ABSTRACT
The digital revolution in healthcare, amplified by the COVID-19 pandemic and artificial intelligence (AI) advances, has led to a surge in the development of digital technologies. However, integrating digital health solutions, especially AI-based ones, in rare diseases like Waldenström macroglobulinemia (WM) remains challenging due to limited data, among other factors. CURATE.AI, a clinical decision support system, offers an alternative to big data approaches by calibrating individual treatment profiles based on that individual's data alone. We present a case study from the PRECISE CURATE.AI trial with a WM patient, where, over two years, CURATE.AI provided dynamic Ibrutinib dose recommendations to clinicians (users) aimed at achieving optimal IgM levels. An 80-year-old male with newly diagnosed WM requiring treatment due to anemia was recruited to the trial for CURATE.AI-based dosing of the Bruton tyrosine kinase inhibitor Ibrutinib. The primary and secondary outcome measures were focused on scientific and logistical feasibility. Preliminary results underscore the platform's potential in enhancing user and patient engagement, in addition to clinical efficacy. Based on a two-year-long patient enrollment into the CURATE.AI-augmented treatment, this study showcases how AI-enabled tools can support the management of rare diseases, emphasizing the integration of AI to enhance personalized therapy.
ABSTRACT
A major component of the extracellular matrix (ECM), laminins, modulates cells via diverse receptors. Their fragments have emerging utility as components of "ECM-mimetics" optimized to promote cell-based therapies. Recently, we reported that a bioactive laminin peptide known as A99 enhanced cell binding and spreading via fusion to an elastin-like polypeptide (ELP). The ELP "handle" serves as a rapid, noncovalent strategy to concentrate bioactive peptide mixtures onto a surface. We now report that this strategy can be further generalized across an expanded panel of additional laminin-derived elastin-like polypeptides (LELPs). A99 (AGTFALRGDNPQG), A2G80 (VQLRNGFPYFSY), AG73 (RKRLQVQLSIRT), and EF1m (LQLQEGRLHFMFD) all promote cell spreading while showing morphologically distinct F-actin formation. Equimolar mixtures of A99:A2G80-LELPs have synergistic effects on adhesion and spreading. Finally, three of these ECM-mimetics promote the neurite outgrowth of PC-12 cells. The evidence presented here demonstrates the potential of ELPs to deposit ECM-mimetics with applications in regenerative medicine, cell therapy, and tissue engineering.
Subject(s)
Cell Adhesion , Elastin , Laminin , Laminin/chemistry , Laminin/pharmacology , Elastin/chemistry , Animals , Rats , PC12 Cells , Cell Adhesion/drug effects , Extracellular Matrix/metabolism , Extracellular Matrix/chemistry , Peptides/chemistry , Peptides/pharmacology , Elastin-Like PolypeptidesABSTRACT
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.
Subject(s)
Neoplasms , Precision Medicine , Humans , Precision Medicine/methods , Neoplasms/radiotherapy , Artificial Intelligence , Phenotype , Radiotherapy DosageABSTRACT
Neuroblastoma is a leading cause of death in childhood cancer cases. Unlike adult malignancies, which typically develop from aged cells through accumulated damage and mutagenesis, neuroblastoma originates from neural crest cells with disrupted differentiation. This distinct feature provides novel therapeutic opportunities beyond conventional cytotoxic methods. Previously, we reported that the mitochondrial uncoupler NEN (niclosamide ethanolamine) activated mitochondria respiration to reprogram the epigenome, promoting neuronal differentiation. In the current study, we further combine NEN with retinoic acid (RA) to promote neural differentiation both in vitro and in vivo. The treatment increased the expression of RA signaling and neuron differentiation-related genes, resulting in a global shift in the transcriptome towards a more favorable prognosis. Overall, these results suggest that the combination of a mitochondrial uncoupler and the differentiation agent RA is a promising therapeutic strategy for neuroblastoma.
ABSTRACT
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.
ABSTRACT
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.
Subject(s)
COVID-19 Drug Treatment , SARS-CoV-2 , Amides , Artificial Intelligence , Auranofin , Guanosine Monophosphate/analogs & derivatives , Humans , Phosphoramides , PyrazinesABSTRACT
Background/Aims: Constipation can be a chronic condition that impacts daily functioning and quality of life (QoL). To aid healthcare providers in accurately assessing patient symptoms and treatment outcomes, patient-related outcome measures (PROMs) have been increasingly adopted in clinical settings. This review aims to (1) evaluate the methodological quality and measurement properties of constipation-related PROMs, using the COnsensus-based Standards for the selection of health Measurement INtruments (COSMIN) criteria; and (2) assess the modes of digital dissemination of constipation-related PROMs. Methods: PubMed, Embase, and PsycINFO databases were searched and 11 011 records ranging from 1989 to 2020 were screened by 2 independent reviewers. A total of 26 studies (23 PROMs; 18 measuring symptom-related items and 5 measuring constipation-related QoL items) were identified for the review and assessed. Results: There were multiple variations between PROMs, including subtypes of constipation, methods of administration, length of PROM and recall period. While no PROM met all the COSMIN quality standards for development and measurement properties, 5 constipation-related PROMs received at least 4 (out of 7) sufficient ratings. Only 2 PROMs were developed in Asia. Five PROMs were administered through digital methods during the validation process but methods of adapting the PROMs into digital formats were not reported. Conclusions: The constipation-related PROMs identified in this review present varying quality of development and validation, with an overall need for improvement. Further considerations should be given towards more consistent methodology and reporting of PROM development, increase in culturally-specific PROMs, and better reporting of protocol for the digitisation of PROMs.
ABSTRACT
IDentif.AI-x, a clinically actionable artificial intelligence platform, was used to rapidly pinpoint and prioritize optimal combination therapies against COVID-19 by pairing a prospective, experimental validation of multi-drug efficacy on a SARS-CoV-2 live virus and Vero E6 assay with a quadratic optimization workflow. A starting pool of 12 candidate drugs developed in collaboration with a community of infectious disease clinicians was first narrowed down to a six-drug pool and then interrogated in 50 combination regimens at three dosing levels per drug, representing 729 possible combinations. IDentif.AI-x revealed EIDD-1931 to be a strong candidate upon which multiple drug combinations can be derived, and pinpointed a number of clinically actionable drug interactions, which were further reconfirmed in SARS-CoV-2 variants B.1.351 (Beta) and B.1.617.2 (Delta). IDentif.AI-x prioritized promising drug combinations for clinical translation and can be immediately adjusted and re-executed with a new pool of promising therapies in an actionable path towards rapidly optimizing combination therapy following pandemic emergence.
ABSTRACT
The emergence of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) led to multiple drug repurposing clinical trials that have yielded largely uncertain outcomes. To overcome this challenge, we used IDentif.AI, a platform that pairs experimental validation with artificial intelligence (AI) and digital drug development to rapidly pinpoint unpredictable drug interactions and optimize infectious disease combination therapy design with clinically relevant dosages. IDentif.AI was paired with a 12-drug candidate therapy set representing over 530,000 drug combinations against the SARS-CoV-2 live virus collected from a patient sample. IDentif.AI pinpointed the optimal combination as remdesivir, ritonavir, and lopinavir, which was experimentally validated to mediate a 6.5-fold enhanced efficacy over remdesivir alone. Additionally, it showed hydroxychloroquine and azithromycin to be relatively ineffective. The study was completed within 2 weeks, with a three-order of magnitude reduction in the number of tests needed. IDentif.AI independently mirrored clinical trial outcomes to date without any data from these trials. The robustness of this digital drug development approach paired with in vitro experimentation and AI-driven optimization suggests that IDentif.AI may be clinically actionable toward current and future outbreaks.
ABSTRACT
Caveolae are membrane organelles formed by submicron invaginations in the plasma membrane, and are involved in mechanosensing, cell signaling, and endocytosis. Although implicated broadly in physiology and pathophysiology, better tools are required to elucidate the precise role of caveolar processes through selective activation and inactivation of their trafficking. Our group recently reported that thermally-responsive elastin-like polypeptides (ELPs) can trigger formation of 'genetically engineered protein microdomains (GEPMs)' functionalized with either Clathrin-light chain or the epidermal growth factor receptor. This manuscript is the first report of this strategy to modulate caveolin-1 (CAV1). By attaching different ELP sequences to CAV1, mild heating can be used to self-assemble CAV1-ELP microdomains inside of cells. The temperature of self-assembly can be controlled by tuning the ELP sequence. The formation of CAV1-ELP microdomains internalizes Cholera Toxin Subunit B, a commonly used marker of caveolae mediated endocytosis. CAV1-ELPs also colocalize with Cavin 1, an essential component of functional caveolae biogenesis. With the emerging significance of caveolae in health and disease and the lack of specific probes to rapidly and reversibly affect caveolar function, CAV1-ELP microdomains are a new tool to rapidly probe caveolae associated processes in endocytosis, cell signaling, and mechanosensing.