Depression is a multifaceted illness with large interindividual variability in clinical response to treatment. In the era of digital medicine and precision therapeutics, new personalized treatment approaches are warranted for depression. Here, we use a combination of longitudinal ecological momentary assessments of depression, neurocognitive sampling synchronized with electroencephalography, and lifestyle data from wearables to generate individualized predictions of depressed mood over a 1-month time period. This study, thus, develops a systematic pipeline for N-of-1 personalized modeling of depression using multiple modalities of data. In the models, we integrate seven types of supervised machine learning (ML) approaches for each individual, including ensemble learning and regression-based methods. All models were verified using fourfold nested cross-validation. The best-fit as benchmarked by the lowest mean absolute percentage error, was obtained by a different type of ML model for each individual, demonstrating that there is no one-size-fits-all strategy. The voting regressor, which is a composite strategy across ML models, was best performing on-average across subjects. However, the individually selected best-fit models still showed significantly less error than the voting regressor performance across subjects. For each individual’s best-fit personalized model, we further extracted top-feature predictors using Shapley statistics. Shapley values revealed distinct feature determinants of depression over time for each person ranging from co-morbid anxiety, to physical exercise, diet, momentary stress and breathing performance, sleep times, and neurocognition. In future, these personalized features can serve as targets for a personalized ML-guided, multimodal treatment strategy for depression.
The identification of a gain-of-function mutation in CACNA1C as the cause of Timothy Syndrome (TS), a rare disorder characterized by cardiac arrhythmias and syndactyly, highlighted unexpected roles for the L-type voltage-gated Ca 2+ The broad array of abnormalities within nonexcitable tissues in Timothy Syndrome (TS) patients (1), however, revealed that Ca V 1.2 controls critical, yet previously unknown, roles in multiple nonexcitable tissues. Identified as a novel cardiac arrhythmia syndrome associated with syndactyly and dysmorphic facial features (2), the TS defect was discovered to be a specific gain-of-function mutation (G406R) in CACNA1C, the gene encoding Ca V 1.2. The mutation greatly slows channel inactivation, and thereby prolongs cellular repolarization in cardiac myocytes, which provided a clear rationale for the cardiac arrhythmias. Yet how Ca V 1.2 affects nonexcitable cells, as indicated by additional phenotypes documented in TS, such as small teeth, baldness at birth, and dysmorphic facial features, is unclear. These phenotypes were not consistent with previously understood roles for Ca V 1.2. Here, we
Coccidioidomycosis (CM) is a fungal infection endemic in the southwestern United States (US). In California, CM incidence increased more than 213% (from 6.0/100,000 (2014) to 18.8/100,000 (2017)) and continues to increase as rates in the first half of 2018 are double that of 2017 during the same period. This cost-of-illness study provides essential information to be used in health planning and funding as CM infections continue to surge. We used a “bottom-up” approach to determine lifetime costs of 2017 reported incident CM cases in California. We defined CM natural history and used a societal approach to determine direct and discounted indirect costs using literature, national datasets, and expert interviews. The total lifetime cost burden of CM cases reported in 2017 in California is just under $700 million US dollars, with $429 million in direct costs and $271 million in indirect costs. Per person direct costs were highest for disseminated disease ($1,023,730), while per person direct costs were lowest for uncomplicated CM pneumonia ($22,039). Cost burden varied by county. This is the first study to estimate total costs of CM, demonstrating its huge cost burden for California.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.