1 paper1 finding
Multifeature 3D CNN
upin silico1
multifeature 3D CNN predicts chronological age prediction in silico (MAE 3.32 years, r = 0.96).
“reduced the mean absolute error (MAE) of age prediction to 3.32 years and improved Pearson's r to 0.96 on 154 healthy controls (HCs).”
In silicoin healthy controlsn = 154
Preprint5 Feb 2024
Tested across multiple molecular platforms, the framework separates technical variation from biological signal to infer cell proportions and chronological age across…Tested across multiple molecular platforms, the framework separates technical variation from biological signal to infer cell proportions and chronological age across independent human cohorts.
A benchmark across 2.5 million single-cell transcriptomes reveals strengths in detecting rare cell states and gene networks, though simple gene sets predicted age better.A benchmark across 2.5 million single-cell transcriptomes reveals strengths in detecting rare cell states and gene networks, though simple gene sets predicted age better.
In middle-aged adults, biological aging correlated with processing speed variability and baseline performance but did not predict cognitive change over time.In middle-aged adults, biological aging correlated with processing speed variability and baseline performance but did not predict cognitive change over time.