Dose Adaptation Research Articles

Precision Dosing in Presence of Multiobjective Therapies by Integrating Reinforcement Learning and PK-PD Models: Application to Givinostat Treatment of Polycythemia Vera.

Precision dosing aims to optimize and customize pharmacological treatment at the individual level. The integration of pharmacometric models with Reinforcement Learning (RL) algorithms is currently under investigation to support the personalization of adaptive dosing therapies. In this study, this hybrid technique is applied to the real multiobjective precision dosing problem of givinostat treatment in polycythemia vera (PV) patients. PV is a chronic myeloproliferative disease with an overproduction of platelets (PLT), white blood cells (WBC), and hematocrit (HCT). The therapeutic goal is to simultaneously normalize the levels of these efficacy/safety biomarkers, thus inducing a complete hematological response (CHR). An RL algorithm, Q-Learning (QL), was integrated with a PK-PD model describing the givinostat effect on PLT, WBC, and HCT to derive both an adaptive dosing protocol (QLpop-agent) for the whole population and personalized dosing strategies by coupling a specific QL-agent to each patient (QLind-agents). QLpop-agent learned a general adaptive dosing protocol that achieved a similar CHR rate (77% vs. 83%) when compared to the actual givinostat clinical protocol on 10 simulated populations. Treatment efficacy and safety increased with a deeper dosing personalization by QLind-agents. These QL-based patient-specific adaptive dosing rules outperformed both the clinical protocol and QLpop-agent by reaching the CHR in 93% of the test patients and completely avoided severe toxicities during the whole treatment period. These results confirm that RL and PK-PD models can be valid tools for supporting adaptive dosing strategies as interesting performances were achieved in both learning a general set of rules and in customizing treatment for each patient.

The Reference-Corrected Visual Predictive Check: A More Intuitive Diagnostic for Non-Linear Mixed Effects Models

The prediction-corrected visual predictive check (pcVPC) is an informative model diagnostic that can offer advantages over the standard visual predictive check (VPC) when heterogenous study designs and adaptive dosing are used. However, a drawback with these plots is that prediction correction often results in y-axis values and trends that are unintuitive, difficult to explain, and challenging to communicate even among experts. The reference-corrected visual predictive check (rcVPC) offers a solution to these problems by leveraging a user-defined set of independent variables, for a more intuitive model diagnostic and an efficient communication of results to a wider audience. The rcVPC methodology is based on the definition of a reference dataset. Simulations are conducted with this reference dataset and the observed dataset, and then the simulated and the observed dependent variables are normalized by the population prediction for the user-defined independent variables in the reference dataset. The opportunity to manipulate time in the reference dataset is a unique feature that gives rcVPC the ability to visually characterize exposure–response relationships with delayed effect onset. The rcVPC approach was compared to pcVPCs and traditional VPCs for a range of examples inspired by real data. The rcVPC methodology was demonstrated to offer a more intuitive interpretation and more effective guidance to model development in a way that is not possible for VPC or pcVPC plots.

Abstract 4362: Body mass index influences imatinib exposure in CML patients: Evidence fromTDM with adaptive dosing in real-world patients

Abstract Imatinib remains a mainstay of treatment for elderly or frail patients with chronic myeloid leukaemia (CML). Trough levels of around 1000 ng/mL are associated with a major molecular response with acceptable tolerability. We present data from 60 adult CML patients treated with imatinib on therapeutic drug monitoring (TDM) and adaptive dosing. Mean trough levels after treatment initiation were 994.2 ±560.6 ng/mL and a large inter-patient variability was observed (CV: 56%). Only 29% of patients were in the therapeutic range. All parameters associated with corpulence (i.e. body weight, height, body surface area, body mass index (BMI)) and age were significantly associated with imatinib plasma levels on univariate analysis. Age and BMI remained the only parameters associated with trough levels on multivariate analysis. As severe toxicities have been previously reported in patients with low BMI treated with standard imatinib, we evaluated the extent to which low BMI may lead to plasma overexposure. We found a statistically significant difference in trough imatinib levels in patients with BMI<18.5, with exposure +61.5% higher than in patients with 18.5<BMI<24.9 and +76.3% higher than in patients with BMI>24.9 (p<0.05, ANOVA). After TDM with adaptive dosing, a statistically significant difference in dosing between patients was observed, with doses ranging from 200 to 700 mg (p<0.001, ANOVA). No difference in toxicity or efficacy was observed regardless of BMI after adaptive dosing (p>0.05, Chi-2 test). Our data suggest that low BMI has a significant impact on imatinib exposure, but that pharmacokinetically-guided dosing limits its clinical impact in patients. Citation Format: Paul Maroselli, Raphaelle Fanciullino, Julien Colle, Laure Farnault, Pauline Roche, Geoffroy Venton, Regis Costello, Joseph Ciccolini. Body mass index influences imatinib exposure in CML patients: Evidence fromTDM with adaptive dosing in real-world patients [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2025; Part 1 (Regular Abstracts); 2025 Apr 25-30; Chicago, IL. Philadelphia (PA): AACR; Cancer Res 2025;85(8_Suppl_1):Abstract nr 4362.

Time Adjustment of Hydrocortisone Doses During Shift Work in Patients with Adrenal Insufficiency.

Shift work causes a disruption between the circadian system and the external light-dark cycle, but also a misalignment between various levels of the circadian system. There is no information on patients with adrenal insufficiency (AI) who are working shifts. The objective of the study was to analyze the hormone replacement therapy with hydrocortisone (HC) and the adaptation scheme in patients with AI on shifts. Patients working on shifts (n=15) from two German endocrine centers received a questionnaire regarding their therapy scheme, dose adaptations, working shifts, dose adaptations during working shifts, and occurrence of adrenal crisis. We observed that 20% of patients stated that they experience difficulties taking glucocorticoid replacement on time, 40% of patients reported these difficulties to occur only occasionally. Consequently, nearly half of the patients had forgotten to take their replacement therapy at some point. More than 50% of patients reported an adrenal crisis during the last two years. The timely adaptation of HC or of modified-release HC during shifts was very inhomogeneous. In conclusion, the adaptation schemes for HC dosing during shift work are currently not evidence-based but opinion-driven. Our findings highlight the need for further investigations of shift workers with AI.

Pharmacokinetic novelties of isavuconazole. Use in special situations.

Pharmacokinetic novelties of isavuconazole. Use in special situations.

Reducing Number of Treatment Fractions for Patients With Abdominal Lymph Node Oligometastases: The Need for Online Adaptive Radiation Therapy to Provide Personalized Adaptive Fractionation.

Reducing Number of Treatment Fractions for Patients With Abdominal Lymph Node Oligometastases: The Need for Online Adaptive Radiation Therapy to Provide Personalized Adaptive Fractionation.

A Comprehensive CYP2D6 Drug-Drug-Gene Interaction Network for Application in Precision Dosing and Drug Development.

Conducting clinical studies on drug-drug-gene interactions (DDGIs) and extrapolating the findings into clinical dose recommendations is challenging due to the high complexity of these interactions. Here, physiologically-based pharmacokinetic (PBPK) modeling networks present a new avenue for exploring such complex scenarios, potentially informing clinical guidelines and handling patient-specific DDGIs at the bedside. Moreover, they provide an established framework for drug-drug interaction (DDI) submissions to regulatory agencies. The cytochrome P450 (CYP) 2D6 enzyme is particularly prone to DDGIs due to the high prevalence of genetic variation and common use of CYP2D6 inhibiting drugs. In this study, we present a comprehensive PBPK network covering CYP2D6 drug-gene interactions (DGIs), DDIs, and DDGIs. The network covers sensitive and moderate sensitive substrates, and strong and weak inhibitors of CYP2D6 according to the United States Food and Drug Administration (FDA) guidance. For the analyzed CYP2D6 substrates and inhibitors, DD(G)Is mediated by CYP3A4 and P-glycoprotein were included. Overall, the network comprises 23 compounds and was developed based on 30 DGI, 45 DDI, and seven DDGI studies, covering 32 unique drug combinations. Good predictive performance was demonstrated for all interaction types, as reflected in mean geometric mean fold errors of 1.40, 1.38, and 1.56 for the DD(G)I area under the curve ratios as well as 1.29, 1.43, and 1.60 for DD(G)I maximum plasma concentration ratios. Finally, the presented network was utilized to calculate dose adaptations for CYP2D6 substrates atomoxetine (sensitive) and metoprolol (moderate sensitive) for clinically untested DDGI scenarios, showcasing a potential clinical application of DDGI model networks in the field of model-informed precision dosing.

Patient- and fraction-specific magnetic resonance volume reconstruction from orthogonal images with generative adversarial networks.

Although deep learning (DL) methods for reconstructing 3D magnetic resonance (MR) volumes from 2D MR images yield promising results, they require large amounts of training data to perform effectively. To overcome this challenge, fine-tuning-a transfer learning technique particularly effective for small datasets-presents a robust solution for developing personalized DL models. A 2D to 3D conditional generative adversarial network (GAN) model with a patient- and fraction-specific fine-tuning workflow was developed to reconstruct synthetic 3D MR volumes using orthogonal 2D MR images for online dose adaptation. A total of 2473 3D MR volumes were collected from 43 patients. The training and test datasets were separated into 34 and 9 patients, respectively. All patients underwent MR-guided adaptive radiotherapy using the same imaging protocol. The population data contained 2047 3D MR volumes from the training dataset. Population data were used to train the population-based GAN model. For each fraction of the remaining patients, the population model was fine-tuned with the 3D MR volumes acquired before beam irradiation of the fraction, named the fine-tuned model. The performance of the fine-tuned model was tested using the 3D MR volume acquired immediately after the beam delivery of the fraction. The model's input was a pair of axial and sagittal MR images at the isocenter level, and the output was a 3D MR volume. Model performance was evaluated using the structural similarity index measure (SSIM), peak signal-to-noise ratio (PSNR), root mean square error (RMSE), and mean absolute error (MAE). Moreover, the prostate, bladder, and rectum in the predicted MR images were manually segmented. To assess geometric accuracy, the 2D Dice Similarity Coefficient (DSC) and 2D Hausdorff Distance (HD) were calculated. A total of 84 3D MR volumes were included in the performance testing. The mean±standard deviation (SD) of SSIM, PSNR, RMSE, and MAE were 0.64±0.10, 93.9±1.5dB, 0.050±0.009, and 0.036±0.007 for the population model and 0.72±0.09, 96.2±1.8dB, 0.041±0.007, and 0.028±0.006 for the fine-tuned model, respectively. The image quality of the fine-tuned model was significantly better than that of the population model (p<0.05). The mean±SD of DSC and HD of the population model were 0.79±0.08 and 1.70±2.35mm for prostate, 0.81±0.10 and 2.75±1.53mm for bladder, and 0.72±0.08 and 1.93±0.59mm for rectum. Contrarily, the mean±SD of DSC and HD of the fine-tuned model were 0.83±0.06 and 1.29±0.77mm for prostate, 0.85±0.07 and 2.16±1.09mm for bladder, and 0.77±0.08 and 1.57±0.52mm for rectum. The geometric accuracy of the fine-tuned model was significantly improved than that of the population model (p<0.05). By employing a patient- and fraction-specific fine-tuning approach, the GAN model demonstrated promising accuracy despite limited data availability.

A safe-enhanced fully closed-loop artificial pancreas controller based on deep reinforcement learning.

Patients with type 1 diabetes and their physicians have long desired a fully closed-loop artificial pancreas (AP) system that can alleviate the burden of blood glucose regulation. Although deep reinforcement learning (DRL) methods theoretically enable adaptive insulin dosing control, they face numerous challenges, including safety and training efficiency, which have hindered their clinical application. This paper proposes a safe and efficient adaptive insulin delivery controller based on DRL. It employed ten tricks to enhance the proximal policy optimization (PPO) algorithm, improving training efficiency. Additionally, a dual safety mechanism of 'proactive guidance + reactive correction' was introduced to reduce the risks of hyperglycemia and hypoglycemia and to prevent emergencies. Performance evaluations in the Simglucose simulator demonstrate that the proposed controller achieved an 87.45% time in range (TIR) median, superior to baseline methods, with a lower incidence of hypoglycemia, notably eliminating severe hypoglycemia and treatment failures. These encouraging results indicate that the DRL-based fully closed-loop AP controller has taken an essential step toward clinical implementation.

Body mass index affects imatinib exposure: Real‐world evidence from TDM with adaptive dosing

AbstractBackgroundImatinib is the treatment of elderly or frail patients with chronic myeloid leukemia (CML). Trough levels of around 1000 ng/ml are considered as the target exposure.ObjectivesWe searched for baseline parameters associated with imatinib pharmacokinetics, and studied the clinical impact of subsequent adaptive dosing.MethodsWe present data from 60 adult CML patients upon imatinib with therapeutic drug monitoring (TDM) and adaptive dosing.ResultsMean trough levels after treatment initiation were 994.2 ± 560.6 ng/ml with 56% inter‐patient variability). Only 29% of patients were in the therapeutic range. Body weight, height, body surface area, body mass index (BMI), and age were associated with imatinib plasma levels on univariate analysis. Age and BMI remained the only parameters associated with imatinib trough levels on multivariate analysis. As severe toxicities have been previously reported in patients with low BMI treated with standard imatinib, we evaluated the extent to which low BMI may lead to plasma overexposure. We found a statistically significant difference in trough imatinib levels in patients with BMI &lt; 18.5 kg/m2, with exposure +61.5% higher than in patients with 18.5 &lt; BMI ≤ 24.9 and +76.3% higher than in patients with BMI ≥ 25. After TDM with adaptive dosing, a statistically significant difference in dosing between patients was observed, with doses ranging from 200 to 700 mg. No difference in toxicity or efficacy was observed regardless of BMI after adaptive dosing.ConclusionOur data suggest that low BMI has a significant impact on imatinib exposure but that pharmacokinetically‐guided dosing limits its clinical impact in patients.

New Insights Into Hepatic Impairment (HI) Trials.

Hepatic impairment (HI) trials are traditionally part of the clinical pharmacology development to assess the need for dose adaptation in people with impaired metabolic capacity due to their diseased liver. This review aimed at looking into the data from dedicated HI studies, cluster these data into various categories and connect the effect by HI with reported pharmacokinetics (PK) properties in order to identify patterns that may allow waiver, extrapolations, or adapted HI study designs. Based on a ratio ≥ 2 or ≤ 0.5 in AUC or Cmax between hepatically impaired participants/healthy controls these were considered "positive" or "negative". In case of more than one HI severity stratum per compound included in the HI trial, the comparison of the AUC ratios for mild, moderate, or severe HI were used to investigate the increase across HI categories. For the in total 436 hits, relevant PK information could be retrieved for 273 compounds of which 199 were categorized negative, 69 positive ups and 5 positive downs. Fourteen out of 69 compounds demonstrated a steep increase in the AUC ratios from mild to severe HI. Compounds demonstrating a steep increase typically had a high plasma protein binding of > 95%, high volume of distribution, lower absolute bioavailability, minor elimination via the kidneys, were predominantly metabolized by CYP3A4 or CYP2D6 and the majority of these compounds were substrates of OATP1B1. While for compounds with steep increase studies in all severity strata may be warranted they may also offer the potential to estimate the appropriate doses in an HI trial. On the other hand, for compounds with slow or no increase across HI severity strata, reduced HI trials may be justified, e.g. only testing PK in moderate HI.

Accelerated therapeutic development during COVID-19: insights, regulatory strategies, and recommendations for future pandemic preparedness.

The clinical development of therapeutics for COVID-19 proceeded at an extraordinary pace. Given the lack of studies evaluating this experience systematically, we analyzed the clinical development methods for COVID-19 therapeutics to determine strategies for shortening the clinical development period in preparation for future pandemics. We confirmed the US-FDA review documents for fourteen products that underwent Emergency Use Authorization (EUA) in the US during the COVID-19 pandemic to examine the time required for clinical development and regulatory review and the submitted data for EUA. Six of the fourteen products with clinical study data for other indications were evaluated in fewer studies than new molecular entities. The application data for each product included the stipulated content, and placebo-controlled comparative studies were included for all products. Clinical development measures were adopted, including adaptive protocol design, nonsequential phase development, and clinical dose adaptation based on non-clinical study results. Products with clinical study data for other indications are advantageous for early approval. However, early approval of new molecular entities is also important because they may not be sufficiently effective against new infectious diseases. It would be effective to approve a product promptly for a limited target population at first and then gradually expand it as data becomes more abundant. To prepare for future pandemics, we recommend establishing a framework for identifying candidates from existing products, managing and disseminating information in emergencies at various levels, and clarifying the conditions for applying regulatory flexibility to encourage pharmaceutical companies to make early decisions regarding clinical development.

A mathematical framework for comparison of intermittent versus continuous adaptive chemotherapy dosing in cancer

Chemotherapy resistance in cancer remains a barrier to curative therapy in advanced disease. Dosing of chemotherapy is often chosen based on the maximum tolerated dosing principle; drugs that are more toxic to normal tissue are typically given in on-off cycles, whereas those with little toxicity are dosed daily. When intratumoral cell-cell competition between sensitive and resistant cells drives chemotherapy resistance development, it has been proposed that adaptive chemotherapy dosing regimens, whereby a drug is given intermittently at a fixed-dose or continuously at a variable dose based on tumor size, may lengthen progression-free survival over traditional dosing. Indeed, in mathematical models using modified Lotka-Volterra systems to study dose timing, rapid competitive release of the resistant population and tumor outgrowth is apparent when cytotoxic chemotherapy is maximally dosed. This effect is ameliorated with continuous (dose modulation) or intermittent (dose skipping) adaptive therapy in mathematical models and experimentally, however, direct comparison between these two modalities has been limited. Here, we develop a mathematical framework to formally analyze intermittent adaptive therapy in the context of bang-bang control theory. We prove that continuous adaptive therapy is superior to intermittent adaptive therapy in its robustness to uncertainty in initial conditions, time to disease progression, and cumulative toxicity. We additionally show that under certain conditions, resistant population extinction is possible under adaptive therapy or fixed-dose continuous therapy. Here, continuous fixed-dose therapy is more robust to uncertainty in initial conditions than adaptive therapy, suggesting an advantage of traditional dosing paradigms.

Adaptive dosing of high-dose busulfan in real-world adult patients undergoing haematopoietic cell transplant conditioning.

To evaluate the effectiveness of a Bayesian adaptive dosing strategy in achieving target busulfan exposure in adult patients undergoing haematopoietic cell transplantation (HCT). This study included 71 adult patients scheduled to receive high-dose busulfan. Busulfan was administered to achieve a cumulative area under the curve (AUC) of 66.0mg.h/L (16 000 μM.min), 82.60 mg.h/L (20 000 μM.min) or 87.6 mg.h/L (21 200 μM.min) depending on the regimen. Individual pharmacokinetic (PK) parameters of busulfan were estimated from three blood samples using a one-compartment model and Bayesian estimation after the first standard dose. Individual PK parameters were used to adjust subsequent doses to achieve the target exposure. All patients had their dose adjusted after the first dose administration. The final deviation from the target AUC was significantly improved compared to the initial deviation after standard mg/kg dosing (mean absolute deviation 19.5% vs 11.7%, P< .01). In addition, the proportion of patients with marked deviation from target exposure (ie, >25%) decreased significantly from 31% after standard dosing to 10% after PK-guided dosing (P< .01). Canonical busulfan-related toxicity, specifically veno-occlusive disease, was observed in 5% of patients who achieved successful PK-guided dosing. In contrast, one-third of patients with off-target exposure with poor dosing experienced toxicity. The Bayesian adaptive dosing strategy significantly improves the accuracy of achieving the target busulfan AUC in patients undergoing HCT. This approach not only reduces marked deviations from target exposure, but also reduces the incidence of busulfan-related toxicity, thereby maintaining a favourable toxicity/efficacy ratio.

Clinical and Oncological Impact of a Protective Ileostomy in Rectal Cancer Patients Undergoing Adjuvant Chemotherapy.

During low anterior rectal resection for rectal cancer, a protective ileostomy (PI) is routinely created to reduce the severity of anastomotic complications. The aim of this study was to investigate the side-effects of PI during adjuvant chemotherapy. A retrospective cohort of patients was operated on for non-metastatic rectal cancer with a PI during 2005-2022. Patients treated with adjuvant chemotherapy (AC) were compared with those not receiving AC. A subgroup analysis compared patients with early PI closure (<10 weeks) and those with a PI in place during chemotherapy. A total of 242 patients were included: 178 (73.6%) without adjuvant chemotherapy and 64 (26.4%) with. History, tumour location, neoadjuvant treatment and postoperative follow-up were similar for both groups. Patients treated with AC had a greater risk of renal failure (37.5% vs. 14.6%, p=0.0002), ionic disorders (45.3% vs. 26.9% p=0.008), malnutrition (23.4% vs. 5.6%, p=0.0002) and rehospitalization (35.9% vs. 18.5% p=0.007). Patients treated with AC needed significant dose adjustments of oxaliplatin in 40.6% of cases, this adjustment being higher in patients with a PI compared to patients with early closure (47.1 vs. 9.1%, p=0.021). Presence of a PI during chemotherapy predisposes to increased episodes of renal failure, and requires major adaptation of chemotherapy doses, especially of oxaliplatin.

Medications for community pharmacists to dose adjust or avoid to enhance prescribing safety in individuals with advanced chronic kidney disease: a scoping review and modified Delphi

BackgroundCommunity pharmacists commonly see individuals with chronic kidney disease (CKD) and are in an ideal position to mitigate harm from inappropriate prescribing. We sought to develop a relevant medication list for community pharmacists to dose adjust or avoid in individuals with an estimated glomerular filtration rate (eGFR) below 30 mL/min informed through a scoping review and modified Delphi panel of nephrology, geriatric and primary care pharmacists.MethodsA scoping review was undertaken to identify higher risk medications common to community pharmacy practice, which require a dose adaptation in individuals with advanced CKD. A 3-round modified Delphi was conducted, informed by the medications identified in our scoping review, to establish consensus on which medications community pharmacists should adjust or avoid in individuals with stage 4 and 5 CKD (non-dialysis).ResultsNinety-two articles and 88 medications were identified from our scoping review. Of which, 64 were deemed relevant to community pharmacy practice and presented for consideration to 27 panel experts. The panel consisted of Canadian pharmacists practicing in nephrology (66.7%), geriatrics (18.5%) and primary care (14.8%). All participants completed rounds 1 and 2 and 96% completed round 3. At the end of round 3, the top 40 medications to adjust or avoid were identified. All round 3 participants selected metformin, gabapentin, pregabalin, non-steroidal anti-inflammatory drugs, nitrofurantoin, ciprofloxacin and rivaroxaban as the top ranked medications.ConclusionMedications eliminated by the kidneys may accumulate and cause harm in individuals with advanced chronic kidney disease. This study provides an expert consensus of the top 40 medications that community pharmacists should collaboratively adjust or avoid to enhance medication safety and prescribing for individuals with an eGFR below 30 mL/min.

Toward a Clinical Decision Support System for Monitoring Therapeutic Antituberculosis Medical Drugs in Tanzania (Project TuberXpert): Protocol for an Algorithm' Development and Implementation.

The end tuberculosis (TB) strategy requires a novel patient treatment approach contrary to the one-size-fits-all model. It is well known that each patient's physiology is different and leads to various rates of drug elimination. Therapeutic drug monitoring (TDM) offers a way to manage drug dosage adaptation but requires trained pharmacologists, which is scarce in resource-limited settings. We will develop an automated clinical decision support system (CDSS) to help practitioners with the dosage adaptation of rifampicin, one of the essential medical drugs targeting TB, that is known for large pharmacokinetic variability and frequent suboptimal blood exposure. Such an advanced system will encourage the spread of a dosage-individualization culture, including among practitioners not specialized in pharmacology. Thus, the objectives of this project are to (1) develop the appropriate population pharmacokinetic (popPK) model for rifampicin for Tanzanian patients, (2) optimize the reporting of relevant information to practitioners for drug dosage adjustment, (3) automate the delivery of the report in line with the measurement of drug concentration, and (4) validate and implement the final system in the field. A total of 3 teams will combine their efforts to deliver the first automated TDM CDSS for TB. A cross-sectional study will be conducted to define the best way to display information to clinicians. In parallel, a rifampicin popPK model will be developed taking advantage of the published literature, complemented with data provided by existing literature data from the Pan-African Consortium for the Evaluation of Antituberculosis Antibiotics (panACEA), and samples collected within this project. A decision tree will be designed and implemented as a CDSS, and an automated report generation will be developed and validated through selected case studies. Expert pharmacologists will validate the CDSS, and finally, field implementation in Tanzania will occur, coupled with a prospective study to assess clinicians' adherence to the CDSS recommendations. The TuberXpert project started in November 2022. In July 2024, the clinical study in Tanzania was completed with the enrollment of 50 patients to gather the required data to build a popPK model for rifampicin, together with a qualitative study defining the report design, as well as the CDSS general architecture definition. At the end of the TuberXpert project, Tanzania will possess a new tool to help the practitioners with the adaptation of drug dosage targeting complicated TB cases (TB or HIV, TB or diabetes mellitus, and TB or malnutrition). This automated system will be validated and used in the field and will be proposed to other countries affected by endemic TB. In addition, this approach will serve as proof of concept regarding the feasibility and suitability of CDSS-assisted TDM for further anti-TB drugs in TB-burdened areas deprived of TDM experts, including second-line treatments considered important to monitor. DERR1-10.2196/58720.

The role of AI in optimizing drug dosage and reducing medication errors

Artificial intelligence (AI) is transforming healthcare by optimizing drug dosage and minimizing medication errors, significantly enhancing patient safety and treatment efficacy. AI algorithms, particularly those utilizing machine learning and deep learning, analyze vast amounts of patient data, including genetic information, medical history, and real-time health metrics, to determine the most effective drug dosages tailored to individual patients. One of the critical areas where AI excels is in precision medicine. AI-driven systems can process complex datasets to predict how different patients will respond to specific medications, thereby personalizing drug dosage. For instance, pharmacogenomics leverages AI to understand how genetic variations affect drug metabolism, helping to customize dosages that maximize therapeutic benefits while minimizing adverse effects​​. Moreover, AI enhances clinical decision support systems (CDSS) by integrating with electronic health records (EHRs). These AI-powered CDSS provide healthcare professionals with real-time alerts about potential medication errors, such as incorrect dosages, drug interactions, or patient-specific contraindications. By continuously learning from new data, these systems improve their accuracy and reliability over time, reducing the incidence of medication errors significantly​. AI is also pivotal in the development of adaptive dosing algorithms. These algorithms use patient-specific data, such as kidney function and liver enzyme levels, to adjust drug dosages dynamically. This approach is particularly beneficial in managing chronic conditions like diabetes and hypertension, where maintaining optimal drug levels is crucial for effective disease management. For example, AI can help determine the precise insulin dose required for diabetic patients by analyzing patterns in their blood glucose levels​​. In addition to individual patient care, AI aids in broader pharmacovigilance efforts by identifying and predicting adverse drug reactions (ADRs). Machine learning models analyze large datasets from clinical trials, post-marketing surveillance, and patient reports to detect early signals of ADRs, allowing for timely interventions and adjustments in drug prescriptions. In conclusion, AI's role in optimizing drug dosage and reducing medication errors is a significant advancement in personalized medicine and patient safety. By harnessing the power of AI, healthcare providers can deliver more precise, effective, and safer treatments, ultimately improving patient outcomes and reducing healthcare costs.

A Randomized Controlled Trial to Assess the Feasibility and Practicability of an Oatmeal Intervention in Individuals with Type 2 Diabetes: A Pilot Study in the Outpatient Sector.

Background/Objectives: The aim of this study was to investigate the feasibility and practicability of repeated three-day sequences of a hypocaloric oat-based nutrition intervention (OI) in insulin-treated outpatients with type 2 diabetes and severe insulin resistance. Methods: A randomized, two-armed pilot study was conducted with three months of intervention and three months follow-up with 17 participants with insulin resistance (≥1 IU/kg body weight). Group A (n = 10) performed one sequence of OI; Group B (n = 7) performed two sequences monthly. A sequence was 3 consecutive days of oat consumption with approximately 800 kcal/d. The main objective was to assess feasibility (≥70% completers) and practicability regarding performance aspects. Biomedical parameters such as HbA1 c were observed. To evaluate the state of health, a standardized questionnaire was used (EQ-5 D). Results: OI was feasible (13/17 completer participants (76.5%): 70.0% Group A, 85.7% Group B). Individually perceived practicability was reported as good by 10/16 participants (62.5%). Total insulin dosage decreased from 138 ± 35 IU at baseline to 126 ± 42 IU after OI (p = 0.04) and 127 ± 42 IU after follow-up (p = 0.05). HbA1 c was lower after OI (-0.3 ± 0.1%; p = 0.01) in all participants. Participants in Group B tended to have greater reductions in insulin (Δ-19 IU vs. Δ-4 IU; p = 0.42) and weight loss (Δ-2.8 kg vs. Δ-0.2 kg; p = 0.65) after follow-up. Severe hypoglycemia was not observed. EQ-5 D increase not significantly after follow-up (57.2 ± 24.0% vs. 64.7 ± 21.5%; p = 0.21). Conclusions: The feasibility and practicability of OI in outpatients were demonstrated. OI frequency appears to correlate with insulin reduction and weight loss. Proper insulin dose adaptation during OI is necessary. Presumably, repeated OIs are required for substantial beneficial metabolic effects.

Adaptive radiotherapy (up to 74 Gy) or standard radiotherapy (66 Gy) for patients with stage III non-small-cell lung cancer, according to [18F]FDG-PET tumour residual uptake at 42 Gy (RTEP7–IFCT-1402): a multicentre, randomised, controlled phase 2 trial

Adaptive radiotherapy (up to 74 Gy) or standard radiotherapy (66 Gy) for patients with stage III non-small-cell lung cancer, according to [18F]FDG-PET tumour residual uptake at 42 Gy (RTEP7–IFCT-1402): a multicentre, randomised, controlled phase 2 trial