Search

Importance: Little is known about the specific timing and sequence of incident psychiatric comorbidities at different stages of dementia diagnosis., Objectives: To examine the temporal risk patterns of psychiatric disorders, including depression, anxiety, stress-related disorders, substance use disorders, sleep disorders, somatoform/conversion disorders, and psychotic disorders, among patients with dementia before, at the time of, and after receipt of a diagnosis., Design, Setting, and Participants: This population-based, nationwide cohort study analyzed data from 796 505 participants obtained from 6 registers between January 1, 2000, and December 31, 2017, including the Swedish registry for cognitive/dementia disorders. Patients with dementia were matched on year of birth (±3 years), sex, and region of residence with up to 4 controls. Data were analyzed between March 1, 2023, and August 31, 2023., Exposures: Any cause of dementia and dementia subtypes., Main Outcomes and Measures: Flexible parametric survival models to determine the time-dependent risk of initial diagnosis of psychiatric disorders, from 7 years prior to dementia diagnosis to 10 years after diagnosis. Subgroup analysis was conducted for psychiatric drug use among persons receiving a diagnosis of dementia from January 1, 2011, to December 31, 2012., Results: Of 796 505 patients included in the study (mean [SD] age at diagnosis, 80.2 [8.3] years; 448 869 (56.4%) female), 209 245 had dementia, whereas 587 260 did not, across 7 824 616 person-years. The relative risk of psychiatric disorders was consistently higher among patients with dementia compared with control participants and began to increase from 3 years before diagnosis (hazard ratio, [HR], 1.72; 95% CI, 1.67-1.76), peaked during the week after diagnosis (HR, 4.74; 95% CI, 4.21-5.34), and decreased rapidly thereafter. Decreased risk relative to controls was observed from 5 years after diagnosis (HR, 0.93; 95% CI, 0.87-0.98). The results were similar for Alzheimer disease, mixed dementia, vascular dementia and unspecified dementia. Among patients with dementia, markedly elevated use of psychiatric medications was observed in the year leading up to the dementia diagnosis and peaked 6 months after diagnosis. For example, antidepressant use was persistently higher among patients with dementia compared with controls, and the difference increased from 2 years before dementia diagnosis (15.9% vs 7.9%, P < .001), peaked approximately 6 months after dementia diagnosis (29.1% vs 9.7%, P < .001), and then decreased slowly from 3 years after diagnosis but remained higher than controls 5 years after diagnosis (16.4% vs 6.9%, P < .001)., Conclusions and Relevance: The findings of this cohort study that patients with dementia had markedly increased risks of psychiatric disorders both before and after dementia diagnosis highlight the significance of incorporating psychiatric preventative and management interventions for individuals with dementia across various diagnostic stages.

Machine learning (ML) could have advantages over traditional statistical models in identifying risk factors. Using ML algorithms, our objective was to identify the most important variables associated with mortality after dementia diagnosis in the Swedish Registry for Cognitive/Dementia Disorders (SveDem). From SveDem, a longitudinal cohort of 28,023 dementia-diagnosed patients was selected for this study. Sixty variables were considered as potential predictors of mortality risk, such as age at dementia diagnosis, dementia type, sex, body mass index (BMI), mini-mental state examination (MMSE) score, time from referral to initiation of work-up, time from initiation of work-up to diagnosis, dementia medications, comorbidities, and some specific medications for chronic comorbidities (e.g., cardiovascular disease). We applied sparsity-inducing penalties for three ML algorithms and identified twenty important variables for the binary classification task in mortality risk prediction and fifteen variables to predict time to death. Area-under-ROC curve (AUC) measure was used to evaluate the classification algorithms. Then, an unsupervised clustering algorithm was applied on the set of twenty-selected variables to find two main clusters which accurately matched surviving and dead patient clusters. A support-vector-machines with an appropriate sparsity penalty provided the classification of mortality risk with accuracy = 0.7077, AUROC = 0.7375, sensitivity = 0.6436, and specificity = 0.740. Across three ML algorithms, the majority of the identified twenty variables were compatible with literature and with our previous studies on SveDem. We also found new variables which were not previously reported in literature as associated with mortality in dementia. Performance of basic dementia diagnostic work-up, time from referral to initiation of work-up, and time from initiation of work-up to diagnosis were found to be elements of the diagnostic process identified by the ML algorithms. The median follow-up time was 1053 (IQR = 516-1771) days in surviving and 1125 (IQR = 605-1770) days in dead patients. For prediction of time to death, the CoxBoost model identified 15 variables and classified them in order of importance. These highly important variables were age at diagnosis, MMSE score, sex, BMI, and Charlson Comorbidity Index with selection scores of 23%, 15%, 14%, 12% and 10%, respectively. This study demonstrates the potential of sparsity-inducing ML algorithms in improving our understanding of mortality risk factors in dementia patients and their application in clinical settings. Moreover, ML methods can be used as a complement to traditional statistical methods., (© 2023. The Author(s).)