Optimizing Combination Therapy for Acute Lymphoblastic Leukemia Using a Phenotypic Personalized Medicine Digital Health Platform: Retrospective Optimization Individualizes Patient Regimens to Maximize Efficacy and Safety

Machine Learning Methods for Precision Dosing in Anticancer Drug Therapy: A Scoping Review

INTRODUCTION

In the last decade, various Machine Learning techniques have been proposed aiming to individualise the dose of anticancer drugs mostly based on a presumed drug effect or measured effect biomarkers. The aim of this scoping review was to comprehensively summarise the research status on the use of Machine Learning for precision dosing in anticancer drug therapy.

METHODS

This scoping review was conducted in accordance with the interim guidance by Cochrane and the Joanna Briggs Institute. We systematically searched the databases Medline (via PubMed), Embase and the Cochrane Library for research articles and reviews including results published after 2016. Results were reported according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews (PRISMA-ScR) checklist.

RESULTS

A total of 17 relevant studies was identified. In 12 of the included studies, Reinforcement Learning methods were used, including Classical, Deep, Double Deep and Conservative Q-Learning and Fuzzy Reinforcement Learning. Furthermore, classical Machine Learning methods were compared in terms of their performance and an artificial intelligence platform based on parabolic equations was used to guide dosing prospectively and retrospectively, albeit only in a limited number of patients. Due to the significantly different algorithm structures, a meaningful comparison between the various Machine Learning approaches was not possible.

CONCLUSION

Overall, this review emphasises the clinical relevance of Machine Learning methods for anticancer drug dose optimisation, as many algorithms have shown promising results enabling model-free predictions with the potential to maximise efficacy and minimise toxicity when compared to standard protocols.

Personalized dose selection for the first Waldenström macroglobulinemia patient on the PRECISE CURATE.AI trial

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.

Nutritional Status as a Risk Factor for Doxorubicin Cardiotoxicity in Mexican Children with Acute Lymphoblastic Leukemia

Acute lymphoblastic leukemia (ALL) is the most common childhood cancer in the world. Doxorubicin (Dox) is a very useful drug in these patients, however, one of the main adverse effects caused by the use of Dox is cardiotoxicity (CT). Protein-calorie malnutrition (PCM) is a factor that, among others, can influence the development of CT due to Dox. The aim of our study was to associate PCM as a risk factor for CT induced by Dox in Mexican children with ALL. We included 89 children with ALL who were treated with Dox, from October 2018 to July 2023, and of whom 14 developed some type of CT, 15 were underweight and 3 were overweight. The analysis of the association risk of CT due to PCM shows a statistically significant association of risk of developing CT due to PCM. On the other hand, healthy weight was associated with protection for developing CT due to Dox use. Of the total number of girls who presented CT, all had systolic dysfunction, while 6 of them also had diastolic dysfunction. On the other hand, of the total number of boys who presented CT, all of them had systolic dysfunction and only one of them also had diastolic dysfunction. These results show that in patients in which Dox is being administered, special attention is suggested for girls with PCM, since systolic failure is a precursor and occurs before diastolic failure in girls with PCM.

N-of-1 medicine

ABSTRACT

The fields of precision and personalised medicine have led to promising advances in tailoring treatment to individual patients. Examples include genome/molecular alteration-guided drug selection, single-patient gene therapy design and synergy-based drug combination development, and these approaches can yield substantially diverse recommendations. Therefore, it is important to define each domain and delineate their commonalities and differences in an effort to develop novel clinical trial designs, streamline workflow development, rethink regulatory considerations, create value in healthcare and economics assessments, and other factors. These and other segments are essential to recognise the diversity within these domains to accelerate their respective workflows towards practice-changing healthcare. To emphasise these points, this article elaborates on the concept of digital health and digital medicine-enabled N-of-1 medicine, which individualises combination regimen and dosing using a patient's own data. We will conclude with recommendations for consideration when developing novel workflows based on emerging digital-based platforms.

CURATE.AI COR-Tx platform as a digital therapy and digital diagnostic for cognitive function in patients with brain tumour postradiotherapy treatment: protocol for a prospective mixed-methods feasibility clinical trial

INTRODUCTION

Conventional interventional modalities for preserving or improving cognitive function in patients with brain tumour undergoing radiotherapy usually involve pharmacological and/or cognitive rehabilitation therapy administered at fixed doses or intensities, often resulting in suboptimal or no response, due to the dynamically evolving patient state over the course of disease. The personalisation of interventions may result in more effective results for this population. We have developed the CURATE.AI COR-Tx platform, which combines a previously validated, artificial intelligence-derived personalised dosing technology with digital cognitive training.

METHODS AND ANALYSIS

This is a prospective, single-centre, single-arm, mixed-methods feasibility clinical trial with the primary objective of testing the feasibility of the CURATE.AI COR-Tx platform intervention as both a digital intervention and digital diagnostic for cognitive function. Fifteen patient participants diagnosed with a brain tumour requiring radiotherapy will be recruited. Participants will undergo a remote, home-based 10-week personalised digital intervention using the CURATE.AI COR-Tx platform three times a week. Cognitive function will be assessed via a combined non-digital cognitive evaluation and a digital diagnostic session at five time points: preradiotherapy, preintervention and postintervention and 16-weeks and 32-weeks postintervention. Feasibility outcomes relating to acceptability, demand, implementation, practicality and limited efficacy testing as well as usability and user experience will be assessed at the end of the intervention through semistructured patient interviews and a study team focus group discussion at study completion. All outcomes will be analysed quantitatively and qualitatively.

ETHICS AND DISSEMINATION

This study has been approved by the National Healthcare Group (NHG) DSRB (DSRB2020/00249). We will report our findings at scientific conferences and/or in peer-reviewed journals.

TRIAL REGISTRATION NUMBER

NCT04848935.

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.

Genetic variants of genes involved in thiopurine metabolism pathway are associated with 6-mercaptopurine toxicity in pediatric acute lymphoblastic leukemia patients from Ethiopia

Introduction: Genetic variation in the thiopurine S-methyltransferase (TPMT) gene by and large predicts variability in 6-mercaptopurine (6-MP) related toxicities. However, some individuals without genetic variants in TPMT still develop toxicity that necessitates 6-MP dose reduction or interruption. Genetic variants of other genes in the thiopurine pathway have been linked to 6-MP related toxicities previously. Objective: The aim of this study was to evaluate the effect of genetic variants in ITPA, TPMT, NUDT15, XDH, and ABCB1 on 6-MP related toxicities in patients with acute lymphoblastic leukemia (ALL) from Ethiopia. Methods: Genotyping of ITPA, and XDH was performed using KASP genotyping assay, while that of TPMT, NUDT15, and ABCB1 with TaqMan^® SNP genotyping assays. Clinical profile of the patients was collected for the first 6 months of the maintenance phase treatment. The primary outcome was the incidence of grade 4 neutropenia. Bivariable followed by multivariable cox regression analysis was performed to identify genetic variants associated with the development of grade 4 neutropenia within the first 6 months of maintenance treatment. Results: In this study, genetic variants in XDH and ITPA were associated with 6-MP related grade 4 neutropenia and neutropenic fever, respectively. Multivariable analysis revealed that patients who are homozygous (CC) for XDH rs2281547 were 2.956 times (AHR 2.956, 95% CI = 1.494-5.849, p = 0.002) more likely to develop grade 4 neutropenia than those with the TT genotype. Conclusion: In conclusion, in this cohort, XDH rs2281547 was identified as a genetic risk factor for grade 4 hematologic toxicities in ALL patients treated with 6-MP. Genetic polymorphisms in enzymes other than TPMT involved in the 6-mercaptopurine pathway should be considered during its use to avoid hematological toxicity.

Artificial intelligence aids in development of nanomedicines for cancer management

Over the last decade, the nanomedicine has experienced unprecedented development in diagnosis and management of diseases. A number of nanomedicines have been approved in clinical use, which has demonstrated the potential value of clinical transition of nanotechnology-modified medicines from bench to bedside. The application of artificial intelligence (AI) in development of nanotechnology-based products could transform the healthcare sector by realizing acquisition and analysis of large datasets, and tailoring precision nanomedicines for cancer management. AI-enabled nanotechnology could improve the accuracy of molecular profiling and early diagnosis of patients, and optimize the design pipeline of nanomedicines by tuning the properties of nanomedicines, achieving effective drug synergy, and decreasing the nanotoxicity, thereby, enhancing the targetability, personalized dosing and treatment potency of nanomedicines. Herein, the advances in AI-enabled nanomedicines in cancer management are elaborated and their application in diagnosis, monitoring and therapy as well in precision medicine development is discussed.

Putting the "mi" in omics: discovering miRNA biomarkers for pediatric precision care

In the past decade, growing interest in micro-ribonucleic acids (miRNAs) has catapulted these small, non-coding nucleic acids to the forefront of biomarker research. Advances in scientific knowledge have made it clear that miRNAs play a vital role in regulating cellular physiology throughout the human body. Perturbations in miRNA signaling have also been described in a variety of pediatric conditions-from cancer, to renal failure, to traumatic brain injury. Likewise, the number of studies across pediatric disciplines that pair patient miRNA-omics with longitudinal clinical data are growing. Analyses of these voluminous, multivariate data sets require understanding of pediatric phenotypic data, data science, and genomics. Use of machine learning techniques to aid in biomarker detection have helped decipher background noise from biologically meaningful changes in the data. Further, emerging research suggests that miRNAs may have potential as therapeutic targets for pediatric precision care. Here, we review current miRNA biomarkers of pediatric diseases and studies that have combined machine learning techniques, miRNA-omics, and patient health data to identify novel biomarkers and potential therapeutics for pediatric diseases. IMPACT: In the following review article, we summarized how recent developments in microRNA research may be coupled with machine learning techniques to advance pediatric precision care.

Combinational treatment of TPEN and TPGS induces apoptosis in acute lymphoblastic and chronic myeloid leukemia cells in vitro and ex vivo

TPEN and TPGS have recently shown selective cytotoxic effects in vitro and ex vivo leukemia cells. In this study, we aimed to test the synergistic effect of combined TPEN and TPGS agents (thereafter, T2 combo) on Jurkat (clone-E61), K562, Ba/F3, and non-leukemia peripheral blood lymphocytes (PBL). The ED50 doses (i.e., TPEN ED50: 3.2 μM and TPGS ED50: 34 μM, potency ratio R = 10.62 = TPGS (ED50)/TPEN (ED50)) were identified as dose-effect curve (%DNA fragmentation (sub-G₁ phase) versus agent concentration). The most effective synergistic doses were determined according to isobole analysis. The apoptotic and oxidative stress effects of combined doses (TPEN 0.1, 0.5, 1 μM) and TPGS (5, 10, 20 μM)) were evaluated by DNA fragmentation (sub-G₁ phase), mitochondrial membrane potential, oxidation of stress sensor protein DJ-1, and activation of executer protein CASPASE-3. They testified to the synergistic effect of the T2 combo (e.g., TPEN 1: TPGS 20, combination index (CI) 0.90 < 1; 1/3.2+ 20/34, > 90% induced apoptosis) in all 3 cell lines. As proof of principle, we challenged complete bone marrow (n = 5) or isolated cells from bone marrow (n = 3) samples from acute pediatric acute B-cell patients and found that T2 combo (1:20; 10:200) dramatically reduced (- 50%) the CD34+/CD19+cell population and increased significantly CD19+/CASP-3+ positive B-ALL cells up to 960%. The T2 combo neither induced DNA fragmentation, altered ΔΨm, nor induced oxidation of stress sensor protein DJ-1, nor activated CASP-3 in PBL cells. We conclude that by using different combinations of TPEN and TPGS, a more efficient treatment strategy can be developed for leukemia patients.

Improving the therapeutic ratio of radiotherapy against radioresistant cancers: Leveraging on novel artificial intelligence-based approaches for drug combination discovery

Despite numerous advances in cancer radiotherapy, tumor radioresistance remain one of the major challenges limiting treatment efficacy of radiotherapy. Conventional strategies to overcome radioresistance involve understanding the underpinning molecular mechanisms, and subsequently using combinatorial treatment strategies involving radiation and targeted drug combinations against these radioresistant tumors. These strategies exploit and target the molecular fingerprint and vulnerability of the radioresistant clones to achieve improved efficacy in tumor eradication. However, conventional drug-screening approaches for the discovery of new drug combinations have been proven to be inefficient, limited and laborious. With the increasing availability of computational resources in recent years, novel approaches such as Quadratic Phenotypic Optimization Platform (QPOP), CURATE.AI and Drug Combination and Prediction and Testing (DCPT) platform have emerged to aid in drug combination discovery and the longitudinally optimized modulation of combination therapy dosing. These platforms could overcome the limitations of conventional screening approaches, thereby facilitating the discovery of more optimal drug combinations to improve the therapeutic ratio of combinatorial treatment. The use of better and more accurate models and methods with rapid turnover can thus facilitate a rapid translation in the clinic, hence, resulting in a better patient outcome. Here, we reviewed the clinical observations, molecular mechanisms and proposed treatment strategies for tumor radioresistance and discussed how novel approaches may be applied to enhance drug combination discovery, with the aim to further improve the therapeutic ratio and treatment efficacy of radiotherapy against radioresistant cancers.

Enabling Technologies for Personalized and Precision Medicine

Individualizing patient treatment is a core objective of the medical field. Reaching this objective has been elusive owing to the complex set of factors contributing to both disease and health; many factors, from genes to proteins, remain unknown in their role in human physiology. Accurately diagnosing, monitoring, and treating disorders requires advances in biomarker discovery, the subsequent development of accurate signatures that correspond with dynamic disease states, as well as therapeutic interventions that can be continuously optimized and modulated for dose and drug selection. This work highlights key breakthroughs in the development of enabling technologies that further the goal of personalized and precision medicine, and remaining challenges that, when addressed, may forge unprecedented capabilities in realizing truly individualized patient care.

Artificial Intelligence and Digital Microscopy Applications in Diagnostic Hematopathology

Digital Pathology is the process of converting histology glass slides to digital images using sophisticated computerized technology to facilitate acquisition, evaluation, storage, and portability of histologic information. By its nature, digitization of analog histology data renders it amenable to analysis using deep learning/artificial intelligence (DL/AI) techniques. The application of DL/AI to digital pathology data holds promise, even if the scope of use cases and regulatory framework for deploying such applications in the clinical environment remains in the early stages. Recent studies using whole-slide images and DL/AI to detect histologic abnormalities in general and cancer in particular have shown encouraging results. In this review, we focus on these emerging technologies intended for use in diagnostic hematology and the evaluation of lymphoproliferative diseases.

CURATE.AI: Optimizing Personalized Medicine with Artificial Intelligence

The clinical team attending to a patient upon a diagnosis is faced with two main questions: what treatment, and at what dose? Clinical trials' results provide the basis for guidance and support for official protocols that clinicians use to base their decisions upon. However, individuals rarely demonstrate the reported response from relevant clinical trials, often the average from a group representing a population or subpopulation. The decision complexity increases with combination treatments where drugs administered together can interact with each other, which is often the case. Additionally, the individual's response to the treatment varies over time with the changes in his or her condition, whether via the indication or physiology. In practice, the drug and the dose selection depend greatly on the medical protocol of the healthcare provider and the medical team's experience. As such, the results are inherently varied and often suboptimal. Big data approaches have emerged as an excellent decision-making support tool, but their application is limited by multiple challenges, the main one being the availability of sufficiently big datasets with good quality, representative information. An alternative approach-phenotypic personalized medicine (PPM)-finds an appropriate drug combination (quadratic phenotypic optimization platform [QPOP]) and an appropriate dosing strategy over time (CURATE.AI) based on small data collected exclusively from the treated individual. PPM-based approaches have demonstrated superior results over the current standard of care. The side effects are limited while the desired output is maximized, which directly translates into improving the length and quality of individuals' lives.

AI‐Enabled Parabolic Response Surface Approach Identifies Ultra Short‐Course Near‐Universal TB Drug Regimens

Tuberculosis (TB) is a major health problem that causes more deaths worldwide than any other single infectious disease. Current multidrug therapy for tuberculosis is exceedingly lengthy, leading to poor drug adherence, and consequently the emergence of drug resistance. Hence, much more rapid treatments are needed. Experimentally identifying the most synergistic drug combinations among available drugs is complicated by the astronomical number of possible drug-dose combinations. This problem is dealt with by the use of an artificial-intelligence-enabled parabolic response surface platform in conjunction with an in vitro Mycobacterium tuberculosis–infected macrophage cell culture assay amenable to high-throughput screening. This strategy allows rapid identification of the most effective drug-dose combinations by testing only a small fraction of the total drug-dose efficacy response surface. The same platform is then used to optimize the in vivo doses of each drug in the most potent regimens. Thus, regimens are identified that are dramatically more effective than the Standard Regimen in treating TB in a mouse model—a model broadly predictive of drug efficacy in humans. The most effective regimens reported herein shorten the duration of treatment required to achieve relapse-free cure by 80% and are suitable for treating both drug-sensitive and most drug-resistant cases of tuberculosis.

Artificial intelligence in nanomedicine

The field of nanomedicine has made substantial strides in the areas of therapeutic and diagnostic development. For example, nanoparticle-modified drug compounds and imaging agents have resulted in markedly enhanced treatment outcomes and contrast efficiency. In recent years, investigational nanomedicine platforms have also been taken into the clinic, with regulatory approval for Abraxane® and other products being awarded. As the nanomedicine field has continued to evolve, multifunctional approaches have been explored to simultaneously integrate therapeutic and diagnostic agents onto a single particle, or deliver multiple nanomedicine-functionalized therapies in unison. Similar to the objectives of conventional combination therapy, these strategies may further improve treatment outcomes through targeted, multi-agent delivery that preserves drug synergy. Also, similar to conventional/unmodified combination therapy, nanomedicine-based drug delivery is often explored at fixed doses. A persistent challenge in all forms of drug administration is that drug synergy is time-dependent, dose-dependent and patient-specific at any given point of treatment. To overcome this challenge, the evolution towards nanomedicine-mediated co-delivery of multiple therapies has made the potential of interfacing artificial intelligence (AI) with nanomedicine to sustain optimization in combinatorial nanotherapy a reality. Specifically, optimizing drug and dose parameters in combinatorial nanomedicine administration is a specific area where AI can actionably realize the full potential of nanomedicine. To this end, this review will examine the role that AI can have in substantially improving nanomedicine-based treatment outcomes, particularly in the context of combination nanotherapy for both N-of-1 and population-optimized treatment.

Theranostic Nanoparticles for Tracking and Monitoring Disease State

The development of novel nanoparticles consisting of both diagnostic and therapeutic components has increased over the past decade. These "theranostic" nanoparticles have been tailored toward one or more types of imaging modalities and have been developed for optical imaging, magnetic resonance imaging, ultrasound, computed tomography, and nuclear imaging comprising both single-photon computed tomography and positron emission tomography. In this review, we focus on state-of-the-art theranostic nanoparticles that are capable of both delivering therapy and self-reporting/tracking disease through imaging. We discuss challenges and the opportunity to rapidly adjust treatment for individualized medicine.

Stimuli-Responsive Nanodiamond-Based Biosensor for Enhanced Metastatic Tumor Site Detection

Metastasis is often critical to cancer progression and linked to poor survival and drug resistance. Early detection of metastasis, as well as identification of metastatic tumor sites, can improve cancer patient survival. Thus, developing technology to improve the detection of cancer metastasis biomarkers can improve both diagnosis and treatment. In this study, we investigated the use of nanodiamonds to develop a stimuli-responsive metastasis detection complex that utilizes matrix metalloproteinase 9 (MMP9) as a metastasis biomarker, as MMP9 increased expression has been shown to be indicative of metastasis. The nanodiamond-MMP9 biosensor complex consists of nanodiamonds functionalized with MMP9-specific fluorescent-labeled substrate peptides. Using this design, protease activity of MMP9 can be accurately measured and correlated to MMP9 expression. The nanodiamond-MMP9 biosensor also demonstrated an enhanced ability to protect the base sensor peptide from nonspecific serum protease cleavage. This enhanced peptide stability, combined with a quantitative stimuli-responsive output function, provides strong evidence for the further development of a nanodiamond-MMP9 biosensor for metastasis site detection. More importantly, this work provides the foundation for use of nanodiamonds as a platform for stimuli-responsive biosensors and theranostic complexes that can be implemented across a wide range of biomedical applications.

Two new species of the genus Mecyclothorax Sharp from New Guinea (Coleoptera: Carabidae: Psydrinae)

Chronic diseases typically require long-term management through healthy lifestyle practices and pharmacological intervention. Although efficacious treatments exist, disease control is often sub-optimal leading to chronic disease-related sequela. Poor disease control can partially be explained by the ‘one size fits all’ pharmacological approach. Precision medicine aims to tailor treatments to the individual. CURATE.AI is a dosing optimisation platform that considers individual factors to improve the precision of drug therapies. CURATE.AI has been validated in other therapeutic areas, such as cancer, but has yet to be applied in chronic disease care. We will evaluate the CURATE.AI system through a single-arm feasibility study (n = 20 hypertensives and n = 20 type II diabetics). Dosing decisions will be based on CURATE.AI recommendations. We will prospectively collect clinical and qualitative data and report on the clinical effect, implementation challenges, and acceptability of using CURATE.AI. In addition, we will explore how to enhance the algorithm further using retrospective patient data. For example, the inclusion of other variables, the simultaneous optimisation of multiple drugs, and the incorporation of other artificial intelligence algorithms. Overall, this project aims to understand the feasibility of using CURATE.AI in clinical practice. Barriers and enablers to CURATE.AI will be identified to inform the system’s future development.