Radiation therapy with phenotypic medicine: towards N-of-1 personalization.

In current clinical practice, radiotherapy (RT) is prescribed as a pre-determined total dose divided over daily doses (fractions) given over several weeks. The treatment response is typically assessed months after the end of RT. However, the conventional one-dose-fits-all strategy may not achieve the desired outcome, owing to patient and tumor heterogeneity. Therefore, a treatment strategy that allows for RT dose personalization based on each individual response is preferred. Multiple strategies have been adopted to address this challenge. As an alternative to current known strategies, artificial intelligence (AI)-derived mechanism-independent small data phenotypic medicine (PM) platforms may be utilized for N-of-1 RT personalization. Unlike existing big data approaches, PM does not engage in model refining, training, and validation, and guides treatment by utilizing prospectively collected patient's own small datasets. With PM, clinicians may guide patients' RT dose recommendations using their responses in real-time and potentially avoid over-treatment in good responders and under-treatment in poor responders. In this paper, we discuss the potential of engaging PM to guide clinicians on upfront dose selections and ongoing adaptations during RT, as well as considerations and limitations for implementation. For practicing oncologists, clinical trialists, and researchers, PM can either be implemented as a standalone strategy or in complement with other existing RT personalizations. In addition, PM can either be used for monotherapeutic RT personalization, or in combination with other therapeutics (e.g. chemotherapy, targeted therapy). The potential of N-of-1 RT personalization with drugs will also be presented.

CURATE.AI-assisted dose titration for anti-hypertensive personalized therapy: study protocol for a multi-arm, randomized, pilot feasibility trial using CURATE.AI (CURATE.AI ADAPT trial).

Aims: Artificial intelligence-driven small data platforms such as CURATE.AI hold potential for personalized hypertension care by assisting physicians in identifying personalized anti-hypertensive doses for titration. This trial aims to assess the feasibility of a larger randomized controlled trial (RCT), evaluating the efficacy of CURATE.AI-assisted dose titration intervention. We will also collect preliminary efficacy and safety data and explore stakeholder feedback in the early design process. Methods and results: In this open-label, randomized, pilot feasibility trial, we aim to recruit 45 participants with primary hypertension. Participants will be randomized in 1:1:1 ratio into control (no intervention), home blood pressure monitoring (active control; HBPM), or CURATE.AI arms (intervention; HBPM and CURATE.AI-assisted dose titration). The home treatments include 1 month of two-drug anti-hypertensive regimens. Primary endpoints assess the logistical (e.g. dose adherence) and scientific (e.g. percentage of participants for which CURATE.AI profiles can be generated) feasibility, and define the progression criteria for the RCT in a 'traffic light system'. Secondary endpoints assess preliminary efficacy [e.g. mean change in office blood pressures (BPs)] and safety (e.g. hospitalization events) associated with each treatment protocol. Participants with both baseline and post-treatment BP measurements will form the intent-to-treat analysis. Following their involvement with the CURATE.AI intervention, feedback from CURATE.AI participants and healthcare providers will be collected via exit survey and interviews. Conclusion: Findings from this study will inform about potential refinements of the current treatment protocols before proceeding with a larger RCT, or potential expansion to collect additional information. Positive results may suggest the potential efficacy of CURATE.AI to improve BP control. Trial registration number: NCT05376683.

Comparing the Performance of Multiple Small-Data Personalized Tacrolimus Dosing Models for Pediatric Liver Transplant: A Retrospective Study.

Tacrolimus is a potent immunosuppressant used after pediatric liver transplant. However, tacrolimus's narrow therapeutic window, reliance on physicians' experience for the dose titration, and intra- and inter-patient variability result in liver transplant patients falling out of the target tacrolimus trough levels frequently. Existing personalized dosing models based on the area-under-the-concentration over time curves require a higher frequency of blood draws than the current standard of care and may not be practically feasible. We present a small-data artificial intelligence-derived platform, CURATE.AI, that uses data from individual patients obtained once daily to model the dose and response relationship and identify suitable doses dynamically. Retrospective optimization using 6 models of CURATE.AI and data from 16 patients demonstrated good predictive performance and identified a suitable model for further investigations.Clinical Relevance- This study established and compared the predictive performance of 6 personalized tacrolimus dosing models for pediatric liver transplant patients and identified a suitable model with consistently good predictive performance based on data from pediatric liver transplant patients.

Digital game-based interventions for cognitive training in healthy adults and adults with cognitive impairment: protocol for a two-part systematic review and meta-analysis.

INTRODUCTION: Digital game-based training interventions are scalable solutions that may improve cognitive function for many populations. This protocol for a two-part review aims to synthesise the effectiveness and key features of digital game-based interventions for cognitive training in healthy adults across the life span and adults with cognitive impairment, to update current knowledge and impact the development of future interventions for different adult subpopulations. METHODS AND ANALYSIS: This systematic review protocol follows the Preferred Reporting Items for Systematic Reviews and Meta-Analyses Protocols guidelines. A systematic search was performed in PubMed, Embase, CINAHL, Cochrane Library, Web of Science, PsycINFO and IEEE Explore on 31 July 2022 for relevant literature published in English from the previous 5 years. Experimental, observational, exploratory, correlational, qualitative and mixed methods studies will be eligible if they report at least one cognitive function outcome and include a digital game-based intervention intended to improve cognitive function. Reviews will be excluded but retained to search their reference lists for other relevant studies. All screening will be done by at least two independent reviewers. The appropriate Joanna Briggs Institute Critical Appraisal Tool, according to the study design, will be applied to perform the risk of bias assessment. Outcomes related to cognitive function and digital game-based intervention features will be extracted. Results will be categorised by adult life span stages in the healthy adult population for part 1 and by neurological disorder in part 2. Extracted data will be analysed quantitatively and qualitatively, according to study type. If a group of sufficiently comparable studies is identified, we will perform a meta-analysis applying the random effects model with consideration of the I2 statistic. ETHICS AND DISSEMINATION: Ethics approval is not applicable for this study since no original data will be collected. The results will be disseminated through peer-reviewed publications and conference presentations. PROSPERO REGISTRATION NUMBER: CRD42022351265.

IDentif.AI-Omicron: Harnessing an AI-Derived and Disease-Agnostic Platform to Pinpoint Combinatorial Therapies for Clinically Actionable Anti-SARS-CoV-2 Intervention.

Nanomedicine-based and unmodified drug interventions to address COVID-19 have evolved over the course of the pandemic as more information is gleaned and virus variants continue to emerge. For example, some early therapies (e.g., antibodies) have experienced markedly decreased efficacy. Due to a growing concern of future drug resistant variants, current drug development strategies are seeking to find effective drug combinations. In this study, we used IDentif.AI, an artificial intelligence-derived platform, to investigate the drug-drug and drug-dose interaction space of six promising experimental or currently deployed therapies at various concentrations: EIDD-1931, YH-53, nirmatrelvir, AT-511, favipiravir, and auranofin. The drugs were tested in vitro against a live B.1.1.529 (Omicron) virus first in monotherapy and then in 50 strategic combinations designed to interrogate the interaction space of 729 possible combinations. Key findings and interactions were then further explored and validated in an additional experimental round using an expanded concentration range. Overall, we found that few of the tested drugs showed moderate efficacy as monotherapies in the actionable concentration range, but combinatorial drug testing revealed significant dose-dependent drug-drug interactions, specifically between EIDD-1931 and YH-53, as well as nirmatrelvir and YH-53. Checkerboard validation analysis confirmed these synergistic interactions and also identified an interaction between EIDD-1931 and favipiravir in an expanded range. Based on the platform nature of IDentif.AI, these findings may support further explorations of the dose-dependent drug interactions between different drug classes in further pre-clinical and clinical trials as possible combinatorial therapies consisting of unmodified and nanomedicine-enabled drugs, to combat current and future COVID-19 strains and other emerging pathogens.