A deep learning approach for generating intracranial pressure waveforms from extracranial signals routinely measured in the intensive care unit.

Intracranial pressure (ICP) is commonly monitored to guide treatment in patients with serious brain disorders such as traumatic brain injury and stroke. Established methods to assess ICP are resource intensive and highly invasive. We hypothesized that ICP waveforms can be computed noninvasively from three extracranial physiological waveforms routinely acquired in the Intensive Care Unit (ICU): arterial blood pressure (ABP), photoplethysmography (PPG), and electrocardiography (ECG). We evaluated over 600 h of high-frequency (125 Hz) simultaneously acquired ICP, ABP, ECG, and PPG waveform data in 10 patients admitted to the ICU with critical brain disorders. The data were segmented in non-overlapping 10-s windows, and ABP, ECG, and PPG waveforms were used to train deep learning (DL) models to re-create concurrent ICP. The predictive performance of six different DL models was evaluated in single- and multi-patient iterations. The mean average error (MAE) ± SD of the best-performing models was 1.34 ± 0.59 mmHg in the single-patient and 5.10 ± 0.11 mmHg in the multi-patient analysis. Ablation analysis was conducted to compare contributions from single physiologic sources and demonstrated statistically indistinguishable performances across the top DL models for each waveform (MAE±SD 6.33 ± 0.73, 6.65 ± 0.96, and 7.30 ± 1.28 mmHg, respectively, for ECG, PPG, and ABP; p = 0.42). Results support the preliminary feasibility and accuracy of DL-enabled continuous noninvasive ICP waveform computation using extracranial physiological waveforms. With refinement and further validation, this method could represent a safer and more accessible alternative to invasive ICP, enabling assessment and treatment in low-resource settings.

Optimization of lipid nanoparticles for gene editing of the liver via intraduodenal delivery.

Lipid nanoparticles (LNPs) have recently emerged as successful gene delivery platforms for a diverse array of disease treatments. Efforts to optimize their design for common administration methods such as intravenous injection, intramuscular injection, or inhalation, revolve primarily around the addition of targeting ligands or the choice of ionizable lipid. Here, we employed a multi-step screening method to optimize the type of helper lipid and component ratios in a plasmid DNA (pDNA) LNP library to efficiently deliver pDNA through intraduodenal delivery as an indicative route for oral administration. By addressing different physiological barriers in a stepwise manner, we down-selected effective LNP candidates from a library of over 1000 formulations. Beyond reporter protein expression, we assessed the efficiency in non-viral gene editing in mouse liver mediated by LNPs to knockdown PCSK9 and ANGPTL3 expression, thereby lowering low-density lipoprotein (LDL) cholesterol levels. Utilizing an all-in-one pDNA construct with Strep. pyogenes Cas9 and gRNAs, our results showcased that intraduodenal administration of selected LNPs facilitated targeted gene knockdown in the liver, resulting in a 27% reduction in the serum LDL cholesterol level. This LNP-based all-in-one pDNA-mediated gene editing strategy highlights its potential as an oral therapeutic approach for hypercholesterolemia, opening up new possibilities for DNA-based gene medicine applications.

Machine Learning Elucidates Design Features of Plasmid DNA Lipid Nanoparticles for Cell Type-Preferential Transfection.

For cell and gene therapies to become more broadly accessible, it is critical to develop and optimize non-viral cell type-preferential gene carriers such as lipid nanoparticles (LNPs). Despite the effectiveness of high throughput screening (HTS) approaches in expediting LNP discovery, they are often costly, labor-intensive, and often do not provide actionable LNP design rules that focus screening efforts on the most relevant chemical and formulation parameters. Here we employed a machine learning (ML) workflow using well-curated plasmid DNA LNP transfection datasets across six cell types to maximize chemical insights from HTS studies and has achieved predictions with 5-9% error on average depending on cell type. By applying Shapley additive explanations to our ML models, we unveiled composition-function relationships dictating cell type-preferential LNP transfection efficiency. Notably, we identified consistent LNP composition parameters that enhance in vitro transfection efficiency across diverse cell types, such as ionizable to helper lipid ratios near 1:1 or 10:1 and the incorporation of cationic/zwitterionic helper lipids. In addition, several parameters were found to modulate cell type-preferentiality, including the ionizable and helper lipid total molar percentage, N/P ratio, cholesterol to PEGylated lipid ratio, and the chemical identity of the helper lipid. This study leverages HTS of compositionally diverse LNP libraries and ML analysis to understand the interactions between lipid components in LNP formulations; and offers fundamental insights that contribute to the establishment of unique sets of LNP compositions tailored for cell type-preferential transfection.