Informatics in Medicine Unlocked

INTRODUCTION: Throughout history, viruses have been infecting humans, leaving genomic traces called endogenous viral elements (EVEs). This study explores the infectious hypothesis for Alzheimer's disease (AD) that suggests that viral infections may contribute to AD by analyzing EVEs in genomes of AD patients and cognitively healthy centenarians (CHCs) measured by long-read sequencing. METHODS: We implemented an EVE detection pipeline that screened the genomes of 248 AD patients and 240 CHCs. EVEs were measured based on EVE count, length, and chromosome location. RESULTS: The genomes of AD patients contain significantly more EVEs than those of CHCs (p=3.2x10-4). Moreover, certain chromosomal regions in AD patients show a higher EVE count, particularly of the Orthoherpesviridae family, near genes differentially expressed in AD brains. DISCUSSION: These findings suggest that viral infections may increase susceptibility to AD, highlighting that preventive measures against infections potentially reduce AD risk.

Deep learning models for electroencephalography (EEG) pathology detection achieve competitive accuracy but offer limited interpretability. In this paper, we introduce concept bottleneck models (CBMs) for EEG pathology detection which use clinical EEG biomarkers computed analytically from the signal as a bottleneck to be used for prediction. Those concepts include band power, spectral ratios, alpha peak frequency and amplitude, hemispheric asymmetry and phase locking values. With the backbone based on shallow convolutional neural network (CNN), we compare a black box baseline with two variants of CBMs. The hybrid variant is a classifier receives a residual projection of the backbone features. The pure variant is a CBM where the classifier receives only the predicted concepts. Models are evaluated on abnormality detection and dementia classification followed by concept prediction quality and leakage analysis. Both CBMs approach the baseline on TUAB (82.7-82.9% vs 83.6%) and are 2-5 percentage points lower on CAUEEG (57.9-60.5% vs 62.7%). The pure CBM exhibits concept fidelity concern where the predicted concepts deviate from their ground truth values. Replacing them with their true values causes severe cost on accuracy by 26 and 22 points on TUAB and CAUEEG. The concept fidelity concern is mitigated by increasing the weight of the concept loss to match the ground truth concepts. the mitigation comes with small accuracy cost on TUAB but a relatively larger cost on CAUEEG. The code of the experiments and full logs are available at https://www.github.com/mhmdrdwn/cbm.

Automated surveillance systems can prove to be extremely useful in detecting outbreaks of respiratory diseases that need further epidemiological investigation. In order for the system to be effective, careful attention has to be paid to the baseline used, absence of the observations, and the use of proper statistical methods. As a solution, the paper describes EpiAlert, a weekly surveillance system based on CDC FluView ILINet. The system is able to transform the number of ILI visits and the total number of visits into a ILI prevalence for the region, create the first reference from the three previous years using a +/- 2-week interval, transform the rate value, and apply two different detectors - CUSUM and EWMA. CUSUM is set at k=0.5 and h=5, whereas EWMA uses {lambda}=0.2 and H=2.7 values. Among the 55 districts, the system gives 45,138 pieces of information about the disease by transforming 44,297 pieces of data into alerts. It is found that there are 2,820 alerts in total (out of which 2,711 alerts used CUSUM, 402 used EWMA, and 293 used both detectors). Additionally, the experiments show that the sensitivity of the device depends greatly on the detector. The latest statistics can be tracked in the report for week 37 of 2026 that recently concluded in West.

PURPOSEPancreatic ductal adenocarcinoma (PDAC) is a deadly malignancy with poor prognosis. A transcriptomic-based algorithm called Purity Independent Subtyping of Tumors (PurIST) relies on expression profiling of a defined set of genes to stratify PDAC into classical and basal-like molecular subtypes and assigns a confidence level to the subtypes as either "strong," "likely," or "lean." In this study, we apply PurIST to Appalachian and non-Appalachian patient cohorts and assess demographic variables between groups that may influence treatment outcomes. PATIENTS AND METHODSThis 13-site study includes 780 PDAC patients. Patients were divided into Appalachian and non-Appalachian cohorts according to Appalachian Regional Commission guidelines, and differences in PurIST classification, tobacco use, and alcohol use were analyzed. RESULTSIndividuals from Appalachian regions were more likely to receive a subtype classification from PurIST with "strong" confidence as opposed to "likely" or "lean" (P=0.0175; odds ratio=1.66). We did not observe any significant difference between basal and classical subtype classification in Appalachia (P=0.1457), yet an exploratory analysis showed that individuals aged [≥]85 were significantly more likely to have basal-like tumor classifications (P=0.005817; odds ratio=3.79). Appalachian patients were more likely to have a history of smoking (59.6% vs 49.9%; P=0.01756) and less likely to report alcohol consumption (50.5% vs 65.6%; P=0.000229). CONCLUSIONWe conducted the largest comparison of the PurIST algorithm in Appalachia to date and found PurIST is more likely to have higher confidence in molecular subtype classifications for Appalachian PDAC tumors compared to non-Appalachian tumors. If PurIST is to be considered as a prognostic or decision-making tool for PDAC patients, we must account for variability in different populations and model the likelihood that tumors will have a strong molecular signature.

The -Bonacci weighted sequence space {ell}(,) is introduced for [&ge;] 2, 1 [&le;] < {infty}, and > 0). It is proved to be a Banach space which is isometrically isomorphic to {ell}, with an unconditional Schauder basis. The space is also reflexive and uniformly convex. Its strict inclusion chain, continuous dual, and asymptotic truncation estimate of order - / are also established. Based on this framework, Scaled &#119898-BonacciNet is proposed as a lightweight CNN that rescales Fibonacci-Net channels using the dominant &#119898-Bonacci root and employs depth wise separable convolutions. Tribonacci-Net achieved 96.09% accuracy and a 0.9581 macro F1-score on the 15-class Brain MRI dataset using 0.85 million parameters and 0.366 GFLOPs. Pentanacci-Net attained 95.87% accuracy on the 44-class dataset while reducing parameters and FLOPs by 47.10% and 44.48%, respectively. On the CKD ultrasound dataset, Hexanacci-Net achieved 83.75% accuracy and a 0.7941 macro F1-score, with corresponding reductions of 50.37% and 45.10%. These findings support dominant-root scaling as a structured approach to lightweight CNN design.

Background: Self-supervised learning may improve segmentation when labelled data are limited, but its benefit may depend on model and initialisation strategy. This study evaluated in-domain masked-reconstruction pretraining across limited annotation budgets. Methods: The International Skin Imaging Collaboration (ISIC) 2016 development set was partitioned into 765 images for self-supervised pretraining, 94 for fine-tuning and 41 for validation. Five nested annotation budgets (12-94 images) and five seeds were evaluated on the 379-image test set. A custom U-Net compared random and in-domain self-supervised initialisation; a ResNet-34 U-Net compared random, ImageNet, in-domain self-supervised and sequential ImageNet-to-self-supervised initialisation. Models trained with 94 labelled images were evaluated without adaptation on ISIC 2017. A separate experiment examined restoration-based pretraining. Results: In the custom U-Net, self-supervised pretraining achieved higher mean Dice than random initialisation at all five budgets, including 0.664 versus 0.615 with 12 labels and 0.811 versus 0.768 with 94 labels. Seed-level 95% confidence intervals for paired differences excluded zero at 47 and 94 labels but not at the other budgets. With 47 labels, the self-supervised model achieved mean Dice of 0.789, compared with 0.768 for random initialisation with 94 labels. In ResNet-34, ImageNet initialisation achieved higher mean Dice than in-domain self-supervised pretraining at all five budgets, and adding self-supervised pretraining after ImageNet reduced mean Dice at four of five budgets. All six 94-label configurations achieved lower mean Dice on ISIC 2017 than ISIC 2016. In the restoration experiment, mean Dice was 0.686 with random initialisation and 0.638-0.642 following pretraining. Conclusions: In-domain masked-reconstruction pretraining improved mean Dice relative to random initialisation in the custom U-Net, but not consistently in the ResNet-34 U-Net, where ImageNet initialisation performed better at every budget. Adding self-supervised pretraining after ImageNet provided no consistent gain. These findings are specific to the dermoscopic lesion-segmentation experiments and do not establish melanoma-specific diagnostic or clinical performance.

Background: Attention-Deficit/Hyperactivity Disorder (ADHD) is a common neurodevelopmental disorder characterized by persistent symptoms of inattention, hyperactivity, and impulsivity that significantly affect cognitive, academic, and social functioning. Although electroencephalography (EEG) has emerged as a promising non-invasive tool for identifying objective neurophysiological biomarkers of ADHD because of its high temporal resolution and cost-effectiveness, many existing machine learning studies rely on single-domain EEG features, which may not adequately capture the complex functional organization of the brain. Methods: This study proposes a subject-level EEG classification framework that integrates three complementary feature domains: spectral characteristics, weighted Phase Lag Index (wPLI)-based functional connectivity, and topological descriptors derived from persistent homology. EEG recordings from 121 subjects were preprocessed and segmented into overlapping windows for feature extraction. Window-level features were aggregated to generate subject-level representations. Recursive Feature Elimination (RFE) was employed to select the 110 most informative features from an initial set of 1,043 descriptors. Five machine learning classifiers, including Support Vector Machine (SVM), Random Forest, XGBoost, CatBoost, and Multi-Layer Perceptron (MLP), were evaluated using stratified five-fold cross-validation. An ablation study was further conducted to assess the contribution of each feature domain. Model interpretability was investigated using SHapley Additive exPlanations (SHAP) and Local Interpretable Model-agnostic Explanations (LIME), two widely adopted Explainable Artificial Intelligence techniques for interpreting machine learning models. Results: Among the evaluated classifiers, the SVM achieved the highest classification performance, yielding an accuracy of 80.17%, an F1-score of 80.95%, a balanced accuracy of 80.14%, a receiver operating characteristic area under the curve (ROC-AUC) of 86.72%, and a precision recall area under the curve (PR-AUC) of 87.34%. The ablation study demonstrated that combining spectral, functional connectivity, and topological features consistently outperformed individual feature domains, highlighting the complementary nature of these representations. Explainable AI analyses further identified functional connectivity features as the primary contributors to classification performance while confirming the additional value of spectral and topological descriptors. Conclusions: The proposed framework demonstrates that integrating spectral analysis, functional connectivity, and topological data analysis provides an effective and interpretable approach for subject-level ADHD classification from EEG recordings. The combination of recursive feature selection, multi-domain feature fusion, ablation analysis, and Explainable Artificial Intelligence establishes a transparent and reproducible pipeline that may facilitate the development of reliable EEG-based clinical decision-support systems for ADHD.

Depression in Alzheimer's disease (AD) is clinically challenging to characterise because affective and cognitive manifestations frequently overlap with the underlying neurodegenerative condition. This study investigates depression-related speech patterns in AD using an explainable multimodal framework that integrates linguistic and acoustic features from elicited picture-description speech. To address the absence of directly observed depression labels in the target AD cohort, we employ a source-informed cross-dataset transfer strategy. Unsupervised clustering identified two distinct speech sub-phenotypes within the AD cohort. By comparing these unsupervised representations to a depression-labelled source corpus, one cluster demonstrated mathematical proximity (measured via cosine similarity in a shared latent space) to the source depression centroid. We explicitly acknowledge that this proximity reflects geometric similarity in a shared latent space, which may encapsulate overlapping domain characteristics alongside affective variance. To validate the structural integrity and separability of these discovered clusters, a proxy supervised classification task was employed. The retained multimodal artificial neural network (ANN) integrated information from both modalities and achieved 92.73\% cluster separability accuracy. This demonstrates that the representation-derived two-cluster partition was highly learnable on the independent internal hold-out test set; it does not establish clinical validity, longitudinal stability, or diagnostic validity of the identified sub-phenotypes. For interpretability, Shapley Additive exPlanations (SHAP) analysis was utilised to extract feature attributions and organise influential acoustic and linguistic features into a multimodal taxonomy. Furthermore, a Multimodal SHAP Attribution Magnitude (MSAM) score was derived as an exploratory model-based attribution score rather than a clinically validated severity measure. Ultimately, this study provides an interpretable computational baseline for characterising depression-related speech variance in AD, establishing a structural foundation for future prospective validation using independently labelled clinical cohorts.

Background & AimsWe previously developed multiple machine-learning and regression-based risk prediction models using retrospective electronic health records (EHR) to estimate near-term risk of pancreatic cancer (PC). This pilot study aimed to assess the feasibility of an early detection strategy combining initial EHR-based risk prediction with downstream imaging and blood-based testing. MethodsThis prospective study included adults aged 50-84 years with an estimated [&ge;]1% 18-month risk of PC, identified between January 2021 and March 2023 using four previously validated models. Patients with a history or active suspicion of PC were excluded. Participants completed cross-sectional imaging and CA19-9 labs at baseline and again at 18 months. Outcomes included enrollment rates, test completion rate, and burden of incidental findings. ResultsOf 1,251 eligible patients, 102 (8.2%) enrolled (median age 69 years [IQR 62-75]; 58% women; 48% Hispanic, 34% White, 11% Black, and 7% Asian). At baseline, 89 (87%) completed imaging and 98 (96%) completed CA19-9. At 18 months, 79% completed both imaging and CA19-9. Ten (10%) participants underwent additional clinical evaluations triggered by imaging findings. Evaluations included an endoscopic ultrasound, renal imaging, and FibroScan. CA19-9 results were normal in most participants, though 18% had elevated levels at baseline. ConclusionsReal-time EHR-based ML algorithms can be combined with blood- and imaging-based surveillance for early detection of PC with acceptable burden of incidental findings. However, improved patient engagement is a key aspect that will need to be addressed in order to successfully scale an AI-guided strategy for early detection.

Introduction: Safety parameters for non-invasive neuromodulation (NINM) remain scattered across consensus documents that differ in format, units, and scope, so pre-session parameter screening stays error-prone and difficult to audit. Objectives: To describe the NINM Safety Parameter Explorer, a browser-based tool that consolidates safety thresholds for six NINM modalities (e.g., TMS, tDCS, peripheral magnetic stimulation, TENS, transcranial ultrasound, and transcutaneous vagus nerve stimulation) into a single rule engine in which every numeric boundary carries an explicit, auditable provenance classification as literature-derived, literature-anchored, or operational default. Methods and Materials: We encoded the tool's rule corpus from published international consensus guidelines and peer-reviewed literature (82 modality threshold rules: 29 literature-derived, 36 literature-anchored, 17 operational defaults; complemented by 5 target-site caps for 87 total evaluative rules, alongside 15 informational reference values), then evaluated it in a simulated, automated internal verification suite of 38 example protocols spanning all six modalities and three expected verdicts, with automated static integrity assertions, regression guards, and behavioural and accessibility unit checks, all under a single pinned software version (v1.1.0-beta). Results: All 38 examples agreed with their declared verdicts (19 safe, 8 caution, 11 unsafe), and all static guards and supporting checks passed. Conclusion: The Explorer shows complete internal self-consistency between its rule corpus, engine, and interface, and its per-rule provenance labelling renders safety reasoning transparent and auditable for research and educational use. The tool is an in-silico protocol planning aid; it is not a medical device and is not intended for clinical decision-making or use in humans.

Electroencephalography (EEG) preprocessing determines signal quality and interpretation, particularly for transcranial magnetic stimulation combined with EEG (TMS-EEG), where recordings are affected by large and complex stimulation-related artifacts. Several preprocessing approaches have been developed, but substantial variability remains in how pipelines are implemented, documented, and evaluated across recordings, limiting reproducibility and comparability across studies. We developed NESTApp, a MATLAB-based graphical interface built on EEGLAB, to provide an accessible and reproducible framework for implementing and evaluating TMS-EEG preprocessing pipelines. Rather than prescribing a specific pipeline, NESTApp allows users to construct and consistently apply customisable workflows incorporating established EEGLAB and TMS-EEG processing tools, while automatically documenting processing decisions and parameters. Integrated quality-control procedures track data removal and flag recordings based on user-defined criteria, facilitating systematic evaluation across participants. The application also supports group-level visualisation and export of processed TMS-EEG measures for subsequent analyses. Applied to 29 recordings from 16 participants, NESTApp processed 27 and identified those requiring further inspection. By integrating pipeline implementation, documentation, quality control, and group-level evaluation within a single interface, NESTApp provides a transparent framework for TMS-EEG preprocessing that may improve reproducibility, facilitate consistent processing across cohorts, and lower technical barriers to the implementation of established preprocessing approaches.

Background: Spontaneous intracerebral hemorrhage (ICH) has high disability and mortality. Accurate early prognostication remains challenging in routine practice. Conventional CT assessment relies mainly on hematoma volume and rough anatomical location, limiting individualized prognosis. Radiomics combined with machine learning may improve prognostic assessment by extracting quantitative texture and heterogeneity features.Methods: In this retrospective multicenter study, we included 2,680 consecutive patients with spontaneous ICH: training (n=1,876), internal validation (n=804), and independent external validation (n=196). Deep learning automatically segmented hematomas, and 1,690 radiomics features were extracted from admission non-contrast CT (NCCT). After reproducibility assessment, univariate screening, and LASSO selection, 42 features were integrated into a Rad-score. The Rad-score was combined with demographic, clinical, and conventional CT variables to construct two complementary machine learning models for functional outcome prediction and comprehensive prognostic stratification. Performance was assessed using R2, mean squared error (MSE), area under the receiver operating characteristic curve (AUC), calibration, decision curve analysis, and external validation. Both models were internally and externally validated. Ambient temperature variation at symptom onset was explored as a potential prognostic modifier. Results: Forty-two reproducible radiomics features constituted the Rad-score. Adding radiomics substantially improved performance over conventional clinical and imaging models. For functional outcome prediction, the integrated model increased R2 from 0.35 to 0.93 and reduced MSE from 387 to 61. For prognostic risk stratification, the clinical-only model achieved an AUC of 0.59, whereas the fully integrated model achieved 0.95 and maintained robust external performance (AUC=0.86). Conclusions: We developed and validated a machine learning-based clinical decision support system integrating conventional CT radiomics and clinical variables for prognostic prediction and risk stratification in ICH. By capturing quantitative imaging information beyond conventional CT markers, this framework improved prognostic discrimination and generalizability. These findings support integrating quantitative imaging biomarkers into clinical decision-making for spontaneous ICH. The association between ambient temperature variation and disease progression warrants prospective investigation. Further prospective validation is warranted.

Background: The Central Brain Tumor Registry of the United States (CBTRUS) uses a histology grouping model based on the World Health Organization (WHO) to classify cancer registry records for clinically relevant statistical reporting. Methods: CBTRUS, together with its consulting neuropathologists, reviewed and aligned its histology groupings with the 2021 WHO Classification update. Obsolete histology nomenclature along with their International Classification of Diseases for Oncology 3rd edition (ICD-O-3) codes were identified, currently included histologies were reclassified as appropriate, and new codes found in 2021 WHO were incorporated. An evaluation was conducted of the frequency of histology codes affected in the reclassification process, as well as incidence and survival pre- and post- reclassification of CBTRUS Tumor Type Groupings. Results: After review of the CBTRUS grouping scheme, 205 codes were reclassified and 2 new codes were incorporated. Tumor type groups most affected were those classified as glioma. Reclassification resulted in 167,038 of 491,804 (34%) cases having a grouping reclassification or reporting change, indicating that the 2021 revision of the WHO Classification has significantly impacted the collection and reporting of primary b CNS tumors. Conclusion: This work demonstrates the need to be responsive to changes in classification and coding for statistics to reflect real-world clinical use. This will require collaboration from all parties to have the ability to reconcile clinical practices and surveillance requirements.

Pancreatic ductal adenocarcinoma (PDAC) arises within an extensively remodeled microenvironment, yet tissue markers that distinguish invasive carcinoma from precursor lesions remain limited. Integrating four single cell RNA sequencing atlases comprising 324,662 cells from 26 patients, we identified cancer associated fibroblast expansion, accumulation of C1QA+ immunoregulatory macrophages, and depletion of a dendritic cell compartment expressing plasmacytoid markers. Fibroblasts were enriched for extracellular matrix and PI3K AKT programs and macrophages for an antigen-presentation program. We then examined the protein level correlates of these populations in a tissue proteomic reference framework of 356 samples spanning non diseased pancreas, normal-adjacent tissue, low and high grade intraductal papillary mucinous neoplasms (IPMNs), IPMN associated invasive carcinoma, and PDAC, prioritizing proteins that changed monotonically across the six histopathologic reference groups or marked tumor enriched cell types. Despite depletion of plasmacytoid dendritic cells, the principal source of type I interferon, the interferon stimulated protein ISG15, expressed by both fibroblasts and macrophages, increased monotonically toward PDAC. In exploratory cross-validated benchmarking of PDAC versus low and high grade IPMN, excluding IPMN-associated invasive carcinoma (145 versus 56 samples), CATB+EPIPL achieved an AUC of 0.98, with a sensitivity of 92% at an achieved specificity of 92%, exceeding protein abundance models of diagnostic IHC-associated markers (S100P+IMP3+maspin+MSLN, 0.79) and refitted published IPMN progression combinations (<0.91). Against non diseased pancreas, candidate and comparator panels performed similarly (AUC 0.99 1.00). These biologically informed tissue protein panels warrant independent validation, including immunohistochemical evaluation of EUS guided fine needle biopsy specimens and measurement in blood.

Accurate prediction of adverse events in the intensive care unit (ICU) following cardiothoracic surgery is crucial for timely interventions, improving patient outcomes and optimizing value in healthcare. By leveraging advanced machine learning techniques, this study demonstrates the transformative potential of predictive analytics to enhance postoperative care using a dataset from the Society of Thoracic Surgeons' (STS) database and time-series intraoperative data. We developed a multi-modal late fusion approach integrating static patient variables with intraoperative time-series data, utilizing an ensemble of models including residual neural networks for static features, CNN and Bidirectional GRU for time-series processing, XGBoost, logistic regression, SVM and Gradient Boosting. Through five-fold cross-validation, our ensemble model with balanced threshold selection achieved an AUC of 0.87, sensitivity of 0.76, specificity of 0.83, PPV of 0.40, and NPV of 0.96. Preoperative heart failure, IABP insertion, cardiopulmonary bypass (CPB) duration and white blood cell (WBC) count emerged as key predictors. Training the same pipeline on each modality separately showed that the static registry variables alone reached the same AUC of 0.87, and that the intraoperative signals alone reached 0.83, so on this cohort the two modalities act as substitutes rather than complements and fusion changed the sensitivity and precision trade-off rather than the amount of separable signal. A per-signal ablation found that no individual monitoring channel was load bearing, with mean arterial pressure and central venous pressure the least substitutable. This balanced approach optimizes the trade-off between sensitivity and specificity, providing a screening tool with high negative predictive value for monitoring high-risk patients, and the modality comparison indicates that comparable performance is attainable at sites holding registry data alone.

Nurse-led skin cancer screening extends specialist reach but depends on the nurse selecting which lesions to forward for diagnosis, and performance varies with experience. We evaluated whether real-time decision support using artificial intelligence (AI) improves malignancy detection in routine nurse-led teledermoscopy screening across MoleMap clinics in New Zealand and Australia (January 2024-July 2025). In this real-world study, clinics using AI decision support were compared with standard clinics. Nurses examined patients, captured dermoscopic images, and forwarded selected lesions to teledermatologists, who provided the reference diagnosis. The analytic cohort comprised 1,102,382 lesions from 98,422 patients across 577 sites. AI-assisted screening was associated with a higher malignancy detection rate than standard screening (25.5 vs 15.7 malignancies per 1,000 lesions; odds ratio adjusted for nurse experience 1.73, 95% CI 1.68-1.77), a finding consistent across all nurse-experience tiers and the three major malignant subtypes. AI assistance was also associated with a shift in recommended management: 21 additional intervention recommendations and 13 additional safety-netting recommendations (self-monitoring, short-term follow-up, or specialist referral) per 1,000 lesions, approximately balanced by 34 fewer no-action recommendations. The reference standard was teledermatologist diagnosis and allocation was not randomised; findings are therefore associational and require prospective, outcome-based confirmation.

Individuals carrying a G4C2 repeat expansion in C9orf72 can develop amyotrophic lateral sclerosis (ALS) and/or frontotemporal dementia (FTD), at various and unpredictable ages. The contribution of the expansion to this extreme clinical variability remained a matter of debate. In this work, we validated the use of optical genome mapping to efficiently size this expansion from blood and applied this method to a cohort of 54 repeat expansion carriers including patients with FTD (n = 23), ALS (n = 22) and presymptomatic individuals (n = 9). Despite the high variability in expansion profiles, distinct groups can be inferred. Although consensus repeat profiles were similar between FTD and ALS patients, relationships between repeat number, indexes of repeat instability, and the age at sampling differed between clinical conditions. An age at sampling-dependent increase of repeat instability in blood was observed in presymptomatic carriers and FTD patients (p = 0.01 and p = 0.04 respectively), in contrast to patients with ALS (p = 0.9). The proportion of shorter repeats ([500-1500 repeats]) increased with the age at sampling in ALS patients but decreased in presymptomatic and FTD cohorts, while the proportion of larger repeats (>2000 G4C2), in particular those exceeding 4000 repeats, increased along with the age at sampling in presymptomatic carriers and FTD cases (p <1.10-e4 and p = 0.006 respectively) conversely to patients with ALS (p = 0.98). In conclusion, this work strongly supports different dynamics of repeat instability of the C9orf72 pathogenic expansion in blood linked to the clinical evolution. These findings provide new insights into the relationship between expansion profiles and clinical variability.

Head and neck radiation oncology, with its complex locality and epidemiology, requires various imaging techniques to achieve sufficient visualization. Through collaboration with medical physicists, radiation therapists, radiation oncologists, and neuroradiologists, our group clinically implemented a standard set of magnetic resonance imaging (MRI) sequences on an MR-simulation scanner for three anatomical regions: skull base, oral cavity, and larynx/pharynx. A total of 41 patients with head and neck cancer and 3 volunteers were scanned on either a 1.5T or 3T MR-simulation scanner. Sequences described include Dixon-based approaches, SPAIR-based approaches, short T2-based approaches, and quantitative imaging methods. We describe and outline the steps to optimize these notable MRI sequences to aid in successful implementation in a radiation oncology clinic.

In many natural dynamical systems, tipping points emerge where slowly changing external factors induce shifts from one state to another, known as critical transitions or bifurcations. In epidemic systems, detecting these transitions is important for outbreak preparedness. Various statistical indicators like lag-1 autocorrelation and variance have been employed as early warning signals (EWS) of critical transitions by showing how the dynamics of the system exhibit critical slowing down (CSD) near the transition. More recently, deep learning-based algorithms have been developed that attempt to more accurately detect and classify bifurcations; however, they are limited by the systems simulated in the training dataset, the length of the time series, and have not been rigorously evaluated on real-world epidemic data spanning multiple geographic regions. In this paper, we evaluate existing deep learning-based bifurcation prediction models, on a CDC-curated dataset containing weekly influenza hospital admissions across all fifty U.S. states and the nation as a whole. We develop a pipeline for data preparation, reproduction number (Rt) estimation using the EpyEstim package (a Python implementation of the EpiEstim framework [4]), and bifurcation point identification. We systematically evaluate the models under several windowing strategies, including rolling, expanding, and fixed-length windows, and report accuracy, precision, recall, F1 score, and specificity. Our best-performing configuration (expanding window, length 100) achieves an accuracy of 90.09%, precision of 72.86%, recall of 96.23%, and F1 score of 82.93%. We additionally discuss Markov Regime Switching models as an alternative framework for detecting epidemic transitions. Our findings indicate that these models can generalize to real-world, state-level influenza data and are capable of online/real-time prediction.

Background. Public-health use of influenza surveillance - situational awareness, planning for clinical surge, and issuing advisories or warnings - needs more than an accurate point estimate of next week's count. What matters operationally is whether a rise is caught early, whether the direction of change is right, and whether an alert threshold is about to be crossed, all with honest uncertainty. For such use a forecast must also respect reporting delay, later data revision, and the calibration of its prediction intervals. Using Japan's sentinel surveillance, we evaluated short-term probabilistic forecasts that respect the data release history, and we measured what adding other surveillance series contributes, focusing on the properties that matter for public-health decisions. Methods. The target was the number of influenza reports per sentinel site in each of the 47 prefectures. For each forecast we predicted, as quantiles, the value 1-4 weeks after the most recent observed week. We compared three models: a ridge regression trained jointly across prefectures; a gradient-boosting quantile regression (GBQR) that learns from many surveillance series; and their equal-weight combination on the log scale. Six seasons were used to develop the models. The 2025/26 season was held out as a temporal evaluation period after the specification was fixed; because its epidemic profile had already been seen, it is not a fully independent prospective test. We scored forecasts with the weighted interval score (WIS) and checked prediction-interval coverage. For the Japanese target series we used the value first published for each week; some auxiliary series were taken as retrieved and therefore include later revisions. Results. In 2025/26, the combination's WIS relative to a persistence forecast was 0.841, 0.811, 0.794 and 0.818 at horizons of 1-4 observed weeks - that is, 16-21% lower than persistence. Coverage of the 80% prediction interval was 79.7%, 77.1%, 74.5% and 75.1%, and of the 95% interval 94.3%, 93.4%, 92.6% and 91.8%. Adding auxiliary series improved the GBQR over the development period. However, on the original scale the combination's edge over ridge regression was not statistically clear, and in some low-level rising phases the combination did worse than ridge. Conclusions. Over the period studied, models that share information across regions scored better than a persistence forecast. For public-health use, however, the operative questions are the real lead time once reporting delay is accounted for, whether rises from low levels and threshold exceedances are caught in time, and whether the upper prediction intervals are wide enough; on these, the present evidence is not yet sufficient. The 2025 change to the sentinel system also means that pre-change advisory and warning thresholds cannot be read mechanically. A prospective evaluation with strictly controlled data availability is needed before such forecasts are used to support advisories or planning.