, helping to identify subgroups with diverse survival probabilities, enabling tailored treatment and improved OS rates. In this analysis, there are two challenges to take into account. First, few studies effectively exploit the information available from each patient, leveraging both uncensored (i.e., dead) and censored (i.e., survivors) patients, considering also the death times. Second, the handling of incomplete data is a common issue in the medical field. This problem is typically tackled through the use of imputation methods. Our objective is to present an AI model able to overcome these limits, effectively learning from both censored and uncensored patients and their available features, for the prediction of OS for NSCLC patients. We present a novel approach to survival analysis in the context of NSCLC, which exploits the strengths of the transformer architecture accounting for only available features without requiring any imputation strategy. By making use of ad-hoc losses for OS, it accounts for both censored and uncensored patients, considering risks over time. We evaluated the results over a period of 6 years using different time granularities obtaining a Ct-index, a time-dependent variant of the C-index, of 71.97, 77.58 and 80.72 for time units of 1 month, 1 year and 2 years, respectively, outperforming all state-of-the-art methods regardless of the imputation method used.

翻译：人工智能（AI）最具挑战性的应用领域之一是肺癌研究，特别是非小细胞肺癌（NSCLC）。其中，总生存期（OS）是患者状态的关键指标，有助于识别具有不同生存概率的亚组，从而实现个性化治疗并提高OS率。在此分析中，需考虑两大挑战：首先，现有研究未能充分利用每位患者的信息，包括未删失（即死亡）和删失（即存活）患者，同时兼顾死亡时间；其次，处理不完整数据是医学领域的常见问题，通常通过插补方法解决。我们的目标是提出一种能够克服这些局限性的AI模型，有效从删失与未删失患者及其可用特征中学习，以预测NSCLC患者的OS。我们提出了一种针对NSCLC生存分析的新方法，该方法利用Transformer架构的优势，仅基于可用特征进行学习，无需任何插补策略。通过采用针对OS的特定损失函数，模型同时考虑了删失与未删失患者，并关注随时间变化的风险。我们在6年时间内以不同时间粒度评估结果，获得时间依赖的C-index变体Ct-index：以1个月、1年和2年为单位时分别达到71.97、77.58和80.72，无论使用何种插补方法，均优于所有现有先进方法。