Develop and Validate a Prognostic Index With Laboratory Tests to Predict Mortality in Middle-Aged and Older Adults Using Machine Learning Models: A Prospective Cohort Study.

BACKGROUND: Prognostic indices can enhance personalized predictions of health burdens. However, a simple, practical, and reproducible tool is lacking for clinical use. This study aimed to develop a machine learning-based prognostic index for predicting all-cause mortality in community-dwelling older individuals. METHODS: We utilized the Healthy Aging Longitudinal Study in Taiwan (HALST) cohort, encompassing data from 5 663 participants. Over the 5-year follow-up, 447 deaths were confirmed. A machine learning-based routine blood examination prognostic index (MARBE-PI) was developed using common laboratory tests based on machine learning techniques. Participants were grouped into multiple risk categories by stratum-specific likelihood ratio analysis based on their MARBE-PI scores. The MARBE-PI was subsequently externally validated with an independent population-based cohort from Japan. RESULTS: Beyond age, sex, education level, and BMI, 6 laboratory tests (low-density lipoprotein, albumin, aspartate aminotransferase, lymphocyte count, high-sensitivity C-reactive protein, and creatinine) emerged as pivotal predictors via stepwise logistic regression (LR) for 5-year mortality. The area under curves of MARBE-PI constructed by LR were 0.799 (95% confidence interval [95% CI]: 0.778-0.819) and 0.756 (95% CI: 0.694-0.814) for the internal and external validation data sets, and were 0.801 (95% CI: 0.790-0.811) and 0.809 (95% CI: 0.774-0.845) for the extended 10-year mortality in both data sets, respectively. Risk categories stratified by MARBE-PI showed a consistent dose-response association with mortality. The MARBE-PI also performed comparably with indices constructed with clinical health deficits and/or laboratory results. CONCLUSIONS: The MARBE-PI is considered the most applicable measure for risk stratification in busy clinical settings. It holds potential to pinpoint older individuals at elevated mortality risk, thereby aiding clinical decision-making.

Impact of physical activity on disability-free and disabled life expectancies in middle-aged and older adults: Data from the healthy aging longitudinal study in Taiwan.

AIM: Leisure-time physical activity (LTPA) promotes healthy aging; however, data on work-related physical activity (WPA) are inconsistent. This study was conducted to examine the disability-free life expectancy (DFLE) and disabled life expectancy (DLE) across physical activity levels, with a focus on WPA, in middle-aged and older adults. METHODS: Data from 5663 community-dwelling participants aged ≥55 years and enrolled in the Healthy Aging Longitudinal Study in Taiwan were evaluated. Energy expenditures from LTPA and WPA were calculated from baseline questionnaires and categorized into sex-specific cutoffs. Disability was based on repeat measures of participants' activities of daily living and instrumental activities of daily living. Mortality was confirmed via data linkage with the Death Certificate database. DFLE and DLE were estimated from discrete-time multistate life-table models. RESULTS: At age 65, women with low WPA had a DLE of 2.88 years (95% confidence interval [CI], 1.67-4.08), which was shorter than that of women without WPA (DLE, 5.24 years; 95% CI, 4.65-5.83) and with high WPA (DLE, 4.01 years; 95% CI, 2.69-5.34). DFLE and DLE were similar across WPA levels in men. DFLE tended to increase as the LTPA increased in men and women. CONCLUSION: Women with low WPA had shorter DLE than did those with no or high WPA. To reduce the risks of disability associated with physical activity, public policy should advocate for older people to watch the type, amount, and intensity of their activities as these may go ignored during WPA. Geriatr Gerontol Int 2024; 24: 229-239.

Association between Alzheimer's disease genes and trajectories of cognitive function decline in Han Chinese in Taiwan.

Genetic background has been considered one of the important contributors to the rate of cognitive decline among patients with Alzheimer's disease (AD). We conducted a 4-year longitudinal follow-up study, recruited 255 AD and 44 mild cognitive impairment (MCI) patients, and used a data-driven trajectory analysis to examine the influence of selected AD risk genes on the age for and the rate of cognitive decline in Han Chinese population. Genotyping of selected single-nucleotide polymorphisms in the APOE, ABCA7, SORL1, BIN1, GAB2, and CD33 genes was conducted, and a Bayesian hierarchical model was fitted to analyze the trajectories of cognitive decline among different genotypes. After adjusting for sex and education years, the APOE ε4 allele was associated with an earlier mean change of -2.39 years in the age at midpoint of cognitive decline, the G allele in ABCA7 rs3764650 was associated with an earlier mean change of -1.75 years, and the T allele in SORL1 rs3737529 was associated with a later mean change of 2.6 years. Additionally, the rate of cognitive decline was associated with the APOE ε4 allele and SORL1 rs3737529. In summary, APOE and SORL1 might be the most important genetic factors related to cognitive decline in Han Chinese population.

Impact of cooking oil fume exposure and fume extractor use on lung cancer risk in non-smoking Han Chinese women.

Smoking tobacco is the major risk factor for developing lung cancer. However, most Han Chinese women with lung cancer are nonsmokers. Chinese cooking methods usually generate various carcinogens in fumes that may inevitably be inhaled by those who cook the food, most of whom are female. We investigated the associations of cooking habits and exposure to cooking fumes with lung cancer among non-smoking Han Chinese women. This study was conducted on 1,302 lung cancer cases and 1,302 matched healthy controls in Taiwan during 2002-2010. Two indices, "cooking time-years" and "fume extractor use ratio," were developed. The former was used to explore the relationship between cumulative exposure to cooking oil fumes and lung cancer; the latter was used to assess the impact of fume extractor use for different ratio-of-use groups. Using logistic models, we found a dose-response association between cooking fume exposure and lung cancer (odds ratios of 1, 1.63, 1.67, 2.14, and 3.17 across increasing levels of cooking time-years). However, long-term use of a fume extractor in cooking can reduce the risk of lung cancer by about 50%. Furthermore, we provide evidence that cooking habits, involving cooking methods and oil use, are associated with risk of lung cancer.

TSGSIS: a high-dimensional grouped variable selection approach for detection of whole-genome SNP-SNP interactions.

MOTIVATION: Identification of single nucleotide polymorphism (SNP) interactions is an important and challenging topic in genome-wide association studies (GWAS). Many approaches have been applied to detecting whole-genome interactions. However, these approaches to interaction analysis tend to miss causal interaction effects when the individual marginal effects are uncorrelated to trait, while their interaction effects are highly associated with the trait. RESULTS: A grouped variable selection technique, called two-stage grouped sure independence screening (TS-GSIS), is developed to study interactions that may not have marginal effects. The proposed TS-GSIS is shown to be very helpful in identifying not only causal SNP effects that are uncorrelated to trait but also their corresponding SNP-SNP interaction effects. The benefit of TS-GSIS are gaining detection of interaction effects by taking the joint information among the SNPs and determining the size of candidate sets in the model. Simulation studies under various scenarios are performed to compare performance of TS-GSIS and current approaches. We also apply our approach to a real rheumatoid arthritis (RA) dataset. Both the simulation and real data studies show that the TS-GSIS performs very well in detecting SNP-SNP interactions. AVAILABILITY AND IMPLEMENTATION: R-package is delivered through CRAN and is available at: https://cran.r-project.org/web/packages/TSGSIS/index.html. CONTACT: hsiung@nhri.org.tw. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

A novel support vector machine-based approach for rare variant detection.

Advances in next-generation sequencing technologies have enabled the identification of multiple rare single nucleotide polymorphisms involved in diseases or traits. Several strategies for identifying rare variants that contribute to disease susceptibility have recently been proposed. An important feature of many of these statistical methods is the pooling or collapsing of multiple rare single nucleotide variants to achieve a reasonably high frequency and effect. However, if the pooled rare variants are associated with the trait in different directions, then the pooling may weaken the signal, thereby reducing its statistical power. In the present paper, we propose a backward support vector machine (BSVM)-based variant selection procedure to identify informative disease-associated rare variants. In the selection procedure, the rare variants are weighted and collapsed according to their positive or negative associations with the disease, which may be associated with common variants and rare variants with protective, deleterious, or neutral effects. This nonparametric variant selection procedure is able to account for confounding factors and can also be adopted in other regression frameworks. The results of a simulation study and a data example show that the proposed BSVM approach is more powerful than four other approaches under the considered scenarios, while maintaining valid type I errors.

SVM-based generalized multifactor dimensionality reduction approaches for detecting gene-gene interactions in family studies.

Gene-gene interaction plays an important role in the etiology of complex diseases, which may exist without a genetic main effect. Most current statistical approaches, however, focus on assessing an interaction effect in the presence of the gene's main effects. It would be very helpful to develop methods that can detect not only the gene's main effects but also gene-gene interaction effects regardless of the existence of the gene's main effects while adjusting for confounding factors. In addition, when a disease variant is rare or when the sample size is quite limited, the statistical asymptotic properties are not applicable; therefore, approaches based on a reasonable and applicable computational framework would be practical and frequently applied. In this study, we have developed an extended support vector machine (SVM) method and an SVM-based pedigree-based generalized multifactor dimensionality reduction (PGMDR) method to study interactions in the presence or absence of main effects of genes with an adjustment for covariates using limited samples of families. A new test statistic is proposed for classifying the affected and the unaffected in the SVM-based PGMDR approach to improve performance in detecting gene-gene interactions. Simulation studies under various scenarios have been performed to compare the performances of the proposed and the original methods. The proposed and original approaches have been applied to a real data example for illustration and comparison. Both the simulation and real data studies show that the proposed SVM and SVM-based PGMDR methods have great prediction accuracies, consistencies, and power in detecting gene-gene interactions.