Unlabelled: Cryptococcal meningitis (CM) is a common opportunistic infection in HIV-negative patients, with mortality rates as high as those in the HIV-negative population. This requires accurate initial clinical decision-making, warranting the development of a prognostic score. Two groups of patients were investigated separately to develop a novel prognostic model (AAIT) for HIV-negative patients with CM. A retrospective analysis of 201 HIV-negative patients with CM was conducted to develop the CM prognostic score. In addition, the CM cohort (n = 21) was recruited longitudinally to verify the new prognostic score. Meanwhile, the association between the prognostic score and 1-year mortality of CM was expounded. AAIT (age, albumin, combined bacterial infection, and total triiodothyronine) is a novel prognostic score based on age, albumin level, combined bacterial infection, and total triiodothyronine (TT3) level, which were significantly higher in nonsurvivors than in survivors (0.68 [-0.70 to 1.55] vs - 1.72 [-3.75 to -0.73], P < .00). Regarding the AAIT-predicted 1-year mortality, the area under the receiver operating characteristic curve (AUROC) value was 0.857, whereas it was 0.965 for the validation cohort. In the induction period, different treatment options did not seem to significantly improve the 1-year survival rate. AAIT is a straightforward and clear prognostic score that can add value to predict the outcomes in HIV-negative patients with CM. In addition, controlling infection and increasing the albumin and TT3 levels may help improve clinical outcomes in HIV-negative patients with CM.
Lay Abstract: AAIT (age, albumin, combined bacterial infection, and total triiodothyronine) is a straightforward and clear prognostic score that can add value to predict the outcomes HIV-negative patients with CM.
Download full-text PDF |
Source |
---|---|
http://dx.doi.org/10.1093/mmy/myaa095 | DOI Listing |
Background: Pivotal Alzheimer's Disease (AD) trials typically require thousands of participants, resulting in long enrollment timelines and substantial costs. We leverage deep learning predictive models to create prognostic scores (forecasted control outcome) of trial participants and in combination with a linear statistical model to increase statistical power in randomized clinical trials (RCT). This is a straightforward extension of the traditional RCT analysis, allowing for ease of use in any clinical program.
View Article and Find Full Text PDFAlzheimers Dement
December 2024
National Center for Geriatrics and Gerontology, Obu, Aichi, Japan.
Background: The effectiveness of multimodal lifestyle interventions to prevent dementia is being validated. Since a relatively long period (∼2 years) is required for manifesting an impact on cognitive function, the exploration of an alternative marker that exhibits changes within a comparatively brief duration, thereby prognosticating future alterations in cognitive function, is needed. The decline in gait function is associated with cognitive impairment and is also a predictor of future cognitive decline.
View Article and Find Full Text PDFBackground: In Alzheimer's Disease (AD) trials, clinical scales are used to assess treatment effect in patients. Minimizing statistical uncertainty of trial outcomes is an important consideration to increase statistical power. Machine learning models can leverage baseline data to create AI-generated digital twins - individualized predictions (or prognostic scores) of how each patient's clinical outcomes may change during a trial assuming they received placebo.
View Article and Find Full Text PDFAlzheimers Dement
December 2024
University of Pennsylvania, Philadelphia, PA, USA.
Background: Structural and functional heterogeneity in the brains of patients with Alzheimer's disease (AD) leads to diagnostic and prognostic uncertainty and confounds clinical treatment planning. Normative modelling, where individual-level deviations in brain measures from a reference sample are computed to infer personalized effects of disease, allows parsing of disease heterogeneity. In this study, GAN based normative modelling technique quantifies individual level neuroanatomical abnormality thereby facilitating measurement of personalized disease related effects in AD patients.
View Article and Find Full Text PDFAlzheimers Dement
December 2024
University of Melbourne, Parkville, VIC, Australia.
Background: Alzheimer's disease (AD) is a progressive neurodegenerative condition, with considerable variation in disease progression from the mild cognitive impairment (MCI) stage. Predicting disease progression will support prognostic decisions and patient management. Here we designed a machine learning (ML) stack model, where a classifier was used to differentiate MCI progressors from non-progressors (i.
View Article and Find Full Text PDFEnter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!