Background: Lung cancer is one of the cancers with the highest mortality rate in China. With the rapid development of high-throughput sequencing technology and the research and application of deep learning methods in recent years, deep neural networks based on gene expression have become a hot research direction in lung cancer diagnosis in recent years, which provide an effective way of early diagnosis for lung cancer. Thus, building a deep neural network model is of great significance for the early diagnosis of lung cancer. However, the main challenges in mining gene expression datasets are the curse of dimensionality and imbalanced data. The existing methods proposed by some researchers can’t address the problems of high-dimensionality and imbalanced data, because of the overwhelming number of variables measured (genes) versus the small number of samples, which result in poor performance in early diagnosis for lung cancer.Method: Given the disadvantages of gene expression data sets with small datasets, high-dimensionality and imbalanced data, this paper proposes a gene selection method based on KL divergence, which selects some genes with higher KL divergence as model features. Then build a deep neural network model using Focal Loss as loss function, at the same time, we use k-fold cross validation method to verify and select the best model, we set the value of k is five in this paper.Result: The deep learning model method based on KL divergence gene selection proposed in this paper has an AUC of 0.99 on the validation set. The generalization performance of model is high.Conclusion: The deep neural network model based on KL divergence gene selection proposed in this paper is proved to be an accurate and effective method for lung cancer prediction.

Background: Depressive symptoms and cognitive impairment often coexisted in the elderly. This study investigates the effect of late-life depressive symptoms on risk of mild cognitive impairment (MCI). Methods: A total of 14,231 dementia- and MCI free participants aged 60+ from the Survey of Health, Ageing, and Retirement in Europe were followed-up for 10 years to detect incident MCI. MCI was defined as 1.5 standard deviation (SD) below the mean of the standardized global cognition score. Depressive symptoms were assessed by a 12-item Europe-depression scale (EURO-D). Severity of depressive symptoms was grouped as: no/minimal (score 0–3), moderate (score 4–5), and severe (score 6–12). Significant depressive symptoms (SDSs) were defined as EURO-D score ≥ 4. Results: During an average of 8.2 (SD = 2.4)-year follow-up, 1,352 (9.50%) incident MCI cases were identified. SDSs were related to higher MCI risk (hazard ratio [HR] = 1.26, 95% confidence intervals [CI]: 1.10–1.44) in total population, individuals aged 70+ (HR = 1.35, 95% CI: 1.14–1.61) and women (HR = 1.28, 95% CI: 1.08–1.51) in Cox proportional hazard model adjusting for confounders. In addition, there was a dose–response association between the severity of depressive symptoms and MCI incidence in total population, people aged ≥70 years and women (p-trend <0.001). Conclusions: Significant depressive symptoms were associated with higher incidence of MCI in a dose–response fashion, especially among people aged 70+ years and women. Treating depressive symptoms targeting older population and women may be effective in preventing MCI.

Depression is the most common mental health problem and often co-occurs with dementia in old age. This study investigates the influence of late-life depression on risk of dementia. A total of 16210 dementia-free participants aged 60+ from the Survey of Health, Aging, and Retirement in Europe were followed up for 10 years to detect incident dementia. Depression was assessed by a 12-item Europe-depression scale, dementia was determined by physician diagnosis reported by the participants and their informants. Fine and Gray model was performed to explore the association between depression and incident dementia taking into account competing risk of death. During an average of 8 years follow-up, 1030 (6.35%) incident dementia were identified. Late-life depression was related to higher subdistribution hazard ratio (sHR) of dementia (sHR=1.52, 95%CI: 1.32-1.75) after adjusting for age, gender, country, education, smoking, drinking, living arrangement, BMI, chronic disease, and physical activity. Further, the risk was only existed in those below age of 80 (sHR=1.75, 95%CI: 1.47-2.07). In addition, a dose-response association was observed between the severity of depression and dementia risk (p for trend<0.001). The ascertainment of depression and dementia was based on information reported by the participants and/or their informants, which might result in information bias. The causal relationship could not be determined because limited follow-up time. Late-life depression is associated with higher incidence of dementia in a dose-response fashion. Interventions targeting depression patients aged 60-79 years and those with severe depression may be effective strategies to prevent dementia.