Drug Development.

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.

Drug Development.

Background: 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.

Efficacy of priming and commitment posters on urgent care patients' antibiotic expectations and knowledge: a cluster randomized trial.

Objective: Successfully educating urgent care patients on appropriate use and risks of antibiotics can be challenging. We assessed the conscious and subconscious impact various educational materials (informational handout, priming poster, and commitment poster) had on urgent care patients' knowledge and expectations regarding antibiotics.

Design: Stratified Block Randomized Control Trial.

Accelerating biosimilar market access: the case for allowing earlier standing.

Biosimilars, which are affordable alternatives to biologic medicines, face delays in market entry due to the current patent litigation framework under the Biologic Price Competition and Innovation Act. Currently, biosimilar manufacturers can only initiate patent litigation to attempt to clear weak and invalid patents after submitting their Biologic License Application to the Food and Drug Administration (FDA), which happens after completing extensive, and costly clinical trials. By contrast, generic drug manufacturers can start litigation earlier due to shorter development times and less stringent clinical requirements, allowing them to launch immediately after the primary patent expires.

Harnessing global HLA data for enhanced patient matching in iPSC haplobanks.

Background: Several countries have either developed or are developing national induced pluripotent stem cell (iPSC) banks of cell lines derived from donors with HLA homozygous genotypes (two identical haplotypes) prevalent in their local populations to provide immune matched tissues and cells to support regenerative medicine therapies. This 'haplobank' approach relies on knowledge of the HLA genotypes of the population to identify the most beneficial haplotypes for patient coverage, and ultimately identify donors or cord blood units carrying two copies of the target haplotype.

Aims: A potentially more efficient alternative to a national bank approach is to assess the haplotypes required to provide global patient coverage and to produce a single, global haplobank.