Informatics in Medicine Unlocked

Skin cancer requires early detection for improved survival rates. Most existing methods rely on deep learning based image classification, which is affected by visual similarity among lesions. Fewer studies use Gene Expression (GE) analysis, which captures molecular characteristics but lacks structural and visual details. To overcome limitations of individual modalities, this paper proposes a multimodal framework integrating dermoscopic images and GE profiles for skin cancer classification. EfficientNet and logistic regression are used for image based analysis and genomic skin lesion profiling, respectively, followed by fuzzy rule based decision systems to reduce uncertainty within individual modalities. Finally, fuzzy fusion combines predictions from both modalities using uncertainty based weighting of classifier outputs. The experimental findings show that both the image based and GE based classification models individually achieved accuracies of nearly 92%. However, the integration of prediction results through the proposed fuzzy fusion strategy further enhanced the classification performance, achieving an overall accuracy of 94.25%. The results obtained outperform contemporary methods, highlighting the effectiveness of combining complementary multimodal information compared with single modality approaches.

Background. Lung metastases in osteosarcoma (OS) are the main cause of the death. The accuracy of the diagnosis of nodules by computed tomography (CT) of the lungs is critically important for determining the disseminated stage of the disease and planning surgical treatment. The use of artificial intelligence (AI) in the search for lung nodules increases the accuracy of diagnosis and reduces the chance of missing metastases. Objective: to evaluate the accuracy of lung nodules diagnosis in adolescents with OS using AI. Methods. A retrospective assessment of CT scans of adolescents with OS was performed. A pathological nodule with an average size of [≥]4 mm was considered a target finding. The diagnostic accuracy of an AI algorithm previously trained on an adult dataset was evaluated, and the number of false positives (FP) and false negatives (FN) was determined. Sensitivity, specificity, accuracy, area under the ROC curve (AUC), positive predictive value, negative predictive value, and F1-measure were calculated. Based on the obtained results, the effectiveness of the algorithm was assessed. Results. 248 CT scans of adolescents with OS were evaluated. The following results were obtained: in 5 cases, the AI algorithm showed a FP result (2.02%), in 34 cases, it showed a FN result (13.71%), and in 209 cases, a correct result (both true positive and true negative) (84.27%). The diagnostic accuracy of the algorithm was 0.843 (95% CI 0.794-0.887). The application of the AI algorithm in the practice of an X-ray doctor in a specific clinical task would allow to increase the sensitivity from 0.805 to 0.891, while ensuring an absolute decrease in the number of FN results by 8.59% and a relative decrease by 44%. Conclusion. The obtained results confirm the practical value of the application of the AI algorithm and justify the implementation of AI-assisted systems in the diagnostic protocols for lung metastases in adolescents with OS.

High-frequency physiological monitoring in ICUs can identify impending deterioration hours before clinical recognition yet extracting reliable early-warning signals from noisy vital-sign streams remains challenging. We present SIgnose, an interpretable prediction framework for early detection of abnormal shock index (SI), built from routinely monitored vital signs using physiologic variability and nonlinear time-series features. SIgnose was developed on the eICU Collaborative Research Database and externally validated on the MIMIC-III adult database and a pediatric SafeICU cohort (AIIMS New Delhi), with additional prospective validation in the pediatric ICU. We benchmarked three representation strategies: (i) engineered physiologic variability and nonlinear time-series features, (ii) deep learning, and (iii) Llama-3.1-8B embeddings with low-rank adaptation. Physiologic variability features consistently demonstrated superior cross-cohort generalization. The final model used 3,970 features from five vital signs to predict abnormal SI up to 8 hours ahead, achieving AUROC 0.861 (95% CI 0.859-0.863) and AUPRC 0.927 (95% CI 0.925-0.929) on eICU. External validation yielded AUROC 0.870 (95% CI 0.863-0.876) and AUPRC 0.935 (95% CI 0.930-0.940) on MIMIC-III, and AUROC 0.875 (95% CI 0.863-0.888) and AUPRC 0.915 (95% CI 0.898-0.930) on SafeICU; prospective pediatric validation (n = 88) achieved AUROC 0.885 (95% CI 0.868-0.902) and AUPRC 0.911 (95% CI 0.882-0.936). SHAP interpretability analysis identified heart rate variability, respiratory trend dynamics, and multi-scale blood pressure variability as key early-warning signatures. These findings establish SIgnose as a reproducible, low-compute, early-warning framework and demonstrate that physiologic variability features provide robust, generalizable representations for early deterioration detection across adult and pediatric critical care.

In spite of well-established global immune landscape, SARS-CoV-2 is still able to further spread and continue causing infection waves. The current understanding about the reason behind is limited, and it is still difficult to predict the evolution or spreading tread of SARS-CoV-2. Therefore, it is necessary to investigate whether the establishment of population immunity has changed the virus evolution or spreading pattern. In this investigation, one overall analysis of the SARS-CoV-2 spreading in the past several years have been carried out through one thorough genomic epidemiology study, with Germany being chosen as one representative location in view of the systemic efforts for genomic surveillance. The growth advantage of a few predominant variants in its early spreading period has been evaluated through a logistic regression model. The results have revealed that the major circulating SARS-CoV-2 variants since 2023 are mainly derived from the Omicron BA.2 family. Since middle of 2024, most predominant variants were produced primarily through recombination, indicating that the evolution derived from recombination might be the major driving force for the continuous spread of SARS-CoV-2 despite the existence of population immunity. Furthermore, the lower growth advantage of recently emerged variants might possibly lead to a tread of reduction in the frequency of infection wave. The information revealed from this investigation suggests that although short-term spreading tread can be affected by specific virus feature as well as local immunity landscape, the long-term spreading tread is mainly decided by the genomic diversity of the viruses, and can be predicted through phylogenetic and genomic epidemiology investigation. The results have emphasized the importance of maintaining the efforts for genomic surveillance of SARS-CoV-2, which is essential from both medical and research perspectives.

This study aims to assess women's perceptions of artificial intelligence (AI) used in breast cancer screening in France by examining their knowledge of AI and the barriers to their participation in organized screening. The results of a survey conducted in June 2025 among a national sample of 2000 women (aged 40-75) reveal limited participation and persistent concerns among women. Nevertheless, despite a low awareness of specific AI applications, a large majority of the women surveyed are very favorable to the use of AI in breast cancer diagnosis, even considering it a lever to increase screening participation.

In February 2026, the FDA announced that a single pivotal phase 3 (P3) trial would become the new default standard for drug approval - a regulatory direction that had been legally enabled since the FDA Modernization Act of 1997. This announcement has strategic, scientific, and economic implications for drug developers, contract research organizations (CROs), and biotech investors. We argue that the expansion of this framework, originally reserved for various niche submissions, represents a paradigm change, dramatically increasing the value of rigorous early phase (P1 and P2) trial design, requiring sponsors to establish both statistical efficacy signals and mechanistic biological understanding before entering phase 3. Using a CNS indication cost model, we show that single P3 approval can reduce total development expenditure from approximately $447 million over 14 years to $297 million over 12 years - a savings of $150 million and providing two years of additional commercial runway for a modeled CNS drug. Case examples including lecanemab, omaveloxolone, and tofersen illustrate how biomarker-informed early phase strategies can establish the confirmatory evidence necessary for single-trial approval. We provide practical guidance for maximizing the value of P1 and P2 under this evolving framework.

Background. Capillary refill time, an examiner-dependent bedside test of distal microvascular perfusion, has become a resuscitation target in septic shock,1,2,3,4 motivating a continuous surrogate computed from the photoplethysmogram (PPG, the optical waveform the pulse oximeter on every ICU patient already records).5,6,7,8 Objective. We attempted three PPG-derived candidate measures on the MIMIC-IV Waveform Database (MIMIC-IV-WDB v0.1.0) and asked, by inspecting randomly drawn examples, whether each captured its intended physiology before any downstream modeling. Methods. MIMIC-IV-WDB v0.1.09 was linked to MIMIC-IV.10 The signals were a cuff-anchored perfusion-index recovery (reactive hyperemia when the cuff shares an arm with the probe), a slow Mayer-wave-band power ratio of the perfusion index (sympathetic vasomotor tone), and a per-beat diastolic exponential decay time constant (a refill-like recovery time). For each signal we drew 10 random examples at a fixed seed and checked them against a checklist fixed in advance. Each was read by the author and, separately, by MedGemma 1.5, a multimodal medical language model run locally. A synthetic test with a known time constant checked the third signal. Results. The cuff-anchored signal showed the expected occlusion-reperfusion shape on 268 of 6,236 evaluable cuff cycles (4.30%) in 15 of 19 patients, consistent with opposite-limb placement of the probe and cuff. The slow-band ratio returned a stable cohort value, but a clear, stationary peak appeared in only4 of 10 random windows. The per-beat fit met its goodness-of-fit threshold in 10 of 10 beats, yet a cardiac-frequency heuristic flagged a possible fit on the heart-rate oscillation in 7 of 10, and in 5 of 17 patients the time constant lay where an exponential is indistinguishable from a straight line. A 0.5Hz high-pass pre-filter implanted its own approximately 318 ms time constant regardless of truth. The language model tracked the human on clear positives but reported the pattern present on every call it returned, never absent. Conclusions. Two of the three candidate signals did not reflect their intended physiology in most examples, and the third was constrained by sensor placement. Inspecting a few random raw inputs against a checklist written in advance is an inexpensive upstream check before downstream inference on PPG-derived microvascular signals.

The Empatica E4 wristband provides continuous multi-modal physiological monitoring including blood volume pulse (BVP), electrodermal activity (EDA) and skin temperature (TEMP) but its validity for sleep-stage-specific autonomic and thermoregulatory monitoring has not been systematically evaluated against concurrent polysomnography (PSG). Using the Wearanize+ dataset which provides synchronised PSG, Empatica E4, and Zmax EEG recordings from 100 home-recorded participants; a systematic validation of Empatica E4 physiological signals against PSG ground truth across five sleep stages was conducted. Of 100 participants, 92 had Empatica data; 69 met Zmax EEG signal quality criteria and formed the analysis sample. Heart rate (HR) from the pre-computed Empatica HR channel showed valid stage-specific patterns (Wake: 70.9 bpm, N3: 61.2 bpm) and moderate inter-device MeanNN correspondence with PSG ECG (Spearman r=0.35-0.42 across stages). Skin temperature showed the expected thermoregulatory pattern (Wake: 33.92C, N3: 35.48C) and is recommended for downstream analyses. Tonic EDA showed an inverted stage pattern attributable to wrist sweat accumulation during deep sleep, representing a known confound for wrist-worn EDA during sleep. Phasic EDA showed plausible patterns and may be used with caution. These findings establish a validated feature set for Empatica E4 sleep research and directly inform multimodal psychiatric biomarker studies using the Wearanize+ dataset.

PURPOSE: Alzheimer disease (AD) is associated with cognitive impairment, brain atrophy, and elevated amyloid-beta and tau. The study aimed to characterize regional atrophy associated with elevated amyloid-beta and tau, as measured by [18F]florbetapir (FBP) and [18F]flortaucipir (FTP) positron emission tomography (PET), respectively, and determine whether combining PET and atrophy data improves the prediction of cognitive impairment. METHODS: Alzheimer Disease Neuroimaging Initiative data (n = 381) were retrospectively analyzed. PET results were correlated with cortical thickness, gray matter (GM) volumes, Mini-Mental State Examination, and Montreal Cognitive Assessment. Linear/logistic regression and area under the curve (AUC) were used to evaluate for significant correlations and compare performances in distinguishing cognitive impairment, respectively. RESULTS: Incremental loss of cortical thickness and GM volume was observed from FBP-/FTP- (n = 205) to single PET-positive (FBP+/FTP-, n = 133; FBP-/FTP+, n = 5) and FBP+/FTP+ (n = 38) groups, particularly in the temporal and parietal lobes. FBP+/FTP+ showed the most severe cortical thickness loss in the entorhinal cortex, temporal lobe GM atrophy, and cognitive impairment. Adding brain atrophy as the third variable resulted in higher odds ratios and improved AUCs for cognitive impairment, with FBP+/FTP+/temporal GM or entorhinal cortical atrophy+ demonstrating the strongest associations with cognitive impairment. CONCLUSION: A multimodal approach combining PET and MRI may help improve the assessment of cognitive impairment in AD.

Objective: Clinical phenotyping methods that rely on clinical and informatics expertise can be time-intensive and costly. We tested both manual and highly automated approaches using electronic health record (EHR) data to identify an FDA Sentinel Initiative health outcome of interest, acute pancreatitis. Materials and Methods: We trained and evaluated machine learning algorithms using EHR data with two approaches: a custom approach that included manually curated features and trained on outcomes data validated with medical record review, and a highly automated approach that greatly simplifies and automates feature engineering and relies on low-cost silver-standard outcomes for model training. Results: Custom algorithms using manually curated structured claims data discriminated cases from non-cases with a high degree of accuracy (cv-AUC 0.89 [95%CI 0.84-0.94]); the inclusion of natural language processing (NLP)-derived covariates from clinical notes increased performance slightly (cv-AUC 0.91[95%CI 0.86-0.97]). The automated algorithm trained on the outcome count of diagnosis codes performed less well (AUC 0.80 [95% CI 0.75-0.85]) but improved using maximum lipase value as an outcome (AUC 0.88 [95% CI 0.84-0.92]). At a positive predictive value of 90%, the custom algorithm had a sensitivity of 92%, the automated algorithm trained on diagnosis code count had a sensitivity of 45%, and the automated algorithm trained on maximum lipase value had a sensitivity of 84%. However, a prediction rule derived by clinicians during chart review was nearly as accurate (maximum lipase value [≥] 3 times upper limit of normal; AUC 0.86, PPV 85%, sensitivity 92%). Discussion: Machine learning algorithms with manually curated structured data and NLP features trained on validated outcomes data successfully identified validated events. Use of an outcome in the automated model based on specific phenotype knowledge (maximum lipase value) allowed for performance similar to the custom model and with considerably less resources.

Objective: Patient-ventilator dyssynchrony (PVD) is a common and clinically consequential problem in critically ill patients receiving invasive mechanical ventilation. Yet automated identification of PVD subtypes at scale remains an unmet clinical need, owing to the lack of large annotated bedside waveform datasets. Methods: We developed and validated a semi-supervised algorithm for automated annotation of PVD. In two medical ICUs at a tertiary academic center, bedside devices continuously collected airway flow and pressure waveforms from the ventilators. We developed a software interface with an information retrieval system that grouped similar breaths for expert human review, yielding 1,542,296 labeled breaths across eight categories: 2 labels for breath delivery mode, 5 labels for PVD subtypes, and 1 label denoting a normal breath. Two pulmonary physicians with expertise in ventilator training and education provided the expert reference labels. We trained an initial classification model on a model-derivation set of 771,148 breaths (divided into training and validation) and evaluated it on a hold-out test set of 771,149 breaths A semi-supervised approach was utilized to extend labeling to an additional 12,965,000 unlabeled breaths. Results: The supervised model performed well across all labels, with Macro-F1 scores between 0.96 and 1.00. Semi-supervised learning across 12 rounds expanded the training set from 771,148 to 8,563,995 breaths without significant performance degradation. Conclusion: We developed a practical and scalable system for automated PVD annotation that performed well across all subtypes. This work provides a reproducible foundation for automated PVD labeling to support the development of machine-learning-based clinical decision support systems for identifying patient-level asynchrony.

Post-surgical adverse outcomes, including mortality, intensive care readmission, and complications, remain major challenges for clinical decision-making. Existing machine learning approaches focus on outcome prediction while operating as opaque systems, limiting clinical trust and the translation of predictions into treatment decisions, and many clinical studies rely on synthetic data in which shared intermediate variables create circular dependencies between inputs and targets that compromise reported performance. We aimed to develop an explainable multimodal architecture and a rigorous evaluation methodology that address these gaps. We designed a two-stage architecture integrating supervised deep learning for risk prediction with conservative Q-learning for action recommendation. The first stage uses five modality-specific encoders for structured records, physiological time-series, chest radiographs, clinical notes, and surgical metadata, unified through cross-modal attention into a shared patient-state representation. The second stage applies offline reinforcement learning to recommend clinical actions while preventing value overestimation. We formally characterized a target-leakage flaw in synthetic pipelines and propose a real-data methodology using a verified clinical database, with event-censored temporal separation and uncertainty-weighted per-task training. Component-level behavior was validated on a controlled synthetic benchmark, demonstrating that the architecture functions as designed without claiming clinical validity. The cross-modal attention and risk-prediction components behaved as expected, whereas the offline reinforcement learning stage did not converge on the benchmark, indicating that value estimation requires further investigation on real clinical data. The architecture provides dual-level explainability through attention visualization and value decomposition, contributing a deployable design, a formal methodological critique of synthetic-data practices, and a complete framework for clinically valid evaluation.

End-of-rotation handoffs are critical for patient safety but add to documentation burden for hospitalists. Generative artificial intelligence (AI) may help automate handoff creation using electronic health record data, but its impact on quality and safety is unclear. Methods: We developed an AI handoff tool with a large language model using clinical notes as input and conducted a retrospective evaluation comparing AI-generated and clinician-authored handoffs. Handoffs were assessed across domains of quality and safety through a structured review. Results: Quality ratings were similar between AI and human handoffs (3.7 vs. 3.5, p=0.57). AI-generated handoffs were rated higher for organization (4.4 vs. 4.1, p=0.05) and completeness (4.1 vs. 3.6, p=0.01), but lower for conciseness (3.7 vs. 4.1, p=0.03) and accuracy (4.1 vs. 4.4, p=0.03). Error rates were comparable (0.3/handoff in both groups); however, AI-generated handoffs included inaccuracies (9% of AI errors) and hallucinations (1% of AI errors), while clinician-authored handoffs contained only omissions. Conclusion: Human and AI handoffs have differing error profiles and tradeoffs between completeness and conciseness. Prospective evaluation in clinical workflows is underway.

In primary care and outpatient settings, clinically important patient information is often embedded in fragmented, ambiguous, repetitive, and noisy communication between physicians and patients. This limits physicians ability to obtain a clear preconsultation overview of symptoms, history of present illness, and visit intent, while also preventing real world clinical dialogues from being reused in hospital information systems and medical artificial intelligence applications. To address this challenge, we developed PCRAgent, a centrally coordinated multi agent framework for preconsultation clinical information organization. Guided by physician inquiry logic, PCRAgent identifies, extracts, corrects, and standardizes patient-reported information from noisy consultations. Its coordinated modules including error detection, semantic editing, output control, contextual memory, and intent recognition enable robust parallel handling of spelling errors, repetitions, grammatical inconsistencies, medical ambiguities, and non-medical interference. A traceable edit list records intermediate corrections and context, allowing iterative refinement without redundant modifications. PCRAgent generates two complementary outputs. One is a PreConsultation Clinical Report for rapid physician review. The other is a Structured Clinical Conversation Dataset for hospital data construction and downstream AI applications. In evaluations using 220000 strongly perturbed consultations, PCRAgent maintained high robustness, achieving a clinical information accuracy of 4.99 out of 5 and key element completeness of 5 out of 5, outperforming GPT4o. Expert review of Chinese and English dialogues confirmed high clinical accuracy of 4.85 out of 5 and high safety of 4.79 out of 5. Multicenter validation in real-world outpatient workflows further demonstrated practical utility. These findings indicate that PCRAgent can efficiently transform noisy and unstructured consultations into physician ready reports and AI ready structured data, improving outpatient efficiency, reducing cognitive burden, ensuring information completeness, supporting precise decision-making, and enabling high-quality reuse of clinical data.

Background: Alpha-1 antitrypsin deficiency (AATD) caused by the PI*ZZ mutation (Glu342Lys) results in hepatic accumulation of misfolded AAT-Z protein and reduced circulating AAT levels, leading to progressive liver disease and emphysema. Gene correction therapy represents a potentially curative approach by directly correcting the underlying genetic defect. We report the first case of successful hepatic gene correction with early histological and functional assessment. Methods/Case presentation: We report the case of a 66-year-old male patient with PI*ZZ AATD who underwent gene correction therapy within the YOLT-202 phase I/Ia clinical trial (clinical trial.gov ID NCT07193615). Ten weeks post treatment a liver biopsy was performed to re-evaluate pre-existing F2 liver fibrosis as measured by elastography before entering the study. Serum samples allowed functional assessment of the AAT-mediated elastase inhibition. Results: Liver biopsy did not show signs of hepatic inflammation and demonstrated 54% (Sanger) and 57% (Illumina) gene correction rate of the PI*ZZ variant on the DNA level with no bystander edits or off-target effects. Following a transient elevation of transaminases during the early post-treatment period, liver enzymes normalized. Monthly serum AAT measurements demonstrated biologically active and stable therapeutic levels throughout follow-up. Conclusions: This case demonstrates efficient and precise hepatic gene correction without concerning histological alterations and with substantial improvement of functional parameters, supporting the feasibility and safety of gene editing approaches for AATD.

Introduction: Synthetic oligopeptides provide a rapid and cost-efficient approach to developing antibodies and diagnostics for emerging viral variants. Methods: This study computationally and experimentally characterized a synthetic peptide analog of the SARS-CoV-2 spike subdomain 2 major disulfide loop (SD2MDL), designated S621 (CPVAIHADQLTPTWRVYSTC). Binding affinity was computationally estimated using the Heuristic Affinity Prediction Tool for Immune Complexes (HAPTIC), while experimental validation was performed using enzyme-linked immunosorbent assay (ELISA) with rabbit-derived antipeptide antibodies. Clinical diagnostic accuracy testing was done using plasma samples from RT-PCR-confirmed COVID-19 patients and pre-COVID-19 controls. Results: S621 demonstrated nanomolar binding affinity (Kdapp = 1.14 nM) and high avidity (3.67 nM), closely matching HAPTIC predictions (3.54 nM). Diagnostic evaluation yielded a sensitivity of 89.92% and specificity of 27.79%, corresponding to an overall accuracy of 71.79%. Discussion: These findings demonstrate that a single synthetic peptide derived from a conserved spike subdomain can function as a high-affinity surrogate for full-length antigens, supporting its potential application in rapid peptide-based immunodiagnostics.

Background. Tethered cord syndrome (TCS) is classically associated with a low-lying conus medullaris, yet many surgically treated children have a normally positioned conus (occult TCS). Large-scale normative data on conus position in children, and the diagnostic value of quantitative conus assessment, are limited. Purpose. To establish a large-cohort reference distribution for conus medullaris termination level in children, to quantify conus position in children surgically treated for presumed (occult) TCS, and to test whether automated conus segmentation and radiomics can distinguish TCS from normal. Materials and Methods. In this retrospective single-center study, conus termination level was extracted from structured radiology reports of consecutive pediatric lumbosacral MRI examinations and encoded numerically (L1 = 1, L2 = 2, etc.). Children surgically treated for tethered cord were identified by linkage to an operative registry (name and date of birth) and restricted to preoperative examinations. A deep-learning model (nnU-Net) was trained for conus segmentation on axial T2-weighted images. IBSI-compliant radiomic features were extracted; reproducibility was assessed by intra- and inter-observer intraclass correlation (ICC). A case-control radiomics analysis used batch-only ComBat harmonization and cross-validated L1-penalized logistic regression; discrimination was compared with conus level by paired bootstrap. Results. Among 9,808 examinations with a parseable conus level (98.5% of reports; parser validated against dual blinded annotation, 99.4% agreement, weighted kappa 0.946), the conus terminated in the L1 region in 85.7% and the L2 region in 14.3% of the reference cohort (postoperative examinations excluded, n = 9,655); a low-lying conus (>=L3) occurred in only 0.05% (5/9,655), and remained rare (0.14%, 14/9,808) including operated examinations (median L1; mean 1.13 +/- 0.33). A slightly more cephalad position was seen with increasing age (negligible correlation). Among 475 preoperative children surgically treated for tethered cord, 99.6% had a normally positioned conus (<=L2) and only 0.4% were low-lying. Automated conus segmentation achieved a held-out Dice of 0.85. Conus radiomics likewise did not distinguish TCS from controls (equivalence-tested null; full segmentation/radiomics pipeline reported in the companion methodological paper). Conclusion. In children, the conus medullaris terminates at L1-L2 in more than 99% of cases and is normally positioned in virtually all children surgically treated for TCS. Within the conus, neither position nor texture (radiomics) identifies tethered cord; whether the filum terminale carries a diagnostic signal was not tested here.

Purpose: Pathogenic or likely pathogenic (P/LP) variants are increasingly identified in genes more commonly associated with adult-onset cancer predisposition, but their prevalence and relevance to children who present with cancer remain unclear. Methods: We retrospectively analyzed 1,280 consecutive pediatric patients with cancer who underwent clinical germline sequencing, using a virtual panel, from 2021 to 2024. Genes with P/LP variants were categorized as aoCPG or pediatric-onset cancer predisposition genes (poCPG) according to cancer risk before age 18 years and pediatric surveillance recommendations. Variant relevance was adjudicated using tumor diagnosis/histopathology, immunohistochemistry, and tumor molecular features and classified as primary, secondary, or indeterminate. Results: Among 1,280 patients, 197 (15.4%) harbored 211 P/LP variants across 54 genes. Sixty-six variants (31.3%) occurred in aoCPG, 87 (41.2%) in poCPG, and 58 (27.5%) were heterozygous variants in autosomal recessive genes. Among adult-onset variants, 7 (10.6%) were primary, 54 (81.8%) secondary, and 5 (7.6%) indeterminate. Among pediatric-onset variants, 77 (88.5%) were primary and 10 (11.5%) secondary. Six patients (3 adult-onset variants; 3 pediatric-onset variants) received targeted therapy informed by germline/somatic sequencing results. Conclusion: In pediatric oncology, most variants in aoCPG are secondary rather than tumor-related findings. Tumor-informed interpretation, beyond variant classification, may improve reporting, counseling, and therapeutic decision-making

Background: Artemisinin-based combination therapies remain the mainstay of malaria control strategies; nevertheless, the advent of genetic markers linked to partial artemisinin resistance in Plasmodium falciparum has elicited substantial concern across African settings. To assess the prevalence, geographic distribution, and clinical associations of these molecular markers, we undertook a systematic review and meta-analysis of observational cohort studies.Methods: We conducted a search of cohort studies published between January 2015 and June 2025, following PRISMA 2020 guidelines. We queried databases including PubMed/MEDLINE, Scopus, Web of Science, and CINAHL. Eligibility required prospective enrollment of patients, longitudinal monitoring (therapeutic efficacy studies), and pfkelch13 propeller domain genotyping.Results: A meta-analytical synthesis of 888 isolates from six core prospective cohorts revealed a pooled prevalence of 6% (95% CI: 2.1%-11.8%) for validated pfkelch13 mutations. A profound geographic dichotomy was identified: while West and Central African cohorts maintained a 0% prevalence, East African hotspots showed significant expansion, with prevalence reaching 12.8% in Rwanda and up to 25.5% in Northern Uganda; high statistical heterogeneity (, ) reflects this biological divergence. Conclusions: These findings highlight the established and expanding presence of artemisinin partial resistance in East Africa. Standardized surveillance is essential to adapt malaria control policies across the continent. Keywords: Africa; artemisinin resistance; clinical indicators; pfkelch13 gene; molecular markers; partial resistance; Plasmodium falciparum.

Objective. To introduce PsiBench, a clinically validated medication-safety benchmark for evaluating large language models (LLMs) against the standards used to certify hospital computerized provider order entry (CPOE) and electronic health record (EHR) systems, and a non-overlapping three-tier evaluation framework separating highest-stakes discrimination, the operational CDS regime, and category-correct alerting. Materials and Methods. PsiBench comprises 492 medication-safety scenarios across 11 safety categories, created by clinical pharmacology experts whose work underpins an annualized testing procedure used by more than 2,000 U.S. hospitals. The three-tier framework partitions the scenarios non-overlappingly: Discrimination (98 scenarios, 50 fatal vs 48 deception, near-balanced 51%/49%); Operational (394 scenarios, 261 serious unsafe plus 133 safe including 41 Excessive Alerts reclassified as operational negatives); and Attribution (311 alert-required scenarios). We evaluated 40 frontier LLMs from 10 providers over 3 runs per scenario at temperature 0.2 (or the provider default where temperature is not configurable), yielding 59,040 evaluations conducted April 21-23, 2026. Results. Headline binary performance on the full benchmark spans a wide range across the 40 models: F1 78.5%-92.3%, accuracy 65.4%-89.8%, sensitivity 81.4%-100.0%, specificity 6.1%-81.8%. Leading models by F1 (o4-mini 92.3%; o3 92.2%) pair high sensitivity with meaningful specificity; three models saturate sensitivity at 100% but fall below 25% specificity, indistinguishable from a naive always-alert classifier. The wide spread on a single headline metric motivates tier-specific analyses, developed in a separate clinical paper. Discussion and Conclusion. PsiBench and the three-tier framework operationalize a rigorous evaluation rubric for LLM medication safety, grounded in two decades of national hospital audit experience. The framework generalizes to any binary medication-safety classifier (rule-based, conventional ML, or LLM-driven), supporting tier-aware model selection and post-deployment surveillance.