OBJECTIVE: Our study aimed to evaluate the discriminative and predictive ability of unimodal, bimodal, and multimodal approaches in a total of seven machine learning (ML) models-clinical, demographic, functional near-infrared spectroscopy (fNIRS), combinations of two unimodal models, as well as a combination of all three-for MDD.
METHODS: We recruited 65 adults with MDD and 68 matched healthy controls, who provided both sociodemographic and clinical information, and completed the HAM-D questionnaire. They were also subject to fNIRS measurement when participating in the verbal fluency task. Using the nested cross validation procedure, the classification performance of each ML model was evaluated based on the area under the receiver operating characteristic curve (ROC), balanced accuracy, sensitivity, and specificity.
RESULTS: The multimodal ML model was able to distinguish between depressed patients and healthy controls with the highest balanced accuracy of 87.98 ± 8.84% (AUC = 0.92; 95% CI (0.84-0.99) when compared with the uni- and bi-modal models.
CONCLUSIONS: Our multimodal ML model demonstrated the highest diagnostic accuracy for MDD. This reinforces the biological and clinical heterogeneity of MDD and highlights the potential of this model to improve MDD diagnosis rates. Furthermore, this model is cost-effective and clinically applicable enough to be established as a robust diagnostic system for MDD based on patients' biosignatures.
METHODS: PubMed, EMBASE, Medline, Cochrane Library, CINAHL, PEDro, and Airiti Library were searched from inception until May 5, 2023. Randomized controlled trials that examined exercise, vitamin D and protein supplementation effects on muscle mass, strength, and physical function. Quality assessment used the Cochrane risk of bias tool, and analysis employed Comprehensive Meta-Analysis version 2.0.
RESULTS: A total of 27 randomized controlled trials, involving 1,989 participants were identified. Meta-analysis results showed exercise improved lean body mass (SMD = 0.232, 95% CI: 0.097, 0.366), handgrip strength (SMD = 0.901, 95% CI: 0.362, 1.441), knee extension strength (SMD = 0.698, 95% CI: 0.384, 1.013). Resistance training had a small effect on lean body mass, longer exercise duration (> 12 weeks) and higher frequency (60-90 min, 3 sessions/week) showed small to moderate effects on lean body mass. Vitamin D supplementation improved handgrip strength (SMD = 0.303, 95% CI: 0.130, 0.476), but not knee extension strength. There was insufficient data to assess the impact of protein supplementation on muscle strength.
CONCLUSIONS: Exercise effectively improves muscle mass, and strength in menopausal women. Resistance training with 3 sessions per week, lasting 20-90 min for at least 6 weeks, is most effective. Vitamin D supplementation enhances small muscle group strength. Further trials are needed to assess the effects of vitamin D and protein supplementation on sarcopenia prevention.
REGISTRATION NUMBER: This review was registered on PROSPERO CRD42022329273.
RESULTS: This work describes a computational methodology to achieve this analysis, with data of dengue, West Nile, hepatitis A, HIV-1, and influenza A viruses as examples. Our methodology has been implemented as an analytical pipeline that brings significant advancement to the field of reverse vaccinology, enabling systematic screening of known sequence data in nature for identification of vaccine targets. This includes key steps (i) comprehensive and extensive collection of sequence data of viral proteomes (the virome), (ii) data cleaning, (iii) large-scale sequence alignments, (iv) peptide entropy analysis, (v) intra- and inter-species variation analysis of conserved sequences, including human homology analysis, and (vi) functional and immunological relevance analysis.
CONCLUSION: These steps are combined into the pipeline ensuring that a more refined process, as compared to a simple evolutionary conservation analysis, will facilitate a better selection of vaccine targets and their prioritization for subsequent experimental validation.