Using Hypothesis-Led Machine Learning and Hierarchical Cluster Analysis to Identify Disease Pathways Prior to Dementia: Longitudinal Cohort Study

BACKGROUND

Dementia development is a complex process in which the occurrence and sequential relationships of different diseases or conditions may construct specific patterns leading to incident dementia.

OBJECTIVE

This study aimed to identify patterns of disease or symptom clusters and their sequences prior to incident dementia using a novel approach incorporating machine learning methods.

METHODS

Using Taiwan's National Health Insurance Research Database, data from 15,700 older people with dementia and 15,700 nondementia controls matched on age, sex, and index year (n=10,466, 67% for the training data set and n=5234, 33% for the testing data set) were retrieved for analysis. Using machine learning methods to capture specific hierarchical disease triplet clusters prior to dementia, we designed a study algorithm with four steps: (1) data preprocessing, (2) disease or symptom pathway selection, (3) model construction and optimization, and (4) data visualization.

RESULTS

Among 15,700 identified older people with dementia, 10,466 and 5234 subjects were randomly assigned to the training and testing data sets, and 6215 hierarchical disease triplet clusters with positive correlations with dementia onset were identified. We subsequently generated 19,438 features to construct prediction models, and the model with the best performance was support vector machine (SVM) with the by-group LASSO (least absolute shrinkage and selection operator) regression method (total corresponding features=2513; accuracy=0.615; sensitivity=0.607; specificity=0.622; positive predictive value=0.612; negative predictive value=0.619; area under the curve=0.639). In total, this study captured 49 hierarchical disease triplet clusters related to dementia development, and the most characteristic patterns leading to incident dementia started with cardiovascular conditions (mainly hypertension), cerebrovascular disease, mobility disorders, or infections, followed by neuropsychiatric conditions.

CONCLUSIONS

Dementia development in the real world is an intricate process involving various diseases or conditions, their co-occurrence, and sequential relationships. Using a machine learning approach, we identified 49 hierarchical disease triplet clusters with leading roles (cardio- or cerebrovascular disease) and supporting roles (mental conditions, locomotion difficulties, infections, and nonspecific neurological conditions) in dementia development. Further studies using data from other countries are needed to validate the prediction algorithms for dementia development, allowing the development of comprehensive strategies to prevent or care for dementia in the real world.

Multimorbidity and health literacy: A population-based survey among 28,627 Danish adults

AIM

Individuals with multimorbidity often have complex healthcare needs challenging their health literacy skills. This study aimed to investigate the association between the number of physical conditions and health literacy and to examine the difference in health literacy levels between individuals with multimorbidity based on physical conditions and individuals with additional mental disorders.

METHODS

Respondents aged 25 years or older from a Danish population-based survey were included (N = 28,627). Multimorbidity was assessed based on 18 self-reported chronic conditions; health literacy was measured using two scales from the Health Literacy Questionnaire focusing on understanding health information and engaging with healthcare providers. Associations were examined using multiple logistic regression analysis.

RESULTS

We found a positive association between number of physical conditions and the odds of having difficulties in understanding health information and engaging with healthcare providers. For example, the adjusted odds ratio (OR) of having difficulties in understanding health information was 1.45 (95% confidence interval (CI): 1.09-1.94) for individuals with two physical conditions compared with individuals without multimorbidity. The associations formed a positive exposure-response pattern. Furthermore, respondents with both mental and physical conditions had more than twice the odds of having health literacy difficulties compared to respondents with only physical conditions (adjusted OR 2.53 (95% CI 2.02-3.18) and 2.28 (95% CI 1.92-2.72) for the scales, respectively).

CONCLUSIONS

Our results suggest that responding to patients' health literacy needs is crucial for individuals with multimorbidity - especially those with combined mental and physical conditions.

The Use of Passive Smartphone Data to Monitor Anxiety and Depression Among College Students in Real-World Settings: Protocol for a Systematic Review

BACKGROUND

College students are particularly at risk of depression and anxiety. These disorders have a serious impact on public health and affect patients' daily lives. The potential for using smartphones to monitor these mental conditions, providing passively collected physiological and behavioral data, has been reported among the general population. However, research on the use of passive smartphone data to monitor anxiety and depression among specific populations of college students has never been reviewed.

OBJECTIVE

This review's objectives are (1) to provide an overview of the use of passive smartphone data to monitor depression and anxiety among college students, given their specific type of smartphone use and living setting, and (2) to evaluate the different methods used to assess those smartphone data, including their strengths and limitations.

METHODS

This review will follow the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines. Two independent investigators will review English-language, full-text, peer-reviewed papers extracted from PubMed and Web of Science that measure passive smartphone data and levels of depression or anxiety among college students. A preliminary search was conducted in February 2022 as a proof of concept.

RESULTS

Our preliminary search identified 115 original articles, 8 of which met our eligibility criteria. Our planned full study will include an article selection flowchart, tables, and figures representing the main information extracted on the use of passive smartphone data to monitor anxiety and depression among college students.

CONCLUSIONS

The planned review will summarize the published research on using passive smartphone data to monitor anxiety and depression among college students. The review aims to better understand whether and how passive smartphone data are associated with indicators of depression and anxiety among college students. This could be valuable in order to provide a digital solution for monitoring mental health issues in this specific population by enabling easier identification and follow-up of the patients.

TRIAL REGISTRATION

PROSPERO CRD42022316263; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=316263.

INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID)

DERR1-10.2196/38785.

Psychological well-being and worries among pregnant women in the first trimester during the early phase of the COVID-19 pandemic in Denmark compared with a historical group: A hospital-based cross-sectional study

INTRODUCTION

A pandemic may negatively influence psychological well-being in the individual. We aimed to assess the potential influence of the first national lockdown in Denmark (March to June 2020) due to the COVID-19 pandemic on psychological well-being and the content and degree of worries among pregnant women in early pregnancy.

MATERIAL AND METHODS

In this hospital-based cross-sectional study based on self-reported data we compared psychological well-being and worries among women who were pregnant during the first phase of the pandemic (COVID-19 group) (n = 685), with women who were pregnant the year before (Historical group) (n = 787). Psychological well-being was measured by the five-item World Health Organization Well-being Index (WHO-5), using a score ≤50 as indicator of reduced psychological well-being. Differences in WHO-5 mean scores and in the prevalence of women with score ≤50 were assessed using general linear and log-binomial regression analyses. The Cambridge Worry Scale was used to measure the content and degree of major worries. To detect differences between groups, Pearson's Chi-square test was used.

RESULTS

We found no differences in mean WHO-5 score between groups (mean difference) 0.1 (95% CI -1.5 to 1.6) or in the prevalence of women with WHO-5 score ≤50 (prevalence ratio 1.04, 95% CI 0.83-1.29) in adjusted analyses. A larger proportion of women in the COVID-19 group reported major worries about Relationship with husband/partner compared with the Historical group (3% [n = 19] vs 1% [n = 6], p = 0.04), and 9.2% in the COVID-19 group worried about the possible negative influence of the COVID-19 restrictions.

CONCLUSIONS

Our findings indicate that national restrictions due to the COVID-19 pandemic did not influence the psychological well-being or the content and degree of major worries among pregnant women. However, a larger proportion of women in the COVID-19 group reported major worries concerning Relationship with husband/partner compared with the Historical group and 9.2% in the COVID-19 group worried about the possible negative influence of the COVID-19 restrictions.

Prevalence of somatic-mental multimorbidity and its prospective association with disability among older adults in China

We aimed to identify prevalent somatic-mental multimorbidity (SMM) and examine its prospective association with disability among a nationally representative sample. A total of 6728 participants aged 60 years and older in the China Health and Retirement Longitudinal Study were included. A total of 14 somatic or mental conditions were assessed in 2013. SMM was defined as any combination of two or more conditions in which at least one condition was somatic and at least one condition was mental. Disability risk was measured using the combined Activities of Daily Living (ADL)-Instrumental Activities of Daily Living (IADL) index (range 0–11; higher index indicates higher disability) in 2013 and 2015. Overall, the prevalence of SMM was 35.7% (95% confidence interval (CI): 34.1%-37.3%) in 2013. After adjustment for sociodemographic characteristics, lifestyles and baseline ADL-IADL index, over a maximum follow-up period of 2 years, SMM was associated with a 2.61 (95% CI: 2.12-3.22)-fold increase in ADL-IADL disability risk compared with that of healthy participants. In conclusion, SMM was prevalent in older Chinese adults, and it was associated with a higher risk of prospective disability.