Research Appraisals
Evidence-based critical appraisals of the latest medical research, systematically evaluated using Oxford CEBM methodology.
Showing 21 appraisals
PLoS computational biology
Twelve quick tips for AI-assisted coding in science.
While AI coding tools have demonstrated potential to accelerate software development, their use in scientific computing raises critical questions about code quality and scientific validity. In this paper, we provide twelve practical tips for AI-assisted coding that balance the capabilities of AI with the demands of scientific and methodological rigor. We address how AI can be leveraged strategically throughout the development cycle with four key themes: problem preparation and understanding, managing context and interaction, testing and validation, and code quality assurance and iterative improvement. These principles serve to emphasize maintaining human agency in coding decisions, establishing robust validation procedures, and preserving the domain expertise essential for methodologically sound research. These tips are intended to help researchers harness AI's transformative potential for faster software development while ensuring that their code meets the standards of reliability, reproducibility, and scientific validity that research integrity demands.
29 July 2026
Read appraisal →Philosophical transactions. Series A, Mathematical, physical, and engineering sciences
Predictability-Computability-Stability workflow for veridical data science in the age of artificial intelligence
Data science is a pillar of artificial intelligence (AI), which is transforming nearly every domain of human activity, from the social and physical sciences to engineering and medicine. While data-driven findings in AI offer unprecedented power to extract insights and guide decision-making, many are difficult or impossible to replicate. A key reason for this challenge is the uncertainty introduced by the many choices made throughout the data science life cycle (DSLC). Traditional statistical frameworks often fail to account for this uncertainty. The Predictability-Computability-Stability (PCS) framework for veridical (truthful) data science (VDS) offers a principled approach to addressing this challenge throughout the DSLC. This paper presents an updated and streamlined PCS workflow, tailored for practitioners and enhanced with guided use of generative AI (GenAI). We include a running example to display the PCS framework in action and conduct a related case study that showcases the uncertainty in downstream predictions caused by judgement calls in the data cleaning stage. This article is part of the theme issue 'Statistical workflow'.
30 May 2026
Read appraisal →JMIR cancer
Machine Learning-Based Survival Prediction Models for Young Patients With Gastric Cancer: Model Development and Validation Study
BACKGROUND: Despite a global decline in the incidence of gastric cancer (GC), the number of cases diagnosed among younger individuals continues to increase. Several studies have been conducted to develop predictive models of mortality in patients with GC. OBJECTIVE: We developed 3- and 5-year survival prediction models for young patients with GC based on machine learning-based survival modeling approaches. METHODS: Data from 813 young patients (≤50 years) diagnosed with GC between 2013 and 2015 were retrieved from the Gastric Cancer Public Staging Database. Among these 813 patients, data from 569 (70%) and 244 (30%) were allocated to the model training and testing datasets, respectively. Random survival forest, gradient boosting survival analysis, extra survival tree, and the Cox proportional hazards model were applied to predict survival outcomes at the 3- and 5-year time horizons. Model performance was assessed and quantified using the concordance index (C-index) metric. For the machine learning prediction models, the mean C-index values and corresponding 95% CIs were estimated across 100 repeated training iterations. RESULTS: For the random survival forest model, the C-index for predicting 3-year mortality was 95.89% (95% CI 95.80%-95.97%), whereas the C-index for predicting 5-year mortality was 91.82% (95% CI 91.68%-91.96%). In the gradient boosting survival analysis model, the C-index for predicting 3-year mortality was 95.32% (95% CI 95.31%-95.33%), and the C-index for predicting 5-year mortality was 89.98% (95% CI 89.95%-90.01%). For the extra survival tree model, the C-index for predicting 3-year mortality was 95.53% (95% CI 95.46%-95.60%), whereas the C-index for predicting 5-year mortality was 94.60% (95% CI 94.50%-94.70%). In addition, the Cox proportional hazards model showed a C-index of 94.15% for predicting 3-year mortality and 82.26% for predicting 5-year mortality. Tumor stage and tumor size were the primary predictive variables used to train the models for mortality prediction at different time points. Other variables exhibited varying levels of predictive contribution across different time points. CONCLUSIONS: These findings may facilitate the identification of high-risk young patients with GC who may benefit from more aggressive treatment strategies by enabling the prediction of mortality risk at different time points.
28 May 2026
Read appraisal →Current obesity reports
How Have Researchers Estimated the Impact of Excess Weight on Mortality? A Systematic Review.
OBJECTIVE: The aim of this review is to describe and reflect on the methodology of the studies that estimate the attributable mortality (AM) to excess weight. The purpose was to provide a methodological framework and serve as a starting point to improve the estimation of AM to excess weight. This will lead to more comparable estimates over time and across countries. METHODS: A systematic review was conducted considering MEDLINE (Ovid), Embase and Web of Science databases. Studies that had estimated AM to excess weight published until December 2024 were included. Data extraction was performed in an ad-hoc table based on the STREAMS-P tool, and a descriptive analysis of the methodology employed was performed. RESULTS: The search strategy yielded 2,163 results. Twenty-three studies estimating AM in four continents were included. The majority estimated AM to all-cause mortality (n = 9) and for cardiovascular diseases (n = 9), followed by cancer without specifying which type of cancer (n = 7). Variation was observed in the body mass index (BMI) cut-off points used to define overweight, obesity and excess weight. Thirteen studies applied the population attributable fraction (PAF) formula denoted by PAF = [P (RR-1)] / [1 + P (RR-1)]. Most of the relative risks (RR) derived from meta-analysis (n = 14), and only a minority studies (n = 6) used RR from national studies based on the population for which AM was estimated. CONCLUSION: This review emphasizes methodological constraints on AM estimation to excess weight. Causes of death causally associated with excess weight should be prioritized rather than relying solely on all-cause mortality. The ideal scenario would be to consider lag times; RR derived from the population under study and to use WHO BMI cut-offs and measured data rather than self-reported weight and height. The absence of this data should not prevent AM estimation if limitations are acknowledged. Expanding available estimates worldwide is essential to improve understanding of the mortality burden associated with excess weight.
26 May 2026
Read appraisal →Lifetime data analysis
Kolmogorov-Smirnov and Cramér-von Mises tests for the k-sample problem with left-truncated and right-censored data
k-Sample versions of the Kolmogorov-Smirnov and Cramér-von Mises tests are proposed for data subject to left truncation and right censoring. Their asymptotic behaviour is studied and a bootstrap resampling plan is proposed to approximate the null distribution of the new tests. The performance of the tests with finite sample sizes is investigated in a simulation study, where the classical log-rank test is also considered. An illustration with a real dataset regarding unemployment times is discussed.
18 May 2026
Read appraisal →Biological psychiatry
Overview of Challenges in Brain-Based Predictive Modeling: Toward Meaningful Predictive Insights
Predictive analytics based on machine learning (ML) and artificial intelligence is a powerful tool enabling precision psychiatry and providing insights into brain-behavior relationships. However, given the mixed results observed in the field so far, making meaningful progress requires careful consideration of several key challenges to ensure the validity of models and findings, including overfitting, confounding biases, site effect harmonization, and interpretability, among others. First, we highlight limitations of cross-validation, a ubiquitous ML strategy used to prevent overfitting and obtain generalization estimates, emphasizing the risk of performance inflation and the need for independent validation. Next, we introduce different types of so-called third variables that can influence the examination of a brain-behavioral relationship of interest in different ways, using causal inference principles. We emphasize the biasing impact of confounding variables on ML models and summarize common mitigation strategies. We then discuss site-specific effects in multisite datasets, reviewing different harmonization strategies to reduce unwanted variability and site-specific noise. Finally, we explore post hoc model interpretation methods to enhance model transparency while cautioning against misinterpretation. By integrating rigorous result validation, confounder control, and interpretability techniques, researchers can ensure that ML models produce more reliable and generalizable findings and avoid spurious associations.
18 May 2026
Read appraisal →Journal of pharmacokinetics and pharmacodynamics
Multi-objective optimization in population pharmacokinetic model selection and optimization: application of NSGA-II in pyDarwin
The selection of a "good" model usually involves a combination of objective and subjective criteria. Although many aspects of model quality can be expressed numerically, certain desirable characteristics remain difficult-or even impossible-to quantify precisely. Multi-objective optimization (MOO) provides a systematic way to handle this challenge by explicitly incorporating and balancing both objective (measurable) and subjective (judgment-based) considerations when choosing among candidate solutions. The generated Pareto front represents a set of non-dominated models where no single solution can be improved in one objective without sacrificing the performance in another objective. Using the non-dominated sorting genetic algorithm II (NSGA-II), an implementation of MOO, we simultaneously considered objective function value and number of estimated parameters as competing criteria. Concentration measurements of 17-DMAG, quetiapine, clozapine and ziprasidone were applied to build population pharmacokinetic models through traditional stepwise search, machine learning based single-objective hybrid genetic algorithm (SOHGA) and MOO. Local downhill search with MOO was also assessed in this study. While both objectives improved, models with lower objective function value generally contained more estimated parameters. The number of non-dominated solutions for DMAG, ziprasidone, clozapine, and quetiapine was 17, 9, 9, and 13, respectively. The optimal model selected by SOHGA appeared on the Pareto front for DMAG, ziprasidone and clozapine datasets. Overall, MOO provides objective transparency to the cost of tradeoffs between competing model objectives, allowing researchers to better contextualize subjective criteria (e.g., biological plausibility, improvements in diagnostic plots) when aligning model selection with clinical context.
18 May 2026
Read appraisal →PloS one
Classification of soft decision-making methods via fuzzy parameterized fuzzy soft matrices and their performance-based statistical analysis in machine learning
This study provides a comprehensive evaluation and classification of 35 soft decision-making (SDM) algorithms based on fuzzy parameterized fuzzy soft matrices (fpfs-matrices). Although fpfs-matrices offer a strong mathematical framework for modeling uncertainty, there has been a lack of large-scale comparisons of their derivative SDM methods in machine learning. To address this, we used the Comparison Matrix-Based Fuzzy Parameterized Fuzzy Soft Classifier (FPFS-CMC) to benchmark these 35 algorithms across ten diverse datasets from the UCI Machine Learning Repository. The methods were thoroughly assessed utilizing metrics such as accuracy, precision, recall (sensitivity), specificity, and F1-score, and statistical significance was confirmed using the Friedman and Nemenyi tests. Our results show that SDM methods via fpfs-matrices perform competitively in classification tasks involving uncertainty. Notably, the best algorithms according to F1-scores were A19 (Rank 1), YHX14 (Rank 2), and a three-way tie for Rank 3 among VMH16, AKO18o, and A19/2. By identifying the most effective algorithms and offering a structured decision-support framework, this research provides both a theoretical reference and practical guidance for practitioners selecting SDM methods for complex machine learning challenges.
15 May 2026
Read appraisal →Biology of sex differences
Importance of integrating biological sex and age analyses in health research
Research findings in human, animal and cell populations may be influenced by biological sex and age. The traditional statistical approach to sex and/or age differences that are discovered in research data is to consider them as confounders that interfere with the ability to make accurate estimations and thus need to be controlled for. This article provides examples of how combining sexes or controlling for sex and/or age may lead to inaccurate findings and overlook important insights. Rather than treating these variables as confounding factors, they should be viewed as variables of importance to the research question. We contend that data should be analyzed according to sex/age as the primary analysis, while controlling for sex and age should be conducted as a secondary analysis. This topic is increasingly important as data are made publicly available and deep learning models/artificial intelligence are used to analyze large volumes of data. Mechanistic insights will continue to be lost if prompt action is not taken to report data according to sex and age and to analyze data by sex and age in health research.
14 May 2026
Read appraisal →Pediatric surgery international
Development of a machine learning-based prognostic prediction model and a web-based tool for pediatric hepatoblastoma: a Surveillance, Epidemiology, and End Results (SEER) database study
BACKGROUND: Prognostic evaluation of pediatric hepatoblastoma (HB) remains challenging due to the low accuracy of traditional risk stratification models. This study aims to leverage the U.S. Surveillance, Epidemiology, and End Results (SEER) database to develop and compare several machine learning-based survival models and create an online prediction tool for individualized survival probability estimation in children with HB. METHODS: A total of 614 pediatric HB patients diagnosed from 2000 to 2021 in the SEER database were identified and randomly split (7:3 ratio) into a training set (n = 429) and an internal hold-out validation cohort (n = 185). This split was selected to retain sufficient data for model development while preserving an adequate validation cohort for performance assessment. Least Absolute Shrinkage and Selection Operator (LASSO) regression analysis was used for feature selection, and three prognostic prediction models (Cox regression, random survival forest (RSF), and a deep learning-based survival (DeepSurv) neural network) were developed using the training data. Model performance was evaluated by Harrell's concordance index (C-index), time-dependent area under the receiver operating characteristic (ROC) curve (AUC) at 1, 3, and 5 years, and decision curve analysis (DCA). We also used SHapley Additive exPlanations (SHAP) analysis to interpret the RSF model. Based on RSF-derived risk scores, patients were classified into high-, intermediate-, and low-risk groups for survival analysis. Ultimately, a web-based tool was developed to enable real-time prediction of 1-, 3-, and 5-year survival probabilities using individual patient characteristics. RESULTS: In the validation cohort, the RSF model achieved the highest C-index (0.745), outperforming the DeepSurv (0.720) and Cox regression models (0.709). The RSF also yielded favorable 1-year, 3-year, and 5-year AUC values, and DCA indicated a greater net benefit across clinically relevant threshold probabilities. SHAP analysis highlighted distant-stage disease, surgical treatment status, and tumor extent as key factors influencing survival predictions. Kaplan-Meier curves stratified by the RSF risk groups showed significantly different survival outcomes among high-, intermediate-, and low-risk patients (log-rank P < 0.001 for all comparisons). The finalized online tool allows users to input patient characteristics and obtain estimated 1-year, 3-year, and 5-year survival probabilities, which may assist individualized prognostic assessment as an adjunctive reference. CONCLUSION: The RSF-based prognostic model showed favorable predictive performance compared with the Cox and DeepSurv models in this retrospective SEER-based cohort of pediatric HB. With interpretable model outputs and an accessible web-based interface, the model may serve as an adjunctive tool for individualized risk assessment. However, external validation and prospective evaluation are required before routine clinical implementation.
13 May 2026
Read appraisal →Journal of biopharmaceutical statistics
Revolutionizing cardiovascular disease classification through machine learning and statistical methods
BACKGROUND: Cardiovascular diseases (CVDs) include abnormal conditions of the heart, diseased blood vessels, structural problems of the heart, and blood clots. Traditionally, CVD has been diagnosed by clinical experts, physicians, and medical specialists, which is expensive, time-consuming, and requires expert intervention. On the other hand, cost-effective digital diagnosis of CVD is now possible because of the emergence of machine learning (ML) and statistical techniques. METHOD: In this research, extensive studies were carried out to classify CVD via 19 promising ML models. To evaluate the performance and rank the ML models for CVD classification, two benchmark CVD datasets are considered from well-known sources, such as Kaggle and the UCI repository. The results are analysed considering individual datasets and their combination to assess the efficiency and reliability of ML models on the basis of various performance measures, such as precision, kappa, accuracy, recall, and the F1 score. Since some of the ML models are stochastic, we repeated the simulation 50 times for each dataset using each model and applied nonparametric statistical tests to draw decisive conclusions. RESULTS: The nonparametric Friedman - Nemenyi hypothesis test suggests that the Extra Tree Classifier provides statistically superior accuracy and precision compared with all other models. However, the Extreme Gradient Boost (XGBoost) classifier provides statistically superior recall, kappa, and F1 scores compared with those of all the other models. Additionally, the XGBRF classifier achieves a statistically second-best rank in terms of the recall measures.
10 May 2026
Read appraisal →The Proceedings of the Nutrition Society
Good practices and common pitfalls of machine learning in nutrition research
Machine learning is increasingly being utilised across various domains of nutrition research due to its ability to analyse complex data, especially as large datasets become more readily available. However, at times, this enthusiasm has led to the adoption of machine learning techniques prior to a proper understanding of how they should be applied, leading to non-robust study designs and results of questionable validity. To ensure that research standards do not suffer, key machine learning concepts must be understood by the research community. The aim of this review is to facilitate a better understanding of machine learning in research by outlining good practices and common pitfalls in each of the steps in the machine learning process. Key themes include the importance of generating high-quality data, employing robust validation techniques, quantifying the stability of results, accurately interpreting machine learning outputs, adequately describing methodologies, and ensuring transparency when reporting findings. Achieving this aim will facilitate the implementation of robust machine learning methodologies, which will reduce false findings and make research more reliable, as well as enable researchers to critically evaluate and better interpret the findings of others using machine learning in their work.
4 May 2026
Read appraisal →Behavior research methods
A review and evaluation of doubly robust approaches for estimating average treatment effects
In nonexperimental studies, obtaining an unbiased estimate of the average treatment effect (ATE) typically requires two key assumptions: that all relevant covariates are measured (i.e., no unmeasured confounding) and that the statistical model used for covariate adjustment is correctly specified. Two common approaches for adjustment are specifying an outcome model and propensity score weighting. To mitigate bias from model misspecification, doubly robust methods combine both approaches, ensuring unbiased ATE estimates if either the outcome model or the propensity score model is correctly specified. In this study, we review four doubly robust methods that have received considerable attention in the methodological literature but remain underutilized in psychological research: augmented inverse probability weighting, regression weighted by the inverse propensity score, regression incorporating the inverse propensity score as a covariate, and calibrated propensity score weighting. Using two simulation studies, we compare these methods with regression estimation and inverse probability weighting estimators. Our results suggest that doubly robust methods-particularly regression weighted by the inverse propensity score-offer greater protection against bias from model misspecification across various data-generating scenarios. We also discuss practical considerations for implementing doubly robust methods, including weight normalization, propensity score truncation, and potential efficiency losses due to overfitting. The different methods for estimating the ATE are illustrated in a data example.
26 Apr 2026
Read appraisal →Journal of the American College of Cardiology
Extension Reports in Clinical Trials: A Systematic Review and Consequent Guidance
BACKGROUND: Following the primary publication of a clinical trial, questions of longer-term efficacy and safety remain unanswered. Investigators often have sequel publications based on extended follow-up; yet, no guidelines exist for such extension reports. OBJECTIVES: The purpose of this analysis was to assess the characteristics of extension reports of cardiovascular trials published in 7 high-impact medical journals. METHODS: We searched MEDLINE to identify cardiovascular trial extension papers published between January 2019 and October 2023 in 7 high-impact medical journals. Extension reports were defined as those presenting additional follow-up data after publication of the primary results. Papers were screened by 2 reviewers before extracting data using a standard proforma. RESULTS: After screening 1,388 papers, 69 extension reports across 64 trials were identified. A variety of cardiovascular topics were covered, coronary heart disease (n = 20) being the most common. Interventions were medical devices, drugs, surgery, or treatment strategies. Duration of follow-up varied considerably, most common being an original 1-year report (n = 20) with extension at 2, 3, 5, or 10 years. Nearly all extension reports had a superiority hypothesis (n = 68). Most extensions (n = 53) examined the same primary outcome as the original publication. There were also 7 nonrandomized open-label extensions, which suffered from the lack of a concurrent control arm. In 18 reports, treatment crossovers were permitted during the extension, and in 16 cases, alternatives to analysis by intention to treat were utilized. One-half of the extension studies were prespecified (n = 38), and only 10 had dedicated protocols or statistical analysis plans. No study used multiplicity corrections to control type I error across the totality of evidence. Landmark analyses were common (n = 39) which, while descriptively useful, were not based on the original randomized groups. Considerable loss to follow-up (>10%) occurred in 10 of 50 extension reports with clear reporting of this issue. For some trials, the conclusions regarding treatment effects were altered by the extended follow-up. In a previous survey of cardiovascular trials published in the New England Journal of Medicine, Lancet, and Journal of the American Medical Association in 2019, we identified a total of 23 of 84 trials involving extensions in some form. CONCLUSIONS: This first systematic investigation into the reporting of extension studies found a great diversity in practice, noting several issues that need more adequate consideration. Considerations are provided on what trialists should consider when planning, conducting, and reporting extension studies.
25 Apr 2026
Read appraisal →Behavior research methods
A modified expectation-maximization algorithm for accelerated item response theory model estimation with large datasets
The expectation-maximization (EM) algorithm is widely used for parameter estimation in item response theory (IRT) modeling. However, when applied to datasets with large numbers of individuals and items, the standard EM algorithm can be slow to converge, with computationally expensive E-steps. We propose a modified EM algorithm to accelerate estimation for unidimensional two-parameter logistic IRT models. The modified algorithm uses a two-stage structure with partial-step updating over data subsets to reduce convergence time, while maintaining comparable accuracy and precision. The first two simulation studies evaluated its performance relative to standard EM, focusing on convergence time, parameter recovery, and standard error estimation across varying subset sizes and item counts. The third study demonstrated its scalability and runtime advantage in a large-scale testing scenario involving one million respondents and 100 items. The fourth study evaluated robustness under departures from unidimensionality. The proposed algorithm showed time reductions under smaller subsets with 36 items, consistent reductions across all subset sizes with 54 items, and the largest reduction (60%) with 40-item forms constructed from 100 items, while maintaining comparable estimation performance. These results highlight the algorithm's potential for large-scale applications involving tens of thousands of respondents and moderate-to-large item pools, with modifications that can be integrated into existing EM routines. We conclude with directions for operational use and potential extensions to multidimensional IRT estimation.
23 Apr 2026
Read appraisal →Trials
The wood and the trees: estimands in cluster randomised trials.
BACKGROUND: The estimand framework was introduced into guidance on good clinical practice to address a variety of shortcomings and ambiguities in the reporting of trials, including the use of terms such as "intention to treat" and the handling of non-adherence to treatment. The framework was primarily grounded in individually randomised trials, and some thorny issues still cloud understanding of its application to cluster randomised trials. ESTIMANDS IN CLUSTER RANDOMISED TRIALS: This commentary addresses some of the challenges in thinking about the estimands behind cluster randomised trials. These challenges include informative cluster size-the possibility that a treatment effect may be modified by the size of the cluster. In particular, we consider the perspectives of different actors-a population-level decision maker or politician, a cluster manager, and a patient-and examine possible estimands for each, and how they differ. CONCLUSIONS: In the cluster randomised trial context, the estimand framework can be complex to navigate. Different perspectives lead to different estimands. We caution against abandoning careful statistical modelling. This is particularly true in the presence of informative cluster size, where modelling any interaction between cluster size and treatment effect could be useful from a number of perspectives.
22 Apr 2026
Read appraisal →Journal of medical Internet research
Beyond Missingness: Systematizing Methods for Comprehensive Data Fitness Assessment in Clinical Research
Secondary use of clinical data offers unprecedented opportunities to rapidly conduct large-scale research and improve patient care. However, incomplete understanding of data quality requirements for a study often causes significant delays in executing analyses and validating results. Current practice has largely followed 2 paths. First, multi-institutional networks have developed general data quality programs, but these are typically tied to unique network characteristics and do not address study-specific requirements well. Second, models have been proposed to formalize the requirements for data fitness analyses without extending to the methods needed to meet these requirements. More recently, tools have been developed to conduct cohort-centric screening, focusing on generally applicable structural checks such as missingness or facial implausibility. These provide a first level of information but incompletely capture the fitness requirements of an analysis. In turn, investigators conduct per-study exploratory analyses, but these efforts are typically ad hoc and partially reported, which can hinder reproducible science and delay advances in patient care. Analogously to advances over the past decade in data modeling and reproducible analytics, there is a need for a more systematic, capable approach to study-specific data quality assessment (SSDQA). We discuss such a model, which guides improved SSDQA design and implementation, including metadata for consistent annotation and reporting of data quality assessment results. The model integrates theoretical principles of data quality testing with pragmatic considerations of application to clinical data, providing a consistent approach to specifying data quality assessment checks. Additionally, it proposes to regularize check application through a standard set of options. The SSDQA model builds on current practice, providing a path toward more complete, sound, and reproducible assessments. These characteristics foster multidisciplinary collaboration to identify data quality issues that, in turn, inform decisions about study design and provide important context that has a bearing on adoption of results.
17 Apr 2026
Read appraisal →International journal of medical informatics
A structured decision-support framework for selecting imputation methods in clinical structured datasets: A secondary analysis
OBJECTIVE: Missing values are a common challenge in healthcare data analysis, and inadequate handling can introduce bias and undermine the validity of findings. Imputation methods offer a practical solution, but selecting an appropriate approach depends on multiple dataset-specific factors. This study proposes a structured decision-support framework that defines key prerequisites for choosing suitable imputation methods during the preprocessing of clinically structured datasets. METHODS: A secondary analysis of a previous systematic review was conducted, covering 69 studies to identify factors influencing imputation method selection. Domain experts evaluated assumptions regarding missing data characteristics and dataset structure, reaching consensus on the most relevant factors. These factors were synthesized into a structured framework designed to guide systematic and transparent imputation method selection in clinical data preprocessing workflows. RESULTS: Nine key factors were identified as essential for determining an appropriate imputation method. These include missing data characteristics, mechanism, pattern, and ratio and dataset attributes such as data type, variable role, distribution, and correlation. The ratio of missingness was the most influential factor, followed by variable role and missing value mechanism. Most studies emphasized the combined importance of both missing data properties and dataset features in imputation selection. CONCLUSIONS: Understanding the characteristics of missing values and dataset structure is crucial for selecting appropriate imputation methods. The proposed structured decision-support framework provides an evidence-based checklist to enhance transparency, reproducibility, and reliability in preprocessing clinical datasets within medical informatics workflows.
16 Apr 2026
Read appraisal →Trials
The use of complex clinical trials: a regulatory review.
BACKGROUND: Complex clinical trials offer flexibility in evaluating multiple treatments or diseases simultaneously. These trials often feature adaptive designs, common controls, and the potential to add new arms. However, the increased complexity raises methodological challenges particularly regarding multiple testing or the adequate choice of control groups. Despite guidance from regulatory bodies like the European Medicines Agency and the U.S. Food and Drug Administration, uncertainties remain about the regulatory acceptance of these trials. METHODS: This systematic review examines scientific advice procedures of products in the remit of the Paul-Ehrlich-Institut for complex clinical trials to highlight key concerns and regulatory feedback. We identified 30 scientific advice procedures corresponding to 29 different complex clinical trials. RESULTS: Our findings reveal an increasing number of complex trial designs proposed by applicants. A lack of multiplicity control due to multiple arms was generally considered acceptable by regulators in exploratory trials and if cohorts can be considered independent. Additionally, the use of common control groups is frequently proposed by applicants. The review underscores the importance of pre-planning for new treatment arms, appropriate multiplicity control, and the definition of control groups in trial designs. CONCLUSION: Overall, our findings suggest that regulatory concerns regarding complex trials largely align with those in traditional trial designs, though their complexity requires careful, case-by-case consideration. Early engagement with regulatory agencies can be crucial to ensure the successful design and implementation of these trials.
12 Apr 2026
Read appraisal →Lifetime data analysis
Q-learning via deep learning-based Buckley-James method for non-linear censored data
In healthcare, personalized treatment strategies are vital for improving patient outcomes, especially under right-censored survival data. We propose Dynamic Deep Buckley-James Q-Learning, a novel counterfactual Q-learning algorithm that integrates deep learning with the Buckley-James method to simultaneously address censoring and nonlinear modeling challenges. By explicitly capturing complex, nonlinear interactions between covariates and treatment effects, the algorithm robustly estimates optimal dynamic treatment regimes. Leveraging a counterfactual framework, we define and estimate potential survival outcomes under hypothetical treatment sequences, enabling unbiased Q-function estimation even in the presence of time-dependent covariates and right censoring. The algorithm maximizes the expected imputed survival reward under these counterfactual scenarios. Simulation studies and real-world data analysis demonstrate its superior performance in predictive accuracy and treatment decision-making, offering a powerful framework for individualized care in complex clinical settings.
6 Apr 2026
Read appraisal →Pharmacology research & perspectives
Improving Population Pharmacokinetic Modelling with Artificial Patients using Generative Artificial Intelligence
In population pharmacokinetics (PopPK), non-linear mixed effects (NLME) models are used to simultaneously describe a drug's pharmacokinetics (PK) and dynamics (PD) in a patient population using systems of ordinary differential equations. In this field, machine learning is mainly used for data preparation, hypothesis generation, predictive modeling, and model validation. Some approaches to integrate artificially generated information have already been explored, but real-world application is still limited. We therefore conducted a proof-of-concept study to analyze the ability of generative artificial intelligence (AI) to create artificial patient profiles to augment PopPK data sets and assess their influence on parameter estimates. We defined the pharmacokinetic parameters of a hypothetical drug and simulated the concentration curves of 20 patients. We then trained Wasserstein Generative Adversarial Networks (WGANs) with gradient penalty (GP) to generate artificial patients. The data distribution of original and artificial patients was statistically indistinguishable as shown by the Maximum Mean Discrepancy test. Therefore, the WGAN-GP is neither overfitted, that is producing only single instances of artificial patients, nor underfitted, that is producing unrealistic artificial patients. We then combined different shares of original and artificial patients in separate data sets to build and compare PopPK model estimates. Addition of artificial patients led to narrower confidence intervals, indicating more robust parameter estimates, and accentuated the allometric effect of weight on the volume of distribution. In conclusion, we provide a proof-of-concept that generative AI can be used to augment pharmacokinetic data sets, with preliminary evidence suggesting improved parameter estimation.
4 Apr 2026
Read appraisal →