Asian American sub-ethnic disparities and trends in epithelial ovarian cancer diagnosis, treatment and survival.

OBJECTIVES: Studies on ovarian cancer (OC) diagnosis, treatment and survival across disaggregated Asian sub-ethnic groups are sparse. Few studies have also conducted trend analyses of these outcomes within and across Asian groups. METHODS: Using logistic, Cox, and Joinpoint regression analyses of the 2000-2018 Surveillance, Epidemiology, and End Results (SEER) data, we examined disparities and trends in OC advanced stage diagnosis, receipt of treatments and the 5-year cause-specific survival across seven Asian sub-ethnic groups. RESULTS: There were 6491 OC patients across seven Asian sub-ethnic groups (mean [SD] age, 57.29 [13.90] years). There were 1583(24.39%) Filipino, 1183(18.23%) Chinese, and 761(11.72%) Asian Indian or Pakistani (AIP) patients. The majority (52.49%) were diagnosed with OC with at an advanced stage. AIP were more likely to have advanced stage diagnosis than other subgroups (ORs, 95%CIs: 0.77, 0.62-0.96 [Filipino]; 0.76, 0.60-0.95 [Chinese]; 0.71, 0.54-0.94 [Japanese]; 0.74, 0.56-0.98 [Vietnamese] and 0.66, 0.53-0.83 [Other Asians]). The Filipinos were least likely to receive surgery but most likely to undergo chemotherapy. Japanese patients had the worst 5-year OC cause-specific survival (50.29%, 95%CI: 46.20%-54.74%). Based on the aggregated analyses, there was a significantly decreased trend in advanced-stage diagnosis and an increased trend in receipt of chemotherapy. Trends in OC outcomes for several subethnicities differed from those observed in aggregated analyses. CONCLUSION: In this cohort study of 6491 patients, OC diagnosis, treatment, survival, and trends differed across Asian American ethnic subgroups. Such differences must be considered in future research and interventions to ensure all Asian American subethnicities equally benefit from the advancements in OC care and control.

Risk perception predicts post-traumatic growth during the COVID-19 pandemic in China: the mediation effect of engaging in health-protective behaviors.

The COVID-19 pandemic exposed the public to enormous health risks and induced wide-ranging impacts on people's mental health. Post-traumatic growth is a possible psychological benefits that may occur during struggling with the COVID-19 pandemic. This research explored 1) demographics differences on risk perception of COVID-19 pandemic, engagement in health-protective behavior and post-traumatic growth during the COVID-19 pandemic; and 2) the mediation effect of engaging in health-protective behaviors between risk perception and post-traumatic growth during the COVID-19 pandemic. Females showed a significant higher level of engagement in health-protective behaviors. People who were married reported a significantly higher level of risk perception, engagement in health-protective behavior and post-traumatic growth than those who were in other marital status (i.e. single, divorced, widowed). People who had acquaintances being infected with COVID-19 reported significant higher level of risk perception and engagement in health-protective behaviors. Engagement in health-protective behaviors mediated the relationship between risk perception and post-traumatic growth. Implications of the results for public health interventions are discussed.

Predicting all-cause mortality and premature death using interpretable machine learning among a middle-aged and elderly Chinese population.

Objective: To develop machine learning-based prediction models for all-cause and premature mortality among the middle-aged and elderly population in China. Method: Adults aged 45 years or older at baseline of 2011 from the China Health and Retirement Longitudinal Study (CHARLS) were included. The stacked ensemble model was built utilizing five selected machine learning algorithms. These models underwent training and testing using the CHARLS 2011-2015 cohort (derivation cohort) and subsequently underwent external validation using the CHARLS 2015-2018 cohort (validation cohort). SHapley Additive exPlanations (SHAP) was introduced to quantify the importance of risk factors and explain machine learning algorithms. Result: In derivation cohort, a total of 10,677 subjects were included, 478 died during the follow-up. The stacked ensemble model demonstrated the highest efficacy in terms of its discrimination capability for predicting all-cause mortality and premature death, with an AUC[95 % CI] of 0.826[0.792-0.859] and 0.773[0.725-0.821], respectively. In validation cohort, the corresponding AUC[95 % CI] were 0.803[0.743-0.864] and 0.791[0.719-0.863], respectively. Risk factors including age, sex, self-reported health, activities of daily living, cognitive function, ever smoker, levels of systolic blood pressure, Cystatin C and low density lipoprotein were strong predictors for both all-cause mortality and premature death. Conclusion: Stacked ensemble models performed well in predicting all-cause and premature death in this Chinese cohort. Interpretable techniques can aid in identifying significant risk factors and non-linear relationships between predictors and mortality.

A transformer-based unified multimodal framework for Alzheimer's disease assessment.

In Alzheimer's disease (AD) assessment, traditional deep learning approaches have often employed separate methodologies to handle the diverse modalities of input data. Recognizing the critical need for a cohesive and interconnected analytical framework, we propose the AD-Transformer, a novel transformer-based unified deep learning model. This innovative framework seamlessly integrates structural magnetic resonance imaging (sMRI), clinical, and genetic data from the extensive Alzheimer's Disease Neuroimaging Initiative (ADNI) database, encompassing 1651 subjects. By employing a Patch-CNN block, the AD-Transformer efficiently transforms image data into image tokens, while a linear projection layer adeptly converts non-image data into corresponding tokens. As the core, a transformer block learns comprehensive representations of the input data, capturing the intricate interplay between modalities. The AD-Transformer sets a new benchmark in AD diagnosis and Mild Cognitive Impairment (MCI) conversion prediction, achieving remarkable average area under curve (AUC) values of 0.993 and 0.845, respectively, surpassing those of traditional image-only models and non-unified multimodal models. Our experimental results confirmed the potential of the AD-Transformer as a potent tool in AD diagnosis and MCI conversion prediction. By providing a unified framework that jointly learns holistic representations of both image and non-image data, the AD-Transformer paves the way for more effective and precise clinical assessments, offering a clinically adaptable strategy for leveraging diverse data modalities in the battle against AD.